CN117976774B

CN117976774B - Intelligent process control method and system for photovoltaic module production

Info

Publication number: CN117976774B
Application number: CN202410331603.3A
Authority: CN
Inventors: 刘亮; 李静宜; 林宁
Original assignee: Xuzhou Taiyi Optoelectronic Technology Co ltd
Current assignee: Xuzhou Taiyi Optoelectronic Technology Co ltd
Priority date: 2024-03-22
Filing date: 2024-03-22
Publication date: 2024-06-07
Anticipated expiration: 2044-03-22
Also published as: CN117976774A

Abstract

The application provides a process intelligent control method and a system for photovoltaic module production, which relate to the technical field of production control, and the method comprises the following steps: matching rated intervals of pressure, time, temperature, vacuum degree and pressing speed according to the model of the photovoltaic module laminating machine; the method comprises the steps of obtaining a model of a photovoltaic module, and backtracking rated intervals of pressure, time, temperature, vacuum degree and pressing speed to obtain a first lamination control parameter; when the number of the first lamination control parameters is not equal to 0, processing is carried out in the control abnormality analysis component to obtain lamination control abnormality coefficients; and when the anomaly coefficient is smaller than or equal to the anomaly coefficient threshold value, initializing and laminating control according to the first lamination control parameter. The application can solve the problems of lower quality, stability and efficiency of lamination production caused by lower accuracy and higher fluctuation of lamination control parameter setting, and can achieve the effect of improving the quality, stability and efficiency of lamination production.

Description

Intelligent process control method and system for photovoltaic module production

Technical Field

The application relates to the technical field of production control, in particular to a process intelligent control method and system for photovoltaic module production.

Background

The lamination process of the photovoltaic module is to combine materials such as front and back glass, EVA films, battery pieces and the like at high temperature and high pressure through certain process parameters to form a firm module structure, which is a key step in the manufacturing process of the photovoltaic module.

When the traditional photovoltaic module is subjected to lamination production, the module is subjected to lamination production control generally by depending on control parameters subjectively set by workers, and as the working time length and working experience of each worker are different, the lamination control parameters are uneven, the conditions of lower accuracy and instability exist, the automation and intelligent degree of the lamination production control are poor, the lamination quality of the photovoltaic module is poor, and the working efficiency is low.

In summary, the existing photovoltaic module lamination control method has the technical problems of lower quality, stability and efficiency of the photovoltaic module lamination production due to lower lamination control parameter setting accuracy and higher fluctuation, which results in lower automation control degree of the lamination production.

Disclosure of Invention

The application aims to provide a process intelligent control method and a process intelligent control system for photovoltaic module production, which are used for solving the technical problems of low quality, stability and efficiency of photovoltaic module lamination production caused by poor automation control degree of lamination production due to low lamination control parameter setting accuracy and high volatility of the traditional photovoltaic module lamination control method.

In view of the above problems, the application provides a process intelligent control method and a system for photovoltaic module production.

In a first aspect, the present application provides a process intelligent control method for producing a photovoltaic module, where the method is implemented by a process intelligent control system for producing a photovoltaic module, where the method is applied to a photovoltaic module laminator, and the photovoltaic module laminator includes a lamination cavity, a vacuum suction port, a cavity temperature controller, and a module presser, and includes: obtaining lamination basic information, wherein the lamination basic information comprises a model of a photovoltaic module laminating machine and a model of the photovoltaic module; matching a pressure rated interval, a time rated interval, a temperature rated interval, a vacuum rated interval and a pressing speed rated interval according to the model of the photovoltaic module laminating machine; obtaining the model of the photovoltaic module, and performing local historical backtracking on the pressure rated interval, the time rated interval, the temperature rated interval, the vacuum rated interval and the pressing speed rated interval to obtain a first lamination control parameter; when the number of the first lamination control parameters is not equal to 0, processing in a control abnormality analysis assembly according to the first lamination control parameters, the type of the photovoltaic assembly laminating machine and the type of the photovoltaic assembly to obtain lamination control abnormality coefficients, wherein the control abnormality analysis assembly is embedded in a control terminal of the photovoltaic assembly laminating machine; and initializing the vacuum suction port, the cavity temperature controller and the assembly presser according to the first lamination control parameter when the lamination control abnormal coefficient is smaller than or equal to an abnormal coefficient threshold value, and carrying out lamination control on the photovoltaic assembly in the lamination cavity.

In a second aspect, the present application further provides a process intelligent control system for producing a photovoltaic module, for executing a process intelligent control method for producing a photovoltaic module according to the first aspect, where the system includes a photovoltaic module laminator, the photovoltaic module laminator includes a lamination cavity, a vacuum suction port, a cavity temperature controller, and a module presser, and includes: the system comprises a laminated basic information obtaining module, a control module and a control module, wherein the laminated basic information obtaining module is used for obtaining laminated basic information, and the laminated basic information comprises a photovoltaic component laminating machine model and a photovoltaic component model; the rated interval matching module is used for matching a pressure rated interval, a time rated interval, a temperature rated interval, a vacuum degree rated interval and a pressing speed rated interval according to the type of the photovoltaic module laminating machine; the first lamination control parameter obtaining module is used for obtaining the model of the photovoltaic module, and carrying out local historical backtracking on the pressure rated interval, the time rated interval, the temperature rated interval, the vacuum rated interval and the lamination speed rated interval to obtain first lamination control parameters; the lamination control abnormal coefficient obtaining module is used for obtaining the lamination control abnormal coefficient when the number of the first lamination control parameters is not equal to 0, and processing the first lamination control parameters, the model of the photovoltaic module laminating machine and the model of the photovoltaic module at a control abnormal analysis module, wherein the control abnormal analysis module is embedded in a control terminal of the photovoltaic module laminating machine; and the lamination control module is used for initializing the vacuum suction port, the cavity temperature controller and the assembly presser according to the first lamination control parameter when the lamination control abnormal coefficient is smaller than or equal to an abnormal coefficient threshold value, and carrying out lamination control on the photovoltaic assembly in the lamination cavity.

One or more technical schemes provided by the application have at least the following technical effects or advantages:

1. Obtaining lamination basic information, wherein the lamination basic information comprises a model of a photovoltaic module laminating machine and a model of the photovoltaic module; matching a pressure rated interval, a time rated interval, a temperature rated interval, a vacuum rated interval and a pressing speed rated interval according to the model of the photovoltaic module laminating machine; obtaining the model of the photovoltaic module, and performing local historical backtracking on the pressure rated interval, the time rated interval, the temperature rated interval, the vacuum rated interval and the pressing speed rated interval to obtain a first lamination control parameter; when the number of the first lamination control parameters is not equal to 0, processing in a control abnormality analysis assembly according to the first lamination control parameters, the type of the photovoltaic assembly laminating machine and the type of the photovoltaic assembly to obtain lamination control abnormality coefficients, wherein the control abnormality analysis assembly is embedded in a control terminal of the photovoltaic assembly laminating machine; and initializing the vacuum suction port, the cavity temperature controller and the assembly presser according to the first lamination control parameter when the lamination control abnormal coefficient is smaller than or equal to the abnormal coefficient threshold value, and carrying out lamination control on the photovoltaic assembly in the lamination cavity. The accuracy and stability of lamination control parameter setting can be improved, the technical targets of automation and intellectualization of lamination control are improved, and the technical effects of improving the lamination production quality, stability and efficiency of the photovoltaic module are achieved.

2. The lamination control parameters are subjected to control anomaly analysis to obtain lamination control anomaly coefficients, and under the condition that the lamination control anomaly coefficients are smaller than or equal to a preset anomaly coefficient threshold value, lamination control is performed according to the lamination control parameters, so that the lamination control risk can be reduced, and the accuracy and stability of lamination production control are further improved.

The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent. It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the application or to delineate the scope of the application. Other features of the present application will become apparent from the description that follows.

Drawings

In order to more clearly illustrate the application or the technical solutions of the prior art, the following brief description will be given of the drawings used in the description of the embodiments or the prior art, it being obvious that the drawings in the description below are only exemplary and that other drawings can be obtained from the drawings provided without the inventive effort for a person skilled in the art.

Fig. 1 is a schematic flow chart of a process intelligent control method for photovoltaic module production.

Fig. 2 is a schematic flow chart of obtaining abnormal lamination control coefficients in the intelligent control method for the process of photovoltaic module production.

Fig. 3 is a schematic structural diagram of a process intelligent control system for photovoltaic module production according to the present application.

Reference numerals illustrate:

A lamination basic information obtaining module 11, a rated interval matching module 12, a first lamination control parameter obtaining module 13, a lamination control abnormal coefficient obtaining module 14, and a lamination control module 15.

Detailed Description

The application provides the intelligent control method and the intelligent control system for the process for producing the photovoltaic module, which solve the technical problems of low quality, stability and efficiency of the lamination production of the photovoltaic module caused by the poor automation control degree of the lamination production due to the low accuracy and the high fluctuation of the lamination control parameter setting of the traditional photovoltaic module lamination control method. The accuracy and stability of lamination control parameter setting can be improved, the technical targets of automation and intellectualization of lamination control are improved, and the technical effects of improving the lamination production quality, stability and efficiency of the photovoltaic module are achieved.

In the following, the technical solutions of the present application will be clearly and completely described with reference to the accompanying drawings, and it should be understood that the described embodiments are only some embodiments of the present application, but not all embodiments of the present application, and that the present application is not limited by the exemplary embodiments described herein. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application. It should be further noted that, for convenience of description, only some, but not all of the drawings related to the present application are shown.

Example 1

Referring to fig. 1, the application provides a process intelligent control method for photovoltaic module production, wherein the method is applied to a process intelligent control system for photovoltaic module production, the system comprises a photovoltaic module laminating machine, and the photovoltaic module laminating machine comprises a laminating cavity, a vacuum suction port, a cavity temperature controller and a module pressing device, and specifically comprises the following steps:

Step one: obtaining lamination basic information, wherein the lamination basic information comprises a model of a photovoltaic module laminating machine and a model of the photovoltaic module;

Specifically, the method provided by the application is used for optimizing the existing photovoltaic module laminating production process to achieve the purpose of improving the accuracy and stability of laminating control parameter setting, and the method is specifically implemented in an intelligent process control system for photovoltaic module production, wherein the system comprises a photovoltaic module laminating machine which is one of key equipment for manufacturing a photovoltaic module and mainly aims to press materials such as front glass, rear glass, EVA (ethylene-vinyl acetate) film, battery sheets and the like together under the conditions of high temperature and high pressure to form a complete photovoltaic module.

The photovoltaic module laminating machine comprises a laminating cavity, a vacuum suction port, a cavity temperature controller and a module pressing device, wherein the laminating cavity is one of key components in the photovoltaic module laminating machine and mainly has the function of providing a closed and controllable environment, so that all layers of materials of a photovoltaic module can be tightly pressed together at specific temperature and pressure; the vacuum suction port has the main function of tightly adsorbing a photovoltaic module or other materials to be processed on a working table surface of a laminating machine by generating negative pressure so as to ensure that the materials can keep stable positions in the laminating process and prevent the materials from shifting or sliding in the processing process; the main function of the cavity temperature controller is to precisely control the temperature inside the lamination cavity so as to ensure that the photovoltaic module can obtain the optimal process conditions in the lamination process; the module press is typically made of a high strength material and the primary function is to provide a uniform and sufficient pressure during lamination to ensure that the layers of material of the photovoltaic module are tightly bonded together.

Firstly, obtaining lamination basic information, wherein the lamination basic information comprises a photovoltaic component laminating machine model and a photovoltaic component model, and the photovoltaic component laminating machine model comprises information such as equipment type, equipment specification, equipment control parameters and the like; the photovoltaic module model comprises information such as module type, module size, module function and the like; wherein photovoltaic module laminator model and photovoltaic module model field technicians can set up according to actual conditions. By obtaining lamination basic information, support is provided for the next lamination control analysis of the photovoltaic module.

Step two: matching a pressure rated interval, a time rated interval, a temperature rated interval, a vacuum rated interval and a pressing speed rated interval according to the model of the photovoltaic module laminating machine;

Specifically, the lamination control parameters are obtained according to the type of the photovoltaic module laminating machine, wherein the lamination control parameters comprise pressure, time, temperature, vacuum degree and laminating speed, and further a rated interval corresponding to the lamination control parameters is obtained, the rated interval refers to an adjustment range of the lamination control parameters, the adjustment range comprises a pressure rated interval, a time rated interval, a temperature rated interval, a vacuum degree rated interval and a laminating speed rated interval, and the control parameter rated intervals of the photovoltaic module laminating machines of different types are different. The pressure is applied to the single battery piece, the rated interval of the pressure is about 10 to 50N/square centimeter, the battery piece is easy to crack when the pressure is too small, and the battery piece is damaged when the pressure is too large; the time refers to the residence time of the battery piece in the laminating machine, the rated time interval is generally 5 to 15 minutes, the EVA film is easy to be incompletely fused due to the too short time, and the battery piece is easy to be damaged due to the too long time; the temperature refers to the temperature of the battery piece and the EVA film, the rated temperature interval is usually 140-155 ℃, the EVA film cannot be completely fused due to the fact that the temperature is too low, and the battery piece is easy to generate chromatic aberration or fusion deformation due to the fact that the temperature is too high; the vacuum degree refers to the vacuum degree in the laminating machine, the rated interval of the vacuum degree is generally required to be smaller than 15 Pa, and the suction of the EVA film can influence the quality of the assembly due to the fact that the vacuum degree is too low; the lamination speed refers to the contact speed of the battery piece and the EVA film, the rated interval of the lamination speed is usually 0.05 to 0.15 meter per second, and bubbles are easily generated due to the fact that the lamination speed is too high.

The corresponding pressure rated interval, time rated interval, temperature rated interval, vacuum rated interval and pressing speed rated interval are obtained through matching according to the model of the photovoltaic module laminating machine, and support is provided for the next step of laminating control parameter analysis and obtaining of the first laminating control parameter.

Step three: obtaining the model of the photovoltaic module, and performing local historical backtracking on the pressure rated interval, the time rated interval, the temperature rated interval, the vacuum rated interval and the pressing speed rated interval to obtain a first lamination control parameter;

Specifically, according to the photovoltaic module model, performing local historical backtracking on the pressure rated section, the time rated section, the temperature rated section, the vacuum rated section and the pressing speed rated section, wherein the local historical backtracking refers to feature extraction on historical pressing control parameters corresponding to the photovoltaic module model by taking the pressure rated section, the time rated section, the temperature rated section, the vacuum rated section and the pressing speed rated section as constraints, obtaining feature value sets corresponding to a plurality of lamination control parameters, constructing a first lamination control parameter according to the plurality of historical feature value sets, and obtaining the first lamination control parameter, wherein the first lamination control parameter comprises the feature value sets of the plurality of lamination control parameters. By obtaining the first lamination control parameters, raw data support is provided for the next step of control anomaly analysis of the lamination control parameters, determining lamination control anomaly coefficients.

Step four: when the number of the first lamination control parameters is not equal to 0, processing in a control abnormality analysis assembly according to the first lamination control parameters, the type of the photovoltaic assembly laminating machine and the type of the photovoltaic assembly to obtain lamination control abnormality coefficients, wherein the control abnormality analysis assembly is embedded in a control terminal of the photovoltaic assembly laminating machine;

Specifically, whether the number of the control parameter characteristic values in the first lamination control parameter is 0 is judged, if the number of the control parameter characteristic values is not 0, control abnormality analysis is performed in a control abnormality analysis assembly according to the first lamination control parameter, the type of the photovoltaic assembly laminating machine and the type of the photovoltaic assembly, wherein the control abnormality analysis assembly is embedded in a control terminal of the photovoltaic assembly laminating machine, and a lamination control abnormality coefficient is determined according to an abnormality analysis result. The abnormal analysis of the first lamination control parameter is used for determining the lamination control abnormal coefficient, so that support is provided for judging the control abnormality of the first lamination control parameter, and the accuracy and reliability of the setting of the lamination control parameter are improved.

Step five: and initializing the vacuum suction port, the cavity temperature controller and the assembly presser according to the first lamination control parameter when the lamination control abnormal coefficient is smaller than or equal to an abnormal coefficient threshold value, and carrying out lamination control on the photovoltaic assembly in the lamination cavity.

Specifically, an abnormal coefficient threshold value is obtained, which can be set by a person skilled in the art according to the actual situation, wherein the higher the actual demand control accuracy is, the smaller the abnormal coefficient threshold value is. And then judging the abnormal lamination control coefficient according to the abnormal coefficient threshold, initializing the vacuum suction port, the cavity temperature controller and the component pressing device when the abnormal lamination control coefficient is smaller than or equal to the abnormal coefficient threshold, and carrying out lamination control on the photovoltaic component in the lamination cavity according to the first lamination control parameter.

The intelligent process control method for the production of the photovoltaic module is applied to an intelligent process control system for the production of the photovoltaic module, the system comprises a photovoltaic module laminating machine, and the photovoltaic module laminating machine comprises a laminating cavity, a vacuum suction port, a cavity temperature controller and a module pressing device, so that the technical problems of lower quality, stability and efficiency of the lamination production of the photovoltaic module caused by poor automation control degree of the lamination production due to lower accuracy and higher fluctuation of lamination control parameter setting in the traditional photovoltaic module lamination control method can be solved.

Firstly, obtaining lamination basic information, wherein the lamination basic information comprises a model of a photovoltaic module laminating machine and a model of the photovoltaic module; then, matching a pressure rated interval, a time rated interval, a temperature rated interval, a vacuum rated interval and a pressing speed rated interval according to the model of the photovoltaic module laminating machine; then, the model of the photovoltaic module is obtained, and local history backtracking is carried out on the pressure rated interval, the time rated interval, the temperature rated interval, the vacuum rated interval and the pressing speed rated interval to obtain a first lamination control parameter; then, when the number of the first lamination control parameters is not equal to 0, processing is performed on a control abnormality analysis component according to the first lamination control parameters, the type of the photovoltaic component laminating machine and the type of the photovoltaic component to obtain lamination control abnormality coefficients, wherein the control abnormality analysis component is embedded in a control terminal of the photovoltaic component laminating machine; and finally, initializing the vacuum suction port, the cavity temperature controller and the assembly presser according to the first lamination control parameter when the lamination control abnormal coefficient is smaller than or equal to an abnormal coefficient threshold value, and carrying out lamination control on the photovoltaic assembly in the lamination cavity. The accuracy and stability of lamination control parameter setting can be improved, the technical targets of automation and intellectualization of lamination control are improved, and the technical effects of improving the lamination production quality, stability and efficiency of the photovoltaic module are achieved.

Further, the third step of the present application includes:

according to the model of the photovoltaic module, performing local pressfitting log retrieval to obtain pressfitting log data;

And sorting the lamination log data by taking the pressure rated interval, the time rated interval, the temperature rated interval, the vacuum rated interval and the lamination speed rated interval as constraints to obtain the pressure record characteristic value set, the time record characteristic value set, the temperature record characteristic value set, the vacuum record characteristic value set and the lamination speed record characteristic value set, and adding the pressure record characteristic value set, the time record characteristic value set, the temperature record characteristic value set, the vacuum record characteristic value set and the lamination speed record characteristic value set into the first lamination control parameter.

Specifically, firstly, performing local press log search by taking the type of the photovoltaic module as a search condition, wherein the local search is to store a database of press logs of the photovoltaic module to obtain press log data, and the press log data comprises historical press control parameters, namely historical press control parameters, historical time control parameters, historical temperature control parameters, historical vacuum degree control parameters and historical press speed control parameters.

And sorting the lamination log data by taking the pressure rated interval, the time rated interval, the temperature rated interval, the vacuum rated interval and the lamination speed rated interval as constraints, wherein sorting refers to extracting historical lamination control data meeting the rated interval to obtain a pressure record characteristic value set meeting the pressure rated interval, a time record characteristic value set meeting the time rated interval, a temperature record characteristic value set meeting the temperature rated interval, a vacuum record characteristic value set meeting the vacuum rated interval and a lamination speed record characteristic value set meeting the lamination speed rated interval, and adding the pressure record characteristic value set, the time record characteristic value set, the temperature record characteristic value set, the vacuum record characteristic value set and the lamination speed record characteristic value set into a first lamination control parameter to obtain the first lamination control parameter.

The laminating log is retrieved by taking the type of the photovoltaic module as a constraint condition, laminating log data are extracted according to a laminating control rated interval of the photovoltaic module laminating machine, a first laminating control parameter is obtained, the accuracy of setting the first laminating control parameter can be improved, and therefore the analysis efficiency of the laminating control parameter is improved.

Further, as shown in fig. 2, the fourth step of the present application includes:

the first lamination control parameter comprises a pressure record characteristic value set, a time record characteristic value set, a temperature record characteristic value set, a vacuum degree record characteristic value set and a lamination speed record characteristic value set, wherein the pressure record characteristic value set, the time record characteristic value set, the temperature record characteristic value set, the vacuum degree record characteristic value set and the lamination speed record characteristic value set are in one-to-one correspondence;

Extracting a first pressure record characteristic value, a first time record characteristic value, a first temperature record characteristic value, a first vacuum record characteristic value and a first pressing speed record characteristic value according to the pressure record characteristic value set, the time record characteristic value set, the temperature record characteristic value set, the vacuum record characteristic value set and the pressing speed record characteristic value set;

processing the first pressure record characteristic value, the first time record characteristic value, the first temperature record characteristic value, the first vacuum degree record characteristic value and the first lamination speed record characteristic value through the control abnormality analysis component to obtain a first lamination control abnormality coefficient;

Specifically, the first lamination control parameter includes the pressure record feature value set, the time record feature value set, the temperature record feature value set, the vacuum record feature value set, and the lamination speed record feature value set, and the pressure record feature value set, the time record feature value set, the temperature record feature value set, the vacuum record feature value set, and the lamination speed record feature value set are in one-to-one correspondence.

And randomly extracting a first pressure record characteristic value from the pressure record characteristic value set, wherein the first pressure record characteristic value is any one of the pressure record characteristic value sets, randomly extracting a first time record characteristic value from the time record characteristic value set, randomly extracting a first temperature record characteristic value from the temperature record characteristic value set, randomly extracting a first vacuum record characteristic value from the vacuum record characteristic value set, randomly extracting a first lamination speed record characteristic value from the lamination speed record characteristic value set, and obtaining a first pressure record characteristic value, a first time record characteristic value, a first temperature record characteristic value, a first vacuum record characteristic value and a first lamination speed record characteristic value.

And further performing anomaly control analysis on the first pressure record characteristic value, the first time record characteristic value, the first temperature record characteristic value, the first vacuum degree record characteristic value and the first pressing speed record characteristic value through the control anomaly analysis component, and outputting a first lamination control anomaly coefficient. And then adding the first lamination control anomaly coefficient to a lamination control anomaly coefficient to obtain the lamination control anomaly coefficient, wherein the lamination control anomaly coefficient comprises a plurality of control anomaly coefficients.

Further, the application also comprises the following steps:

The first pressure record characteristic value, the first time record characteristic value and the first temperature record characteristic value are taken as control constraints, the model of the photovoltaic component laminating machine and the model of the photovoltaic component are taken as equipment constraints, and the abnormal probability of the battery piece is obtained through processing of the abnormal control analysis component;

Specifically, before the first lamination control anomaly coefficient is obtained, the first pressure record characteristic value, the first time record characteristic value and the first temperature record characteristic value are used as control constraints, the type of the photovoltaic component laminating machine and the type of the photovoltaic component are used as equipment constraints, anomaly analysis is performed through the control anomaly analysis component, and the anomaly probability of the battery piece is determined according to the anomaly analysis result.

Further, the application also comprises the following steps:

Taking the first pressure record characteristic value, the first time record characteristic value and the first temperature record characteristic value as control constraints, taking the model of the photovoltaic component laminating machine and the model of the photovoltaic component as equipment constraints, and collecting a battery piece pressing state record data set through the control abnormity analysis component in a networking way;

Configuring a battery piece abnormal state set, wherein the battery piece abnormal state set at least comprises a split battery piece, an unfused EVA film, a battery piece chromatic aberration, a fusion deformation of the battery piece and a breakage of the battery piece;

When the first battery piece pressing state record data of the battery piece pressing state record data set comprises one or more of rupture of the battery piece, unfused EVA film, chromatic aberration of the battery piece, melting deformation of the battery piece and damage of the battery piece, adding one to an abnormal count value of the battery piece, wherein the initial value of the abnormal count value of the battery piece is zero;

And when traversing the battery piece pressing state record data set, obtaining the proportion of the battery piece abnormal count value in the battery piece pressing state record data set, and setting the proportion as the battery piece abnormal probability.

The method for obtaining the abnormal probability of the battery piece comprises the following steps of firstly taking the first pressure record characteristic value, the first time record characteristic value and the first temperature record characteristic value as control constraints, taking the model of the photovoltaic component laminating machine and the model of the photovoltaic component as equipment constraints, and acquiring a battery piece lamination state record data set through networking of the control abnormal analysis component based on a big data technology, wherein the big data technology is a series of technologies and methods for excavating and showing values contained in massive data, and comprises the technical means of data planning, data acquisition, analysis excavation and the like, wherein the battery piece lamination state record data set comprises a plurality of historical battery piece lamination state record data.

And configuring a battery piece abnormal state set, wherein the battery piece abnormal state set at least comprises a battery piece split, an unfused EVA film, a battery piece chromatic aberration, a battery piece fusion deformation and a battery piece breakage, and the battery piece abnormal state can be increased according to actual requirements by a person skilled in the art. And judging first battery piece pressing state record data in the battery piece pressing state record data set according to the battery piece abnormal state set, wherein the first battery piece pressing state record data is any one record data in the battery piece pressing state record data set, and when the first battery piece pressing state record data in the battery piece pressing state record data set comprises one or more of rupture of the battery piece, unfused EVA film, battery piece chromatic aberration, melting deformation of the battery piece and breakage of the battery piece, adding one to the abnormal count value of the battery piece, wherein the initial value of the abnormal count value of the battery piece is zero.

And sequentially judging the battery piece pressing state record data set according to the battery piece abnormal state set until the traversal is completed, obtaining a battery piece abnormal count value after the traversal is completed, further calculating the ratio of the battery piece abnormal count value to the number of the battery piece pressing state record data in the battery piece pressing state record data set, setting the ratio as the battery piece abnormal probability, and obtaining the battery piece abnormal probability.

The first vacuum degree record characteristic value is used as constraint, the type of the photovoltaic component laminating machine and the type of the photovoltaic component are used as equipment constraint, and the control abnormality analysis component is used for processing to obtain EVA film air suction probability;

the first lamination speed recording characteristic value is used as constraint, the type of the photovoltaic component laminating machine and the type of the photovoltaic component are used as equipment constraint, and the control abnormality analysis component is used for processing to obtain the bubble occurrence probability;

when the abnormal probability of the battery piece is smaller than or equal to a first probability threshold, the suction probability of the EVA film is smaller than or equal to a second probability threshold, the occurrence probability of bubbles is smaller than or equal to a third probability threshold, and a first lamination control abnormal coefficient is equal to 0;

Otherwise, the first lamination control anomaly coefficient is equal to 1.

Specifically, the first vacuum degree record characteristic value is taken as constraint, the type of the photovoltaic component laminating machine and the type of the photovoltaic component are taken as equipment constraint, a battery piece lamination state record data set is collected through the control anomaly analysis component in a networking mode, and the EVA film suction probability is calculated and obtained by the method that the battery piece anomaly probability is the same; and taking the first lamination speed record characteristic value as constraint, taking the type of the photovoltaic component laminating machine and the type of the photovoltaic component as equipment constraint, collecting a battery piece lamination state record data set through the control anomaly analysis component in a networking manner, and calculating to obtain the bubble occurrence probability by using the same method for obtaining the battery piece anomaly probability.

The method comprises the steps of setting a first probability threshold, a second probability threshold and a third probability threshold respectively, wherein the first probability threshold is the maximum probability of allowing the battery piece to be abnormal, the second probability threshold is the maximum probability of allowing the EVA film to be in an air suction state, and the third probability threshold is the maximum probability of allowing air bubbles to occur, and all the first probability threshold, the second probability threshold and the third probability threshold can be set according to actual conditions by a person skilled in the art. And judging the abnormal probability of the battery piece, the suction probability of the EVA film and the bubble occurrence probability according to the first probability threshold, the second probability threshold and the third probability threshold respectively, setting the first lamination control abnormal coefficient to 0 when the abnormal probability of the battery piece is smaller than or equal to the first probability threshold, the suction probability of the EVA film is smaller than or equal to the second probability threshold, and the bubble occurrence probability is smaller than or equal to the third probability threshold, otherwise, setting the first lamination control abnormal coefficient to 1 when the abnormal probability of the battery piece is larger than the first probability threshold, or the suction probability of the EVA film is larger than the second probability threshold, or the bubble occurrence probability is larger than the third probability threshold.

The first lamination control anomaly coefficient is added to the lamination control anomaly coefficient.

Specifically, the first lamination control anomaly coefficient is added to the lamination control anomaly coefficient to obtain the lamination control anomaly coefficient, and the abnormal state of the lamination control parameter can be clearly and intuitively clarified by obtaining the lamination control anomaly coefficient, and support is provided for screening the lamination control parameter.

Further, the application also comprises the following steps:

when the number of the first lamination control parameters is equal to 0 or the lamination control abnormality coefficient is larger than the abnormality coefficient threshold, optimizing the first lamination control parameters according to the abnormal probability of the battery piece, the EVA film air suction probability and the bubble occurrence probability to obtain second lamination control parameters;

Specifically, when the number of the first lamination control parameters is equal to 0, or when the lamination control abnormality coefficient is greater than the abnormality coefficient threshold, optimizing the first lamination control parameters according to the cell abnormality probability, the EVA film air suction probability and the bubble occurrence probability, and obtaining a second lamination control parameter according to the optimizing result.

Further, the application also comprises the following steps:

Searching a lamination control parameter record data set in a networking way by taking the model of the photovoltaic module laminating machine and the model of the photovoltaic module as retrieval limits, wherein the lamination control parameter record data set is at least equal to 500 groups;

traversing the lamination control parameter record data set, and processing by the control abnormality analysis component to obtain an initial battery piece abnormality probability set, an initial EVA film inspiration probability set and an initial bubble occurrence probability set;

Traversing the initial battery piece abnormal probability set, comparing the initial EVA film inspiration probability set with the initial bubble occurrence probability set, and judging whether lamination control parameter record data meeting the first probability threshold, the second probability threshold and the third probability threshold exists or not;

if so, setting the output as the second lamination control parameter;

If not, traversing the initial battery piece abnormal probability set, the initial EVA film inspiration probability set and the initial bubble occurrence probability set by taking the battery piece abnormal probability, the EVA film inspiration probability and the bubble occurrence probability as references, and constructing an optimized particle swarm, wherein any particle of the optimized particle swarm stores a group of lamination control parameter record data, the initial battery piece abnormal probability is smaller than or equal to the battery piece abnormal probability, the initial EVA film inspiration probability is smaller than or equal to the EVA film inspiration probability, and the initial bubble occurrence probability is smaller than or equal to the bubble occurrence probability;

And carrying out optimizing analysis according to the optimized particle swarm to obtain the second lamination control parameter.

Specifically, the method for optimizing the first lamination control parameter according to the abnormal probability of the battery piece, the suction probability of the EVA film and the occurrence probability of the bubble, and obtaining the second lamination control parameter is as follows, firstly, the lamination control parameter record data set is searched in a networking mode by taking the model of the photovoltaic module laminating machine and the model of the photovoltaic module as retrieval limits based on a big data technology, wherein the lamination control parameter record data in the lamination control parameter record data set is greater than or equal to 500 groups, the specific number of the lamination control parameter record data can be set according to actual requirements, and the greater the number of the lamination control parameter record data is, the higher the optimizing accuracy of the lamination control parameter is.

And carrying out abnormal control analysis on the lamination control parameter record data set through the control abnormal analysis component to obtain an initial battery piece abnormal probability set, an initial EVA film inspiration probability set and an initial bubble occurrence probability set. And further judging the initial battery piece abnormal probability set, the initial EVA film inspiration probability set and the initial bubble occurrence probability set according to the first probability threshold, the second probability threshold and the third probability threshold respectively, and if the lamination control parameter record data meeting the first probability threshold, the second probability threshold and the third probability threshold are met, setting the lamination control parameter record data as a second lamination control parameter to obtain the second lamination control parameter.

If the first probability threshold is not met, the second probability threshold is met, and the lamination control parameter recording data of the third probability threshold is met, traversing the initial battery piece abnormal probability set, the initial EVA film inspiration probability set and the initial bubble occurrence probability set based on the battery piece abnormal probability, the EVA film inspiration probability and the bubble occurrence probability, and constructing an optimized particle swarm according to the comparison result, wherein the optimized particle swarm comprises a plurality of particles, and a group of lamination control parameter recording data is stored in each particle, wherein the initial battery piece abnormal probability of the lamination control parameter recording data in each particle is smaller than or equal to the battery piece abnormal probability, the initial EVA film inspiration probability is smaller than or equal to the EVA film inspiration probability, and the initial bubble occurrence probability is smaller than or equal to the bubble occurrence probability.

And finally, taking the optimized particle swarm as an optimizing space, and optimizing the lamination control parameter in the optimizing space to obtain a second lamination control parameter. The method has the advantages that the lamination control parameter record data set is obtained based on networking search, and the lamination control parameter record data smaller than the historical abnormal probability in the lamination control parameter record data set is selected to construct the optimized particle swarm, so that the accuracy and the rationality of setting the optimized particle swarm can be improved, and the accuracy and the efficiency of optimization of the lamination control parameters can be improved.

Further, the application also comprises the following steps:

constructing an fitness function based on the first probability threshold, the second probability threshold, and the third probability threshold:

；

Wherein, Characterization of the ith optimized particle,/>Characterization of initial cell anomaly probability for the ith optimized particle,/>Characterization of initial EVA film inspiration probability of the ith optimized particle,/>Characterization of the initial bubble occurrence probability of the ith optimized particle, when/>、/>、/>Less than or equal to one thousandth, set as one thousandth,/>Is constant,/>A first probability threshold value is characterized and,Characterizing a second probability threshold,/>Characterization of a third probability threshold,/>Characterizing fitness of the ith optimized particle;

traversing the optimized particle swarm to process according to the fitness function to obtain a fitness characteristic value set;

selecting a first solution set with a first preset proportion from the optimized particle swarm according to the fitness characteristic value set from large to small, and selecting a second solution set with a second preset proportion from the optimized particle swarm according to the fitness characteristic value set from small to large, wherein the second preset proportion is at least equal to two times of the first preset proportion;

taking the head solution set as an optimizing target, and carrying out advancing adjustment on the tail solution set to obtain an optimized particle swarm updating result;

Outputting the second lamination control parameter when the optimized particle swarm updating result has lamination control parameter record data meeting the first probability threshold, the second probability threshold and the third probability threshold;

Otherwise, repeating the optimizing.

Specifically, the method for obtaining the second lamination control parameter by optimizing the particle swarm includes the following steps of firstly, constructing an fitness function based on the first probability threshold, the second probability threshold and the third probability threshold, wherein the fitness function has the expression: ; in the function of the degree of adaptation, Characterizing an ith optimized particle, wherein the ith optimized particle is any one optimized particle in the optimized particle group; /(I)Representing the abnormal probability of the initial battery piece of the ith optimized particle; /(I)Characterizing the initial EVA film inspiration probability of the ith optimized particle; /(I)Characterizing the initial bubble occurrence probability of the ith optimized particle; when/>、/>、/>Setting the time less than or equal to one thousandth as one thousandth; /(I)Is a constant and can be set according to actual conditions; /(I)Characterizing a first probability threshold; /(I)Characterizing a second probability threshold; /(I)Characterizing a third probability threshold; /(I)The i-th optimized particle is characterized by the adaptability, and the higher the adaptability is, the better the quality of the optimized particle is characterized.

And sequentially carrying out fitness calculation on the optimized particles in the optimized particle swarm according to the fitness function to obtain a fitness characteristic value set. And further arranging the optimized particles in the optimized particle swarm from large to small according to the fitness based on the fitness characteristic value set to obtain an optimized particle sequence. And then selecting a first solution set with a first preset proportion from the optimized particle sequence according to the order of the fitness from large to small, and selecting a second solution set with a second preset proportion from the optimized particle sequence according to the order of the fitness from small to large, wherein the second preset proportion is more than or equal to two times of the first preset proportion, and the first preset proportion and the second preset proportion can be set according to actual conditions.

Then, taking the head solution set as an optimizing target, performing travelling adjustment on the tail solution set, for example: firstly, acquiring a preset adjustment step length, wherein the preset adjustment step length is the amplitude of each adjustment of lamination control parameters, and the preset adjustment step length can be set according to the attribute of the lamination control parameters, namely, the amplitude of each adjustment of the pressure control parameters, the temperature control parameters, the time control parameters, the vacuum degree control parameters and the lamination speed control parameters is different; then, taking the tail solution as a starting point, taking the head solution as a target point, and adjusting the pressure, temperature, time, vacuum degree, pressing speed and the like of the tail solution according to the preset adjusting step length, so that a new solution is generated in the process that the tail solution is close to the head solution, and the probability of obtaining a better solution is improved; and obtaining an updating result of the optimized particle swarm after the adjustment is completed.

Further judging the optimized particle swarm updating result according to the first probability threshold, the second probability threshold and the third probability threshold, and setting the lamination control parameter record data as a second lamination control parameter when the optimized particle swarm updating result has lamination control parameter record data meeting the first probability threshold, the second probability threshold and the third probability threshold; and if the updating result of the optimized particle swarm does not have lamination control parameter record data meeting the first probability threshold, the second probability threshold and the third probability threshold, repeating the optimizing until the lamination control parameter record data meeting the first probability threshold, the second probability threshold and the third probability threshold is obtained, and stopping optimizing.

By optimizing the optimized particle swarm by utilizing an optimization algorithm, the global searching capability of the algorithm is strong, so that the situation of sinking into a local optimal state can be avoided, and the accuracy and the rationality of obtaining an optimizing result are improved.

And initializing the vacuum suction port, the cavity temperature controller and the assembly presser according to the second lamination control parameter, and laminating the photovoltaic assembly in the lamination cavity.

Specifically, first, the vacuum suction port, the cavity temperature controller and the component presser are initialized, and lamination control is performed on the photovoltaic component in the lamination cavity according to the second lamination control parameter.

In summary, the process intelligent control method for photovoltaic module production provided by the application has the following technical effects:

1. the lamination control parameters are optimized by constructing the optimized particle swarm, so that the optimal second lamination control parameters are obtained to carry out lamination control on the photovoltaic module, the accuracy and stability of the setting of the lamination control parameters can be improved, the technical targets of improving the automation and the intellectualization of the lamination control are realized, and the technical effects of improving the lamination production quality, the stability and the efficiency of the photovoltaic module are achieved.

2. The method has the advantages that the lamination control parameter record data set is obtained based on networking search, and the lamination control parameter record data smaller than the historical abnormal probability in the lamination control parameter record data set is selected to construct the optimized particle swarm, so that the accuracy and the rationality of setting the optimized particle swarm can be improved, and the accuracy and the efficiency of optimization of the lamination control parameters can be improved.

3. By optimizing the optimized particle swarm by utilizing an optimization algorithm, the global searching capability of the algorithm is strong, so that the situation of sinking into a local optimal state can be avoided, and the accuracy and the rationality of obtaining an optimizing result are improved.

Example two

Based on the same inventive concept as the process intelligent control method for photovoltaic module production in the foregoing embodiment, the present application further provides a process intelligent control system for photovoltaic module production, referring to fig. 3, the system includes:

A laminated base information obtaining module 11, wherein the laminated base information obtaining module 11 is used for obtaining laminated base information, and the laminated base information comprises a photovoltaic component laminating machine model and a photovoltaic component model;

The rated interval matching module 12 is used for matching a pressure rated interval, a time rated interval, a temperature rated interval, a vacuum rated interval and a pressing speed rated interval according to the type of the photovoltaic module laminating machine;

The first lamination control parameter obtaining module 13 is configured to obtain the type of the photovoltaic module, and perform local historical backtracking on the pressure rated interval, the time rated interval, the temperature rated interval, the vacuum rated interval and the lamination speed rated interval to obtain a first lamination control parameter;

The lamination control abnormal coefficient obtaining module 14 is configured to obtain a lamination control abnormal coefficient when the number of the first lamination control parameters is not equal to 0, and the lamination control abnormal coefficient is obtained by processing a control abnormal analysis component according to the first lamination control parameters, the model of the photovoltaic component laminator and the model of the photovoltaic component laminator, wherein the control abnormal analysis component is embedded in a control terminal of the photovoltaic component laminator;

And the lamination control module 15 is used for initializing the vacuum suction port, the cavity temperature controller and the assembly presser according to the first lamination control parameter when the lamination control abnormal coefficient is smaller than or equal to an abnormal coefficient threshold value, and carrying out lamination control on the photovoltaic assembly in the lamination cavity.

Further, the first lamination control parameter obtaining module 13 in the system is further configured to:

Further, the lamination control anomaly coefficient obtaining module 14 in the system is also configured to:

Otherwise, the first lamination control anomaly coefficient is equal to 1.

if so, setting the output as the second lamination control parameter;

；

Wherein, Characterization of the ith optimized particle,/>Characterization of initial cell anomaly probability for the ith optimized particle,/>Characterization of initial EVA film inspiration probability of the ith optimized particle,/>Characterization of the initial bubble occurrence probability of the ith optimized particle, when/>、/>、/>Less than or equal to one thousandth, set as one thousandth,/>Is constant,/>A first probability threshold value is characterized and,Characterizing a second probability threshold,/>Characterization of a third probability threshold,/>Characterizing fitness of the ith optimized particle; /(I)

Otherwise, repeating the optimizing.

In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the difference from other embodiments, so that a process intelligent control method and a specific example for producing a photovoltaic module in the first embodiment are also applicable to a process intelligent control system for producing a photovoltaic module in the first embodiment, and by the foregoing detailed description of a process intelligent control method for producing a photovoltaic module, those skilled in the art can clearly know that a process intelligent control system for producing a photovoltaic module in the first embodiment is not described in detail herein for brevity of the specification. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.

The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the present application and the equivalent techniques thereof, the present application is also intended to include such modifications and variations.

Claims

1. The intelligent process control method for the production of the photovoltaic module is characterized by being applied to a photovoltaic module laminating machine, wherein the photovoltaic module laminating machine comprises a laminating cavity, a vacuum suction port, a cavity temperature controller and a module pressing device, and comprises the following steps:

Obtaining lamination basic information, wherein the lamination basic information comprises a model of a photovoltaic module laminating machine and a model of the photovoltaic module;

matching a pressure rated interval, a time rated interval, a temperature rated interval, a vacuum rated interval and a pressing speed rated interval according to the model of the photovoltaic module laminating machine;

Obtaining the model of the photovoltaic module, and performing local historical backtracking on the pressure rated interval, the time rated interval, the temperature rated interval, the vacuum rated interval and the pressing speed rated interval to obtain a first lamination control parameter;

When the number of the first lamination control parameters is not equal to 0, processing in a control abnormality analysis assembly according to the first lamination control parameters, the type of the photovoltaic assembly laminating machine and the type of the photovoltaic assembly to obtain lamination control abnormality coefficients, wherein the control abnormality analysis assembly is embedded in a control terminal of the photovoltaic assembly laminating machine;

when the abnormal coefficient of lamination control is smaller than or equal to an abnormal coefficient threshold value, initializing the vacuum suction port, the cavity temperature controller and the assembly presser according to the first lamination control parameter, and carrying out lamination control on the photovoltaic assembly in the lamination cavity;

When the number of the first lamination control parameters is not equal to 0, processing is performed on the control abnormality analysis component according to the first lamination control parameters, the type of the photovoltaic component laminating machine and the type of the photovoltaic component to obtain lamination control abnormality coefficients, wherein the control abnormality analysis component is embedded in a control terminal of the photovoltaic component laminating machine, and the method comprises the following steps:

adding the first lamination control anomaly coefficient to the lamination control anomaly coefficient;

Processing, by the control anomaly analysis component, the first pressure record feature value, the first time record feature value, the first temperature record feature value, the first vacuum degree record feature value, and the first lamination speed record feature value to obtain a first lamination control anomaly coefficient, including:

Otherwise, the first lamination control anomaly coefficient is equal to 1.

2. The method of claim 1, wherein obtaining the photovoltaic module model, performing local historical backtracking on the pressure rating interval, the time rating interval, the temperature rating interval, the vacuum rating interval, and the lamination speed rating interval, obtaining a first lamination control parameter, comprising:

3. The method of claim 1, wherein processing by the control anomaly analysis component with the first pressure record feature value, the first time record feature value, the first temperature record feature value as control constraints, and the photovoltaic module laminator model and the photovoltaic module model as device constraints, comprises:

4. The method as recited in claim 1, further comprising:

5. The method of claim 4, wherein optimizing the first lamination control parameter based on the cell anomaly probability, the EVA film gettering probability, and the bubble occurrence probability, to obtain a second lamination control parameter, comprises:

if so, setting the output as the second lamination control parameter;

6. The method of claim 5, wherein performing a optimizing analysis based on the optimized particle swarm to obtain the second lamination control parameter comprises:

；

Wherein, Characterization of the ith optimized particle,/>Characterization of initial cell anomaly probability for the ith optimized particle,/>Characterization of initial EVA film inspiration probability of the ith optimized particle,/>Characterization of the initial bubble occurrence probability of the ith optimized particle, when/>、/>、/>Less than or equal to one thousandth, set as one thousandth,/>Is constant,/>Characterization of the first probability threshold,/>Characterizing a second probability threshold,/>Characterization of a third probability threshold,/>Characterizing fitness of the ith optimized particle;

Otherwise, repeating the optimizing.

7. A process intelligence control system for photovoltaic module production, characterized by steps for implementing the method of any of claims 1 to 6, the system comprising a photovoltaic module laminator comprising a lamination chamber, a vacuum suction, a chamber temperature controller and a module press, comprising:

the system comprises a laminated basic information obtaining module, a control module and a control module, wherein the laminated basic information obtaining module is used for obtaining laminated basic information, and the laminated basic information comprises a photovoltaic component laminating machine model and a photovoltaic component model;

the rated interval matching module is used for matching a pressure rated interval, a time rated interval, a temperature rated interval, a vacuum degree rated interval and a pressing speed rated interval according to the type of the photovoltaic module laminating machine;

The first lamination control parameter obtaining module is used for obtaining the model of the photovoltaic module, and carrying out local historical backtracking on the pressure rated interval, the time rated interval, the temperature rated interval, the vacuum rated interval and the lamination speed rated interval to obtain first lamination control parameters;

The lamination control abnormal coefficient obtaining module is used for obtaining the lamination control abnormal coefficient when the number of the first lamination control parameters is not equal to 0, and processing the first lamination control parameters, the model of the photovoltaic module laminating machine and the model of the photovoltaic module at a control abnormal analysis module, wherein the control abnormal analysis module is embedded in a control terminal of the photovoltaic module laminating machine;

And the lamination control module is used for initializing the vacuum suction port, the cavity temperature controller and the assembly presser according to the first lamination control parameter when the lamination control abnormal coefficient is smaller than or equal to an abnormal coefficient threshold value, and carrying out lamination control on the photovoltaic assembly in the lamination cavity.