阅读说明：本技术 成型条件决定辅助装置以及树脂状态推断装置 (Molding condition determination support device and resin state estimation device ) 是由 大久保勇佐 立花幸子 沟口翔太 马场纪行 木村幸治 足立智也 于 2021-06-04 设计创作，主要内容包括：成型条件决定辅助装置以及树脂状态推断装置具备：基于检测数据通过机器学习推断成型品的品质的品质推断部；对推断出的成型品的品质进行累积,并存储被累积的多个成型品的品质推移的品质推移存储部；基于品质推移来评价相对于规定的品质基准的品质变化趋势的趋势评价部；存储品质变化趋势与用于返回到品质基准的成型条件的修正量的关系的关系存储部；以及基于品质变化趋势与关系决定成型条件的修正量的修正条件决定部。(The molding condition determination support device and the resin state estimation device are provided with: a quality estimation unit for estimating the quality of the molded product by machine learning based on the detection data; a quality transition storage unit for accumulating the estimated quality of the molded product and storing the accumulated quality transition of the plurality of molded products; a trend evaluation unit for evaluating a quality change trend relative to a predetermined quality standard based on the quality transition; a relation storage unit for storing the relation between the quality change trend and the correction amount of the molding condition for returning to the quality standard; and a correction condition determining unit for determining a correction amount of the molding condition based on the quality change tendency and the relationship.)

1. A molding condition determination assisting device used in a molding method for molding a molded article by supplying a molten material obtained by melting a molding material into a cavity of a mold of a molding machine, and determining a molding condition of the molded article, comprising:

a detection data acquisition unit that acquires detection data detected by a sensor attached to the molding machine during molding;

a quality estimation unit that estimates the quality of the molded product by machine learning based on the detection data;

a quality transition storage unit that accumulates the estimated qualities of the molded products and stores quality transitions regarding the accumulated qualities of the plurality of molded products;

a trend evaluation unit that evaluates a quality change trend with respect to a predetermined quality standard based on the quality transition;

a relationship storage unit that stores a relationship between the quality change tendency and a correction amount of molding conditions for returning the quality to the quality reference; and

and a correction condition determination unit that determines a correction amount of the molding condition based on the quality change tendency evaluated by the tendency evaluation unit and the relationship stored in the relationship storage unit.

2. The molding condition determination assisting device according to claim 1,

further comprising a molten state estimating unit that estimates a molten state of the molten material in the cavity based on the detection data,

the relationship storage unit stores the relationship between the quality change tendency and the correction amount of the molding condition for returning the quality to the quality standard in association with the molten state,

the correction condition determining unit determines the correction amount of the molding condition based on the quality change tendency evaluated by the tendency evaluating unit, the molten state estimated by the molten state estimating unit, and the relationship stored in the relationship storage unit.

3. The molding condition determination assisting device according to claim 2,

the molten state estimating unit estimates a degree of fluidity of the molten material as the molten state of the molten material by the machine learning.

4. The molding condition determination assisting device according to claim 3,

the molten state estimating unit estimates, as the detection data, a degree of fluidity of the molten material as the molten state of the molten material by the machine learning based on a filling time required from start of filling of the molten material in the cavity to completion thereof.

5. The molding condition determination assisting device according to claim 2,

the molten state estimating unit estimates the molten state of the molten material based on the detection data and the molding conditions.

6. The molding condition determination assisting device according to any one of claims 2 to 5,

the molten state estimating unit estimates the molten state of the molten material by referring to an inspection report for a raw material of the molding material in addition to the detection data.

7. The molding condition determination assisting device according to any one of claims 1 to 6,

the trend evaluation section evaluates the quality change trend except for quality changes based on sudden abnormalities.

8. The molding condition determination assisting device according to any one of claims 1 to 7,

the trend evaluation unit evaluates the degree of deviation of a plurality of quality categories from the quality standard as the quality change trend,

the relationship storage unit stores the relationship in which the degree of deviation and the correction amount of the molding condition are expressed in a matrix for each quality type.

9. The molding condition determination assisting device according to claim 8,

the correction condition determining section determines a grade closest to the degree of deviation evaluated by the trend evaluating section among the relationships expressed by the matrix,

the correction amount of the molding condition corresponding to the grade is used as the correction amount of the molding condition.

10. The molding condition determination assisting device according to any one of claims 1 to 9,

the relationship storage unit stores the relationship determined based on relationship information between a quality type estimated as the quality change tendency by the machine learning and a type of molding condition, or,

the relationship determined based on the relationship information between the feature amount of the detection data estimated by the machine learning and the quality type as the quality change tendency and the relationship information between the feature amount of the detection data estimated by the machine learning and the type of the molding condition is stored.

11. The molding condition determination assisting device according to any one of claims 1 to 10,

the kind of the detection data is at least one of a temperature of the molten material in the cavity and a pressure to which the mold is subjected from the molten material,

the quality type of the molded product is at least one of the mass of the molded product, the size of the molded product, and the void volume in the molded product,

the molding conditions are at least one of injection molding speed, pressure holding pressure, pressure holding time, mold temperature during pressure holding, and cooling time.

12. The molding condition determination assisting device according to any one of claims 1 to 11,

the molding condition determining auxiliary device is applied to the molding method for continuously molding the molded product,

in the case where the second molded article is molded after the first molded article,

the detection data acquisition unit performs processing based on the detection data relating to the first molded product,

the quality estimation unit, the trend evaluation unit, and the correction condition determination unit are processed in parallel with a preparation process of the molding machine until molding of the second molded product is started,

the correction condition determining section determines a correction amount of the molding condition with respect to the second molded product.

13. The molding condition determination assisting device according to any one of claims 1 to 12,

the molding condition determination support device further includes a server that forms the same network with a plurality of molding machines having the molding machine,

the server includes at least the relationship storage unit and the correction condition determination unit,

the server receives, from the molding machine or a computer integrally formed with the molding machine, one of the detection data detected by the sensor, the detection data acquired by the detection data acquisition unit, and the quality of the molded product estimated by the quality estimation unit,

determining a correction amount of the molding condition based on the received one of the information,

transmitting the determined correction amount of the molding condition to the molding machine.

14. A resin state estimation device for estimating a molten state of a resin in a cavity of a mold of an injection molding machine, comprising:

a detection data acquisition unit that acquires detection data detected by a sensor attached to the injection molding machine at the time of molding;

a feature value generation unit that generates a feature value group including a plurality of feature values related to the detection data, based on the detection data;

a control parameter acquisition unit that acquires a control parameter value group including a plurality of control parameter values for control in the injection molding machine;

an identification parameter value calculation unit that defines a molten state of the resin as being represented by the characteristic amount group and the control parameter value group, and calculates a resin state identification parameter value representing the molten state of the resin corresponding to each of the characteristic amounts based on the characteristic amount group and the control parameter value group; and

and a group acquisition unit configured to acquire the group of the molten states of the resins by applying multivariate analysis using the resin state identification parameter values as explanatory variables based on the resin state identification parameter values when the molten states of the resins are defined to be classified into a plurality of groups.

15. The resin state inference device according to claim 14, wherein,

the resin state estimation device further includes a learned model storage unit,

the learned model storage unit stores a learned model, sets the resin state identification parameter value as an explanatory variable, sets a group of molten states of the resin as a target variable, applies a cluster analysis as the multivariate analysis, and performs machine learning of the cluster analysis using a training data set including the explanatory variable and the target variable,

the group acquisition unit acquires a group of molten states of the resin as an output of the learned model when the resin state identification parameter value is input.

16. The resin state inference device according to claim 14 or 15,

the identification parameter value calculation unit calculates the resin state identification parameter value according to equations (1) and (2),

wherein the content of the first and second substances,

A(Fj)＝ΠAk …(2)。

17. the resin state estimation device according to any one of claims 14 to 16, wherein,

the identification parameter value calculation unit calculates the resin state identification parameter value corresponding to each of the feature amounts using the feature amount and one or more control parameter values having a high degree of influence on the feature amount.

18. The resin state inference device according to claim 17, wherein,

one or more of the control parameter values having a high degree of influence on the feature amount are extracted by machine learning using the feature amount of the object and the control parameter value group.

19. The resin state inference device according to claim 15, wherein,

the resin state estimation device further includes a learned model generation unit that generates the learned model by performing machine learning of the cluster analysis using a training data set including the explanatory variable and the target variable,

the learned model generation unit acquires a set of molten states of the resin with respect to the acquired detection data in a state where the number of sets of molten states of the resin is set to an initial set number,

determining whether or not the quality of the molded product satisfies a predetermined range when the control parameter value is corrected based on the correction amount of the control parameter value corresponding to the acquired group of the molten states of the resin,

when the quality of the molded product does not satisfy a predetermined range, the number of sets is increased to repeatedly determine whether or not the acquisition of the set of molten states of the resin and the quality of the molded product satisfy the predetermined range,

the number of groups when the quality of the molded product satisfies a predetermined range is set as the number of groups in the learned model.

20. A molding condition determination assisting device applied to a molding method for molding a molded article by supplying a molten material obtained by melting a resin into a cavity of a mold of an injection molding machine, and determining a molding condition of the molded article, comprising:

the resin state inference device of any one of claims 14-19;

a quality estimation unit that estimates the quality of the molded product by machine learning based on the detection data;

a quality transition storage unit that accumulates the estimated qualities of the molded products and stores a plurality of accumulated quality transitions of the molded products;

a trend evaluation unit that evaluates a quality change trend with respect to a predetermined quality standard based on the quality transition;

a relationship storage unit that stores a relationship between the quality change tendency and a correction amount of molding conditions for returning the quality to the quality standard, and a correspondence relationship between a group of molten states of the resin; and

a correction condition determination unit that determines a correction amount of the molding condition based on the quality change tendency evaluated by the tendency evaluation unit, the group of molten states of the resin acquired by the group acquisition unit, and the relationship stored in the relationship storage unit.

Technical Field

The present disclosure relates to a resin state estimation device and a molding condition determination support device.

Background

In a method of molding a molded product by supplying a molding material or a molten material obtained by melting a resin to a cavity of a mold of a molding machine, such as injection molding, when a defective product is generated, a worker needs to correct molding conditions. Modification of the molding conditions requires skilled skill. It is difficult for an unskilled person to judge which molding condition should be changed to which degree.

Therefore, studies on artificial intelligence have been advanced in recent years, and for example, japanese patent laid-open nos. 2020 and 49843 and 2020 and 49929 describe correction amounts for determining molding conditions by machine learning. In the technique described in japanese patent application laid-open No. 2020 and 49843, the relationship between the type of quality of the molded product and the type of molding condition is obtained by machine learning in advance, and when a defect occurs in a certain type of quality, it is sufficient to output which molding condition is corrected. In the technique described in japanese patent application laid-open No. 2020 and 49929, the correction amount of the molding condition is determined by machine learning based on detection data detected by a sensor attached to the molding machine at the time of molding.

In the above-described related art, even if molding is performed under the same molding conditions, the quality of the molded product may vary due to changes in environmental temperature and the like. For example, even during the day, the ambient temperature is different in the morning and at noon. As the ambient temperature increases from morning to noon, the quality of the molded product may change. The same applies to the case where the ambient temperature is low from midday to evening. In addition, the quality of the molded product may be gradually changed in some cases even in seasonal changes. Further, by changing the production lot of the raw material of the molding material, the quality of the molded product may be changed before and after the change. Therefore, when the quality of the molded product changes due to the external factors as described above, it is desirable to correct the molding conditions so that the quality of the molded product approaches the quality standard.

In addition, in injection molding, it is known that the quality of a molded product differs depending on the molten state of the resin in the cavity. For example, the quality of the finished molded product differs between a state in which the fluidity of the resin in the cavity is high and a state in which the fluidity is low.

The molten state of the resin in the cavity is naturally influenced by control parameters for control in the injection molding machine, but may be influenced by other factors, such as the structure, function, and ambient temperature of components constituting the injection molding machine. That is, if the molten state of the resin in the cavity can be grasped, an appropriate correction amount of the molding condition can be determined. However, it is not easy to grasp the molten state of the resin in the cavity.

Further, even if molding is performed under the same molding conditions, the quality of the molded product may vary depending on the slight difference in the components of the raw material of the molding material. Therefore, when the quality of the molded product changes due to the external factors and the slight difference in the content of the raw material of the molding material as described above, it is desirable to correct the molding conditions so that the quality of the molded product approaches the quality standard.

Disclosure of Invention

In view of the above-described related art, the present disclosure provides a molding condition determination assisting device that can modify a molding condition so that the quality of a molded product approaches a quality standard in a case where the quality of the molded product changes due to an external factor.

In addition, the present disclosure provides a resin state estimation device capable of estimating a molten state of a resin in a cavity. Further, the present disclosure provides a molding condition determination assisting device that can correct a molding condition using a resin state estimating device so that the quality of a molded product approaches a quality standard.

Further, the present disclosure provides a molding condition determination assisting device that can correct a molding condition so that the quality of a molded product approaches a quality standard when the quality of the molded product changes due to an external factor or a slight difference in the content of a raw material of a molding material.

(1. auxiliary device for determining Molding conditions)

According to one aspect of the present disclosure, a molding condition determination assisting device is used in a molding method for molding a molded article by supplying a molten material, which is obtained by melting a molding material, to a cavity of a mold of a molding machine, and determines a molding condition of the molded article. The auxiliary device is provided with: a detection data acquisition unit that acquires detection data detected by a sensor attached to the molding machine during molding; a quality estimation unit configured to estimate the quality of the molded product by machine learning based on the detection data; a quality transition storage unit that accumulates the estimated qualities of the molded products and stores accumulated quality transitions of the plurality of molded products; a trend evaluation unit that evaluates a quality change trend with respect to a predetermined quality standard based on the quality transition; a relationship storage unit that stores a relationship between the quality change tendency and a correction amount of molding conditions for returning the quality to the quality standard; and a correction condition determining unit that determines a correction amount of the molding condition based on the quality change tendency evaluated by the tendency evaluating unit and the relationship stored in the relationship storage unit.

The quality transition storage unit accumulates the quality of the molded product estimated by the machine learning and stores the quality transition. The quality transition is information for arranging the qualities of a plurality of molded products in the molding order. Therefore, the trend evaluating unit can evaluate the quality change trend based on the quality shifts of a plurality of continuous molded products.

In particular, the trend evaluation unit evaluates the trend of quality change with respect to a predetermined quality standard. For example, the trend evaluation unit can evaluate, as the quality change trend, a state in which the quality continuously deviates from a predetermined quality standard, a variation in the quality within a quality allowable range including the predetermined quality standard, and the like.

The relationship between the quality change tendency and the correction amount of the molding conditions is stored in the relationship storage unit in advance. The relationship may be set using experience of a skilled person, an output result of machine learning, an experimental result, or the like. The correction condition determination unit determines the correction amount of the molding condition based on the newly evaluated quality change tendency and the relationship stored in the relationship storage unit. Here, the relationship stored in the relationship storage unit is related to a correction amount of the molding condition for returning the quality to a predetermined quality standard. Therefore, when the molding conditions of the molding machine are corrected in accordance with the correction amount of the molding conditions determined by the correction condition determining unit, the quality of the molded product to be molded next can be brought close to the predetermined quality standard.

That is, even when the quality of the molded product changes due to external factors such as the environmental temperature, the molding conditions can be corrected so that the quality of the molded product can be set to a predetermined quality standard by grasping the tendency of the change in quality. Therefore, the molding conditions can be corrected not only by a skilled person but also by an unskilled person so that the quality of the molded product can be improved.

(2-1. resin state estimating device)

According to another aspect of the present disclosure, a resin state estimation device estimates a molten state of a resin in a cavity of a mold of an injection molding machine, the resin state estimation device including: a detection data acquisition unit for acquiring detection data detected by a sensor mounted on the injection molding machine during molding; a feature value generation unit that generates a feature value group including a plurality of feature values related to the detection data based on the detection data; and a control parameter acquisition unit that acquires a control parameter value group composed of a plurality of control parameter values for control in the injection molding machine; an identification parameter value calculation unit that defines a molten state of the resin as being represented by the characteristic amount group and the control parameter value group, and calculates a resin state identification parameter value representing the molten state of the resin corresponding to each characteristic amount based on the characteristic amount group and the control parameter value group; and a group acquisition unit that acquires a group of the molten state of the resin by applying a multivariate analysis in which the resin state identification parameter value is set as an explanatory variable based on the resin state identification parameter value, when the molten state of the resin is defined to be classified into a plurality of groups.

The detection data detected by the sensor attached to the injection molding machine at the time of molding is considered to be influenced by the control parameters of the injection molding machine and the molten state of the resin in the cavity. In other words, the molten state of the resin is defined as being represented by the feature value group and the control parameter value group generated from the detection data.

With this definition, the identification parameter value calculation unit calculates a resin state identification parameter value indicating the molten state of the resin corresponding to each characteristic amount, based on the characteristic amount group and the control parameter value group of the detection data. That is, the resin state identification parameter values are generated in the same number as the number of kinds of the feature amounts.

When the molten state of the resin is defined to be classified into a plurality of groups, the group acquisition unit acquires the group of molten states of the resin by applying multivariate analysis in which the resin state identification parameter value is set as an explanatory variable based on the resin state identification parameter value. Here, the group of molten states of the resins need not be clearly defined, but for example, the degree of fluidity can be classified as one of the elements.

That is, according to the resin state estimating device, by performing arithmetic processing using the detection data and the control parameter, it is possible to classify the set of the molten state of the resin in the cavity at the time of molding the molded product, for example, the degree of fluidity of the resin, as one of the factors. In this way, the molten state of the resin in the cavity can be grouped, and the correction amount of the molding condition corresponding to the group can be determined.

(2-2. auxiliary device for determining Molding Condition)

According to another aspect of the present disclosure, a molding condition determination assisting device is used in a molding method for supplying a molten material, which is obtained by melting a resin, to a cavity of a mold of an injection molding machine to mold a molded article, and determines a molding condition of the molded article, the molding condition determination assisting device including: the resin state estimating device described above; a quality estimation unit for estimating the quality of the molded product by machine learning based on the detection data; a quality transition storage unit which accumulates the estimated quality of the molded product and stores accumulated quality transitions of the plurality of molded products; a trend evaluation unit for evaluating a quality change trend relative to a predetermined quality standard based on the quality transition; a relationship storage unit that stores a relationship between a quality change trend and a correction amount of molding conditions for returning the quality to a quality standard, in association with a set of molten states of the resin; and a correction condition determining unit that determines a correction amount of the molding condition based on the quality change tendency evaluated by the tendency evaluating unit, the group of molten states of the resin acquired by the group acquiring unit, and the relationship stored in the relationship storage unit.

That is, the correction amount of the molding condition is determined using the set of molten states of the resin acquired by the resin state estimation device. This makes it possible to easily determine the correction amount of the appropriate molding conditions.

(3. auxiliary device for determining formation)

According to another aspect of the present disclosure, a molding condition determination assisting device is used in a molding method for molding a molded article by supplying a molten material, which is obtained by melting a molding material, to a cavity of a mold of a molding machine, and determines a molding condition of the molded article. The auxiliary device is provided with: a detection data acquisition unit for acquiring detection data detected by a sensor mounted on the molding machine during molding; a quality estimation unit configured to estimate the quality of the molded product by machine learning based on the detection data; a quality transition storage unit configured to accumulate the estimated qualities of the molded products and store accumulated quality transitions of the plurality of molded products; a trend evaluation unit for evaluating a quality change trend with respect to a predetermined quality standard based on the quality transition; a molten state estimating unit configured to estimate a molten state of the molten material in the cavity based on the detection data; a relationship storage unit that stores a relationship between the quality change tendency and a correction amount of molding conditions for returning the quality to the quality standard, in association with the molten state; and a correction condition determining unit configured to determine a correction amount of the molding condition based on the quality change tendency evaluated by the tendency evaluating unit, the molten state evaluated by the molten state estimating unit, and the relationship stored in the relationship storage unit.

The quality transition storage unit accumulates the quality of the molded product estimated by the machine learning and stores the quality transition. The quality transition is information for arranging the qualities of a plurality of molded products in the molding order. Therefore, the trend evaluating unit can evaluate the quality change trend based on the quality shifts of a plurality of continuous molded products.

In particular, the trend evaluation unit evaluates the trend of quality change with respect to a predetermined quality standard. For example, the trend evaluation unit can evaluate, as the quality change trend, a state in which the quality continuously deviates from a predetermined quality standard, a variation in the quality within a quality allowable range including the predetermined quality standard, and the like.

The molten state estimating unit estimates the molten state of the molten material in the cavity based on the detection data. Here, the molten state depends on the content of the raw material of the molding material. For example, the variation of the content of the component in the raw material of the molding material includes the moisture content, the length of the reinforcing fiber, the ratio of the reinforcing fiber, the molecular weight of the main component, and the like. Further, the molten state in the cavity affects the detection data at the time of molding. Therefore, the molten state estimating unit can estimate the molten state by using the detection data depending on the molten state at the time of actual molding.

The relationship between the quality change trend and the correction amount of the molding conditions is stored in the relationship storage unit in advance by establishing a correspondence relationship between the molten state of the molten material in the cavity. That is, the relationship between the quality change tendency and the correction amount of the molding conditions is stored in the relationship storage unit for each type of the molten state of the molten material. The relationship may be set using experience of a skilled person, an output result of machine learning, an experimental result, or the like.

The correction condition determination unit determines the correction amount of the molding condition based on the newly evaluated quality change tendency, the newly estimated melting state of the molten material in the cavity, and the relationship stored in the relationship storage unit. Here, the relationship stored in the relationship storage unit is related to a correction amount of the molding condition for returning the quality to a predetermined quality standard. In particular, the amount of correction of the molding conditions is determined according to the molten state of the molten material in the cavity. Therefore, when the molding conditions of the molding machine are corrected in accordance with the correction amount of the molding conditions determined by the correction condition determining unit, the quality of the molded product to be molded next can be brought close to the predetermined quality standard.

That is, even when the quality of the molded product changes due to external factors such as ambient temperature and slight differences in the content of the raw material of the molding material, the molding conditions can be corrected so that the quality of the molded product can be brought to a predetermined quality standard by grasping the tendency of the change in quality and further grasping the molten state of the molten material in the cavity. Therefore, the molding conditions can be corrected so as to improve the quality of the molded product, not only by a skilled person but also by an unskilled person.

Drawings

Fig. 1 is a diagram showing an overall configuration of a molding machine system according to a first embodiment.

Fig. 2 is an enlarged view of a mold of the molding machine shown in fig. 1.

Fig. 3 is a cross-sectional view of the mold taken along line III-III of fig. 2.

Fig. 4 is a functional block diagram showing a molding condition determination assisting apparatus.

Fig. 5 is a graph showing detection data.

Fig. 6 is a graph showing the transition of quality.

Fig. 7 is a graph showing the trend of quality change.

Fig. 8 is a diagram showing a relationship between the degree of quality deviation and the correction amount.

Fig. 9 is a diagram illustrating a first example of the learning stage of the relationship between the quality deviation degree and the correction amount.

Fig. 10 is a diagram for explaining a second example in the stage of learning the relationship between the quality deviation degree and the correction amount.

Fig. 11 is a diagram showing operation timings of the process of the molding machine and the process of the molding condition determination assisting device. Is a graph of the passage of time from top to bottom.

Fig. 12 is a diagram showing a configuration example of the molding machine system.

Fig. 13 is a diagram showing an overall configuration of a molding machine system according to a first example of the second embodiment.

Fig. 14 is a diagram showing the relationship between control parameters, the molten state of the resin, and detection data.

Fig. 15 is a relational expression schematically showing the resin state identification parameter values.

Fig. 16 is a graph showing detection data.

Fig. 17 is a schematic diagram of a group showing a molten state of a resin.

Fig. 18 is a diagram showing a functional block configuration of the resin state estimating device.

Fig. 19 is a diagram showing an overall configuration of a molding machine system according to a second example of the second embodiment.

Fig. 20 is a diagram showing a functional block configuration of the molding condition determination assisting apparatus.

Fig. 21 is a graph showing the transition of quality.

Fig. 22 is a diagram showing a trend of quality change.

Fig. 23 is a diagram showing a set of resins in a molten state.

Fig. 24 is a diagram showing a relationship between a quality deviation degree and a correction amount.

Fig. 25 is a diagram showing a configuration example of the molding machine system.

Fig. 26 is a diagram showing the overall configuration of the molding machine system according to the third embodiment.

Fig. 27 is an enlarged view of a mold of the molding machine shown in fig. 26.

Fig. 28 is a cross-sectional view of the mold taken along line III-III of fig. 27.

Fig. 29 is a functional block diagram of a molding condition determination assisting apparatus.

Fig. 30 is a graph showing detection data.

Fig. 31 is a graph showing the transition of quality.

Fig. 32 is a graph showing the trend of quality change.

Fig. 33 is a diagram showing the type of molten state of the molten material.

Fig. 34 is a diagram showing a relationship between a quality deviation degree and a correction amount.

Fig. 35 is a diagram for explaining a first example of the learning stage of the relationship between the quality deviation degree and the correction amount.

Fig. 36 is a diagram for explaining a second example in the stage of learning the relationship between the quality deviation degree and the correction amount.

Fig. 37 is a diagram showing operation timings of the process of the molding machine and the process of the molding condition determination assisting device. Is a graph of the passage of time from top to bottom.

Fig. 38 is a diagram showing a configuration example of the molding machine system.

Detailed Description

The following describes a molding condition determination assisting device as a first embodiment. The present disclosure is not limited to the first embodiment, and various design changes can be made without departing from the spirit of the present disclosure.

(1. applicable object)

The molding condition determination assisting device is suitable for a molding method for molding a molded product by supplying a molten material obtained by melting a molding material into a cavity of a mold of a molding machine. The molding machine to which the present invention is applied may be, for example, an injection molding machine that performs injection molding of resin, rubber, or the like as a molding material. Other molding machines to which the present invention is applied may be blow molding machines and compression molding machines, for example. Examples of the resin as the molding material include a thermoplastic resin such as polyamide as a monomer, and a reinforced resin obtained by adding a filler to a base material of the thermoplastic resin. Examples of the filler include micron-sized or nano-sized fillers. Examples of the filler include glass fibers and carbon fibers.

(2. Molding machine System 1)

A molding machine system 1 including a molding condition determination assisting device will be described with reference to fig. 1. As shown in fig. 1, the molding machine system 1 includes a molding machine 2 and a molding condition determination assisting device 3.

The molding machine 2 is an injection molding machine, a blow molding machine, a compression molding machine, or the like. In this example, the molding machine 2 is exemplified by an injection molding machine. The molding machine 2 molds a resin molded product, for example. The molding condition determination assisting device 3 is a device for determining the molding condition in the molding machine 2. In particular, in the present example, when the molding condition determination assisting device 3 performs molding of the molded article according to the molding condition that has been applied, it determines the correction amount of the molding condition for improving the quality of the molded article.

The molding condition determination assisting device 3 may be a device separate from the molding machine 2, or may be an assembling device of the molding machine 2. Further, the molding condition determination assisting device 3 may be partially assembled to the molding machine 2 and the remaining part may be separated from the molding machine 2. When all or a part of the molding condition determination assisting device 3 is separate from the molding machine 2, the separate part may be connected to only one molding machine 2 or may be connected to a plurality of molding machines 2. In the latter case, the separate part of the molding condition determination support device 3 and the plurality of molding machines 2 form the same network and are configured to be able to communicate with each other.

(3. Forming machine 2)

(3-1. Structure of Forming machine 2)

A structure of an injection molding machine as an example of the molding machine 2 will be described with reference to fig. 1. The molding machine 2 mainly includes a base 20, an injection device 30, a mold 40, a mold clamping device 50, and a control device 60.

The injection molding device 30 is disposed on the base 20. The injection molding apparatus 30 melts the molding material and supplies the molten material to the cavity C1 of the mold 40 by applying pressure to the molten material. The injection molding device 30 mainly includes a hopper 31, a heating cylinder 32, a screw 33, a nozzle 34, a heater 35, a driving device 36, and an injection molding device sensor 37.

The hopper 31 is a charging port for particles (granular molding material) as a raw material of the molding material. The heating cylinder 32 heats and melts the pellets fed into the hopper 31 and pressurizes the formed molten material. In addition, the heating cylinder 32 is provided to be movable in the axial direction of the heating cylinder 32 with respect to the base 20. The screw 33 is disposed inside the heating cylinder 32, and is provided to be rotatable and movable in the axial direction. The nozzle 34 is an injection port provided at the tip of the heating cylinder 32, and supplies the molten material inside the heating cylinder 32 to the mold 40 by the axial movement of the screw 33.

The heater 35 is provided outside the heating cylinder 32, for example, and heats the particles inside the heating cylinder 32. The driving device 36 moves the heating cylinder 32 in the axial direction, rotates the screw 33, and moves the screw in the axial direction. The injection device sensor 37 is collectively referred to as a sensor for acquiring the amount of accumulated molten material, the holding pressure, the holding time, the injection speed, the state of the drive device 36, and the like. However, the sensor 37 for the injection device is not limited to the above, and can acquire various kinds of information.

The mold 40 is a metal mold including a first mold 41 as a fixed side and a second mold 42 as a movable side. The mold 40 forms a cavity C1 between the first mold 41 and the second mold 42 by clamping the first mold 41 and the second mold 42. The first mold 41 includes a supply path 43 (sprue, runner, gate) for guiding the molten material supplied from the nozzle 34 to the cavity C1. The mold 40 is provided with a pressure sensor 44 and a temperature sensor 45. The pressure sensor 44 detects the pressure received from the molten material in the supply path 43. The temperature sensor 45 directly detects the temperature of the molten material in the supply path 43.

The mold clamping device 50 is disposed on the base 20 so as to face the injection device 30. The mold clamping device 50 performs opening and closing operations of the attached mold 40, and prevents the mold 40 from being opened by the pressure of the molten material injected into the cavity C1 in a state where the mold 40 is fastened.

The mold clamping device 50 includes a fixed platen 51, a movable platen 52, a tie bar 53, a drive device 54, and a mold clamping device sensor 55. The first mold 41 is fixed to the fixed platen 51. The stationary platen 51 can be brought into contact with the nozzle 34 of the injection device 30, and guides the molten material injected from the nozzle 34 to the mold 40. The second mold 42 is fixed to the movable platen 52. The movable disk 52 can be moved toward and away from the fixed disk 51. The pull rod 53 supports the movement of the movable disk 52. The driving device 54 is constituted by, for example, a cylinder device, and moves the movable disk 52. The mold clamping device sensor 55 is collectively referred to as a sensor for acquiring a mold clamping force, a mold temperature, a state of the drive device 54, and the like.

The controller 60 controls the drive unit 36 of the injection molding device 30 and the drive unit 54 of the mold clamping device 50. For example, the controller 60 acquires various information from the injection device sensor 37 and the mold clamping device sensor 55, and controls the drive device 36 of the injection device 30 and the drive device 54 of the mold clamping device 50 to perform operations according to the operation command data.

(3-2. Molding method)

A method of molding a molded article by the molding machine 2 will be described. In the molding method using the molding machine 2, a metering process, a mold clamping process, an injection filling process, a pressure maintaining process, a cooling process, and a mold releasing and taking-out process are sequentially performed in one cycle. That is, the above-described steps are sequentially executed again in the molding of the next molded product. Here, the measurement step and the mold clamping step constitute a start preparation step, the injection filling step, the pressure holding step, and the cooling step constitute a molding step, and the mold release removal step constitutes an end treatment step. In addition, the initial stage of the mold release removal step (immediately after the mold is opened) may be included in the molding step, and the subsequent stage may be a finishing step.

In the metering step, the pellets are melted by heating by the heater 35 and shear friction heat accompanying rotation of the screw 33, and the molten material is accumulated between the tip of the screw 33 and the nozzle 34 in the heating cylinder 32. Since the screw 33 is retreated as the amount of the molten material stored increases, the amount of the molten material stored is measured in accordance with the retreated position of the screw 33.

In the mold clamping step after the measuring step, the movable platen 52 is moved to align the first mold 41 and the second mold 42, and mold clamping is performed. The heating cylinder 32 is moved in the axial direction to approach the mold clamping device 50, and the nozzle 34 is connected to a stationary platen 51 of the mold clamping device 50. Next, in the injection filling step, the screw 33 is moved toward the nozzle 34 by a predetermined thrust force in a state where the rotation of the screw 33 is stopped, and thereby the molten material is injection filled into the mold 40 at a high pressure. When the cavity C1 is filled with the molten material, the process proceeds to the pressure maintaining step.

In the pressure holding step, the molten material is further press-fitted into the cavity C1 in a state where the cavity C1 is filled with the molten material, and pressure holding processing is performed to apply a predetermined pressure (pressure holding pressure) to the molten material in the cavity C1 for a predetermined time. Specifically, a predetermined holding pressure is applied to the molten material by applying a constant thrust force to the screw 33.

After the dwell pressure treatment is performed for a predetermined time at a predetermined dwell pressure, the process proceeds to a cooling step. In the cooling step, the mold 40 is cooled by stopping the pushing of the molten material and reducing the holding pressure. By cooling the mold 40, the molten material supplied to the mold 40 is solidified. Finally, in the mold-releasing and taking-out step, the second mold 42 is separated from the first mold 41, and the molded article is taken out.

(3-3. mold 40)

The detailed structure of the mold 40 will be described with reference to fig. 2 and 3. The mold 40 is a so-called multiple-part mold, and a plurality of cavities C1 are formed in the mold 40, but only one cavity C1 is shown in fig. 2 and 3 to simplify the drawing. In this example, the molded article molded by the molding machine 2 is a retainer for a constant velocity universal joint. Therefore, the molded product is annular, and the cavity C1 is formed in an annular shape conforming to the shape of the retainer. The shape of the molded article and the cavity C1 may be other than annular, for example, C-shaped, rectangular frame-shaped, or the like.

The supply path 43 includes a sprue 43a, a runner 43b, and a gate 43 c. The nozzle 43a is a passage through which the molten material is supplied from the nozzle 34. The runner 43b is a passage branched from the sprue 43a, and the molten material supplied to the sprue 43a flows into the runner 43 b. The gate 43C is a passage for introducing the molten material flowing into the runner 43b into the cavity C1, and the flow path cross-sectional area of the gate 43C is smaller than that of the runner 43 b. In the mold 40, runners 43b and gates 43C are formed in the same number as the number of the cavities C1, and the molten material supplied to the sprue 43a is supplied to each cavity C1 via the runners 43b and the gates 43C.

When the cavity C1 is annular and the first mold 41 includes one gate 43C, the inflow path of the molten material in the cavity C1 is a path that flows from the gate 43C in the annular circumferential direction of the cavity C1. That is, in the cavity C1, the molten material first flows into the vicinity of the gate 43C and finally flows into the farthest distance from the gate 43C.

Further, the mold 40 is provided with a pressure sensor 44, and the pressure sensor 44 detects the pressure received from the molten material in the supply path 43. In this example, a plurality of pressure sensors 44 are provided. For example, the pressure sensor 44 is provided in the cavity C1 in the vicinity of the gate 43C, which is the farthest position from the gate 43C. The pressure sensor 44 may be provided in the sprue 43a and the runner 43 b. The pressure sensor 44 may be a contact sensor or a non-contact sensor.

Further, the mold 40 is provided with a temperature sensor 45 that detects the temperature of the molten material in the supply path 43. The temperature sensor 45 may be provided in the cavity C1, or may be provided in the sprue 43a or the runner 43b, as in the case of the pressure sensor 44. In addition, a plurality of temperature sensors 45 may be provided.

(4. Structure of auxiliary device for determining Molding Condition 3)

The structure of the molding condition determination assisting apparatus 3 will be described with reference to fig. 4 to 8. The molding condition determination assisting device 3 includes, for example: an arithmetic processing device including a processor, a storage device, an interface, and the like; an input device connectable to an interface of the arithmetic processing apparatus; and an output device connectable to an interface of the arithmetic processing apparatus. The output device may also include a display device, for example. The arithmetic processing device, the input device, and the output device may be configured as a single unit without an interface. In addition, a physical server or a cloud server may be applied to a part of the arithmetic processing device and a part of the storage device.

As shown in fig. 4, the molding condition determination support device 3 includes a detection data acquisition unit 101, a quality estimation unit 102, a quality transition storage unit 103, a trend evaluation unit 104, a relationship storage unit 105, and a correction condition determination unit 106.

The detection data acquiring unit 101 acquires detection data detected by the sensors 44 and 45 attached to the molding machine 2 at the time of molding. That is, the type of the detection data acquired by the detection data acquiring unit 101 is at least one of the pressure that the mold 40 receives from the molten material in the supply path 43 and the temperature of the molten material in the supply path 43.

The detection data by the pressure sensor 44 is, for example, data as shown in fig. 5. In fig. 5, a time T1 is a filling start time, a time T2 is a filling end time and a holding pressure start time, a time T3 is a holding pressure end time and a cooling start time, and a time T4 is a cooling end time and a mold opening time. That is, the injection filling step is performed between T1 and T2, the pressure holding step is performed between T2 and T3, and the cooling step is performed between T3 and T4. In fig. 5, the maximum pressure in the pressure holding step is set to the maximum pressure Pmax, the pressure integrated value in the pressure holding step is set to the pressure holding area Sa, and the pressure integrated value in the cooling step is set to the cooling area Sb.

The quality estimation unit 102 estimates the quality of the molded product by machine learning based on the detection data acquired by the detection data acquisition unit 101. For example, the quality estimation unit 102 estimates a numerical value in one or more quality types in the molded product. The quality type of the molded product is at least one of the mass of the molded product, the size of the molded product, and the void volume in the molded product.

The quality estimation unit 102 generates a learned model in which the relationship between the detection data and the quality of the molded product is learned by machine learning in advance. The learning completion model is generated for each quality type. Further, the quality estimation unit 102 stores the learned model, and estimates the quality of the molded product using the newly acquired detection data and the learned model.

The quality transition storage unit 103 accumulates the qualities of the molded products estimated by the quality estimation unit 102, and stores the transition of the qualities of the plurality of accumulated molded products. The quality transition is information for arranging the qualities of a plurality of molded products in the molding order. The quality transition is, for example, data as shown in fig. 6. Fig. 6 shows an example of the quality of the molded product. In fig. 6, Std is a predetermined quality standard, Thmax is an upper limit value of a quality allowable range, and Thmin is a lower limit value of the quality allowable range. That is, a range between the upper limit value Thmax and the lower limit value Thmin means a non-defective product, and the deviation range means a defective product. Even a non-defective product is ideally a predetermined quality standard Std.

In fig. 6, the quality of most of the molded articles at the beginning of molding shows a value near the quality standard Std. However, as the sudden abnormality, there is a molded article which shows a value exceeding the upper limit value Thmax (a 2 in fig. 6). That is, when the molded article having an unexpected abnormality is excluded, the quality of the molded article at the beginning of molding shows a value near the quality standard Std (a 1 in fig. 6). Thereafter, when the molding is continued, the quality of the molded product gradually deviates from the quality standard Std. Further, the quality of the molded article showed an increase from the quality standard Std by around the value of + N% (a 3 in fig. 6).

The trend evaluation unit 104 evaluates the trend of the quality change with respect to the quality standard Std based on the quality transition stored in the quality transition storage unit 103. As shown in fig. 7, the trend evaluation unit 104 evaluates, as the quality change trend, the degree of deviation of the quality from the quality standard Std for each of the plurality of quality types and the degree of deviation of the quality of the plurality of molded articles for each of the plurality of quality types.

The trend evaluation unit 104 sets in advance the number of molded articles in which the quality changes for evaluating the trend of quality changes. That is, the trend evaluating unit 104 calculates the degree of quality deviation of the number of molded products set in advance. For example, the trend evaluating unit 104 calculates the degree (absolute value or relative value) of deviation of the average value of the quality of the number of molded products from the quality standard Std as the degree of deviation of the quality. Further, the degree of variation means a degree of quality variation or stability indicating the number of molded articles set in advance. Further, the degree of deviation may be a value such as a standard deviation or a variance.

As shown in fig. 7, for example, the trend evaluating unit 104 evaluates the degree of deviation "+ 2.2%" for the quality and the degree of deviation "stable", evaluates the degree of deviation "+ 0.3%" for the size and the degree of deviation "stable", and evaluates the degree of deviation "-0.5%" for the void volume and the degree of deviation "stable".

In a1 showing the quality transition shown in fig. 6, the trend evaluation unit 104 evaluates that the trend is stable and is located near the quality standard Std as the quality change trend. Here, the trend evaluation unit 104 performs evaluation with the exception of the a2 molded product showing a quality change due to sudden abnormality in a1 showing a quality transition shown in fig. 6. In this case, the trend evaluation unit 104 evaluates the degree of deviation from the quality standard Std as "0.1%" and the degree of deviation as "stable" for the target quality type. Also, since the quality of the molded product returns to normal after the sudden abnormality, the sudden abnormality is not related to the molding conditions. Therefore, the burst anomaly is evaluated exclusive of the other.

In a3 showing the quality transition shown in fig. 6, the trend evaluation unit 104 evaluates that the trend of the quality is stable and shows a value that is deviated from the quality standard Std by about + N%. In this case, the trend evaluation unit 104 evaluates the degree of deviation from the quality standard Std as "+ N%" and the degree of deviation as "stable" for the target quality type.

The relationship storage unit 105 stores the relationship between the quality change tendency and the correction amount of the molding condition for returning the quality to the quality standard. The relation storage unit 105 stores, for example, as shown in fig. 8, a relation between the degree of deviation of the matrix and the correction amount of the molding condition for each quality type. For example, the mass, the size, and the void volume are each set to six levels as the level of the degree of deviation. The type of the molding condition to be corrected is at least one of an injection speed, a holding pressure, a holding time, a mold temperature at the time of holding pressure, a cooling time, and the like.

Here, the degree of the relationship between the quality type and the type of the molding condition, and the relationship between the degree of deviation of the quality type and the correction amount of the molding condition can be derived by machine learning. That is, the relationship stored in the relationship storage unit 105 can be generated by machine learning. Of course, this relationship may be set based on an experiment, past experience, or the like, instead of machine learning.

The correction condition determining unit 106 determines the correction amount of the molding condition based on the quality change tendency evaluated by the tendency evaluating unit 104 and the relationship stored in the relationship storage unit 105. For example, the correction condition determination unit 106 determines a grade closest to the degree of deviation evaluated by the trend evaluation unit 104 among the relationships expressed by the matrix as shown in fig. 8, and sets the correction amount of the molding condition corresponding to the grade as the correction amount of the determined molding condition. For example, as shown in fig. 7, when the degree of deviation of the mass is "+ 2.2%", the rank "+ 2%" of the degree of deviation of the mass is selected in the matrix shown in fig. 8.

Here, the correction condition determination unit 106 determines the correction amount of the molding condition for each of the plurality of quality types. Therefore, the correction condition determination unit 106 determines the final correction amount for the molding condition based on a plurality of correction amounts for the same type of molding condition. In this case, the correction condition determination unit 106 may determine, for example, a value obtained by summing a plurality of correction amounts as a final correction amount, or may determine, as a final correction amount, a value obtained by multiplying a weighting coefficient according to the quality type and then further summing the values.

Then, the correction condition determining unit 106 outputs the final correction amount to the control device 60 of the molding machine 2, and adds the correction amount to the molding condition of the next molded product. Therefore, the control device 60 performs molding of the next molded product according to the corrected molding conditions. As a result, the quality of the molded product molded under the corrected molding conditions can be brought close to the quality standard Std.

(5. determining the Effect of the auxiliary device 3 based on the Molding conditions)

The effect of the auxiliary device 3 determined by the molding conditions described above will be described. The quality transition storage unit 103 accumulates the quality of the molded product estimated by the machine learning and stores the quality transition. The quality transition is information for arranging the qualities of a plurality of molded products in the molding order. Therefore, the trend evaluating unit 104 can evaluate the quality change trend based on the quality shifts of a plurality of continuous molded products.

In particular, the trend evaluation unit 104 evaluates the trend of the quality change with respect to a predetermined quality standard Std. For example, the trend evaluation unit 104 can evaluate, as the quality change trend, a state in which the quality continuously deviates from the predetermined quality standard Std, a variation in the quality within a quality allowable range including the predetermined quality standard, and the like.

Further, the relationship between the quality change tendency and the correction amount of the molding condition is stored in the relationship storage unit 105 in advance. The relationship is set using experience of a skilled person, an output result of machine learning, an experimental result, and the like. Further, the correction condition determination unit 106 determines the correction amount of the molding condition based on the newly evaluated quality change tendency and the relationship stored in the relationship storage unit 105.

Here, the relationship stored in the relationship storage unit 105 is related to a correction amount of the molding condition for returning the quality to the predetermined quality standard Std. Therefore, when the molding conditions of the molding machine 2 are corrected in accordance with the correction amount of the molding conditions determined by the correction condition determining unit 106, the quality of the molded product to be molded next can be brought close to the predetermined quality standard Std.

That is, even when the quality of the molded product changes due to an external factor such as the ambient temperature, the molding conditions can be corrected so that the quality of the molded product can be set to the predetermined quality standard Std by grasping the tendency of the change in quality. Therefore, the molding conditions can be corrected not only by a skilled person but also by an unskilled person, and the quality of the molded product can be improved.

(6. learning stage in quality inference)

As described above, the quality estimation unit 102 estimates the quality by machine learning. The learned model is stored in the quality estimation unit 102. The learned model is generated in advance. An example of the learning phase, which is the generation of the learned model, will be described.

First, detection data for a plurality of molded articles is acquired. Here, the feature amount of the detection data is extracted based on the detection data. For the extraction of the feature amount, for example, the maximum holding pressure Pmax in the holding step, the pressure deviation in the holding step, the holding area Sa (shown in fig. 5), the actual holding time (holding time obtained based on the pressure data), the change speed of the pressure at the start of the holding step (pressure differential value), and the like are used based on the pressure data detected by the pressure sensor 44. For the extraction of the feature amount, the cooling area Sb (shown in fig. 5), the change speed of the pressure in the cooling step (pressure differential value), and the like are used based on the pressure data.

Then, for the extraction of the feature amount, the maximum temperature in the pressure holding step, the temperature deviation in the pressure holding step, the temperature area (temperature × time) in the pressure holding step, the cooling area (temperature × time) in the cooling step, the change speed (differential value) of the temperature in the cooling step, and the like are used based on the temperature data detected by the temperature sensor. In addition, since the plurality of pressure sensors 44 and temperature sensors 45 are provided in the mold 40, the above-described information is used for extracting the feature amount for each sensor.

Then, the plurality of pieces of information are acquired for the plurality of molded articles. Then, for each of the above information, the maximum value, the minimum value, the average value, the variance, and the like of the plurality of molded articles are calculated and used as the feature values.

On the other hand, the quality of a plurality of molded articles is measured using an external measuring instrument or the like. For example, as the quality, the mass, the size, the void volume, and the like are measured. Then, a learned model is generated by performing machine learning with the feature amount as an explanatory variable and the quality as a target variable. The learned model is a model into which the feature quantity and the output quality of the detection data can be input.

In the above description, a learning model in which the feature amount is used as the explanatory variable has been described, but the feature amount may not be used as the explanatory variable but the detection data itself may be used as the explanatory variable by the learning model to output the quality as the target variable.

(7. learning phase of relationship decision)

The relationship between the degree of quality deviation and the correction amount stored in the relationship storage unit 105 can be generated by machine learning, for example. In the following, the generation of the relationship will be described with respect to a case of using machine learning.

(7-1. first example)

A first example of the learning phase will be described with reference to fig. 9. In the first example of the learning stage, as shown in fig. 9, the relationship between the quality type and the type of molding condition is directly generated by machine learning.

For example, a value of quality in each quality type and a value of molding condition are input, and a degree of influence (contribution degree, influence degree) of the molding condition on the quality type is acquired by machine learning. Further, the degree to which the correction amount of the value of the molding condition affects the value of the quality may be acquired. As a result, it is possible to obtain information on the relationship between the quality type and the type of the molding condition, and further obtain information on the relationship between the quality value and the correction amount of the molding condition.

The human determines the relationship expressed by the matrix shown in fig. 8 based on the relationship information obtained by machine learning. Of course, a matrix such as that shown in fig. 8 can also be generated by machine learning.

(7-2. second example)

A second example of the learning phase will be described with reference to fig. 10. In the second example of the learning stage, as shown in fig. 10, the relationship between the quality type and the type of molding condition is indirectly generated by machine learning.

In the first example shown in fig. 9, the relationship between the quality type and the type of molding condition is directly generated by machine learning. However, the relationship between the quality type and the type of molding conditions may not be obtained directly. Here, the molding conditions determine the state at the time of molding, and the state determination quality at the time of molding is obvious. That is, it can be said that the molding conditions and the quality are kept in relation to each other depending on the state at the time of molding. The state during molding is, for example, the maximum holding pressure Pmax, the holding area Sa, the cooling area Sb, and the like.

Therefore, first, a value of quality in each quality type and a feature amount of detection data (a feature amount obtained from the maximum holding pressure or the like) are input, and a degree (contribution degree, influence degree) of influence of the feature amount of the detection data on the quality type is acquired by machine learning. Further, the degree of influence of the value of the feature amount of the detection data on the value of the quality may be acquired. As a result, it is possible to obtain information on the relationship between the quality type and the feature value of the detection data, and further obtain information on the relationship between the quality value and the feature value of the detection data.

Next, the feature amount of the detection data and the type of the molding condition are input, and the degree (contribution degree, influence degree) of influence of the type of the molding condition on the feature amount of the detection data is acquired by machine learning. Further, the degree to which the correction amount of the value of the molding condition affects the value of the feature amount of the detection data may be acquired. As a result, it is possible to obtain information on the relationship between the feature amount of the detection data and the type of the molding condition, and further obtain information on the relationship between the correction amount of the feature amount value of the detection data and the value of the molding condition.

Then, the person determines the relationship expressed by the matrix as shown in fig. 8 based on the information on the relationship between the quality type and the feature amount of the detection data, the information on the relationship between the feature amount of the detection data and the type of the molding condition, and the like. Of course, a matrix such as that shown in fig. 8 can also be generated by machine learning.

(8. operation timing of molding machine System 1)

(8-1. basic)

The operation timing of the molding machine system 1, in particular, the operation timing of the process performed by the molding machine 2 and the process performed by the molding condition determination assisting device will be described with reference to fig. 11. First, the molding machine 2 continuously molds the molded product. For ease of description, a case where the second molded article is molded after the first molded article will be described.

As shown in fig. 11, the molding machine 2 performs a start preparation process for the first molded product (S11). The start preparation step includes, for example, a measurement step and a mold clamping step. Next, the molding machine 2 performs a molding process for the first molded product (S12). The molding step includes, for example, an injection filling step, a pressure holding step, and a cooling step. Next, the molding machine 2 performs a finishing process for the first molded product (S13). The finishing step includes, for example, a mold release removal step.

However, when the molding condition determination assisting device 3 uses the detection data detected by the pressure sensor 44 and the temperature sensor 45 at the beginning of the mold release taking-out step (immediately after the mold is opened), the beginning of the mold release taking-out step may be included in the molding step.

After the molding of the first molded article, the molding machine 2 starts processing related to the molding of the second molded article. First, the molding machine 2 performs a start preparation process for a second molded product (S21). Next, the molding machine 2 performs a molding process for a second molded product (S22). Next, the molding machine 2 performs a finishing process for the second molded product (S23).

On the other hand, the molding condition determination assisting device 3 performs processing in parallel with the processing of the molding machine 2. Specifically, a primary processing step (S101) of processing in parallel with the detection of data by the pressure sensor 44 and the temperature sensor 45 when the first molded product is molded, and a secondary processing step (S102) of processing in parallel with the finishing processing step (S13) of the first molded product and the start preparation step (S21) of the second molded product are executed. That is, the secondary processing step (S102) is executed in the preparation step of the molding machine 2 (the finishing processing step (S13) of the first molded article and the starting preparation step (S21)) from the finishing of the molding step of the first molded article to the starting of the molding step of the second molded article.

The primary processing step (S101) includes at least processing performed by the detection data acquisition unit 101. The secondary processing step (S102) includes at least the processing performed by the correction condition determination unit 106. The correction condition determining unit 106 determines the amount of correction of the molding condition relating to the second molded product. That is, the molding machine 2 makes the molding conditions in the molding step (S22) of the second molded product the molding conditions corrected using the data in the molding step of the first molded product. Thus, the correction amount of the molding condition is determined in 1 cycle of molding of the molded article. Therefore, since the molding information immediately before can be used for determining the correction amount of the molding condition, the correction amount of the molding condition can be adapted to the current situation with higher accuracy.

(8-2. first example)

The first example of the processing of the molding condition determination assisting device 3 is as follows. The primary processing step (S101) performs processing of the detection data acquisition unit 101. On the other hand, the secondary processing step (S102) performs the processing of the quality estimation unit 102, the processing of the trend evaluation unit 104, and the processing of the correction condition determination unit 106.

(8-3. second example)

The second example of the process of the auxiliary device 3 is as follows. The primary processing step (S101) performs the processing of the detection data acquisition unit 101 and the processing of the quality estimation unit 102. On the other hand, the secondary processing step (S102) performs the processing of the trend evaluating unit 104 and the processing of the correction condition determining unit 106.

(9. structural example of Molding System 1)

(9-1. first example)

A configuration of a first example of the molding machine system 1 will be described with reference to fig. 12. As shown in fig. 12, the molding machine system 1 includes a plurality of molding machines 2, edge computers 4, 4 integrally formed with the molding machines 2, respectively, and a server 5 forming the same network as the plurality of molding machines 2, 2. The edge computers 4 and 4 may be formed as a part of the molding machines 2 and 2, or may be formed separately from the molding machines 2 and 2.

The edge computers 4 and the server 5 constitute a molding condition determination support device 3. The edge computers 4 and 4 are provided with a detection data acquisition unit 101. The server 5 includes a quality estimation unit 102, a quality transition storage unit 103, a trend evaluation unit 104, a relationship storage unit 105, and a correction condition determination unit 106.

That is, the server 5 receives the detection data acquired by the detection data acquiring unit 101 from the edge computer 4 that is separate from the molding machine 2 or the edge computer 4 built in the molding machine 2. The server 5 determines the correction amount of the molding condition based on the received information, and transmits the determined correction amount of the molding condition to the molding machine 2.

In this case, the server 5 can accumulate information on a plurality of molding machines 2. Further, by providing the server 5 with a processor capable of executing high-speed processing, the processing of the quality estimation unit 102, the processing of the trend evaluation unit 104, and the processing of the correction condition determination unit 106 can be performed at high speed. On the other hand, since it is not necessary to make each edge computer 4 high-specification, cost reduction can be achieved.

(9-2. second example)

In the second example of the molding machine system 1, the molding machine system 1 includes a plurality of molding machines 2 and 2, edge computers 4 and 4 connected to the molding machines 2 and 2, respectively, and a server 5 forming the same network with the plurality of molding machines 2 and 2, as in the first example.

The edge computers 4 and 4 include a detection data acquisition unit 101 and a quality estimation unit 102. The server 5 includes a quality transition storage unit 103, a trend evaluation unit 104, a relationship storage unit 105, and a correction condition determination unit 106. That is, the server 5 receives the quality of the molded product estimated by the quality estimation unit 102 from the edge computer 4 separate from the molding machine 2 or the edge computer 4 built in the molding machine 2. The server 5 determines the correction amount of the molding condition based on the received information, and transmits the determined correction amount of the molding condition to the molding machine 2.

(9-3. third example)

The third example of the molding machine system 1 is that the server 5 has all the functions. In this case, the edge computers 4, 4 are not required. The detection data acquisition unit 101 in the server 5 receives the detection data detected by the sensors 44 and 45 from the molding machine 2. Then, the correction condition determining unit 106 in the server 5 transmits the correction amount of the molding condition to the molding machine 2.

The resin state estimating device and the molding condition determination assisting device will be described below as a second embodiment. The present disclosure is not limited to the second embodiment, and various design changes can be made without departing from the spirit of the present disclosure.

(1. applicable object)

The resin state estimation device and the molding condition determination support device are suitable for a molding method for molding a molded product by supplying a molten material obtained by melting a molding material (resin) to a cavity of a mold of an injection molding machine. Examples of the resin as the molding material include a thermoplastic resin such as polyamide as a monomer, and a reinforced resin obtained by adding a filler to a base material of the thermoplastic resin. Examples of the filler include micron-sized or nano-sized fillers. Examples of the filler include glass fibers and carbon fibers.

(2. first example Molding machine System 501A)

A molding machine system 501A including a first example of the resin state estimating device 503 will be described with reference to fig. 13. As shown in fig. 13, the molding machine system 501A includes an injection molding machine 502 (hereinafter, referred to as "molding machine") and a resin state estimation device 503.

The molding machine 502 molds a resin molded product. The resin state estimating device 503 estimates the molten state of the resin in the cavity C2 of the mold 540 of the molding machine 502. The estimated molten state of the resin is used, for example, to determine molding conditions in the molding machine 502.

The resin state estimating device 503 may be a device separate from the molding machine 502, or may be an assembly device of the molding machine 502. Further, the resin state estimation device 503 may be partly assembled to the molding machine 502 and the remaining part may be separated from the molding machine 502. When all or a part of the resin state estimation device 503 is separate from the molding machine 502, the separate part may be connected to only one molding machine 502 or may be connected to a plurality of molding machines 502. In the latter case, the separate part of the resin state estimation device 503 and the plurality of molding machines 502 form the same network, and are configured to be able to communicate with each other.

(3. Forming machine 502)

(3-1. Structure of Forming machine 502)

The structure of the molding machine 502 will be described with reference to fig. 13. The molding machine 502 mainly includes a base 520, an injection device 530, a mold 540, a mold clamping device 550, and a control device 560.

The injection molding device 530 is disposed on the base 520. The injection device 530 melts a molding material (resin) and applies pressure to the molten material to supply the molten material to the cavity C2 of the mold 540. The injection molding device 530 mainly includes a hopper 531, a heating cylinder 532, a screw 533, a nozzle 534, a heater 535, a drive device 536, and an injection molding device sensor 537.

The hopper 531 is an inlet for particles (granular molding material) as a raw material of the molding material. The heating cylinder 532 heats and melts the pellets fed into the hopper 531 to pressurize the molten material. In addition, the heating cylinder 532 is provided to be movable in the axial direction of the heating cylinder 532 with respect to the base 520. The screw 533 is disposed inside the heating cylinder 532, and is provided to be rotatable and movable in the axial direction. The nozzle 534 is an injection port provided at the tip of the heating cylinder 532, and supplies the molten material in the heating cylinder 532 to the mold 540 by the axial movement of the screw 533.

The heater 535 is provided, for example, outside the heating cylinder 532, and heats the particles inside the heating cylinder 532. The driving device 536 moves the heating cylinder 532 in the axial direction, rotates the screw 533, and moves the screw in the axial direction. The injection device sensor 537 is collectively referred to as a sensor for acquiring the amount of accumulated molten material, the holding pressure, the holding time, the injection speed, the state of the drive unit 536, and the like. However, the sensor 537 for the injection device is not limited to the above, and may acquire various kinds of information.

The mold 540 is a metal mold including a first mold 541 as a fixed side and a second mold 542 as a movable side. The mold 540 forms a cavity C2 between the first mold 541 and the second mold 542 by clamping the first mold 541 and the second mold 542. The first mold 541 includes a supply path 543 (sprue, runner, gate) for guiding the molten material supplied from the nozzle 534 to the cavity C2. The mold 540 is provided with a pressure sensor 544 and a temperature sensor 545. The pressure sensor 544 detects the pressure received from the molten material in the supply path 543. The temperature sensor 545 directly detects the temperature of the molten material in the supply path 543.

The mold clamping device 550 is disposed on the base 520 so as to face the injection molding device 530. The mold clamping device 550 performs opening and closing operations of the attached mold 540, and prevents the mold 540 from being opened by the pressure of the molten material injected into the cavity C2 in a state where the mold 540 is fastened.

The mold clamping device 550 includes a fixed platen 551, a movable platen 552, a tie rod 553, a drive device 554, and a mold clamping device sensor 555. A first mold 541 is fixed to the fixed plate 551. The fixed plate 551 can come into contact with the nozzle 534 of the injection device 530, and guides the molten material injected from the nozzle 534 to the mold 540. The second mold 542 is fixed to the movable platen 552. The movable plate 552 can be moved toward and away from the fixed plate 551. The pull rod 553 supports the movement of the movable board 552. The drive unit 554 is constituted by, for example, a cylinder device, and moves the movable disk 552. The mold clamping device sensor 555 is collectively referred to as a sensor for acquiring a mold clamping force, a mold temperature, a state of the drive unit 554, and the like.

The controller 560 controls the drive unit 536 of the injection molding device 530 and the drive unit 554 of the mold clamping device 550. For example, the controller 560 acquires various information from the injection device sensor 537 and the mold clamping device sensor 555, and controls the drive unit 536 of the injection device 530 and the drive unit 554 of the mold clamping device 550 to perform an operation according to the operation command data.

(3-2. Molding method)

A molding method of a molded product by the molding machine 502 will be described. In the molding method using the molding machine 502, a metering process, a mold clamping process, an injection filling process, a pressure holding process, a cooling process, and a mold releasing and taking-out process are sequentially performed in one cycle. That is, the above-described steps are sequentially executed again in the molding of the next molded product. Here, the measurement step and the mold clamping step constitute a start preparation step, the injection filling step, the pressure holding step, and the cooling step constitute a molding step, and the mold release removal step constitutes an end treatment step. In addition, the initial stage of the mold release removal step (immediately after the mold is opened) may be included in the molding step, and the subsequent stage may be a finishing step.

In the metering step, the particles are melted by the heating of the heater 535 and the shear friction heat accompanying the rotation of the screw 533, and the molten material is accumulated between the tip of the screw 533 and the nozzle 534 in the heating cylinder 532. Since the screw 533 is retreated as the amount of the molten material stored increases, the amount of the molten material stored is measured in accordance with the retreat position of the screw 533.

In the mold clamping step after the measuring step, the movable platen 552 is moved to align the second mold 542 with the first mold 541, and mold clamping is performed. The heating cylinder 532 is moved in the axial direction to approach the mold clamping unit 550, and the nozzle 534 is connected to the stationary platen 551 of the mold clamping unit 550. Next, in the injection filling step, the screw 533 is moved toward the nozzle 534 by a predetermined thrust force in a state where the rotation of the screw 533 is stopped, and the molten material is injection-filled into the mold 540 at a high pressure. When the cavity C2 is filled with the molten material, the process proceeds to the pressure maintaining step.

In the pressure holding step, pressure holding processing is performed in which the molten material is further pressed into the cavity C2 with the cavity C2 filled with the molten material, and a predetermined pressure (pressure holding pressure) is applied to the molten material in the cavity C2 for a predetermined time. Specifically, a predetermined holding pressure is applied to the molten material by applying a constant thrust force to the screw 533.

After the dwell pressure treatment is performed for a predetermined time at a predetermined dwell pressure, the process proceeds to a cooling step. In the cooling step, the mold 540 is cooled by stopping the pressing of the molten material and reducing the holding pressure. By cooling the mold 540, the molten material supplied to the mold 540 is solidified. Finally, in the mold releasing and taking-out step, the second mold 542 is separated from the first mold 541, and the molded article is taken out.

(4. basic estimation of molten State of resin)

The basic estimation of the molten state of the resin in the cavity C2 will be described with reference to fig. 14 to 17. In this example, the molten state of the resin is defined as a group classified into a plurality of groups, and the estimation of the molten state of the resin is defined as a group for estimating the molten state of the resin.

Fig. 14 shows that the control parameters and the molten state of the resin affect the detection data during molding. Here, the molten state of the resin depends on the content of the raw material of the molding material. For example, the variation of the content of the component in the raw material of the molding material includes the moisture content, the length of the reinforcing fiber, the ratio of the reinforcing fiber, the molecular weight of the main component, and the like. As described above, the molten state of the resin in the cavity C2 affects the detection data during molding.

Specifically, it is considered that detection data detected by the sensors 544 and 545 attached to the molding machine 502 during molding is influenced by control parameters for control in the molding machine 502 and the molten state of the resin in the cavity C2. In other words, the molten state of the resin affects the detection data and the control parameters.

The above relationship is expressed as a relational expression having values as shown in fig. 15. Here, the information as the value relating to the detection data at the time of molding is a feature amount group [ F ] composed of a plurality of kinds of feature amounts relating to the detection data. The feature value is a statistic (maximum value, minimum value, average value, variance, maximum value of differential, minimum value of differential, integral value, etc.) in the detection data of the pressure sensor 544 in each molding step (injection filling step, pressure holding step, cooling step, etc.), and is a statistic in the detection data of the temperature sensor 545 in each molding step. When a plurality of pressure sensors 544 and temperature sensors 545 are provided, the statistics of the respective sensors 544 and 545 are used as the feature quantities. Thus, a plurality of feature amounts can be obtained, and the plurality of feature amounts are collectively referred to as a feature amount group [ F ].

For example, a part of the feature amount will be described using detection data of the pressure sensor 544 shown in fig. 16. As shown in fig. 16, in the detection data of the pressure sensor 544, the time T1 is a filling start time, the time T2 is a filling end time and a holding pressure start time, the time T3 is a holding pressure end time and a cooling start time, and the time T4 is a cooling end time and a mold opening time. That is, the injection filling step is performed between T1 and T2, the pressure holding step is performed between T2 and T3, and the cooling step is performed between T3 and T4. In fig. 16, the maximum pressure value in the pressure holding step is Pmax, the pressure holding area as the pressure integrated value in the pressure holding step is Sa, and the cooling area as the pressure integrated value in the cooling step is Sb. The maximum value Pmax, the holding pressure area Sa, and the cooling area Sb are part of the characteristic amount.

The information as the value related to the control parameter is the plurality of control parameter values themselves used for control in the molding machine 502, and is a control parameter value group [ a ] composed of the plurality of control parameter values. The unit of each control parameter value may be adjusted so as to be a predetermined value in which the number of bits of the control parameter value is set. The types of control parameter values include, for example, injection speed, holding pressure, holding time, mold temperature at the time of holding, cooling time, nozzle temperature, injection pressure (nozzle pressure), and the like.

The information as a value related to the molten state of the resin is a resin state identification parameter value indicating the molten state of the resin. Here, the resin state identification parameter value is not meaningful as a value itself, but an index for grouping of the melting state of the resin. The resin state identification parameter value is a value corresponding to each feature amount. That is, the resin state identification parameter value is present in the same number as the number of kinds of the feature amount. Therefore, the plurality of resin state identification parameter values are set as the resin state identification parameter value group [ P ].

As shown in fig. 15, the resin state identification parameter value group [ P ] is represented by a feature value group [ F ] and a control parameter value group [ a ] of detection data at the time of molding. Specifically, the resin state identification parameter value group [ P ] is defined as a value obtained by dividing the feature quantity group [ F ] of the detection data at the time of molding by the control parameter value group [ a ].

Here, the content expressed as numerical expression is expression (1). The resin state identification parameter value group [ P ], the feature quantity group [ F ], and the control parameter value group [ a ] are matrices represented by the resin state identification parameter value P1-Pm, the feature quantity F1-Fm, and the control parameter value a (F1) -a (Fm), respectively, as shown by the condition of equation (1).

Wherein the content of the first and second substances,

the control parameter values a (F1) -a (fm) are represented by formula (2). The control parameter value a (fj) is an infinite product of the plurality of control parameter values Ak. Either one of the two types described below is applied to the control parameter value a (fj).

A(Fj)＝ΠAk…(2)

The first control parameter value a (fj) is the infinite product of all control parameter values Ak. For example, a (F1) and a (F2) are as shown in formulas (3) and (4).

A(F1)＝A1×A2×A3×…×Am…(3)

A(F2)＝A1×A2×A3×…×Am…(4)

The second control parameter value a (fj) is an infinite product of a portion of the control parameter value Ak. For example, A (F1) and A (F2) are as shown in formulas (5) and (6).

A(F1)＝A3×A4×A9×…×Am-1…(5)

A(F2)＝A1×A2×A4×…×Am-2…(6)

In the second control parameter values a (Fj), a part of the control parameter values Ak is one or more control parameter values having a high influence on the characteristic amount Fj.

Next, when a resin state identification parameter value group is obtained for each of the plurality of detection data using the plurality of detection data, the resin melt state is grouped by performing multivariate analysis using the resin state identification parameter value group. That is, multivariate analysis is performed in which a plurality of types of resin state identification parameter values are respectively set as explanatory variables.

For ease of explanation, the resin state identification parameter values are assumed to be two types, P1, P2. In this case, as shown in fig. 17, the two-dimensional coordinate system is represented by a two-dimensional coordinate system with P1 and P2 as explanatory variables. In the two-dimensional coordinate system, points of P1 and P2 are plotted with respect to the respective detection data.

Fig. 17 plots the resin state identification parameter values obtained using the detection data and the control parameter values acquired in the learning stage, and the groups of the molten states of the resins are, for example, two groups G1, G2. In this case, the group of the molten state of the resin obtained using the newly acquired detection data and the control parameter value is classified into any one of G1 and G2.

In particular, the resin state identification parameter value may be set as an explanatory variable, the group of the molten states of the resin may be set as a target variable, and the clustering analysis may be applied as the multivariate analysis. In this case, a learned model can be generated by performing machine learning of cluster analysis using a training data set including an explanatory variable and a target variable. The set of molten states of the resin can be determined using the generated learned model.

Here, in the cluster analysis, the number of groups in the molten state of the resin is set in advance. That is, the learned model is generated so as to be classified into a predetermined number of groups. The number of sets is described later, but when the molding conditions are corrected by the correction amount of the molding conditions set for each set of the molten state of the resin, the number of sets may be set to a number that can obtain a desired quality of the molded product.

(5. Structure of resin State estimation device 503)

The structure of the resin state estimating device 503 will be described with reference to fig. 18. The resin state estimating device 503 is a device for acquiring the above-described group of molten states of the resin. The resin state estimation device 503 includes, for example: an arithmetic processing device including a processor, a storage device, an interface, and the like; an input device connectable to an interface of the arithmetic processing apparatus; and an output device connectable to an interface of the arithmetic processing apparatus. The output device may also include a display device, for example. The arithmetic processing device, the input device, and the output device may be configured as a single unit without an interface. In addition, a physical server or a cloud server may be applied to a part of the arithmetic processing device and a part of the storage device.

As shown in fig. 18, the resin state estimation device 503 includes a detection data acquisition unit 601, a feature amount generation unit 602, a control parameter acquisition unit 603, a recognition parameter value calculation unit 604, a learned model generation unit 605, a learned model storage unit 606, and a group acquisition unit 607.

The detection data acquisition unit 601 acquires detection data detected by the sensors 544 and 545 attached to the molding machine 502 at the time of molding. For example, the detection data detected by the pressure sensor 544 becomes time-series data as shown in fig. 16. Although not shown, detection data detected by the temperature sensor 545 may be acquired as time-series data.

The feature amount generation unit 602 generates a feature amount group [ F ] (see formula (1)) composed of a plurality of feature amounts related to the detection data, based on the detection data. That is, a plurality of kinds of feature quantities are generated for each detection data. The feature amount is a statistic amount (maximum value, minimum value, average value, variance, maximum value of differential, minimum value of differential, integral value, etc.) in detection data of each of the sensors 544 and 545 in each molding process (injection filling process, pressure holding process, cooling process, etc.).

The control parameter acquisition unit 603 acquires a control parameter value group [ a ] (see expression (1)) including a plurality of control parameter values used for control in the molding machine 502. The types of control parameter values include, for example, injection speed, holding pressure, holding time, mold temperature at the time of holding, cooling time, nozzle temperature, injection pressure (nozzle pressure), and the like.

The identification parameter value calculation unit 604 calculates a resin state identification parameter value P1-Pm indicating the molten state of the resin corresponding to each characteristic amount, based on the characteristic amount group [ F ] and the control parameter value group [ a ]. The identification parameter value calculation unit 604 calculates the resin state identification parameter value P1-Pm based on the above equations (1) and (2).

As shown in the above-described equations (3) and (4), the identification parameter value calculation unit 604 may calculate the resin state identification parameter value Pj using all the control parameter values Ak in the respective control parameters a (F1) -a (fm). In this case, the resin state identification parameter value Pj is an infinite product of all the control parameter values Ak.

As in the above-described equations (5) and (6), the identification parameter value calculation unit 604 may calculate the resin state identification parameter value Pj corresponding to the characteristic quantity Fj using the characteristic quantity Fj and one or more control parameter values Ak having a high influence on the characteristic quantity Fj in each of the control parameters a (F1) -a (fm). In this case, the resin state identification parameter value Pj is an infinite product of a part of the control parameter values Ak.

For example, one or more control parameter values Ak having a high influence on the feature quantity Fj may be extracted by machine learning using the feature quantity Fj of the object and the control parameter value group [ a ]. For example, a predetermined number of control parameter values Ak can be extracted from control parameters having high influence coefficients using the influence coefficients obtained by machine learning. The influence coefficient is, for example, a lasso coefficient obtained by lasso regression, a ridge coefficient obtained by a ridge regression set, or the like.

The learned model generation unit 605 generates a learned model for machine learning as a learning stage. When the molten state of the resin is defined to be classified into a plurality of groups G1, G2, and …, the learned model generation unit 605 applies cluster analysis as multivariate analysis using the resin state identification parameter value P1-Pm as an explanatory variable and the groups G1, G2, and … of the molten state of the resin as target variables.

The learned model generation unit 605 performs machine learning of cluster analysis using a training data set including the above-described explanatory variables and target variables, thereby generating a learned model. The generated learned model is stored in the learned model storage unit 606. That is, when the resin state identification parameter value is input to the learned model, the group is output.

The group acquisition unit 607 acquires the groups G1, G2, … of the molten state of the resin based on the resin state identification parameter value P1-Pm. In this example, the group acquisition unit 607 uses a learned model generated by applying a cluster analysis which is a multivariate analysis having the resin state identification parameter value P1-Pm as an explanatory variable. That is, the group acquisition unit 607 acquires the groups G1, G2, and … of the molten state of the resin, which are outputs of the learned model, when the resin state identification parameter value P1-Pm is input as an application stage (also referred to as an inference stage) of the machine learning.

As described above, the resin state estimation device 503 determines the set of molten states of the resin in the cavity C2 when the target molded product is molded, using the detection data of the target molded product at the time of molding and the control parameter values for molding the target molded product.

(6. Effect of the resin state estimating device 503)

As described above, the detection data detected by the sensors 544 and 545 attached to the molding machine 502 during molding is considered to be influenced by the control parameters of the molding machine 502 and the molten state of the resin in the cavity C2. In other words, the molten state of the resin is defined as being represented by the feature quantity group [ F ] and the control parameter value group [ a ] generated from the detection data.

With this definition, the identification parameter value calculation unit 604 calculates the resin state identification parameter values P1-Pm indicating the molten state of the resin corresponding to the respective characteristic amounts F1-Fm, based on the characteristic amount group [ F ] and the control parameter value group [ a ] of the detection data. That is, the resin state identification parameter value P1-Pm is generated in the same number as the number of kinds of the characteristic quantities F1-Fm.

When the molten state of the resin is defined as being classified into a plurality of groups G1, G2, and …, the group acquisition unit 607 acquires groups G1, G2, and … of the molten state of the resin by applying multivariate analysis in which the resin state identification parameter value P1-Pm is set as an explanatory variable, based on the resin state identification parameter value P1-Pm. Here, the groups G1, G2, and … of the molten state of the resin do not need to be clearly defined, but for example, the degree of fluidity can be classified as one of the elements.

That is, the resin state estimating device 503 can classify the groups G1, G2, … of the molten state of the resin in the cavity C2 of the molded product at the time of molding, for example, by performing arithmetic processing using the detection data and the control parameter, as one of the elements, the degree of fluidity of the resin, and the like. In this way, the molten state of the resin in the cavity C2 can be grouped, and the correction amount of the molding condition corresponding to the group G1, G2, … can be determined.

(7. second embodiment Molding machine System 501B)

A molding machine system 501B of a second example including the molding condition determination assisting device 504 will be described with reference to fig. 19. As shown in fig. 19, the molding machine system 501B includes a molding machine 502 and a molding condition determination assisting device 504.

The molding condition determination assisting device 504 is a device for determining the molding conditions in the molding machine 502. In particular, in the present example, when the molding conditions are applied to mold a molded article, the molding condition determination assisting device 504 determines a correction amount of the molding conditions for improving the quality of the molded article. The molding condition determination assisting device 504 includes the resin state estimating device 503, and performs processing using the set of molten states of the resin obtained by the resin state estimating device 503.

(8. Structure of auxiliary device 504 for determining Molding conditions)

The structure of the molding condition determination assisting apparatus 504 will be described with reference to fig. 20 to 24. The molding condition determination assisting device 504 includes, for example: an arithmetic processing device including a processor, a storage device, an interface, and the like; an input device connectable to an interface of the arithmetic processing apparatus; and an output device connectable to an interface of the arithmetic processing apparatus. The output device may also include a display device, for example. The arithmetic processing device, the input device, and the output device may be configured as a single unit without an interface. In addition, a physical server or a cloud server may be applied to a part of the arithmetic processing device and a part of the storage device.

As shown in fig. 20, the molding condition determination support device 504 includes a resin state estimation device 503, a quality estimation unit 701, a quality transition storage unit 702, a trend evaluation unit 703, a relationship storage unit 704, and a correction condition determination unit 705. The resin state estimating device 503 has the same configuration as the resin state estimating device 503 explained in the molding machine system 501A of the first example.

The quality estimation unit 701 estimates the quality of the molded product by machine learning based on the detection data acquired by the detection data acquisition unit 601. For example, the quality estimation unit 701 estimates a numerical value in one or more quality types in the molded product. The quality type of the molded product is at least one of the mass of the molded product, the size of the molded product, and the void volume in the molded product.

The quality estimation unit 701 generates a learned model in which the relationship between the detection data and the quality of the molded product is learned by machine learning in advance. The learning completion model is generated for each quality type. Further, the quality estimation unit 701 stores the learned model, and estimates the quality of the molded product using the newly acquired detection data and the learned model.

The quality transition storage unit 702 accumulates the qualities of the molded products estimated by the quality estimation unit 701, and stores the quality transitions of the accumulated plurality of molded products. The quality transition is information for arranging the qualities of a plurality of molded products in the molding order. The quality transition is, for example, data as shown in fig. 21. Fig. 21 shows an example of the quality of the molded product. In fig. 21, Std is a predetermined quality standard, Thmax is an upper limit value of a quality allowable range, and Thmin is a lower limit value of the quality allowable range. That is, a range between the upper limit value Thmax and the lower limit value Thmin means a non-defective product, and the deviation range means a defective product. Even a non-defective product is ideally a predetermined quality standard Std.

In fig. 21, the quality of most of the molded articles at the beginning of molding shows a value near the quality standard Std. However, as the sudden abnormality, there is a molded article that shows a value exceeding the upper limit value Thmax. (D2 of FIG. 21). That is, when the molded article having an unexpected abnormality is excluded, the quality of the molded article at the beginning of molding shows a value near the quality standard Std (D1 in fig. 21). Thereafter, when the molding is continued, the quality of the molded product gradually deviates from the quality standard Std. Further, the quality of the molded article showed an increase from the quality standard Std by around the value of + N% (D3 in fig. 21).

The trend evaluation unit 703 evaluates the trend of the quality change with respect to the quality standard Std based on the quality transition stored in the quality transition storage unit 702. As shown in fig. 22, the trend evaluation unit 703 evaluates, as the quality change trend, the degree of deviation of the quality from the quality standard Std for each of the plurality of quality types and the degree of deviation of the quality of the plurality of molded articles for each of the plurality of quality types.

The trend evaluation unit 703 sets in advance the number of molded articles in which the quality changes for evaluating the trend of quality changes. That is, the trend evaluating unit 703 calculates the degree of deviation in the quality of the number of molded products set in advance. For example, the trend evaluating unit 703 calculates the degree (absolute value or relative value) of deviation of the average value of the quality of the number of molded products from the quality standard Std as the degree of deviation of the quality. Further, the degree of variation means a degree of quality variation or stability indicating the number of molded articles set in advance. Further, the degree of deviation may be a value such as a standard deviation or a variance.

As shown in fig. 22, for example, the trend evaluating unit 703 evaluates the degree of deviation "+ 2.2%" for the quality and the degree of deviation "stable", evaluates the degree of deviation "+ 0.3%" for the size and the degree of deviation "stable", and evaluates the degree of deviation "-0.5%" for the void volume and the degree of deviation "stable".

In D1 showing the quality transition shown in fig. 21, the trend evaluation unit 703 evaluates that the trend of the quality change is stable and is located near the quality standard Std. Here, the trend evaluation unit 703 excludes the molded product of D2 indicating a quality change due to an unexpected abnormality from D1 showing a quality transition shown in fig. 21. In this case, the trend evaluating unit 703 evaluates the degree of deviation from the quality standard Std as "0.1%" and the degree of deviation as "stable" for the target quality type. Also, since the quality of the molded product returns to normal after the sudden abnormality, the sudden abnormality is not related to the molding conditions. Therefore, the burst anomaly is evaluated exclusive of the other.

In D3 showing the quality transition shown in fig. 21, the trend evaluation unit 703 evaluates that the trend of the quality is stable and shows a value that is deviated from the quality standard Std by about + N%. In this case, the trend evaluating unit 703 evaluates the degree of deviation from the quality standard Std as "+ N%" and the degree of deviation as "stable" for the target quality type.

As described above, the group acquisition unit 607 of the resin state estimation device 503 acquires the group in the molten state of the resin in the cavity C2. Here, in the group acquisition unit 607, the groups of the molten state of the resin are classified into any one of four types, i.e., Type-A, Type-B, Type-C, Type-D, as shown in fig. 23, for example.

The relationship storage unit 704 stores the relationship between the quality change tendency and the correction amount of the molding condition for returning the quality to the quality standard, in association with the set of the molten state of the resin in the cavity C2. The relationship storage unit 704 stores, for example, as shown in fig. 24, the relationship between the quality change tendency and the correction amount of the molding condition for each group of molten states of the resin. Specifically, the relationship storage unit 704 stores the relationship between the level of the degree of deviation expressed in the matrix and the correction amount of the molding condition for each quality type for each group of the molten state of the resin. For example, the mass, the size, and the void volume are each set to six levels as the level of the degree of deviation. The type of the molding condition to be corrected is at least one of an injection speed, a holding pressure, a holding time, a mold temperature at the time of holding pressure, a cooling time, and the like.

Here, the degree of the relationship between the quality type and the type of the molding condition, and the relationship between the degree of deviation of the quality type and the correction amount of the molding condition can be derived by machine learning. That is, the relationship stored in the relationship storage unit 704 can be generated by machine learning. Of course, this relationship may be set based on an experiment, past experience, or the like, instead of machine learning.

The correction condition determining unit 705 determines the correction amount of the molding condition based on the quality change tendency evaluated by the tendency evaluating unit 703, the group of the molten state of the resin acquired by the group acquiring unit 607, and the relationship stored in the relationship storage unit 704.

The correction condition determining unit 705 first selects a group corresponding to the group in the molten state of the resin acquired by the group acquiring unit 607 from among the relationships shown in fig. 24. Next, for example, the correction condition determining section 705 determines a grade closest to the degree of deviation evaluated by the trend evaluating section 703 in the relationship expressed by the matrix as shown in fig. 24, and sets the correction amount of the molding condition corresponding to the grade as the correction amount of the determined molding condition. For example, as shown in fig. 22, when the degree of deviation of the mass is "+ 2.2%", the rank "+ 2%" of the degree of deviation of the mass is selected in the matrix shown in fig. 24.

Here, the correction condition determining section 705 determines the correction amount of the molding condition for each of the plurality of quality types. Therefore, the correction condition determination unit 705 determines the final correction amount for the molding condition based on a plurality of correction amounts for the same type of molding condition. In this case, the correction condition determination unit 705 may determine, for example, a value obtained by summing a plurality of correction amounts as a final correction amount, or may determine a value obtained by multiplying a weighting coefficient according to the quality type and then further summing the resultant values as a final correction amount.

Then, the correction condition determining unit 705 outputs the final correction amount to the control unit 560 of the molding machine 502, and adds the correction of the magnitude of the correction amount to the molding condition of the next molded product. Therefore, the control unit 560 executes molding of the next molded product according to the corrected molding conditions. As a result, the quality of the molded product molded under the corrected molding conditions can be brought close to the quality standard Std.

(9. determining the Effect of the auxiliary device 504 based on the Molding conditions)

The effect of the auxiliary device 504 determined by the molding conditions described above will be described. The quality transition storage unit 702 accumulates the quality of the molded product estimated by the machine learning and stores the quality transition. The quality transition is information for arranging the qualities of a plurality of molded products in the molding order. Therefore, the trend evaluating unit 703 can evaluate the quality change trend based on the quality shifts of a plurality of continuous molded articles.

In particular, the trend evaluation unit 703 evaluates the trend of the quality change from a predetermined quality standard Std. For example, the trend evaluation unit 703 can evaluate, as the quality change trend, a state in which the quality continuously deviates from the predetermined quality standard Std, a variation in the quality within a quality allowable range including the predetermined quality standard, and the like.

The relationship between the trend of quality change and the correction amount of molding conditions is stored in the relationship storage unit 704 in advance in association with the set of molten states of the resin in the cavity C2. That is, the relationship between the quality change tendency and the correction amount of the molding condition is stored in the relationship storage unit 704 for each group of the molten state of the resin. The relationship is set using experience of a skilled person, an output result of machine learning, an experimental result, and the like.

The correction condition determining unit 705 determines the correction amount of the molding condition based on the newly evaluated quality change tendency, the newly acquired set of the molten state of the resin in the cavity C2, and the relationship stored in the relationship storage unit 704. Here, the relationship stored in the relationship storage unit 704 relates to a correction amount of the molding condition for returning the quality to the predetermined quality standard Std. In particular, the correction amount of the molding condition is determined according to the set of molten states of the resin in the cavity C2. Therefore, when the molding conditions of the molding machine 502 are corrected according to the correction amount of the molding conditions determined by the correction condition determining unit 705, the quality of the molded product to be molded next can be brought close to the predetermined quality standard Std.

That is, even when the quality of the molded product changes due to external factors such as ambient temperature and slight differences in the content of the raw material of the molding material, the molding conditions can be corrected so that the quality of the molded product can be brought to the predetermined quality standard Std by grasping the tendency of the change in quality and further grouping the molten states of the resin in the cavity C2. Therefore, the molding conditions can be corrected not only by a skilled person but also by an unskilled person, and the quality of the molded product can be improved.

(10. method for setting number of sets)

The learned model generation unit 605 sets the number of sets of molten resin states in cooperation with other configurations in addition to the generation of the learned model described above. Here, the number of sets can be set to any number by the operator, but can be set to an appropriate number by using the molding condition determination support device 504 described above.

The learned model generation unit 605 acquires a group (any one of G1 and G2) of the molten states of the resins with respect to the acquired detection data, with the number of groups of the molten states of the resins set to an initial set number (for example, 2) (a group acquisition step).

Then, the relationship between the quality change tendency and the correction amount of the molding conditions when the number of sets is set to the initial set number is set in correspondence with the set of molten states of the resin (relationship setting step). Further, the relationship storage unit 704 stores the relationship. Next, the correction condition determining unit 705 determines the correction amount of the molding condition (correction amount of the control parameter value) based on the relationship between the acquired group (any one of G1 and G2) and the relationship stored in the relationship storage unit 704 (correction amount determining step).

Next, when the control parameter value is corrected based on the correction amount of the control parameter value corresponding to the group G1 or G2 of the obtained molten state of the resin, the learned model generation unit 605 determines whether or not the quality of the molded product satisfies a predetermined range (determination step).

When the quality of the molded product does not satisfy the predetermined range, the above-described group acquisition step, relationship setting step, correction amount determination step, and determination step are repeated while increasing the number of groups. That is, when the quality of the molded product does not satisfy the predetermined range, the learned model generation unit 605 repeatedly determines whether or not the acquisition of the group in the molten state of the resin and the quality of the molded product satisfy the predetermined range by increasing the number of groups, and sets the number of groups when the quality of the molded product satisfies the predetermined range as the number of groups in the learned model.

By setting the number of sets in this manner, the correction amount of the molding condition can be determined according to the set of molten states of the resin. That is, the correction amount of the appropriate molding condition can be determined.

(11. structural example of Molding machine System 501B)

(11-1. first example)

A configuration of a first example of the molding machine system 501B will be described with reference to fig. 25. As shown in fig. 25, the molding machine system 501B includes a plurality of molding machines 502 and 502, edge computers 505 and 505 integrally formed with the molding machines 502 and 502, respectively, and a server 506 forming the same network as the plurality of molding machines 502 and 502. The edge computers 505 and 505 may be formed as a part of the molding machines 502 and 502, or may be formed separately from the molding machines 502 and 502.

The edge computers 505 and the server 506 constitute a molding condition determination support device 504. The edge computers 505 and 505 include a detection data acquisition unit 601. The server 506 includes a configuration other than the detection data acquisition unit 601 in the resin state estimation device 503, a quality estimation unit 701, a quality transition storage unit 702, a trend evaluation unit 703, a relationship storage unit 704, and a correction condition determination unit 705.

That is, the server 506 receives the detection data acquired by the detection data acquisition unit 601 from the edge computer 505 that is separate from the molding machine 502 or the edge computer 505 built in the molding machine 502. The server 506 determines the correction amount of the molding condition based on the received information, and transmits the determined correction amount of the molding condition to the molding machine 502.

In this case, the server 506 can accumulate information related to a plurality of molding machines 502. Further, by providing the server 506 with a processor capable of executing high-speed processing, the processing of the feature quantity generation unit 602, the processing of the identification parameter value calculation unit 604, the processing of the group acquisition unit 607, the processing of the quality estimation unit 701, the processing of the trend evaluation unit 703, and the processing of the correction condition determination unit 705 can be performed at high speed. On the other hand, since it is not necessary to make each edge computer 505 high-specification, cost reduction can be achieved.

(11-2. second example)

In the second example of the molding machine system 501B, as in the first example, the molding machine system 501B includes a plurality of molding machines 502 and 502, edge computers 505 and 505 connected to the molding machines 502 and 502, respectively, and a server 506 that forms the same network as the plurality of molding machines 502 and 502.

The edge computers 505 and 505 include all the configurations of the resin state estimation device 503 and the quality estimation unit 701. The server 506 includes a quality transition storage unit 702, a trend evaluation unit 703, a relationship storage unit 704, and a correction condition determination unit 705. That is, the server 506 receives the group of molten states of the resin acquired by the group acquisition unit 607 of the resin state estimation device 503 and the quality of the molded product estimated by the quality estimation unit 701 from the edge computer 505 separate from the molding machine 502 or the edge computer 505 built in the molding machine 502. The server 506 determines the correction amount of the molding condition based on the received information, and transmits the determined correction amount of the molding condition to the molding machine 502.

(111-3. third example)

The third example of the molding machine system 501B is a system in which the server 506 has all the functions of the molding condition determination support device 504. In this case, the edge computers 505, 505 are not required. The detection data acquisition unit 601 in the server 506 receives the detection data detected by the sensors 544 and 545 from the molding machine 502. Then, the correction condition determining unit 705 in the server 506 transmits the correction amount of the molding condition to the molding machine 502.

The following describes a molding condition determination assisting device as a third embodiment. The present disclosure is not limited to the third embodiment, and various design changes can be made without departing from the spirit of the present disclosure.

(1. applicable object)

The molding condition determination assisting device is suitable for a molding method for molding a molded product by supplying a molten material obtained by melting a molding material into a cavity of a mold of a molding machine. The molding machine to which the present invention is applied may be, for example, an injection molding machine that performs injection molding of resin, rubber, or the like as a molding material. Other molding machines to which the present invention is applied may be blow molding machines and compression molding machines, for example. Examples of the resin as the molding material include a thermoplastic resin such as polyamide as a monomer, and a reinforced resin obtained by adding a filler to a base material of the thermoplastic resin. Examples of the filler include micron-sized or nano-sized fillers. Examples of the filler include glass fibers and carbon fibers.

(2. Molding machine System 1001)

A molding machine system 1001 including a molding condition determination assisting device will be described with reference to fig. 26. As shown in fig. 26, the molding machine system 1001 includes a molding machine 1002 and a molding condition determination assisting device 1003.

The molding machine 1002 is an injection molding machine, a blow molding machine, a compression molding machine, or the like. In this example, the molding machine 1002 is an injection molding machine as an example. The molding machine 1002 molds a resin molded product, for example. The molding condition determination assisting device 1003 is a device for determining the molding condition in the molding machine 1002. In particular, in the present example, the molding condition determination assisting device 1003 determines a correction amount of the molding condition for improving the quality of the molded product when the molded product is molded under the molding condition already applied.

The molding condition determination assisting device 1003 may be a device separate from the molding machine 1002, or may be an assembly device of the molding machine 1002. The molding condition determination assisting device 1003 may be partly assembled to the molding machine 1002 and the remaining part may be separated from the molding machine 1002. When all or a part of the molding condition determination assisting device 1003 is separate from the molding machine 1002, the separate part may be connected to only one molding machine 1002, or may be connected to a plurality of molding machines 1002. In the latter case, the separate part of the molding condition determination assisting apparatus 1003 and the plurality of molding machines 1002 form the same network, and are configured to be able to communicate with each other.

(3. Forming machine 1002)

(3-1. Structure of Forming machine 1002)

The structure of an injection molding machine as an example of the molding machine 1002 will be described with reference to fig. 26. The molding machine 1002 mainly includes a base 1020, an injection device 1030, a mold 1040, a mold clamping device 1050, and a control device 1060.

The injection molding device 1030 is disposed on the base 1020. The injection device 1030 is a device that melts a molding material, applies pressure to the molten material, and supplies the molten material to the cavity C3 of the mold 1040. The injection device 1030 mainly includes a hopper 1031, a heating cylinder 1032, a screw 1033, a nozzle 1034, a heater 1035, a driving device 1036, and an injection device sensor 1037.

The hopper 1031 is an inlet for particles (granular molding material) as a raw material of the molding material. The heating cylinder 1032 heats and melts the particles fed into the hopper 1031 and pressurizes the formed molten material. In addition, the heating cylinder 1032 is provided so as to be movable in the axial direction of the heating cylinder 1032 with respect to the base 1020. The screw 1033 is disposed inside the heating cylinder 1032 and is provided to be rotatable and movable in the axial direction. The nozzle 1034 is an injection port provided at the front end of the heating cylinder 1032, and supplies the molten material in the heating cylinder 1032 to the mold 1040 by the axial movement of the screw 1033.

The heater 1035 is provided, for example, outside the heating cylinder 1032, and heats the particles inside the heating cylinder 1032. The driving device 1036 moves the heating cylinder 1032 in the axial direction, rotates the screw 1033, and moves the heating cylinder in the axial direction. The injection device sensor 1037 is generally referred to as a sensor for acquiring a stored amount of the molten material, a holding pressure, a holding time, an injection speed, a state of the drive device 1036, and the like. However, the sensor 1037 for the injection device is not limited to the above, and may acquire various kinds of information.

The mold 1040 is a mold provided with a first mold 1041 as a fixed side and a second mold 1042 as a movable side. The mold 1040 forms a cavity C3 between the first mold 1041 and the second mold 1042 by clamping the first mold 1041 and the second mold 1042. The first mold 1041 includes a supply path 1043 (sprue, runner, gate) for guiding the molten material supplied from the nozzle 1034 to the cavity C3. The mold 1040 is provided with a pressure sensor 1044 and a temperature sensor 1045. The pressure sensor 1044 detects the pressure received from the molten material in the supply path 1043. The temperature sensor 1045 directly detects the temperature of the molten material in the supply path 1043.

The mold clamping unit 1050 is disposed on the base 1020 so as to face the injection unit 1030. The mold clamping device 1050 opens and closes the attached mold 1040, and in a state where the mold 1040 is closed and fastened, the mold 1040 is not opened by the pressure of the molten material injected into the cavity C3.

The mold clamping device 1050 includes a fixed platen 1051, a movable platen 1052, a tie rod 1053, a drive device 1054, and a mold clamping device sensor 1055. A first die 1041 is fixed to the fixed disk 1051. The fixed disk 1051 can abut against a nozzle 1034 of the injection device 1030, and guide the molten material injected from the nozzle 1034 to the mold 1040. A second die 1042 is fixed to the movable platen 1052. The movable disk 1052 can be approached and separated with respect to the fixed disk 1051. The pull rod 1053 supports the movement of the movable plate 1052. The driving device 1054 is constituted by, for example, a cylinder device, and moves the movable plate 1052. The mold clamping device sensor 1055 is generally referred to as a sensor for acquiring a mold clamping force, a mold temperature, a state of the drive device 1054, and the like.

The controller 1060 controls a drive 1036 of the injection unit 1030 and a drive 1054 of the mold clamping unit 1050. For example, the control device 1060 acquires various information from the injection device sensor 1037 and the mold clamping device sensor 1055, and controls the drive device 1036 of the injection device 1030 and the drive device 1054 of the mold clamping device 1050 to perform an operation corresponding to the operation command data.

(3-2. Molding method)

A molding method of a molded product by the molding machine 1002 will be described. In the molding method using the molding machine 1002, a metering step, a mold clamping step, an injection filling step, a pressure holding step, a cooling step, and a mold releasing and taking-out step are sequentially performed in one cycle. That is, the above-described steps are sequentially executed again in the molding of the next molded product. Here, the measurement step and the mold clamping step constitute a start preparation step, the injection filling step, the pressure holding step, and the cooling step constitute a molding step, and the mold release removal step constitutes an end treatment step. In addition, the initial stage of the mold release removal step (immediately after the mold is opened) may be included in the molding step, and the subsequent stage may be a finishing step.

In the metering process, the particles are melted by the heating of the heater 1035 and the shear friction heat accompanying the rotation of the screw 1033, and the molten material is accumulated between the tip of the screw 1033 and the nozzle 1034 in the heating cylinder 1032. Since the screw 1033 is retreated as the amount of the molten material stored increases, the amount of the molten material stored is measured from the retreated position of the screw 1033.

In the mold clamping step after the metering step, the movable platen 1052 is moved to align the second mold 1042 with the first mold 1041, and mold clamping is performed. The heating cylinder 1032 is moved in the axial direction to approach the mold clamping unit 1050, and the nozzle 1034 is connected to a fixed platen 1051 of the mold clamping unit 1050. Next, in the injection filling step, the screw 1033 is moved toward the nozzle 1034 by a predetermined thrust force in a state where the rotation of the screw 1033 is stopped, and thereby the molten material is injection-filled into the mold 1040 at a high pressure. When the cavity C3 is filled with the molten material, the process proceeds to the pressure maintaining step.

In the pressure holding step, pressure holding processing is performed in which the molten material is further pressed into the cavity C3 with the cavity C3 filled with the molten material, and a predetermined pressure (pressure holding pressure) is applied to the molten material in the cavity C3 for a predetermined time. Specifically, a predetermined holding pressure is applied to the molten material by applying a constant thrust force to the screw 1033.

After the dwell pressure treatment is performed for a predetermined time at a predetermined dwell pressure, the process proceeds to a cooling step. In the cooling step, the molten material is stopped from being pushed in, and the holding pressure is reduced, so that the mold 1040 is cooled. By cooling the mold 1040, the molten material supplied to the mold 1040 solidifies. Finally, in the mold releasing and taking-out step, the second mold 1042 is separated from the first mold 1041, and the molded article is taken out.

(3-3. mold 1040)

The detailed structure of the mold 1040 will be described with reference to fig. 27 and 28. The mold 1040 is a so-called multiple metal mold, and a plurality of cavities C3 are formed in the mold 1040, but only one cavity C3 is shown in fig. 27 and 28 to simplify the drawing. In this example, the molded article molded by the molding machine 1002 is a retainer for a constant velocity universal joint. Therefore, the molded product is annular, and the cavity C3 is formed in an annular shape conforming to the shape of the retainer. The shape of the molded article and the cavity C3 may be other than annular, for example, C-shaped, rectangular frame-shaped, or the like.

The supply path 1043 includes a sprue 1043a, a runner 1043b, and a gate 1043 c. The nozzle 1043a is a passage through which the molten material is supplied from the nozzle 1034. The runner 1043b is a passage branched from the nozzle 1043a, and the molten material supplied to the nozzle 1043a flows into the runner 1043 b. The gate 1043C is a passage for introducing the molten material flowing into the runner 1043b into the cavity C3, and the flow path cross-sectional area of the gate 1043C is smaller than the flow path cross-sectional area of the runner 1043 b. In the mold 1040, runners 1043b and gates 1043C of the same number as the number of the cavities C3 are formed, and the molten material supplied to the sprue 1043a is supplied to each cavity C3 via the runners 1043b and the gates 1043C.

When the cavity C3 is annular and the first mold 1041 includes one gate 1043C, the inflow path of the molten material in the cavity C3 is a path that flows from the gate 1043C in the annular circumferential direction of the cavity C3. That is, in the cavity C3, the molten material first flows into the vicinity of the gate 1043C and finally flows into the farthest distance from the gate 1043C.

In addition, a pressure sensor 1044 is provided in the mold 1040, and the pressure sensor 1044 detects a pressure received from the molten material in the supply path 1043. In this example, a plurality of pressure sensors 1044 are provided. For example, a pressure sensor 1044 is provided near the gate 1043C in the vicinity of the farthest position from the gate 1043C in the cavity C3. The pressure sensor 1044 may be provided to the nozzle 1043a and the runner 1043 b. The pressure sensor 1044 may be a contact sensor or a non-contact sensor.

Further, the mold 1040 is provided with a temperature sensor 1045 that detects the temperature of the molten material in the supply path 1043. The temperature sensor 1045 may be provided in the cavity C3, or may be provided in the nozzle 1043a or the runner 1043b, similarly to the pressure sensor 1044. In addition, a plurality of pressure sensors 1044 may be provided.

(4. Structure of auxiliary device 1003 for determining Molding Condition)

The structure of the molding condition determination assisting apparatus 1003 will be described with reference to fig. 29 to 34. The molding condition determination assisting device 1003 includes, for example: an arithmetic processing device including a processor, a storage device, an interface, and the like; an input device connectable to an interface of the arithmetic processing apparatus; and an output device connectable to an interface of the arithmetic processing apparatus. The output device may also include a display device, for example. The arithmetic processing device, the input device, and the output device may be configured as a single unit without an interface. In addition, a physical server or a cloud server may be applied to a part of the arithmetic processing device and a part of the storage device.

As shown in fig. 29, the molding condition determination assisting apparatus 1003 includes a detection data acquiring unit 1101, a quality estimating unit 1102, a quality transition storage unit 1103, a trend evaluating unit 1104, a molten state estimating unit 1105, a relationship storage unit 1106, and a correction condition determining unit 1107.

The detection data acquisition unit 1101 acquires detection data detected by the sensors 1044 and 1045 attached to the molding machine 1002 at the time of molding. That is, the type of the detection data acquired by the detection data acquiring unit 1101 is at least one of the pressure applied to the mold 1040 from the molten material in the supply path 1043 and the temperature of the molten material in the supply path 1043.

The detection data by the pressure sensor 1044 is, for example, data as shown in fig. 30. In fig. 30, a time T1 is a filling start time, a time T2 is a filling end time and a holding pressure start time, a time T3 is a holding pressure end time and a cooling start time, and a time T4 is a cooling end time and a mold opening time. That is, the injection filling step is performed between T1 and T2, the pressure holding step is performed between T2 and T3, and the cooling step is performed between T3 and T4. In fig. 30, the maximum pressure in the pressure holding step is set to the maximum pressure Pmax, the pressure integrated value in the pressure holding step is set to the pressure holding area Sa, and the pressure integrated value in the cooling step is set to the cooling area Sb.

The quality estimation unit 1102 estimates the quality of the molded product by machine learning based on the detection data acquired by the detection data acquisition unit 1101. For example, the quality estimation unit 1102 estimates a numerical value in one or more quality types in the molded product. The quality type of the molded product is at least one of the mass of the molded product, the size of the molded product, and the void volume in the molded product.

The quality estimation unit 1102 generates a learned model in which the relationship between the detection data and the quality of the molded product is learned by machine learning in advance. The learning completion model is generated for each quality type. Further, the quality estimation unit 1102 stores the learned model, and estimates the quality of the molded product using the newly acquired detection data and the learned model.

The quality transition storage unit 1103 accumulates the qualities of the molded products estimated by the quality estimation unit 1102, and stores the transition of the qualities of the plurality of accumulated molded products. The quality transition is information for arranging the qualities of a plurality of molded products in the molding order. The quality transition is, for example, data as shown in fig. 31. Fig. 31 shows an example of the quality of a molded product. In fig. 31, Std is a predetermined quality standard, Thmax is an upper limit value of a quality allowable range, and Thmin is a lower limit value of the quality allowable range. That is, a range between the upper limit value Thmax and the lower limit value Thmin means a non-defective product, and the deviation range means a defective product. Even a non-defective product is ideally a predetermined quality standard Std.

In fig. 31, the quality of most of the molded articles at the beginning of molding shows a value near the quality standard Std. However, as the sudden abnormality, there is a molded article which shows a value exceeding the upper limit value Thmax (a 2 in fig. 31). That is, when the molded article having an unexpected abnormality is excluded, the quality of the molded article at the beginning of molding shows a value near the quality standard Std (a 1 in fig. 31). Thereafter, when the molding is continued, the quality of the molded product gradually deviates from the quality standard Std. Further, the quality of the molded article showed an increase from the quality standard Std by around the value of + N% (a 3 in fig. 31).

The trend evaluation unit 1104 evaluates the trend of the quality change with respect to the quality standard Std based on the quality transition stored in the quality transition storage unit 1103. As shown in fig. 32, the trend evaluation unit 1104 evaluates, as the quality change trend, the degree of deviation of the quality from the quality standard Std for each of the plurality of quality types and the degree of deviation of the quality of the plurality of molded articles for each of the plurality of quality types.

The trend evaluation unit 1104 sets the number of molded articles in advance, which are subjected to quality transition for evaluating the trend of quality change. That is, the trend evaluating unit 1104 calculates the degree of quality deviation of the number of molded products set in advance. For example, the trend evaluating unit 1104 calculates a degree (absolute value or relative value) of deviation of the average value of the quality of the number of molded products from the quality standard Std as the degree of deviation of the quality. Further, the degree of variation means a degree of quality variation or stability indicating the number of molded articles set in advance. Further, the degree of deviation may be a value such as a standard deviation or a variance.

As shown in fig. 32, for example, the trend evaluating unit 1104 evaluates the degree of deviation "+ 2.2%" and the degree of deviation "stable" for the quality, the degree of deviation "+ 0.3%" and the degree of deviation "stable" for the size, and the degree of deviation "-0.5%" and the degree of deviation "stable" for the void volume.

In a1 showing the quality transition shown in fig. 31, the trend evaluation unit 1104 evaluates that the trend of the quality is stable and is located near the quality standard Std. Here, the trend evaluation unit 1104 performs evaluation with the exception of a2 molded product showing a quality change due to sudden abnormality in a1 showing a quality transition shown in fig. 31. In this case, the trend evaluation unit 1104 evaluates the degree of deviation from the quality standard Std as "0.1%" and the degree of deviation as "stable" for the target quality type. Also, since the quality of the molded product returns to normal after the sudden abnormality, the sudden abnormality is not related to the molding conditions. Therefore, the burst anomaly is evaluated exclusive of the other.

In a3 showing the quality transition shown in fig. 31, the trend evaluation unit 1104 evaluates that the trend of the quality is stable and shows a value that is deviated from the quality standard Std by about + N%. In this case, the trend evaluation unit 1104 evaluates the degree of deviation from the quality standard Std as "+ N%" and the degree of deviation as "stable" for the target quality type.

The molten state estimating unit 1105 estimates the molten state of the molten material in the cavity C3 based on the detection data acquired by the detection data acquiring unit 1101. In particular, the molten state estimating unit 1105 estimates the degree of fluidity of the molten material as the molten state of the molten material.

Here, the molten state depends on the content of the raw material of the molding material. The content of the components affecting the molten molding material includes moisture content, length of the reinforcing fibers, proportion of the reinforcing fibers, molecular weight of the main component, and the like. The molten state in the cavity C3 affects the detection data during molding. Therefore, the molten state estimating unit can estimate the molten state by using the detection data depending on the molten state at the time of actual molding. The molten state is classified into four kinds, i.e., Type-A, Type-B, Type-C, Type-D, as shown in FIG. 33, for example.

The relationship storage unit 1106 stores the relationship between the quality change tendency and the correction amount of the molding condition for returning the quality to the quality standard, in correspondence with the molten state of the molten material in the cavity C3. As shown in fig. 34, for example, the relationship storage unit 1106 stores the relationship between the quality change tendency and the correction amount of the molding condition for each type of molten state of the molten material. Specifically, the relationship storage unit 1106 stores the relationship between the degree of deviation expressed in the matrix and the correction amount of the molding conditions for each quality type for each type of molten material. For example, the mass, size, and void volume are each rated in six stages as the degree of deviation. The type of the molding condition to be corrected is at least one of an injection speed, a holding pressure, a holding time, a mold temperature at the time of holding pressure, a cooling time, and the like.

Here, the degree of the relationship between the quality type and the type of the molding condition, and the relationship between the degree of deviation of the quality type and the correction amount of the molding condition can be derived by machine learning. That is, the relationship stored in the relationship storage unit 1106 can be generated by machine learning. Of course, this relationship may be set based on an experiment, past experience, or the like, instead of machine learning.

The correction condition determining unit 1107 determines the amount of correction of the molding conditions based on the trend of change in quality evaluated by the trend evaluating unit 1104, the molten state of the molten material estimated by the molten state estimating unit 1105, and the relationship stored in the relationship storing unit 1106.

The correction condition determining unit 1107 first selects a molten state corresponding to the molten state estimated by the molten state estimating unit 1105 from among the relationships shown in fig. 34. Next, for example, the correction condition determination unit 1107 determines a rank closest to the degree of deviation evaluated by the trend evaluation unit 1104 in the relationship expressed by the matrix as shown in fig. 34, and sets the correction amount of the molding condition corresponding to the rank as the correction amount of the determined molding condition. For example, as shown in fig. 32, when the degree of deviation of the mass is "+ 2.2%", the rank "+ 2%" of the degree of deviation of the mass is selected in the matrix shown in fig. 34.

Here, the correction condition determination unit 1107 determines the correction amount of the molding condition for each of the plurality of quality types. Therefore, the correction condition determination unit 1107 determines the final correction amount for the molding condition based on a plurality of correction amounts for the same type of molding condition. In this case, the correction condition determination unit 1107 may use, for example, a value obtained by summing a plurality of correction amounts as the final correction amount, or may use a value obtained by multiplying a weighting coefficient according to the quality type and further summing the result as the final correction amount.

Then, the correction condition determining unit 1107 outputs the final correction amount to the control device 1060 of the molding machine 1002, and adds the correction amount to the molding condition of the next molded product. Therefore, the control device 1060 performs the molding of the next molded product according to the molding conditions corrected. As a result, the quality of the molded product molded under the corrected molding conditions can be brought close to the quality standard Std.

(5. determining the Effect of the assisting apparatus 1003 Using the Molding conditions)

The effect of the auxiliary device 1003 determined by the molding conditions is described. The quality transition storage unit 1103 accumulates the quality of the molded product estimated by the machine learning and stores the quality transition. The quality transition is information for arranging the qualities of a plurality of molded products in the molding order. Therefore, the trend evaluating unit 1104 can evaluate the quality change trend based on the quality shifts of a plurality of continuous molded products.

In particular, the trend evaluation unit 1104 evaluates the trend of the quality change with respect to a predetermined quality standard Std. For example, the trend evaluation unit 1104 can evaluate, as the quality change trend, a state in which the quality continuously deviates from the predetermined quality standard Std, a variation in the quality within a quality allowable range including the predetermined quality standard, and the like.

The molten state estimating unit 1105 estimates the molten state of the molten material in the cavity C3 based on the detection data. Here, the molten state depends on the content of the raw material of the molding material. For example, the variation of the content of the component in the raw material of the molding material includes the moisture content, the length of the reinforcing fiber, the ratio of the reinforcing fiber, the molecular weight of the main component, and the like. The molten state in the cavity C3 affects the detection data during molding. Therefore, the molten state estimating unit 1105 can estimate the molten state by using the detection data depending on the molten state at the time of actual molding.

The relationship between the quality change tendency and the correction amount of the molding conditions is stored in the relationship storage unit 1106 in advance in correspondence with the molten state of the molten material in the cavity C3. That is, the relationship storage unit 1106 stores the relationship between the quality change tendency and the correction amount of the molding condition for each type of the molten state of the molten material. The relationship is set using experience of a skilled person, an output result of machine learning, an experimental result, and the like.

The correction condition determining unit 1107 determines the amount of correction of the molding conditions based on the newly estimated trend of change in quality, the newly estimated molten state of the molten material in the cavity C3, and the relationship stored in the relationship storage unit 1106. Here, the relationship stored in the relationship storage unit 1106 is related to a correction amount of the molding condition for returning the quality to the predetermined quality standard Std. In particular, the amount of correction of the molding conditions is determined according to the molten state of the molten material in the cavity C3. Therefore, when the molding conditions of the molding machine 1002 are corrected in accordance with the correction amount of the molding conditions determined by the correction condition determining unit 1107, the quality of the molded product to be molded next can be brought close to the predetermined quality standard Std.

That is, even when the quality of the molded product changes due to external factors such as ambient temperature and slight differences in the content of the raw material of the molding material, the molding conditions can be corrected so that the quality of the molded product becomes the predetermined quality standard Std by grasping the tendency of the change in quality and further grasping the molten state of the molten material in the cavity C3. Therefore, the molding conditions can be corrected not only by a skilled person but also by an unskilled person, and the quality of the molded product can be improved.

(6. learning stage in quality inference)

As described above, the quality estimation unit 1102 estimates the quality by machine learning. The quality estimation unit 1102 stores a learned model. The learned model is generated in advance. An example of the learning phase, which is the generation of the learned model, will be described.

First, detection data for a plurality of molded articles is acquired. Here, the feature amount of the detection data is extracted based on the detection data. The feature value extraction is performed, for example, based on the pressure data detected by the pressure sensor 1044, the maximum holding pressure Pmax in the holding pressure step, the pressure deviation in the holding pressure step, the holding pressure area Sa (shown in fig. 30), the actual holding pressure time (the holding pressure time obtained based on the pressure data), the pressure change rate (pressure differential value) at the start of the holding pressure step, and the like. For the extraction of the feature amount, the cooling area Sb (shown in fig. 30), the change speed of the pressure in the cooling step (pressure differential value), and the like are used based on the pressure data.

For the extraction of the feature amount, the maximum temperature in the pressure holding step, the temperature deviation in the pressure holding step, the temperature area in the pressure holding step (temperature × time), the cooling area in the cooling step (temperature × time), the change speed of the temperature in the cooling step (differential value), and the like are used based on the temperature data detected by the temperature sensor 1045. In addition, since the plurality of pressure sensors 1044 and temperature sensors 1045 are provided in the mold 1040, the above-described information is used for extracting the feature amount for each sensor.

Further, the plurality of pieces of information are acquired for the plurality of molded articles. Then, for each of the above information, the maximum value, the minimum value, the average value, the variance, and the like of the plurality of molded articles are calculated and used as the feature values.

On the other hand, the quality of a plurality of molded articles is measured using an external measuring instrument or the like. For example, as the quality, the mass, the size, the void volume, and the like are measured. Then, the learned model is generated by performing machine learning with the feature amount as an explanatory variable and the quality as a target variable. The learned model is a model into which the feature quantity and the output quality of the detection data can be input.

In the above description, the learning model having the feature amount as the explanatory variable has been described, but it is also possible to output the quality as the target variable by the learning model without using the feature amount as the explanatory variable and using the detection data itself as the explanatory variable.

(7. molten state of molten Material in Cavity C3)

(7-1. relationship between molten State and quality)

In the case where the fluidity of the molten material in the cavity C3 is high, the specific volume of the molten material in the cavity C3 can be increased. Therefore, the molten state of the molten material affects the quality of the molded product.

The fluidity of the molten material is affected by, for example, the amount of moisture absorbed by the particles as the raw material of the molding material. Hydrolysis occurs in the molten material due to the moisture of the particles, and as a result, the fluidity of the molten material is improved. Hydrolysis tends to occur more easily as the moisture content of the molding material increases. Further, it is considered that the length, ratio, and the like of the reinforcing fibers contained in the particles as the raw material of the molding material also affect the fluidity of the molten material. In addition, it is considered that the molecular weight of the main component of the molding material also affects the fluidity of the molten material.

(7-2. relationship between molten State and detection data)

The time for filling the cavity C3 with the molten material (hereinafter referred to as "cavity filling time") changes depending on the molten state of the molten material in the cavity C3. The cavity filling time is a time required from the start of filling of the molten material in the cavity C3 to the completion thereof.

For example, the start time of the cavity filling time may be a timing at which detection data of a sensor located closest to the gate 1043C among the pressure sensors 1044 in the cavity C3 rises. Note that the start timing of the cavity filling time may be detected by using detection data of the pressure sensor 1044 provided in the runner 1043 b. The completion timing of the cavity filling time can be a timing at which detection data of a sensor located at the farthest position from the gate 1043C among the pressure sensors 1044 in the cavity C3 rises.

The molten state estimating unit 1105 can estimate the molten state of the molten material in the cavity C3 using the cavity filling time. However, the relationship between the cavity filling time and the molten state can be obtained by machine learning.

In this case, the relationship between the cavity filling time and the molten state can be grasped with higher accuracy by machine learning while referring to the inspection report of the raw material for the molding material. That is, the molten state estimating unit can estimate the molten state of the molten material by machine learning by referring to an inspection report for the raw material of the molding material in addition to the detection data (particularly, the cavity filling time). In the inspection report of the raw material of the molding material, the molecular weight and the moisture content of the main component, the type of the reinforcing fiber, the length of the reinforcing fiber, the ratio of the reinforcing fiber, and the like are contained.

(7-3. other method of estimating molten State)

As described above, the molten state can be estimated using the cavity filling time. In addition, the molten state can be estimated by the following method.

Here, it is obvious that the values of the detection data based on the sensors such as the pressure sensor 1044 and the temperature sensor 1045 are influenced by the molding conditions of the molding machine 1002 at the time of molding. It is considered that the value of the detection data is influenced by the molten state of the molten material in the cavity C3 in addition to the molding conditions.

That is, the value of the detection data is affected by the molding conditions and the molten state of the molten material. The relationship can be considered to be a value of detection data obtained by multiplying a value relating to molding conditions and a value relating to the molten state of the molten material, for example. When the substitution is performed, the value related to the molten state of the molten material is the result of dividing the value related to the molding condition by the value of the detection data.

Therefore, the feature quantities for a plurality of detection data are acquired and multiplied. And, values of a plurality of molding conditions are acquired and multiplied. The result of dividing the product of the molding conditions by the product of the characteristic quantities of the detection data is used as an index indicating the molten state of the molten material in the cavity C3. Further, by classifying the obtained index, it is possible to determine to which type the molten state belongs. This can estimate the molten state of the molten material in the cavity C3.

(8. learning phase of relationship decision)

The relationship between the degree of quality deviation and the correction amount stored in the relationship storage unit 1106 can be generated by machine learning, for example. In the following, the generation of the relationship will be described with respect to a case of using machine learning.

(8-1. first example)

A first example of the learning phase will be described with reference to fig. 35. In the first example of the learning stage, as shown in fig. 35, the relationship between the quality type and the type of molding condition is directly generated by machine learning.

For example, a value of quality in each quality type and a value of molding condition are input, and a degree of influence (contribution degree, influence degree) of the molding condition on the quality type is acquired by machine learning. Further, the degree to which the correction amount of the value of the molding condition affects the value of the quality may be acquired. As a result, it is possible to obtain information on the relationship between the quality type and the type of the molding condition, and further obtain information on the relationship between the quality value and the correction amount of the molding condition.

Based on the relationship information obtained by machine learning, a person determines a relationship expressed by a matrix as shown in fig. 34. Of course, a matrix as shown in fig. 34 can be generated by machine learning.

(8-2. second example)

A second example of the learning phase will be described with reference to fig. 36. In the second example of the learning stage, as shown in fig. 36, the relationship between the quality type and the type of molding condition is indirectly generated by machine learning.

In the first example shown in fig. 35, the relationship between the quality type and the type of molding condition is directly generated by machine learning. However, the relationship between the quality type and the type of molding conditions may not be obtained directly. Here, the molding conditions determine the state at the time of molding, and the state determination quality at the time of molding is obvious. That is, it can be said that the molding conditions and the quality are kept in a relationship with each other depending on the state at the time of molding. The state during molding is, for example, the maximum holding pressure Pmax, the holding area Sa, the cooling area Sb, and the like.

Therefore, first, a value of quality in each quality type and a feature amount of detection data (a feature amount obtained from the maximum holding pressure or the like) are input, and a degree (contribution degree, influence degree) of influence of the feature amount of the detection data on the quality type is acquired by machine learning. Further, the degree of influence of the value of the feature amount of the detection data on the value of the quality may be acquired. As a result, the information on the relationship between the quality type and the feature value of the detection data can be obtained, and the information on the relationship between the quality value and the feature value of the detection data can be further obtained.

Next, the feature amount of the detection data and the type of the molding condition are input, and the degree (contribution degree, influence degree) of influence of the type of the molding condition on the feature amount of the detection data is acquired by machine learning. Further, the degree to which the correction amount of the value of the molding condition affects the value of the feature amount of the detection data may be acquired. As a result, it is possible to obtain information on the relationship between the feature amount of the detection data and the type of the molding condition, and further obtain information on the relationship between the correction amount of the feature amount value of the detection data and the value of the molding condition.

Then, the person determines the relationship expressed by the matrix shown in fig. 34 based on the information on the relationship between the quality type and the feature amount of the detection data, the information on the relationship between the feature amount of the detection data and the type of the molding condition, and the like. Of course, a matrix as shown in fig. 34 can be generated by machine learning.

(9. operation timing of molding machine system 1001)

(9-1. basic)

The operation timing of the molding machine system 1001, in particular, the operation timing of the process performed by the molding machine 1002 and the process performed by the molding condition determination support device will be described with reference to fig. 37. First, the molding machine 1002 continuously molds the molded product. For ease of description, a case where the second molded article is molded after the first molded article will be described.

As shown in fig. 37, the molding machine 1002 performs a start preparation process for the first molded product (S1011). The start preparation step includes, for example, a measurement step and a mold clamping step. Next, the molding machine 1002 performs a molding process for the first molded product (S1012). The molding step includes, for example, an injection filling step, a pressure holding step, and a cooling step. Next, the molding machine 1002 executes an end processing step for the first molded product (S1013). The finishing step includes, for example, a mold release removal step.

However, when the detection data detected by the pressure sensor 1044 and the temperature sensor 1045 at the beginning of the mold release taking-out step (immediately after the mold is opened) is used in the molding condition determination assisting device 1003, the beginning of the mold release taking-out step may be included in the molding step.

After the molding of the first molded article, the molding machine 1002 starts processing related to the molding of the second molded article. First, the molding machine 1002 performs a start preparation process for a second molded product (S1021). Next, the molding machine 1002 performs a molding process for a second molded product (S1022). Next, the molding machine 1002 executes an end processing step for the second molded product (S1023).

On the other hand, the molding condition determination assisting device 1003 performs processing in parallel with the processing of the molding machine 1002. Specifically, a primary processing step (S1101) of processing in parallel with detection of data by the pressure sensor 1044 and the temperature sensor 1045 at the time of molding the first molded product and a secondary processing step (S1102) of processing in parallel with the finishing processing step of the first molded product and the preparation starting step of the second molded product are executed. That is, the secondary processing step (S1102) is performed in the preparatory step of the molding machine 1002 (the finishing processing step of the first molded product and the starting preparatory step of the second molded product) from the finishing of the molding step of the first molded product to the starting of the molding step of the second molded product.

The primary processing step (S1101) includes at least processing performed by the detection data acquisition unit 1101. The secondary processing step (S1102) includes at least the processing performed by the correction condition determination unit 1107. The correction condition determining unit 1107 determines the amount of correction of the molding condition relating to the second molded product. That is, the molding machine 1002 sets the molding conditions in the molding step (S1022) of the second molded product to the molding conditions corrected by using the data in the molding step of the first molded product. Thus, the correction amount of the molding condition is determined in 1 cycle of molding of the molded article. Therefore, since the molding information immediately before can be used for determining the correction amount of the molding condition, the correction amount of the molding condition can be adapted to the current situation with higher accuracy.

(9-2. first example)

The first example of the processing of the molding condition determination assisting device 1003 is as follows. The primary processing step (S1101) performs processing of the detection data acquisition unit 1101. On the other hand, the secondary processing step (S1102) performs the processing of the quality estimation unit 1102, the processing of the trend evaluation unit 1104, and the processing of the correction condition determination unit 1107.

(9-3. second example)

The second example of the processing of the molding condition determination assisting device 1003 is as follows. The primary processing step (S1101) performs the processing of the detection data acquisition unit 1101 and the processing of the quality estimation unit 1102. On the other hand, the secondary processing step (S1102) performs the processing of the trend evaluating unit 1104 and the processing of the correction condition determining unit 1107.

(10. structural example of Molding machine System 1001)

(10-1. first example)

A configuration of a first example of the molding machine system 1001 will be described with reference to fig. 38. As shown in fig. 38, molding machine system 1001 includes a plurality of molding machines 1002 and 1002, edge computers 1004 and 1004 integrally configured with molding machines 1002 and 1002, and a server 1005 that forms the same network as the plurality of molding machines 1002 and 1002. Edge computers 1004 and 1004 may form a part of molding machines 1002 and 1002, or may be formed separately from molding machines 1002 and 1002.

The edge computers 1004 and the server 1005 constitute a molding condition determination support device 1003. The edge computers 1004 and 1004 include a detection data acquisition unit 1101. The server 1005 includes a quality estimation unit 1102, a quality transition storage unit 1103, a trend evaluation unit 1104, a molten state estimation unit 1105, a relationship storage unit 1106, and a correction condition determination unit 1107.

That is, the server 1005 receives the detection data acquired by the detection data acquisition unit 1101 from the edge computer 1004 separate from the molding machine 1002 or the edge computer 1004 built in the molding machine 1002. The server 1005 determines the correction amount of the molding condition based on the received information, and transmits the determined correction amount of the molding condition to the molding machine 1002.

In this case, the server 1005 can accumulate information relating to a plurality of molding machines 1002. Further, by providing the server 1005 with a processor capable of executing high-speed processing, the processing of the quality estimation unit 1102, the processing of the trend evaluation unit 1104, the processing of the molten state estimation unit 1105, and the processing of the correction condition determination unit 1107 can be performed at high speed. On the other hand, since it is not necessary to make each edge computer 1004 high-specification, cost reduction can be achieved.

(10-2. second example)

In the second example of the molding machine system 1001, as in the first example, the molding machine system 1001 includes a plurality of molding machines 1002 and 1002, edge computers 1004 and 1004 connected to the molding machines 1002 and 1002, respectively, and a server 1005 that forms the same network with the plurality of molding machines 1002 and 1002.

The edge computers 1004 and 1004 include a detection data acquisition unit 1101, a quality estimation unit 1102, and a molten state estimation unit 1105. The server 1005 includes a quality transition storage unit 1103, a trend evaluation unit 1104, a relationship storage unit 1106, and a correction condition determination unit 1107. That is, the server 1005 receives the quality of the molded product estimated by the quality estimation unit 1102 and the molten state estimated by the molten state estimation unit 1105 from the edge computer 1004 separate from the molding machine 1002 or the edge computer 1004 built in the molding machine 1002. The server 1005 determines the correction amount of the molding condition based on the received information, and transmits the determined correction amount of the molding condition to the molding machine 2.

(10-3. third example)

A third example of the molding machine system 1001 is where the server 1005 has all the functions. In this case, the edge computers 1004, 1004 are not required. Detection data acquisition unit 1101 in server 1005 receives detection data detected by sensors 1044 and 1045 from molding machine 1002. Then, correction condition determination unit 1107 in server 1005 transmits the correction amount of the molding condition to molding machine 1002.