An EVA foaming production whole-process multi-process collaborative control system

Abstract

The application discloses a kind of EVA foaming production whole-process multi-process collaborative control system, it is related to collaborative control technical field, the present application is by collecting the state parameters of each process in EVA foaming production and production order data and processing, after processing is completed, the state parameters after processing are analyzed by data analysis mode, obtain the state parameters after analysis;After analysis is completed, based on the state parameters after analysis and the production order data after processing set production control constraint, and construct production control model;After construction is completed, based on time synchronization mode, the production control model of construction is controlled in coordination, and constructs collaborative control model, finally, the state parameters of each process in EVA foaming production and production order data are collected in real time, and based on the state parameters of each process in EVA foaming production and production order data in collaborative control model construction are controlled scheduling, improve the accuracy of multi-process collaborative control.

Description

Technical Field

[0001] This invention relates to the field of collaborative control technology, specifically to a multi-process collaborative control system for the entire EVA foaming production process. Background Technology

[0002] Currently, EVA foam production companies operate under neither a single, continuous nor a discrete model. Their products have long production cycles, are diverse in type, and the production demands from different clients vary significantly, with highly complex manufacturing processes. EVA foam production typically involves various types of equipment, and combinations of different equipment can constitute part of the product's production process. However, precisely because of this diversity in production processes, the management and control of EVA foam production is becoming increasingly difficult, lacking intelligent and collaborative control systems.

[0003] Existing technology, such as the invention patent application with publication number CN121613846A, discloses a multi-process, multi-objective collaborative optimization control method and device for a silk production line. The method includes: acquiring process parameters, outlet moisture process values, and outlet moisture content data for different processes during silk production; constructing a moisture chain dataset for the silk production line, wherein the process flow includes main processing processes and auxiliary processes; preprocessing the process parameters, outlet moisture process values, and outlet moisture content data to obtain the moisture chain dataset for the silk production line; and based on the dataset, constructing moisture prediction models for the main processing processes and moisture dissipation models for the auxiliary processes to form a whole-line moisture chain prediction model. The beneficial effect is that by connecting the prediction models for the four main processes—loosening and rehydration, leaf moistening and feeding, silk drying, and blending and flavoring—with the moisture dissipation models for auxiliary processes such as premixing and leaf storage, the method accurately describes the transfer and change process of moisture throughout the entire production line.

[0004] As can be seen from the above solutions, current production collaborative control methods are mainly based on product process parameters for control and optimization, ignoring the synchronization of production orders and processes, which has certain limitations. Summary of the Invention

[0005] The purpose of this invention is to provide a multi-process collaborative control system for the entire EVA foaming production process, which solves the problems existing in the background technology.

[0006] To solve the above-mentioned technical problems, the present invention adopts the following technical solution: The present invention provides a multi-process collaborative control system for the entire EVA foaming production process, specifically including the following steps: S1. Collect historical status parameters and historical production order data of each process in EVA foaming production, and process the collected historical status parameters and historical production order data of each process through data processing methods to obtain the processed historical status parameters and historical production order data. S2. Analyze the processed historical state parameters using data analysis methods to obtain the analyzed historical state parameters; S3. Based on the analyzed historical state parameters and processed historical production order data, set production control constraints and construct a production control model based on the set production control constraints; S4. Based on time synchronization, perform collaborative control on the constructed production control model and construct a collaborative control model; S5. Real-time collection of status parameters and production order data for each process in EVA foaming production, and control and schedule the status parameters and production order data for each process in EVA foaming production based on the constructed collaborative control model.

[0007] Preferably, the process of collecting historical status parameters and historical production order data for each process in EVA foaming production, and processing the collected historical status parameters and historical production order data to obtain the processed historical status parameters and historical production order data includes the following steps: The historical status parameters of each process include: control command data for each process and production status parameters for each process; The production status parameters for each process include: temperature data, pressure data, time data, and VA content data; The historical production order data includes: order number, order start time, order end time, quantity required for the order, and order priority; S11. The historical status parameters of each process collected are processed by data processing methods to obtain the processed historical status parameters; A sample set was constructed based on historical state parameters collected from each process in the EVA foaming production. ,in, Represents the sample set, This represents the production status parameters in the first process of EVA foam production. This represents the control command data for the first process in EVA foam production. This represents the production status parameter at the nth process in EVA foaming production. This represents the control instruction data for the nth process in EVA foaming production. Traverse the historical state parameters of each process in the sample set, locate the missing data, and calculate the mean of the historical state parameters of the two adjacent groups of missing data by means of imputation. Use the calculated mean of historical state parameters as the imputation value of the missing data. The processed historical status parameters are obtained by summarizing and supplementing the historical status parameters of each process in the sample set. S12. The historical production order data collected from each process is processed using data processing methods to obtain the processed historical production order data.

[0008] Preferably, the step of processing the historical production order data collected from each process to obtain the processed historical production order data includes the following steps: The historical production order data collected for each process was filtered using Bloom filtering. Create an array of length m, and select... Each hash function iterates through each set of data in the historical production order data for each process and stores the results in an array; During the traversal using the hash function, if two sets of data have the same traversal result, each data in these two sets is compared. When the comparison results are consistent, the two sets of data are set to be the same data, and the software requirement data that arrives after the software requirement time is deleted. After the traversal is complete, the historical production order data for each process stored in the array during the traversal is summarized to obtain the processed historical production order data.

[0009] Preferably, the step of analyzing the processed historical state parameters through data analysis to obtain the analyzed historical state parameters includes the following steps: S21. Initialize the processed historical state parameters and construct the dataset. ; Select the processed historical state parameters of group C in the dataset as the initial data center. Set each Data center is a data category that represents a type of processed historical state parameters; in, Represents a collection of data centers. This represents the Cth data center; S22. Based on the processed historical state parameters in the dataset. Based on the distance formula, calculate the post-treatment results for each group. Historical state parameters Distance to data center C; The distance formula is as follows: ; in, Represents the processed historical state parameters To data center The distance is calculated and then divided into groups with the smallest distance. In the data categories corresponding to the data centers, add one group at a time until all data clustering is completed, and then use the results of this classification as the input for step S23. S23. After all data has been classified, update the data center for each data category based on the mean calculation method. S24. Repeat steps S22-S23 until the data in the data center and data category no longer changes. Output the data category, the amount of data in each category, the data center, and the historical state parameters after clustering. S25. Determine the distribution of historical state parameters based on data categories, data volume of each category, data centers, and historical state parameters after clustering, and determine the failure rate based on the distribution of state parameters. Collect the range of qualified parameters for EVA foaming production, and compare the collected range of qualified parameters with the clustered historical state parameters to filter out unqualified historical state parameters. The failure rate is calculated based on the filtered-out unqualified historical status parameters; Failure rate = Number of unqualified historical status parameters / Data volume of each category; S26. Summarize the clustered historical state parameters and failure rates to obtain the analyzed historical state parameters.

[0010] Preferably, the step of setting production control constraints based on the analyzed historical state parameters and processed historical production order data, and constructing a production control model based on the set production control constraints, includes the following steps: S31. Set production control constraints based on the analyzed historical status parameters and processed historical production order data; S32. Construct different production control models based on the set production control constraints.

[0011] Preferably, the step of setting production control constraints based on the analyzed historical state parameters and processed historical production order data includes the following steps: Setting production process decisions, The formulas for production process decision variables are shown below: ; in, This indicates whether the i-th order has gone through the j-th process. =1 indicates that the i-th order has gone through the j-th process. =0 indicates that the i-th order does not go through the j-th process; Production order constraints: ; in, Take a positive integer, representing i orders in the queue. This represents the maximum number of queue slots that can be filled. number Orders are being counted and queued. Process product production volume constraints: ; in, This represents the production quantity of the product in the j-th process of the i-th order. These represent the minimum and maximum production quantities, respectively. Multi-process production capacity constraints: ; in, This represents the pass rate of the j-th process in the i-th order. This represents the hourly production volume of the j-th process in the i-th order. This represents the usage time of the equipment corresponding to the j-th process. Indicates the order quantity; Capacity reservation constraints: ; in, This represents the reserve quantity for the equipment corresponding to the j-th process. This represents the reserved quantity of the equipment corresponding to the i-th order.

[0012] Preferably, the collaborative control of the constructed production control model based on time synchronization and the construction of the collaborative control model include the following steps: S41. Construct a time synchronization model based on the historical state parameters of each process in the EVA foaming production process. S42. Based on the time synchronization model, the constructed production control model is used for collaborative control.

[0013] Preferably, the collaborative control of the constructed production control model based on the time synchronization model includes the following steps: A production control chart is set based on the analyzed historical status parameters, processed historical production order data, time synchronization model, and production control model. ; in, This represents a production control chart. This represents the set of production nodes, obtained from processed historical production order data and analyzed historical status parameters. The set of edges representing the connections between production processes is obtained from the production control model. This represents the synchronization constraints of production nodes, obtained from the time synchronization model; The production control chart is trained and inferred using a graph convolutional neural network, and a collaborative control model is constructed based on the training and inference results. The collaborative control model is defined as a combination of a graph convolutional neural network and a multilayer perceptron. The graph convolutional neural network consists of 5 graph convolutional layers, 5 graph pooling layers and 1 fully connected layer, with the graph convolutional layers and graph pooling layers nested together. The established production control chart is input into the graph convolutional neural network, and the graph convolutional layer extracts the production control chart through message passing and state update processes. Calculate the neural transmission information between each pair of nodes and their neighboring nodes, and aggregate the features of the neighboring nodes and the node itself through a weighted summation method via message passing; After aggregation is complete, the aggregation result is processed by setting an update function through the state update process to generate new features for the current node; The new features of the aggregated nodes are input into the graph pooling layer, which then transforms the production control graph extracted by the graph convolutional layer into a feature vector through mean calculation. The processing results of five nested graph convolutional layers and graph pooling layers are summarized, and the feature vectors of the five layers are concatenated through a fully connected layer to obtain the trained collaborative control features. The trained collaborative control features are input into a multilayer perceptron. The multilayer perceptron then fuses and reduces the dimensionality of the trained collaborative control features, and outputs the collaborative control quantity corresponding to the production control model.

[0014] Preferably, the real-time acquisition of status parameters and production order data of each process in EVA foaming production, and the control and scheduling of status parameters and production order data of each process in EVA foaming production based on the constructed collaborative control model, includes the following steps: The status parameters and production order data of each process in the EVA foaming production are collected in real time and input into the constructed collaborative control model; After receiving real-time collected status parameters and production order data, the collaborative control model will generate corresponding collaborative control quantities based on different production control models. The administrator controls and schedules the status parameters and production order data of each process in EVA foaming production based on the generated corresponding collaborative control variables.

[0015] This invention provides a multi-process collaborative control system for the entire EVA foaming production process, which further includes: a data acquisition module, a data processing module, a data analysis module, a production control constraint module, a production control module, and a control scheduling module; The data acquisition module is used to collect status parameters and production order data for each process in EVA foaming production. The data processing module is used to process the collected status parameters and production order data to obtain the processed status parameters and production order data. The data analysis module is used to analyze the processed state parameters to obtain the analyzed state parameters; The production control constraint module is used to set production control constraints based on the analyzed status parameters and processed production order data. The production control module is used to construct a production control model based on the set production control constraints. The control and scheduling module is used to control and schedule the status parameters and production order data of each process in EVA foaming production according to the constructed production control model.

[0016] The beneficial effects of this invention are as follows: (1) This invention collects and processes the state parameters and production order data of each process in EVA foaming production. After processing, the state parameters are analyzed by data analysis to obtain the analyzed state parameters. After analysis, production control constraints are set based on the analyzed state parameters and the processed production order data, and a production control model is constructed. After construction, the constructed production control model is coordinated and controlled based on time synchronization, and a collaborative control model is constructed. Finally, the state parameters and production order data of each process in EVA foaming production are collected in real time, and the state parameters and production order data of each process in EVA foaming production are controlled and scheduled based on the constructed collaborative control model, which improves the accuracy of multi-process collaborative control. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of the multi-process collaborative control system for the entire EVA foaming production process of the present invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] In a specific embodiment of the present invention, Reference Figure 1 As shown, this invention provides a multi-process collaborative control system for the entire EVA foaming production process, including the following steps: S1. Collect historical status parameters and historical production order data of each process in EVA foaming production, and process the collected historical status parameters and historical production order data of each process through data processing methods to obtain the processed historical status parameters and historical production order data. S2. Analyze the processed historical state parameters using data analysis methods to obtain the analyzed historical state parameters; S3. Based on the analyzed historical state parameters and processed historical production order data, set production control constraints and construct a production control model based on the set production control constraints; S4. Based on time synchronization, perform collaborative control on the constructed production control model and construct a collaborative control model; S5. Real-time collection of status parameters and production order data of each process in EVA foaming production, and control and schedule the status parameters and production order data of each process in EVA foaming production based on the constructed collaborative control model; Furthermore, referring to Figure 1 As shown, historical status parameters and historical production order data for each process in EVA foaming production are collected. The collected historical status parameters and historical production order data are then processed using data processing methods to obtain the processed historical status parameters and historical production order data. The process includes the following steps: The historical status parameters of each process include: control command data for each process and production status parameters for each process; The production status parameters for each process include: temperature data, pressure data, time data, and VA content data; The historical production order data includes: order number, order start time, order end time, quantity required for the order, and order priority; S11. The historical status parameters of each process collected are processed by data processing methods to obtain the processed historical status parameters; A sample set was constructed based on historical state parameters collected from each process in the EVA foaming production. ,in, Represents the sample set, This represents the production status parameters in the first process of EVA foam production. This represents the control command data for the first process in EVA foam production. This represents the production status parameter at the nth process in EVA foaming production. This represents the control instruction data for the nth process in EVA foaming production. Furthermore, the historical state parameters of each process in the sample set are traversed to locate the missing data. The mean of the historical state parameters of the two adjacent groups of missing data is calculated by the mean imputation method, and the calculated mean of the historical state parameters is used as the imputation value of the missing data. Furthermore, the historical state parameters of each process in the completed sample set are summarized to obtain the processed historical state parameters. S12. The historical production order data collected from each process is processed using data processing methods to obtain the processed historical production order data; The historical production order data collected for each process was filtered using Bloom filtering. Create an array of length m, and select... Each hash function iterates through each set of data in the historical production order data for each process and stores the results in an array; During the traversal using the hash function, if two sets of data have the same traversal result, each data in these two sets is compared. When the comparison results are consistent, the two sets of data are set to be the same data, and the software requirement data that arrives after the software requirement time is deleted. After the traversal is complete, the historical production order data for each process stored in the array during the traversal is summarized to obtain the processed historical production order data. Furthermore, referring to Figure 1 As shown, the processed historical state parameters are analyzed using data analysis methods. The steps to obtain the analyzed historical state parameters are as follows: S21. Initialize the processed historical state parameters and construct the dataset. ; Select the processed historical state parameters of group C in the dataset as the initial data center. Set each Data center is a data category that represents a type of processed historical state parameters; in, Represents a collection of data centers. This represents the Cth data center; S22. Based on the processed historical state parameters in the dataset. Based on the distance formula, calculate the post-treatment results for each group. Historical state parameters Distance to data center C; The distance formula is as follows: ; in, Represents the processed historical state parameters To data center The distance is calculated and assigned to the group with the smallest distance. In the data category corresponding to the data center, add one group at a time until all data clustering is completed, and then use the result of this classification as the input for step S23; S23. After all data has been classified, update the data center for each data category based on the mean calculation method. Furthermore, based on the updated data center for each data category, the clustered data in each data category is recalculated; S24. Repeat steps S22-S23 until the data in the data center and data category no longer changes. Output the data category, the amount of data in each category, the data center, and the historical state parameters after clustering. S25. Determine the distribution of historical state parameters based on data categories, data volume of each category, data centers, and historical state parameters after clustering, and determine the failure rate based on the distribution of state parameters. Collect the range of qualified parameters for EVA foaming production, and compare the collected range of qualified parameters with the clustered historical state parameters to filter out unqualified historical state parameters. Furthermore, the failure rate is calculated based on the filtered-out unqualified historical state parameters; Failure rate = Number of unqualified historical status parameters / Data volume of each category; S26. Summarize the clustered historical state parameters and failure rates to obtain the analyzed historical state parameters; Furthermore, referring to Figure 1 As shown, the process of setting production control constraints based on the analyzed historical state parameters and processed historical production order data, and constructing a production control model based on these constraints, includes the following steps: S31. Set production control constraints based on the analyzed historical status parameters and processed historical production order data; Setting production process decisions, The formulas for production process decision variables are shown below: ; in, This indicates whether the i-th order has gone through the j-th process. =1 indicates that the i-th order has gone through the j-th process. =0 indicates that the i-th order does not go through the j-th process; Production order constraints: ; in, Take a positive integer, representing i orders in the queue. This represents the maximum number of queue slots that can be filled. A number of orders are queued; Process product production volume constraints: ; in, This represents the production quantity of the product in the j-th process of the i-th order. These represent the minimum and maximum production quantities, respectively. Multi-process production capacity constraints: ; in, This represents the pass rate of the j-th process in the i-th order. This represents the hourly production volume of the j-th process in the i-th order. This represents the usage time of the equipment corresponding to the j-th process. Indicates the order quantity; Capacity reservation constraints: ; in, This represents the reserve quantity for the equipment corresponding to the j-th process. This represents the reserved quantity of the equipment corresponding to the i-th order; S32. Construct different production control models based on the set production control constraints; Production capacity maximization model; ; in, This represents a production capacity maximization model. Indicates the number of steps in the process; The production cost minimization model is shown below: ; in, This represents a production cost minimization model. This represents the labor cost of the equipment corresponding to the j-th process. Indicates material cost; Combinatorial optimization model; ; in, This represents a combinatorial optimization model. These represent the coefficient weights of the production capacity maximization model and the production cost minimization model, respectively. Furthermore, referring to Figure 1As shown, the collaborative control of the constructed production control model based on time synchronization includes the following steps: S41. Construct a time synchronization model based on the historical state parameters of each process in the EVA foaming production process. The time synchronization model is shown below: ; in, This represents the time synchronization model for the j-th process. Indicates the reference time base. Indicates the j-th worker Time offset of sequence, This represents the clock drift coefficient for the j-th process. and These represent the timestamps of the current moment and the previous moment, respectively. S42. Perform collaborative control of the constructed production control model based on the time synchronization model; A production control chart is set based on the analyzed historical status parameters, processed historical production order data, time synchronization model, and production control model. ; in, This represents a production control chart. This represents the set of production nodes, obtained from processed historical production order data and analyzed historical status parameters. The set of edges representing the connections between production processes is obtained from the production control model. This represents the synchronization constraints of production nodes, obtained from the time synchronization model; Furthermore, a graph convolutional neural network is used to train and infer the set production control chart, and a collaborative control model is constructed based on the training and inference results; The collaborative control model is defined as a combination of a graph convolutional neural network and a multilayer perceptron. The graph convolutional neural network consists of 5 graph convolutional layers, 5 graph pooling layers and 1 fully connected layer, with the graph convolutional layers and graph pooling layers nested together. The established production control chart is input into the graph convolutional neural network, and the graph convolutional layer extracts the production control chart through message passing and state update processes. Calculate the neural transmission information between each pair of nodes and their neighboring nodes, and aggregate the features of the neighboring nodes and the node itself through a weighted summation method via message passing; After aggregation is complete, the aggregation result is processed by setting an update function through the state update process to generate new features for the current node; Furthermore, the new features of the aggregated nodes are input into the graph pooling layer, which then transforms the production control graph extracted by the graph convolutional layer into a feature vector through mean calculation. Furthermore, the processing results of five nested graph convolutional and graph pooling layers are summarized, and the five feature vectors are concatenated through a fully connected layer to obtain the trained collaborative control features. Furthermore, the trained collaborative control features are input into a multilayer perceptron, which then fuses and reduces the dimensionality of the trained collaborative control features to output the collaborative control quantity corresponding to the production control model. Furthermore, referring to Figure 1 As shown, the real-time collection of status parameters and production order data for each process in EVA foaming production, and the control and scheduling of these parameters and data based on a collaborative control model, includes the following steps: The status parameters and production order data of each process in the EVA foaming production are collected in real time and input into the constructed collaborative control model; After receiving real-time collected status parameters and production order data, the collaborative control model will generate corresponding collaborative control quantities based on different production control models. Furthermore, the administrator controls and schedules the status parameters and production order data of each process in the EVA foaming production based on the generated corresponding collaborative control variables; In one specific embodiment, the EVA foaming production process multi-process collaborative control system further includes: a data acquisition module, a data processing module, a data analysis module, a production control constraint module, a production control module, and a control scheduling module; The data acquisition module is used to collect status parameters and production order data for each process in EVA foaming production. The data processing module is used to process the collected status parameters and production order data to obtain the processed status parameters and production order data. The data analysis module is used to analyze the processed state parameters to obtain the analyzed state parameters; The production control constraint module is used to set production control constraints based on the analyzed status parameters and processed production order data. The production control module is used to construct a production control model based on the set production control constraints. The control and scheduling module is used to control and schedule the status parameters and production order data of each process in EVA foaming production according to the constructed production control model.

[0021] It should be noted that, The above content is merely an example and illustration of the concept of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described, or use similar methods to replace them, as long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, and all such modifications and additions should fall within the protection scope of the present invention.

Claims

1. A full-process multi-process collaborative control system for EVA foaming production, characterized in that, Includes the following steps: S1. Collect historical status parameters and historical production order data of each process in EVA foaming production, and process the collected historical status parameters and historical production order data of each process through data processing methods to obtain the processed historical status parameters and historical production order data. S2. Analyze the processed historical state parameters using data analysis methods to obtain the analyzed historical state parameters; S3. Based on the analyzed historical state parameters and processed historical production order data, set production control constraints and construct a production control model based on the set production control constraints; S4. Based on time synchronization, perform collaborative control on the constructed production control model and construct a collaborative control model; S5. Real-time collection of status parameters and production order data for each process in EVA foaming production, and control and schedule the status parameters and production order data for each process in EVA foaming production based on the constructed collaborative control model.

2. The EVA foaming production whole-process multi-process collaborative control system according to claim 1, characterized in that, The process of collecting historical status parameters and historical production order data for each process in EVA foaming production, and then processing the collected historical status parameters and historical production order data to obtain the processed historical status parameters and historical production order data includes the following steps: The historical status parameters of each process include: control command data for each process and production status parameters for each process; The production status parameters for each process include: temperature data, pressure data, time data, and VA content data; The historical production order data includes: order number, order start time, order end time, quantity required for the order, and order priority; S11. The historical status parameters of each process collected are processed by data processing methods to obtain the processed historical status parameters; A sample set was constructed based on historical state parameters collected from each process in the EVA foaming production. wherein, represents a sample set represents a production state parameter under the first process in EVA foaming production, represents control instruction data under the first process in EVA foaming production, represents a production state parameter under the n process in EVA foaming production, represents control instruction data under the n process in EVA foaming production; Traverse the historical state parameters of each process in the sample set, locate the missing data, and calculate the mean of the historical state parameters of the two adjacent groups of missing data by means of imputation. Use the calculated mean of historical state parameters as the imputation value of the missing data. The processed historical status parameters are obtained by summarizing and supplementing the historical status parameters of each process in the sample set. S12. The historical production order data collected from each process is processed using data processing methods to obtain the processed historical production order data.

3. The EVA foaming production whole-process multi-process collaborative control system according to claim 2, characterized in that, The process of processing the historical production order data collected from each process step to obtain the processed historical production order data includes the following steps: The historical production order data collected for each process was filtered using Bloom filtering. Create an array of length m, and select... Each hash function iterates through each set of data in the historical production order data for each process and stores the results in an array; During the traversal using the hash function, if two sets of data have the same traversal result, each data in these two sets is compared. When the comparison results are consistent, the two sets of data are set to be the same data, and the software requirement data that arrives after the software requirement time is deleted. After the traversal is complete, the historical production order data for each process stored in the array during the traversal is summarized to obtain the processed historical production order data.

4. The multi-process collaborative control system for the entire EVA foaming production process according to claim 1, characterized in that, The process of analyzing the processed historical state parameters through data analysis to obtain the analyzed historical state parameters includes the following steps: S21. Initialize the processed historical state parameters and construct the dataset. ; Select the processed historical state parameters of group C in the dataset as the initial data center. Each data center is defined as a data category, representing a type of processed historical state parameters; in, Represents a collection of data centers. This represents the Cth data center; S22. Based on the processed historical state parameters in the dataset. Based on the distance formula, calculate the historical state parameters after each group of processing. Distance to data center C; The distance formula is as follows: ； in, Represents the processed historical state parameters To data center The distance is calculated and the data is assigned to the data category corresponding to the data center with the smallest distance. One group is added at a time until all data is clustered. Then the result of this classification is used as the input for step S23. S23. After all data has been classified, update the data center for each data category based on the mean calculation method. S24. Repeat steps S22-S23 until the data in the data center and data category no longer changes. Output the data category, the amount of data in each category, the data center, and the historical state parameters after clustering. S25. Determine the distribution of historical state parameters based on data categories, data volume of each category, data centers, and historical state parameters after clustering, and determine the failure rate based on the distribution of state parameters. Collect the range of qualified parameters for EVA foaming production, and compare the collected range of qualified parameters with the clustered historical state parameters to filter out unqualified historical state parameters. The failure rate is calculated based on the filtered-out unqualified historical status parameters; Failure rate = Number of unqualified historical status parameters / Data volume of each category; S26. Summarize the clustered historical state parameters and failure rates to obtain the analyzed historical state parameters.

5. The multi-process collaborative control system for the entire EVA foaming production process according to claim 1, characterized in that, The process of setting production control constraints based on analyzed historical state parameters and processed historical production order data, and constructing a production control model based on these constraints, includes the following steps: S31. Set production control constraints based on the analyzed historical status parameters and processed historical production order data; S32. Construct different production control models based on the set production control constraints.

6. The multi-process collaborative control system for the entire EVA foaming production process according to claim 5, characterized in that, Setting production control constraints based on analyzed historical status parameters and processed historical production order data includes the following steps: Setting production process decisions, The formulas for production process decision variables are shown below: ； in, This indicates whether the i-th order has gone through the j-th process. =1 indicates that the i-th order has gone through the j-th process. =0 indicates that the i-th order does not go through the j-th process; Production order constraints: ； in, Take a positive integer, representing i orders in the queue. This represents the maximum number of queue slots that can be filled. A number of orders are queued; Process product production volume constraints: ； in, This represents the production quantity of the product in the j-th process of the i-th order. These represent the minimum and maximum production quantities, respectively. Multi-process production capacity constraints: ； in, This represents the pass rate of the j-th process in the i-th order. This represents the hourly production volume of the j-th process in the i-th order. This represents the usage time of the equipment corresponding to the j-th process. Indicates the order quantity; Capacity reservation constraints: ； in, This represents the reserve quantity for the equipment corresponding to the j-th process. This represents the reserved quantity of the equipment corresponding to the i-th order.

7. The multi-process collaborative control system for the entire EVA foaming production process according to claim 1, characterized in that, The process of collaboratively controlling the production control model based on time synchronization and constructing the collaborative control model includes the following steps: S41. Construct a time synchronization model based on the historical state parameters of each process in the EVA foaming production process. S42. Based on the time synchronization model, the constructed production control model is used for collaborative control.

8. The multi-process collaborative control system for the entire EVA foaming production process according to claim 7, characterized in that, The collaborative control of the constructed production control model based on the time synchronization model includes the following steps: A production control chart is set based on the analyzed historical status parameters, processed historical production order data, time synchronization model, and production control model. ; in, This represents a production control chart. This represents the set of production nodes, obtained from processed historical production order data and analyzed historical status parameters. The set of edges representing the connections between production processes is obtained from the production control model. This represents the synchronization constraints of production nodes, obtained from the time synchronization model; The production control chart is trained and inferred using a graph convolutional neural network, and a collaborative control model is constructed based on the training and inference results. The collaborative control model is defined as a combination of a graph convolutional neural network and a multilayer perceptron. The graph convolutional neural network consists of 5 graph convolutional layers, 5 graph pooling layers and 1 fully connected layer, with the graph convolutional layers and graph pooling layers nested together. The established production control chart is input into the graph convolutional neural network, and the graph convolutional layer extracts the production control chart through message passing and state update processes. Calculate the neural transmission information between each pair of nodes and their neighboring nodes, and aggregate the features of the neighboring nodes and the node itself through a weighted summation method via message passing; After aggregation is complete, the aggregation result is processed by setting an update function through the state update process to generate new features for the current node; The new features of the aggregated nodes are input into the graph pooling layer, which then transforms the production control graph extracted by the graph convolutional layer into a feature vector through mean calculation. The processing results of five nested graph convolutional layers and graph pooling layers are summarized, and the feature vectors of the five layers are concatenated through a fully connected layer to obtain the trained collaborative control features. The trained collaborative control features are input into a multilayer perceptron. The multilayer perceptron then fuses and reduces the dimensionality of the trained collaborative control features, and outputs the collaborative control quantity corresponding to the production control model.

9. The multi-process collaborative control system for the entire EVA foaming production process according to claim 1, characterized in that, The real-time acquisition of status parameters and production order data for each process in EVA foaming production, and the control and scheduling of these parameters and data based on a collaborative control model, includes the following steps: The status parameters and production order data of each process in the EVA foaming production are collected in real time and input into the constructed collaborative control model; After receiving real-time collected status parameters and production order data, the collaborative control model will generate corresponding collaborative control quantities based on different production control models. The administrator controls and schedules the status parameters and production order data of each process in EVA foaming production based on the generated corresponding collaborative control variables.

10. A multi-process collaborative control system for the entire EVA foaming production process as described in claim 1, characterized in that, include: The system includes a data acquisition module, a data processing module, a data analysis module, a production control constraint module, a production control module, and a control scheduling module. The data acquisition module is used to collect status parameters and production order data for each process in EVA foaming production. The data processing module is used to process the collected status parameters and production order data to obtain the processed status parameters and production order data. The data analysis module is used to analyze the processed state parameters to obtain the analyzed state parameters; The production control constraint module is used to set production control constraints based on the analyzed status parameters and processed production order data. The production control module is used to construct a production control model based on the set production control constraints. The control and scheduling module is used to control and schedule the status parameters and production order data of each process in EVA foaming production according to the constructed production control model.

Images