阅读说明：本技术 一种设备预测性维护学习系统 (Equipment predictive maintenance learning system ) 是由 杜雪飞 吴兴鹏 陈亮 贾祥 于 2021-07-14 设计创作，主要内容包括：本发明涉及工业互联网技术领域,提供了一种设备预测性维护学习系统,包括服务器和学习机,学习机与服务器通信连接,服务器包括设备状态监测模块,用于监测实训装置并获取实训装置的运行数据；预测性维护模块,预设有分析策略,用于根据分析策略对实训装置的运行数据进行预测性维护分析得到实训装置运行状态的分析结果；报警模块,用于根据分析结果进行实训装置的报警或预警；其中,服务器还包括设备数字双胞胎模块,用于获取工厂设备的设备数据和运行数据,根据设备数据进行三维建模得到虚拟设备模型,根据运行数据控制虚拟设备模型进行虚拟运行。(The invention relates to the technical field of industrial internet, and provides an equipment predictive maintenance learning system, which comprises a server and a learning machine, wherein the learning machine is in communication connection with the server; the predictive maintenance module is preset with an analysis strategy and used for performing predictive maintenance analysis on the operation data of the practical training device according to the analysis strategy to obtain an analysis result of the operation state of the practical training device; the alarm module is used for alarming or prewarning the practical training device according to the analysis result; the server also comprises an equipment digital twin module which is used for acquiring equipment data and operation data of the factory equipment, carrying out three-dimensional modeling according to the equipment data to obtain a virtual equipment model, and controlling the virtual equipment model to carry out virtual operation according to the operation data.)

1. The equipment predictive maintenance learning system comprises a server and a learning machine, wherein the learning machine is in communication connection with the server, and the server comprises an equipment state monitoring module which is used for monitoring a practical training device and acquiring the operating data of the practical training device;

the predictive maintenance module is preset with an analysis strategy and used for performing predictive maintenance analysis on the operation data of the practical training device according to the analysis strategy to obtain an analysis result of the operation state of the practical training device;

the alarm module is used for alarming or prewarning the practical training device according to the analysis result;

the method is characterized in that: the server also comprises an equipment digital twin module which is used for acquiring equipment data and operation data of the factory equipment, carrying out three-dimensional modeling according to the equipment data to obtain a virtual equipment model, and controlling the virtual equipment model to carry out virtual operation according to the operation data;

the predictive maintenance module is also used for performing predictive maintenance analysis on the operation data of the factory equipment according to the analysis strategy to obtain an analysis result of the operation state of the virtual equipment model, and the alarm module is used for giving an alarm or early warning on the virtual equipment model according to the analysis result.

2. The device predictive maintenance learning system of claim 1, wherein: the predictive maintenance module comprises a rule driving unit, and the rule driving unit is preset with a rule driving strategy and used for performing predictive maintenance analysis on the obtained operation data according to the rule driving strategy to obtain an analysis result.

3. The device predictive maintenance learning system of claim 2, wherein: the predictive maintenance module further comprises a data driving unit, wherein a data driving strategy is preset in the data driving unit, and the data driving unit is used for performing predictive analysis on the obtained operation data according to the data driving strategy to obtain an analysis result.

4. The device predictive maintenance learning system of claim 1, wherein: the server also comprises an equipment operation and maintenance knowledge module, wherein a fault table is prestored, and the fault table comprises an equipment fault expression and a corresponding fault type;

and the work order dispatching module is used for generating and dispatching a maintenance work order according to the analysis result and the fault table, wherein the maintenance work order comprises specific equipment and fault types.

5. The device predictive maintenance learning system of claim 4, wherein: the server also comprises an intelligent operation and maintenance module, maintenance guide videos with different fault types are preset, the maintenance guide videos corresponding to the fault types are matched according to analysis results, and the work order dispatching module also sends the corresponding maintenance guide videos when dispatching the maintenance work orders.

6. The device predictive maintenance learning system of claim 5, wherein: the server also comprises a communication module used for obtaining a maintenance record, wherein the maintenance record comprises the actual type of the fault;

and the equipment operation and maintenance knowledge module is also used for comparing the fault types in the corresponding maintenance work orders according to the maintenance records, and updating the fault table according to the actual fault types and the fault expressions if the actual fault types in the maintenance records are different from the fault types in the maintenance work orders.

7. The device predictive maintenance learning system of claim 1, wherein: the server also comprises a self-defining module which is used for inputting modification information and modifying the corresponding analysis strategy according to the modification information.

8. The device predictive maintenance learning system of claim 7, wherein: the user-defined module is also used for inputting strategy information and generating a new analysis strategy.

9. The device predictive maintenance learning system of claim 1, wherein: the digital twins module is also used for obtaining equipment information disclosed by an equipment manufacturer and establishing an equipment digital twins model according to the equipment information.

Technical Field

The invention relates to the technical field of industrial internet, in particular to an equipment predictive maintenance learning system.

Background

The equipment operation and maintenance refers to the realization of automatic intelligent fault detection of the equipment through data acquisition, identification and analysis technologies, and the automatic judgment of hidden dangers of the equipment in the operation process and the timely warning of the faults, so that an operation and maintenance manager can be assisted to eliminate the troubles and judge and process the root causes of the faults of the equipment. Because the traditional equipment operation and maintenance mainly adopts a post-control mode to solve the problem, namely, the problem is solved in time after the fault occurs, in this case, because the fault already occurs, the loss caused by the fault occurs to the equipment. Therefore, to avoid reducing or avoiding losses due to failures, it is desirable to predict the occurrence of failures for predictive maintenance and timely improvement of potential problems with the equipment.

Because the predictive maintenance relates to the technologies of acquisition, identification, state analysis and the like of equipment operation data, and the comprehensiveness is strong, the teaching about the predictive operation and maintenance of the equipment in schools is less established, only partial related courses and practical training are established, and meanwhile, because the industrial equipment range is wide, the existing teaching practical training equipment comprises mechanical equipment, electrical equipment and the like, and the requirement can not be met. Moreover, most of the current school teaching is theoretical teaching, no actual equipment is provided for students to carry out actual operation, the participation of the students is not high, the predictive maintenance relates to artificial intelligence, big data analysis and the like, the technical requirement is high, and the pure theoretical teaching effect is not ideal. It is therefore desirable to design an equipment predictive maintenance learning system.

Disclosure of Invention

The invention aims to provide an equipment predictive maintenance learning system to solve the problem of poor operability caused by the fact that a school side mostly adopts a theoretical teaching mode for teaching in the prior art.

The basic scheme provided by the invention is as follows: the equipment predictive maintenance learning system comprises a server and a learning machine, wherein the learning machine is in communication connection with the server, and the server comprises an equipment state monitoring module which is used for monitoring a practical training device and acquiring the operating data of the practical training device;

the predictive maintenance module is preset with an analysis strategy and used for performing predictive maintenance analysis on the operation data of the practical training device according to the analysis strategy to obtain an analysis result of the operation state of the practical training device;

the alarm module is used for alarming or prewarning the practical training device according to the analysis result;

the server also comprises an equipment digital twin module, a data processing module and a data processing module, wherein the equipment digital twin module is used for acquiring equipment data and operation data of factory equipment, performing three-dimensional modeling according to the equipment data to obtain a virtual equipment model, and controlling the virtual equipment model to perform virtual operation according to the operation data;

the predictive maintenance module also carries out predictive maintenance analysis on the operation data of the factory equipment according to the analysis strategy to obtain an analysis result of the operation state of the virtual equipment model, and the alarm module carries out alarm or early warning on the virtual equipment model according to the analysis result.

The basic scheme has the working principle and the beneficial effects that: in the scheme, the equipment state monitoring module of the server is used for monitoring the operation data of the practical training device, and the obtained operation data represents the operation state of the practical training device at present; after the predictive maintenance module presets an analysis strategy, the operation data of the practical training device is analyzed according to the analysis strategy, the obtained analysis result can indicate whether the operation state of the practical training device is normal or not, and the alarm module carries out early warning or alarming according to the analysis result so as to remind students to overhaul the practical training device and eliminate faults of the practical training device in time.

Considering that the performance of different devices is different, in order to help students to better understand the use and maintenance of each device, the best mode is to allow the students to actually operate the devices, however, for schools, purchasing a large amount of devices will be a huge expense, for students, the learning of pure theory is tedious, and since there is no actual device operation, the corresponding knowledge cannot be applied in the learning process, therefore, in the scheme, the server is further provided with a digital twins module, the device data of the plant devices is obtained by the digital twins module, the three-dimensional model, i.e. the virtual device model, of the plant devices can be built by the three-dimensional modeling technology according to the obtained device data, and after the virtual device model is built, the students can see the corresponding devices in the learning process, and meanwhile, the digital twins module is used for controlling the virtual equipment model to perform virtual operation according to the acquired operation data, so that better learning can be realized. Similarly, the constructed virtual equipment model is subjected to predictive maintenance analysis by adopting a predictive maintenance module so as to assist students in performing maintenance operation on different types of equipment.

Compared with the prior art, in the scheme, after the device data and the operation data of the factory equipment are acquired by the aid of the set digital twins unit, the corresponding virtual device model is established for students to learn, on one hand, the number of devices purchased by a school party can be reduced by the aid of the mode of establishing the virtual device model, the purchase cost of the devices is reduced for the school party, on the other hand, teaching is assisted by the aid of the established virtual device model, the students can see real objects in the learning process, after all, the operation is performed by operating the virtual device model, and compared with a pure theoretical teaching mode, the teaching can be better performed.

The first preferred scheme is as follows: preferably, the predictive maintenance module comprises a rule driving unit, and the rule driving unit is preset with a rule driving strategy and used for performing predictive maintenance analysis on the acquired operation data according to the rule driving strategy to obtain an analysis result. In this embodiment, the rule-driven strategy refers to analyzing an operation curve of the device according to a characteristic curve of the device. Has the advantages that: in the scheme, the set rule driving unit is used for performing predictive maintenance analysis on the operation of the practical training device and the virtual equipment model according to the acquired operation data so as to maintain the practical training device and the virtual equipment model in time, and the operation is simple.

The preferred scheme II is as follows: preferably, the predictive maintenance module further includes a data driving unit, and the data driving unit is preset with a data driving strategy and used for performing predictive analysis on the acquired operation data according to the data driving strategy to obtain an analysis result. Description of the drawings: in the scheme, the data driving strategy refers to that according to a large amount of operation data of the equipment in the current state, learning is carried out through a machine learning method such as a neural network and the like to obtain the characteristics of the equipment, and then analysis is carried out. Has the advantages that: in consideration of the fact that the characteristic curve of some equipment is not completely analyzed, and the rule driving strategy is not suitable for the equipment, the scheme is also provided with a data driving unit, and the data driving unit is used for performing auxiliary analysis on the operation data in a predictive analysis mode according to the data driving strategy, so that the accuracy of an analysis result is ensured.

The preferable scheme is three: preferably, the server further comprises an equipment operation and maintenance knowledge module, wherein a fault table is prestored, and the fault table comprises an equipment fault expression and a corresponding fault type; and the work order dispatching module is used for generating and dispatching a maintenance work order according to the analysis result and the fault table, wherein the maintenance work order comprises specific equipment and fault types. Has the advantages that: in consideration of the fact that when equipment is maintained, the fault type of the equipment is known in advance to help improve maintenance efficiency, therefore, in the scheme, the work order dispatching module is further arranged to generate the maintenance work order and then dispatch the maintenance work order, and specific equipment and fault types in the maintenance work order can help customers to fully know about the fault so as to improve the maintenance efficiency of the fault.

The preferable scheme is four: preferably, the server further comprises an intelligent operation and maintenance module, maintenance guide videos of different fault types are preset, the maintenance guide videos corresponding to the fault types are matched according to analysis results, and the work order dispatching module further sends the corresponding maintenance guide videos when dispatching the maintenance work orders. The maintenance instruction video in the scheme refers to a maintenance teaching video performed for a corresponding equipment fault, such as a first step of checking what needs to be checked, for example, checking whether a power supply is abnormal or not, whether an indicator lamp is abnormal or not, a second step of checking what needs to be done, and the like. Has the advantages that: in the scheme, the maintenance guidance video is sent to help students to maintain and learn the equipment.

The preferable scheme is five: preferably, the server further includes a communication module, configured to obtain a maintenance record, where the maintenance record includes an actual type of the fault; the equipment operation and maintenance knowledge module is also used for comparing the fault types in the corresponding maintenance work orders according to the maintenance records, and updating the fault table according to the actual fault types and the fault expressions if the actual fault types in the maintenance records are different from the fault types in the maintenance work orders. Has the advantages that: in consideration of the fact that faults different from preset fault types and fault expressions may occur in the using process of the equipment, in the scheme, the communication module is further arranged to obtain the maintenance records, the fault types in the maintenance work order are compared according to the maintenance records, if the actual fault types in the maintenance records are different from the fault types in the maintenance work order, if the fault expressions are that the equipment motor is overheated, the fault types in the maintenance work order are that the motor voltage is overhigh, the actual fault types are found to be short circuits inside the motor during maintenance, namely the actual fault types are not consistent with the pre-judged fault types, and at the moment, the equipment operation and maintenance knowledge module updates the fault table according to the actual fault types and the fault expressions, so that the fault table is perfected, and the accuracy of the maintenance work order is improved.

The preferable scheme is six: preferably, the server further comprises a custom module for entering modification information and modifying the corresponding analysis strategy according to the modification information. Has the advantages that: considering that the performance of the equipment is reduced in the using process of the equipment, the analysis strategy needs to be correspondingly adjusted in order to timely predict potential faults, therefore, the scheme is provided with the custom module, when the analysis strategy needs to be modified, the custom module is used for inputting and modifying, and the operation is simple.

The preferable scheme is seven: as a preferred option of the sixth preferred embodiment, the custom module is further configured to enter policy information and generate a new analysis policy. Has the advantages that: considering that different analysis strategies are generally adopted for analyzing and early warning for different parameters of different equipment, in the scheme, a user-defined module is further utilized to generate a brand-new analysis strategy according to the input strategy information so as to improve the comprehensiveness of the analysis strategy.

The preferable scheme is eight: preferably, the digital twins module is further configured to obtain device information published by a device manufacturer and establish a device digital twins model according to the device information. Has the advantages that: considering that the equipment products released by the equipment manufacturer are far more than the equipment in the factory, in the scheme, the digital twin module is further arranged to obtain the equipment information disclosed by the equipment manufacturer, and the digital twin model of the equipment is established according to the equipment information, and the establishment of the digital twin model of the equipment can expand the equipment model library in the learning system, so that the comprehensiveness of equipment learning is increased.

Drawings

FIG. 1 is a block diagram of a server in an embodiment of a predictive maintenance learning system for equipment according to the invention;

FIG. 2 is a diagram illustrating an analysis of an overflow rule according to a first embodiment;

FIG. 3 is a schematic diagram of analysis of upper and lower bound rules in the third embodiment;

FIG. 4 is a diagram illustrating an analysis of the trend rule according to the third embodiment;

FIG. 5 is an analysis diagram of the rule of deviation according to the third embodiment;

fig. 6 is an analysis diagram of the rocking rule in the third embodiment.

Detailed Description

The following is further detailed by way of specific embodiments:

example one

Substantially as shown in figure 1: the equipment predictive maintenance learning system comprises a server and a learning machine, wherein the learning machine is in communication connection with the server.

The server comprises an equipment knowledge module, wherein the equipment knowledge module stores relevant equipment knowledge, such as equipment type selection, installation, debugging, operation and maintenance and the like, and the equipment knowledge can be acquired online through the Internet or can be input and stored by using input equipment after being provided by a manufacturer.

The equipment state monitoring module is used for monitoring the practical training device and acquiring the operating data of the practical training device; in this embodiment, the practical training device is a typical industrial production line, and includes a material transportation unit, a material assembly unit, a material counting unit, a sensor unit, an industrial network communication unit, a pneumatic unit and an automatic control unit, and a typical factory equipment is simulated through the setting of the practical training device, so that students can perform practical operations.

The predictive maintenance module is preset with an analysis strategy and used for performing predictive maintenance analysis on the operation data of the practical training device according to the analysis strategy to obtain an analysis result of the operation state of the practical training device; specifically, in this embodiment, the analysis policy includes a rule driving policy and a data driving policy, the predictive maintenance module includes a rule driving unit and a data driving unit, the rule driving unit is preset with the rule driving policy and is configured to perform predictive maintenance analysis on the obtained operation data according to the rule driving policy to obtain an analysis result, and the data driving unit is preset with the data driving policy and is configured to perform predictive analysis on the obtained operation data according to the data driving policy to obtain an analysis result. The regular driving strategy refers to analyzing an equipment operation curve according to a characteristic curve of the equipment, such as a motor characteristic curve in an equipment use manual; the data-driven strategy refers to learning by a machine learning method such as a neural network according to a large amount of equipment operation data to obtain the characteristics of the equipment for analysis.

And the custom module is used for inputting modification information, modifying the corresponding analysis strategy according to the modification information, and also used for inputting strategy information and generating a new analysis strategy.

The alarm module is used for alarming or prewarning the practical training device according to the analysis result;

the device digital twin module is used for acquiring device data and operation data of factory equipment, performing three-dimensional modeling according to the device data to obtain a virtual device model, controlling the virtual device model to perform virtual operation according to the operation data, acquiring device information disclosed by a device manufacturer and establishing a device digital twin model according to the device information; in this embodiment, when the virtual device model is constructed, the constructed virtual device model may be split and assembled, and considering that the devices may have requirements on the mounting sequence of each part during mounting, the construction of the split virtual device model is more convenient for students to learn, and provides better teaching for the students. The equipment data and the equipment information comprise equipment manufacturers, equipment models, equipment parameters, installation drawings, instruction manuals, maintenance manuals and the like, and the operation data comprise real-time data of the equipment in the operation process, such as the temperature, the temperature rise, the current, the voltage, the vibration and the like of the motor.

The predictive maintenance module is also used for performing predictive maintenance analysis on the operation data of the factory equipment according to the analysis strategy to obtain an analysis result of the operation state of the virtual equipment model, and the alarm module is used for alarming or early warning the virtual equipment model according to the analysis result;

the equipment operation and maintenance knowledge module is prestored with a fault table, and the fault table comprises equipment fault expressions and corresponding fault types;

the work order dispatching module is used for generating and dispatching a maintenance work order according to the analysis result and the fault table, wherein the maintenance work order comprises specific equipment and fault types;

the intelligent operation and maintenance module is preset with maintenance guide videos of different fault types, matches the maintenance guide videos of corresponding fault types according to analysis results, and sends the corresponding maintenance guide videos when the work order dispatching module dispatches the maintenance work orders;

the communication module is used for acquiring maintenance records, and the maintenance records comprise actual fault types; the equipment operation and maintenance knowledge module is also used for comparing the fault types in the corresponding maintenance work orders according to the maintenance records, and updating the fault table according to the actual fault types and the fault expressions if the actual fault types in the maintenance records are different from the fault types in the maintenance work orders.

The specific implementation process is as follows: when the device is used, a sensor on the practical training device collects operation data of the practical training device, then an equipment state monitoring module of a server monitors and acquires the operation data, then a predictive maintenance module analyzes the operation state of the practical training device according to the operation data to acquire an analysis result, taking a rule driving strategy as an example, a motor characteristic curve of the device is set, when the continuous vibration time of the motor exceeds X hours, a fault occurs, in the operation data acquired by the equipment state monitoring module, the continuous vibration time of the motor is Y hours, the obtained analysis result Y is greater than X, namely the continuous vibration time of the motor exceeds the duration in the equipment motor characteristic curve, the fault is judged to occur, and at the moment, an alarm unit sends alarm information to give an alarm; when analyzing the operation state, it is necessary to preset and select a rule driving strategy or a data driving strategy for analysis.

In the process, when the predictive maintenance module obtains an analysis result, the work order distributing module further obtains and generates a maintenance work order according to the analysis result and the fault table, and sends the maintenance work order to the learning machine, students can know specific equipment with faults and fault types and performances through the learning machine, meanwhile, the intelligent operation and maintenance module can also push maintenance guidance videos of the faults to the learning machine, and the students can complete maintenance of the faults according to the maintenance guidance videos.

After the maintenance is completed, the learning machine uploads the maintenance record, the communication module acquires the maintenance record, the equipment operation and maintenance knowledge module compares the corresponding fault type in the maintenance work order according to the maintenance record, if the actual fault type in the maintenance record is different from the fault type in the maintenance work order, the fault table is updated according to the actual fault type and the fault performance, if the motor works abnormally due to overhigh voltage in the prediction process, and if the motor does not contact well due to the fact that a foreign matter is clamped in the motor in the actual maintenance process, namely the actually occurring fault type has errors with the predicted fault type, at the moment, the equipment operation and maintenance knowledge module corrects the fault table to perfect the fault table, so that the accuracy of the maintenance work order is maintained.

When an analysis strategy needs to be added or an existing analysis strategy needs to be modified, if an analysis strategy 'overflow rule' is added, a custom module enters strategy information and then generates a new analysis strategy, if the entered strategy information is the 'new-overflow rule': and judging that the pressure is abnormal when the difference between the continuous N pressure values and the preset average value is detected to exceed a preset standard value, wherein N can be selected and set according to the actual condition of the equipment, and the average value and the standard value can be obtained from an equipment manufacturer or calculated by collecting multiple groups of pressure values when the equipment runs under the normal condition. Taking N as an example, as shown in fig. 2, since it is detected that the deviations of the eight consecutive pressure values from the average value (X _ mean) all exceed one standard deviation (σ), it may be determined that the pressure is abnormal according to the analysis strategy, that is, the analysis result is abnormal, and at this time, the alarm module sends an alarm message.

Example two

The difference from the first embodiment is that in the first embodiment, the server includes a local server and a cloud server, the student machine is in communication connection with the local server, data related to the practical training device and the factory equipment is stored on the local server, and all data is stored on the cloud server.

In consideration of the reasons of equipment level upgrading, continuous appearance of new equipment and the like, more and more data related to the equipment are obtained, and students learn knowledge related to a practical training device or factory equipment in many times when learning by using a learning machine, so that the server is divided into a local server and a cloud server, and the data related to the practical training device and the factory equipment are stored on the local server, so that the storage capacity of the data on the local server can be reduced, and the access speed is improved.

EXAMPLE III

In this embodiment, the analysis policy in the predictive maintenance module further includes an upper and lower limit rule, a trend rule, a normal distribution rule, an event matching rule, a dynamic restriction rule, a deviation rule, a swing rule, and the like, which are taken as examples, the upper and lower limit rule compares the collected operation data with a preset upper limit threshold and a preset lower limit threshold, and when the compared operation data exceeds the upper limit threshold or the lower limit threshold, it is determined that the operation is abnormal, as shown in fig. 3, because there are two operation data exceeding the upper limit threshold or the lower limit threshold, it is determined that the operation is abnormal at this time; the trend rule is to determine whether the collected operation data has a continuous ascending or descending trend, and if a plurality of (for example, six) continuous operation data keep ascending or descending trends, it is determined that the operation is abnormal, as shown in fig. 4; the deviation rule is to determine whether the plurality of operation data are all smaller than the average value, if so, it is determined that the operation is abnormal, and as shown in fig. 5, the operation is abnormal because the nine continuous operation data are all located below the average value, that is, smaller than the average value; the sway rule is to determine whether the plurality of operation data continuously generate alternate vibration, and as shown in fig. 6, the operation is determined to be abnormal because the fourteen continuous operation data generate alternate vibration.

Example four

In this embodiment, the analysis policy preset in the predictive maintenance module is exemplified by an upper and lower limit rule, a trend rule, a deviation rule, a swing rule and an overflow rule, different analysis rules are preset with different weighted values, and the predictive maintenance module is also preset with a judgment rule, where the judgment rule refers to that after the collected operation data is analyzed according to five preset analysis policies, if the analysis result is abnormal operation, "1" is output, and if the analysis result is normal operation, "0" is output, and a final analysis value is obtained by calculation according to the respective weighted values.

The predictive maintenance module is also preset with an alarm threshold value and an early warning threshold value, the obtained analysis value is compared with the alarm threshold value and the early warning threshold value, if the analysis value is larger than the early warning threshold value, the alarm module carries out early warning, and if the analysis value is larger than the alarm threshold value, the alarm module carries out alarm.

Taking a generator as an example, acquiring operation parameters of the generator, taking the temperature of the generator as an example, analyzing the acquired operation parameters according to an upper limit rule, a lower limit rule, a trend rule, a deviation rule, a swing rule and an overflow rule respectively, setting the upper limit rule, the lower limit rule, the trend rule and the overflow rule as abnormal operation, and setting the deviation rule and the swing rule as normal operation, wherein the weight value of the upper limit rule and the lower limit rule is X1, the weight value of the trend rule is X2, the weight value of the deviation rule is X3, the weight value of the swing rule is X4, the weight value of the overflow rule is X5, and the analysis value X1+ X2+ X3+ X4+ X5 is 1, so that the analysis value X1+ X2+ X5 is obtained.

In this embodiment, after the same group of operation data is analyzed by using a plurality of different analysis strategies, and a final analysis value is calculated according to the weight value, the early warning or alarm is determined according to the analysis value.

The foregoing is merely an example of the present invention, and common general knowledge in the field of known specific structures and characteristics is not described herein in any greater extent than that known in the art at the filing date or prior to the priority date of the application, so that those skilled in the art can now appreciate that all of the above-described techniques in this field and have the ability to apply routine experimentation before this date can be combined with one or more of the present teachings to complete and implement the present invention, and that certain typical known structures or known methods do not pose any impediments to the implementation of the present invention by those skilled in the art. It should be noted that, for those skilled in the art, without departing from the structure of the present invention, several changes and modifications can be made, which should also be regarded as the protection scope of the present invention, and these will not affect the effect of the implementation of the present invention and the practicability of the patent. The scope of the claims of the present application shall be determined by the contents of the claims, and the description of the embodiments and the like in the specification shall be used to explain the contents of the claims.