阅读说明：本技术 松散回潮设备智能控制方法 (Intelligent control method for loosening and dampening equipment ) 是由 刘博� 李自娟 张爱华 方汀 高杨 芦渊 苗旺昌 郑海军 姚卫东 范广斌 孙嘉 于 2020-10-20 设计创作，主要内容包括：本发明公开了一种松散回潮设备智能控制方法,包括松散回潮入口水分预测模型建立、松散回潮智能控制模型建立和模型对接等步骤。本发明实现了该设备的精确智能控制,改善松散回潮出口物料水分不均匀性,提升产品均值化水平,为后道工序提供稳定物料,提高烟丝质量,同时本发明可以减少现场操作人员的数量,改善操作难度,将原经验控制转变为系统智能控制,减轻人员操作劳动强度。(The invention discloses an intelligent control method for loosening and conditioning equipment, which comprises the steps of building a moisture prediction model at a loosening and conditioning inlet, building an intelligent control model for loosening and conditioning, butting the models and the like. The invention realizes the accurate intelligent control of the device, improves the water non-uniformity of the material at the loosening and moisture regaining outlet, improves the equalization level of the product, provides stable material for the next procedure, and improves the quality of the tobacco shred.)

1. The intelligent control method of the loosening and dampening equipment is characterized by comprising the following steps: comprises the following steps

Step 1: establishment of water prediction model of loose moisture regain inlet

1.1 tobacco leaf classification basket

The tobacco leaves are bagged according to the classification standard of year to establish a prediction model from vacuum moisture regain to loosening moisture regain before a moisture meter of the single-grade tobacco leaves;

1.2, detecting the moisture in the tobacco production process

Based on a sample collection point setting mode and a collection method between the vacuum moisture regaining process and the loosening moisture regaining process, tobacco moisture detection of each sampling point between the vacuum moisture regaining process and the loosening moisture regaining process is carried out;

1.3 model building

Establishing a moisture prediction model of the loosening and conditioning inlet of each year by adopting a BP neural network algorithm and taking the moisture data of different sampling points of the tobacco leaves of each year as an input factor and the moisture of the loosening and conditioning inlet of each year as an output factor, and combining the prediction models of each year to form a self-adaptive model which can be automatically tracked and switched to the moisture prediction model of the loosening and conditioning inlet of the corresponding year according to the year of the tobacco leaves;

step 2: loose moisture regain control model establishment

2.1 screening of loosening and moisture regaining control parameters

Carrying out parameter statistics, parameter classification and parameter screening on the modeling parameters;

the basis of parameter screening: 1) non-process fixed parameters; 2) a controllable parameter; 3) parameters can be monitored; 4) related to moisture control;

2.2 model building

Adopting a regression equation algorithm to establish three sequentially associated nested models, wherein:

the nested model I is a total water supply prediction model of loosening and conditioning;

the nested model II is a calculating model of the water output of the loose moisture regaining outlet and the water output of the loose moisture regaining inlet;

the nested model III is a calculation model of the opening value of the water-fetching film valve;

and step 3: the water content prediction model of the loosening and conditioning inlet is butted with the loosening and conditioning control model

Comparing the predicted value of the water content at the loosening and conditioning inlet with the displayed value:

when the standard error x of the contrast value is less than 0.1, the intelligent control model for loosening and dampening adopts the display value to carry out water pumping regulation;

when the standard error of the contrast value is greater than or equal to 0.3 and greater than or equal to 0.1, the loosening and conditioning intelligent control model adopts the average value of the historical water pumping quantity to regulate water pumping;

when the standard error x of the contrast value is more than 0.3, the equipment is automatically stopped to wait for the repair personnel to overhaul.

2. The intelligent control method of the loosening and conditioning equipment according to claim 1, characterized in that:

in the step 1.2, the sample sampling points comprise sampling points arranged in a vacuum moisture regain outlet, a material track of a basket turning feeder and a loosening moisture regain feeder.

3. The intelligent control method of the loosening and conditioning equipment according to claim 1, characterized in that:

in step 1.3, the modeling tools include Excel, Spss holder, and Matlab.

4. The intelligent control method of the loosening and conditioning equipment according to claim 1, characterized in that:

in step 2.1, the screened modeling parameters comprise water content at a loosening and moisture regaining outlet, water content at a loosening and moisture regaining inlet, circulating air temperature, water adding amount at an inlet of a loosening and moisture regaining machine and water adding amount at an outlet of the loosening and moisture regaining machine.

5. The intelligent control method of the loosening and conditioning equipment according to claim 1, characterized in that:

in step 2.2, the nested model I is a loose moisture regain total water yield prediction model established by constructing a unitary regression equation by using the historical loose moisture regain inlet water yield value, the historical loose moisture regain outlet water yield value and the historical loose moisture regain total water yield.

6. The intelligent control method of the loosening and conditioning equipment according to claim 1, characterized in that:

in step 2.2, the nested model II is a sectional type calculation model, and the weight of the water pumping quantity at the loose conditioning inlet in the total water pumping quantity of loose conditioning is set as w, and the weight of the water pumping quantity at the loose conditioning outlet in the total water pumping quantity of loose conditioning is set as y:

when the moisture of the incoming material is in the process standard range, w is 80 percent, and y is 20 percent;

when the moisture of the incoming material is higher than the process standard range, (the moisture of the loose moisture regain inlet-standard upper limit) × 100%/standard median value ═ alpha, w ═ 80% (1+ alpha), y ═ 1-w;

when the moisture content of the incoming material is lower than the process standard range, (the moisture content at the loose moisture regain inlet-standard upper limit) × 100%/standard median value ═ alpha, w ═ 80% (1-alpha), and y ═ 1-w.

7. The intelligent control method of the loosening and conditioning equipment according to claim 1, characterized in that:

in the step 2.2, the nested model III is a linear equation calculation model which is constructed by taking an experimental method as a construction method, setting the water-fetching amount and taking the opening value of the water-fetching film valve under the water-fetching amount.

8. The intelligent control method of the loosening and conditioning equipment according to claim 1, characterized in that:

and step 3, when the standard error x of the comparison value is not less than 0.1, starting the early warning unit to remind the staff of paying attention.

Technical Field

The invention relates to the tobacco industry, in particular to an intelligent control method of loosening and dampening equipment, which is suitable for tobacco leaf dampening processing procedures and is used for improving the material moisture uniformity and the product equalization level.

Background

The loosening and moisture regaining process is the first moisture control process in the cigarette shred making link, the process aims at adjusting the moisture of materials and increasing the processing resistance of the materials, the stability of the outlet moisture of the materials is directly related to the stability of subsequent processing, and meanwhile, the filling value of finished cut tobacco is also influenced. The reason for influencing the moisture stability of the loose moisture regain outlet is mainly the consistency of incoming material moisture.

According to the current state of production investigation, the following problems exist: (1) external factors: the raw material storage warehouse of the company is only a part of constant temperature and humidity warehouse, most raw materials are stored in a natural environment warehouse, the fluctuation of the moisture content of the raw materials is large, the moisture content of the raw material tobacco bale is counted to be between 8% and 14%, and the difference between the lowest moisture content and the highest moisture content in a batch is about 6%. (2) Internal factors: at present, no moisture detection point exists in the process of feeding from an elevated warehouse, vacuum moisture regain and loosening moisture regain in a workshop, so that tobacco leaves cannot acquire moisture information in the process of passing through a path of more than 300 meters and three production posts, control signals cannot be sent to the next process in advance, and the control of the loosening moisture regain process is difficult. (3) Other factors: because the tobacco grade, the producing area and other factors restrict the material moisture fluctuation to be large, and the basket separation can not be optimized according to the grade, the producing area and other factors when the basket is unpacked and packed, the fluctuation of the moisture of the incoming material in the loosening and conditioning process has more influence factors, the randomness is large, the circulation is irregular, the process is controlled to be experience control, and the moisture fluctuation of the material at the process outlet is large.

The influence of the existing problems on production and lifting has the following aspects:

(1) influence on the quality of the product: the fluctuation of the moisture of the incoming material at the loosening and moisture regaining post is large, the chain transmission which is difficult to control the quality of the whole line is caused, and the moisture deviation of the finished tobacco shreds is large.

(2) Influence on process control: the loosening and conditioning automatic control operation principle is that instantaneous water adding amount is obtained through PID calculation according to feedforward data of a moisture meter at a loosening and conditioning inlet, when incoming material moisture suddenly changes in a cliff type or a crest type, the water adding amount also changes, but the water adding amount change rate is slower than that of the moisture, so that the moisture control is not ideal.

Disclosure of Invention

The application aims to provide an intelligent control method of loosening and dampening equipment, which is used for improving the moisture uniformity of materials and the equalization level of products.

According to the application, the moisture nonuniformity of the material at the loosening and conditioning outlet can be improved, the product equalization level is improved, stable materials are provided for the next procedure, and the tobacco shred quality is improved; meanwhile, the operation difficulty is improved, the original experience control is changed into system intelligent control, and the labor intensity of personnel operation is reduced.

The technical scheme adopted by the invention for solving the technical problems is as follows:

an intelligent control method for loosening and conditioning equipment comprises the following steps:

step 1: establishment of water prediction model of loose moisture regain inlet

1.1 tobacco leaf classification basket

The tobacco leaves are bagged according to the classification standard of year to establish a prediction model from vacuum moisture regain to loosening moisture regain before a moisture meter of the single-grade tobacco leaves;

1.2, detecting the moisture in the tobacco production process

Based on a sample collection point setting mode and a collection method between the vacuum moisture regaining process and the loosening moisture regaining process, tobacco moisture detection of each sampling point between the vacuum moisture regaining process and the loosening moisture regaining process is carried out;

1.3 model building

Establishing a moisture prediction model of the loosening and conditioning inlet of each year by adopting a BP neural network algorithm and taking the moisture data of different sampling points of the tobacco leaves of each year as an input factor and the moisture of the loosening and conditioning inlet of each year as an output factor, and combining the prediction models of each year to form a self-adaptive model which can be automatically tracked and switched to the moisture prediction model of the loosening and conditioning inlet of the corresponding year according to the year of the tobacco leaves;

step 2: loose moisture regain control model establishment

2.1 screening of loosening and moisture regaining control parameters

Carrying out parameter statistics, parameter classification and parameter screening on the modeling parameters;

the basis of parameter screening: 1) non-process fixed parameters; 2) a controllable parameter; 3) parameters can be monitored; 4) related to moisture control;

2.2 model building

Adopting a regression equation algorithm to establish three sequentially associated nested models, wherein:

the nested model I is a total water supply prediction model of loosening and conditioning;

the nested model II is a calculating model of the water output of the loose moisture regaining outlet and the water output of the loose moisture regaining inlet;

the nested model III is a calculation model of the opening value of the water-fetching film valve;

and step 3: the water content prediction model of the loosening and conditioning inlet is butted with the loosening and conditioning control model

Comparing the predicted value of the water content at the loosening and conditioning inlet with the displayed value:

when the standard error x of the contrast value is less than 0.1, the intelligent control model for loosening and dampening adopts the display value to carry out water pumping regulation;

when the standard error of the contrast value is greater than or equal to 0.3 and greater than or equal to 0.1, the loosening and conditioning intelligent control model adopts the average value of the historical water pumping quantity to regulate water pumping;

when the standard error x of the contrast value is more than 0.3, the equipment is automatically stopped to wait for the repair personnel to overhaul.

As an improvement of the technical scheme, in the step 1.2, the sample sampling points comprise sampling points arranged in a vacuum moisture regain outlet, a material track of a basket turning feeder and a loosening moisture regain feeder.

As an improvement of the above technical solution, in step 1.3, the modeling tool includes Excel, sps holder, and Matlab.

As an improvement of the above technical scheme, in step 2.1, the screened modeling parameters include loose moisture regain outlet moisture, loose moisture regain inlet moisture, circulating air temperature, water adding amount at an inlet of the loose moisture regain machine and water adding amount at an outlet of the loose moisture regain machine.

As an improvement of the above technical solution, in step 2.2, the nested model I is a loose moisture regain total water yield prediction model established by constructing a unitary regression equation by using the historical loose moisture regain inlet water yield value, the historical loose moisture regain outlet water yield value and the historical loose moisture regain total water yield.

As an improvement of the above technical solution, in step 2.2, the nested model II is a sectional type calculation model, and the weight of the pumping volume at the loose conditioning inlet to the total pumping volume of loose conditioning is set to w, and the weight of the pumping volume at the loose conditioning outlet to the total pumping volume of loose conditioning is set to y:

when the moisture of the incoming material is in the process standard range, w is 80 percent, and y is 20 percent;

when the moisture of the incoming material is higher than the process standard range, (the moisture of the loose moisture regain inlet-standard upper limit) × 100%/standard median value ═ alpha, w ═ 80% (1+ alpha), y ═ 1-w;

when the moisture content of the incoming material is lower than the process standard range, (the moisture content at the loose moisture regain inlet-standard upper limit) × 100%/standard median value ═ alpha, w ═ 80% (1-alpha), and y ═ 1-w.

As an improvement of the above technical solution, in step 2.2, the nested model III is a model calculated by using a linear equation constructed by setting the pumping amount and taking the value of the opening of the pumping membrane valve under the pumping amount by using an experimental method as a construction method.

As an improvement of the above technical solution, step 3 further includes, when the standard error x of the comparison value is ≧ 0.1, starting the early warning unit to remind the worker of paying attention.

The invention has the following beneficial effects:

1. the invention realizes the accurate and intelligent control of the equipment, improves the moisture nonuniformity of the material at the loosening and moisture regaining outlet, promotes the equalization level of the product, provides stable material for the next procedure and improves the quality of the tobacco shreds.

2. The invention can reduce the number of field operators, improve the operation difficulty, convert the original experience control into system intelligent control and reduce the labor intensity of personnel operation.

3. The error-proof early warning function of the invention can effectively avoid the abnormal water-fetching condition.

Drawings

The invention will be further described with reference to the accompanying drawings and specific embodiments,

FIG. 1 is a system block diagram of the system of the present invention;

FIG. 2 is a schematic diagram of a modeling unit I construction method and a model mechanism according to the present invention;

FIG. 3 is a schematic diagram of a modeling unit II construction method and model mechanism of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Referring to fig. 1, the intelligent control system of the loosening and conditioning equipment comprises:

comprises a loose moisture regain inlet water content prediction model, a loose moisture regain intelligent control model and a model docking unit, wherein

The water content prediction model of the loosening and conditioning inlet comprises a data acquisition unit and a modeling unit I.

1. A data acquisition unit:

in order to ensure the uniformity of the penetration rate of the single basket of tobacco leaves, the tobacco leaves are required to be bagged according to the classification standard of year before the model is established;

in order to fully understand the moisture loss condition before the vacuum moisture regain and the loosening moisture regain, the sample collection point setting method and the sample collection method in the process are specifically shown in table 1:

TABLE 1 sampling points and methods between vacuum conditioning and loosening conditioning

Collection point	Time of sample collection
		Vacuum moisture regaining outlet	Vacuum moisture regain is finished
Material rail of basket-turning feeding machine	The material is detected every ten minutes on the track
		Loosening and moisture regaining feeding machine	Sampling detection in feeder

2. A modeling unit I:

referring to fig. 2, the unit adopts a BP neural network algorithm, a modeling tool comprises Excel, Spss binder and Matlab, water data of different sampling points of tobacco leaves in each year are used as input factors, water of a loosening and dampening inlet in each year is used as output factors, a loosening and dampening inlet water forecasting model in each year is established, the loosening and dampening inlet water forecasting models in each year are combined, and an adaptive model capable of automatically tracking and switching to the loosening and dampening inlet water forecasting model in the corresponding year according to the year of the tobacco leaves is formed.

The model has the characteristics of strong model specificity, accurate prediction and the like.

The model was used to predict the loose moisture regain inlet moisture for each year grade of 10 batches of tobacco as follows, and the results are shown in table 2:

TABLE 210 Loose entrance moisture prediction results for each year of batch

Through statistical analysis, the average deviation of the predicted value and the displayed value is 0.048, and the model is accurate in prediction.

And secondly, the loosening and conditioning intelligent control model comprises a parameter screening unit and a modeling unit II.

1. A parameter screening unit:

the method is used for screening modeling parameters and comprises the following steps of

1) And parameter statistics:

the water content of the loosening and conditioning outlet, the temperature of the loosening and conditioning outlet, the water content of the loosening and conditioning inlet, the temperature of the loosening and conditioning inlet, the material flow, the rotating speed of the roller, the parameters of the hot air blower, the heating and humidifying steam pressure, the water atomization steam pressure, the circulating air temperature, the opening degree of the moisture exhaust air door, the opening degree of the fresh air door, the water adding amount of the inlet of the loosening and conditioning machine and the water adding amount of the outlet of the loosening and conditioning machine.

2) And parameter classification:

the statistical parameters are classified by referring to documents such as process standards, equipment management systems and the like, and the results are shown in table 3.

TABLE 3 Intelligent control model parameter Classification Table

3) Modeling parameter screening

The parameter selection basis is as follows: non-process fixed parameters; a controllable parameter; parameters can be monitored; in connection with moisture control.

The following parameters were selected according to the above screening criteria, see table 4:

TABLE 4 results of the screening of modeling parameters

Serial number	Parameter(s)	Serial number	Parameter(s)
				1	Water content at loosening and moisture regaining outlet	4	Water adding quantity at inlet of loosening and moisture regaining machine
2	Water content at inlet of loose moisture regain	5	Water adding quantity at outlet of loosening and moisture regaining machine
				3	Temperature of circulating air	6

2. Modeling Unit II

Referring to fig. 3, the unit adopts a regression equation algorithm to establish three nested models which are sequentially associated, wherein:

the nested model I is a total water supply prediction model of loosening and conditioning; the nested model II is a calculating model of the water output of the loose moisture regaining outlet and the water output of the loose moisture regaining inlet; the nested model III is a calculation model of the valve opening value of the water-beating film.

Specifically, the method comprises the following steps:

the nested model I is used for constructing a unitary regression equation by utilizing the historical loose moisture regain inlet water content value, the historical loose moisture regain outlet water content value and the historical loose moisture regain total water supply quantity, and the loose moisture regain outlet water content value is a process standard median value generally. For example: the standard median value of moisture of a diamond (hard red) loose moisture regain outlet is 20.5 (+ -1.5), the loose moisture regain equation is 20.5 ═ ax1+ bx2+ c, x1 is the moisture value of a historical loose moisture regain inlet, x2 is the total water supply amount of the historical loose moisture regain, and c is a compensation coefficient; through the equation, parameters are optimized every month by using production parameters of a month close to one month, so that each parameter of the equation is obtained, and a unitary regression equation is established: and y (total water yield of loosening and conditioning) is ax (moisture value of a loosening and conditioning inlet) + b (compensation coefficient), so that a prediction model of the total water yield of loosening and conditioning is established.

The nested model II is a sectional type calculation model, and the weight of the water pumping quantity at the loose moisture regain inlet in the total water pumping quantity of the loose moisture regain is set as w, and the weight of the water pumping quantity at the loose moisture regain outlet in the total water pumping quantity of the loose moisture regain is set as y:

when the moisture of the incoming material is in the range of the process standard (for example, the diamond (hard red) is 13 +/-1.5, and the standard median values of other brands are different but the ranges are the same, namely +/-1.5), w is 80 percent, and y is 20 percent;

when the moisture of the incoming material is higher than the process standard range, (the moisture of the loose moisture regain inlet-standard upper limit) × 100%/standard median value ═ alpha, w ═ 80% (1+ alpha), y ═ 1-w;

when the moisture content of the incoming material is lower than the process standard range, (the moisture content at the loose moisture regain inlet-standard upper limit) × 100%/standard median value ═ alpha, w ═ 80% (1-alpha), and y ═ 1-w.

The nested model III is a linear equation calculation model which is constructed by setting the water-fetching amount and taking the opening value of the water-fetching film valve under the water-fetching amount by taking an experimental method as a construction method.

Model docking unit

The unit compares the predicted value of the water content at the loosening and conditioning inlet with the display value:

when the standard error x of the contrast value is less than 0.1, the intelligent control model for loosening and dampening adopts the display value to carry out water pumping regulation;

when the standard error of the contrast value is greater than or equal to 0.3 and greater than or equal to 0.1, the loosening and conditioning intelligent control model adopts the average value of the historical water pumping quantity to regulate water pumping;

when the standard error x of the contrast value is more than 0.3, the equipment is automatically stopped to wait for the repair personnel to overhaul.

The model butt joint unit can be further connected with an early warning unit, when the standard error x of the contrast value is not less than 0.1, the early warning unit is started to remind workers to notice, so that a set of error-proof early warning control system of the moisture meter is formed, and the abnormal condition of loose moisture regain and water supply can be effectively prevented.

The embodiment is an intelligent control method of loosening and conditioning equipment, which comprises the following steps:

step 1: establishment of water prediction model of loose moisture regain inlet

1.1 tobacco leaf classification basket

In order to ensure the uniformity of the moisture regain of the single basket of tobacco leaves, the tobacco leaves are required to be bagged according to the classification standard of year before the model is established, so that a prediction model from vacuum moisture regain to loosening moisture regain of the single-grade tobacco leaves is established;

1.2, detecting the moisture in the tobacco production process

In order to fully understand the moisture loss condition before the process from vacuum moisture regain to loosening moisture regain, the tobacco moisture detection of each sampling point between the process from vacuum moisture regain to loosening moisture regain is carried out according to the setting mode and the collection method of the sample collection point in the table 1;

1.3 modeling tool

Excel、Spss molder、matlab；

1.4 model method

BP neural network algorithm;

1.5 model architecture

Referring to fig. 2, the model construction is described by taking yearly 1, yearly 2, and yearly 3 tobacco leaves as examples.

The input factor of the model is the tobacco moisture of each data sampling point grouped by year, so the model is also composed of a plurality of different year prediction models, and the models are mutually embedded and associated/combined to form a self-adaptive model which is automatically tracked and switched to the tobacco leaves in the corresponding year according to the year of the tobacco leaves.

Step 2: loose moisture regain control model establishment

2.1 screening of loosening and moisture regaining control parameters

2.1.1, statistics of parameters

The water content of the loosening and conditioning outlet, the temperature of the loosening and conditioning outlet, the water content of the loosening and conditioning inlet, the temperature of the loosening and conditioning inlet, the material flow, the rotating speed of the roller, the parameters of the hot air blower, the heating and humidifying steam pressure, the water atomization steam pressure, the circulating air temperature, the opening degree of the moisture exhaust air door, the opening degree of the fresh air door, the water adding amount of the inlet of the loosening and conditioning machine and the water adding amount of the outlet of the loosening and conditioning machine;

2.1.2 parameter Classification

Classifying the statistical parameters by referring to files such as process standards, equipment management systems and the like;

the classification results are shown in Table 3;

2.1.3 selection of modeling parameters

The parameter selection basis is as follows: 1. non-process fixed parameters; 2. a controllable parameter; 3. parameters can be monitored; 4. related to moisture control; screening the modeling data according to the selection basis, and the result is shown in table 4;

2.2 model Algorithm

A regression equation;

2.3 model architecture

Refer to fig. 3.

Adopting a regression equation algorithm to establish three sequentially associated nested models, wherein:

the nested model I is a total water supply prediction model of loosening and conditioning;

the nested model II is a calculating model of the water output of the loose moisture regaining outlet and the water output of the loose moisture regaining inlet;

the nested model III is a calculation model of the opening value of the water-fetching film valve;

the modeling process can be seen above.

And step 3: the water content prediction model of the loosening and conditioning inlet is butted with the loosening and conditioning control model

3.1, comparing the predicted value of the water content of the loosening and conditioning inlet with a display value:

when the standard error x of the contrast value is less than 0.1, the intelligent control model for loosening and dampening adopts the display value to carry out water pumping regulation;

when the standard error of the contrast value is greater than or equal to 0.3 and greater than or equal to 0.1, the loosening and conditioning intelligent control model adopts the average value of the historical water pumping quantity to regulate water pumping;

when the standard error x of the contrast value is more than 0.3, the equipment is automatically stopped to wait for the repair personnel to overhaul.

3.2, the unit is connected with an early warning unit, when the standard error x of the contrast value is not less than 0.1, the early warning unit is started to remind workers to notice, and therefore a set of error-preventing early warning control system of the moisture meter is formed, and the abnormal condition of loose moisture regain and water supply is prevented.

And performing online operation on the intelligent control system/method of the loosening and dampening equipment in each embodiment.

The production results of the online operation are counted, and the results are shown in table 5:

TABLE 5 statistical table of production results of online operation of the system of the present application

Batches of	Moisture deviation at outlet of loosening and moisture regaining	Batches of	Moisture deviation at outlet of loosening and moisture regaining	Batches of	Moisture deviation at outlet of loosening and moisture regaining
						1	0.009	8	0.009	15	0.009
2	0.007	9	0.008	16	0.01
						3	0.01	10	0.006	17	0.008
4	0.006	11	0.006	18	0.008
						5	0.005	12	0.006	19	0.009
6	0.008	13	0.005	20	0.008
						7	0.008	14	0.007	21	0.007

Through statistics and analysis, the average deviation of the moisture at the loosening and conditioning outlet is 0.1 before use, and the average deviation of the system after use is 0.0076, so that the system effectively reduces the moisture deviation at the loosening and conditioning outlet and improves the homogenization level of the product.

Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments or portions thereof without departing from the spirit and scope of the invention.