Artificial intelligence-based cold work process parameter optimization and coil plate control method and system

Abstract

The application belongs to the technical field of industrial control method and system, and specifically discloses a cold working process parameter optimization and plate rolling control method based on artificial intelligence, and relates to the technical fields of cold working forming and intelligent control. The method comprises the following steps: collecting historical process parameters and corresponding plate quality data, constructing an evaluation function and outputting process weight values; screening optimal parameters according to the process weight and importing the cold working equipment; monitoring the curvature distribution of the plate in the plate rolling process in real time, and identifying the plate rolling state; executing a maintenance strategy or a correction strategy according to the state, and fusing the corrected feedback to optimize subsequent parameters. The method can significantly improve the plate rolling accuracy and forming consistency, has the ability of self-adaptive correction of abnormal states, reduces the dependence on artificial experience, is suitable for various plate rolling equipment and plate types, and has good universality and promotion value.

Description

Technical Field

[0001] This invention belongs to the technical field of industrial control methods and systems, specifically relating to a method and system for optimizing cold working process parameters and controlling rolled plates based on artificial intelligence. Background Technology

[0002] Cold working is a key process in sheet metal processing, widely used in automotive manufacturing, home appliances, building structures, aerospace, and machinery. Especially in cold bending, cold rolling, and sheet metal coiling, proper process parameter settings directly affect the product's forming quality, dimensional accuracy, and material utilization. However, traditional cold working processes largely rely on rules of thumb or physical models for process setting, often resulting in low parameter adjustment efficiency, poor finished product consistency, and high process uncontrollability in actual production.

[0003] Taking sheet metal rolling as an example, its control process involves multiple variables, such as sheet thickness, yield strength, initial stress state, bending radius, rolling speed, and rolling tension. These variables have strong nonlinear and multi-coupled relationships. Traditional control methods usually employ linear models, lookup tables, or simple control strategies, which are difficult to dynamically respond to complex working conditions and individual differences in multiple batches of materials. This results in uneven product rolling, severe springback, and large processing errors, affecting product quality and subsequent assembly.

[0004] In recent years, artificial intelligence technologies, especially machine learning, neural networks, and reinforcement learning, have been increasingly widely applied in industrial manufacturing. Through training on large-scale production data, they can establish a mapping relationship between input parameters and processing results, possessing self-learning, self-adaptive, and self-optimizing capabilities. This provides new technical means to solve parameter optimization and control problems in cold working processes. For example, by introducing deep learning models, data samples from past plate rolling processes can be analyzed to uncover the influence of key parameters on forming quality; combined with reinforcement learning algorithms, continuous iteration and optimization of control strategies can be achieved, thereby improving process stability and efficiency.

[0005] However, the application of artificial intelligence in the field of cold working is still in its initial stage, and it mainly faces the following problems: 1. The lack of an intelligent parameter optimization framework that is highly coupled with the cold working process makes it difficult to achieve real-time decision-making and fine control; 2. Most existing intelligent models are black box models, lacking physical interpretability, which affects their credibility and scalability in industrial production; 3. Some systems only target a single piece of equipment or process parameter and lack the ability to control the entire cold working production chain in a coordinated manner.

[0006] Therefore, there is an urgent need to develop an AI-based method and system for optimizing cold working process parameters and controlling sheet rolling. This system would construct a multi-dimensional data perception and real-time analysis mechanism, integrating data-driven models and physical mechanism models to achieve intelligent prediction, adaptive parameter adjustment, and closed-loop control of the sheet rolling process under different operating conditions, ensuring sheet forming quality and process stability. This system would not only improve the automation and intelligence level of cold working but also have significant economic benefits and industrial application value, representing an important direction for promoting intelligent manufacturing upgrades. Summary of the Invention

[0007] The purpose of this invention is to provide a method and system for optimizing cold working process parameters and controlling plate rolling based on artificial intelligence. It aims to accurately optimize and control cold working process parameters and plate rolling process through intelligent means, which not only improves production efficiency and product quality, but also enhances process stability. It can monitor and provide feedback for adjustment in real time, effectively solving the problems caused by traditional manual control methods.

[0008] The technical solution adopted in this invention is as follows: A method for optimizing cold working process parameters and controlling rolled plates based on artificial intelligence, comprising the following steps: S1. Obtain historical process data: Collect the actual process parameters of the cold working equipment in multiple past process batches and the corresponding sheet quality data; S2. Constructing a process evaluation function: Using process parameters and sheet quality as input variables, construct an evaluation function to quantify the execution quality of each set of process parameters; S3. Generate process weight values: Output the execution quality of each set of process parameters as a process score, and determine the corresponding process weight values ​​by sorting. S4. Optimize process parameters: Optimize and filter the process parameter set based on all process weight values, and import the filtering results into the parameter control module; S5. Real-time monitoring of curvature distribution: During the plate rolling process, image data of the plate edge is collected, and the curvature distribution curve is identified through the image processing and curvature calculation module; S6. Identify the state of the roll plate: Compare the curvature distribution with the preset evaluation range to identify the current state of the roll plate, including normal state, excessive bending state, and smooth transition state. S7. Output control strategy: Output control strategy based on recognition results, where the maintenance strategy is executed in normal state and the correction strategy is triggered in abnormal state. S8. Integration Correction Feedback: Collect edge data of the board before and after correction under abnormal conditions, calculate the edge change curvature distribution value, and integrate it into the current optimized process parameters as a correction factor.

[0009] Furthermore, the process evaluation function is a multidimensional regression model. Its model weights are obtained by training on dimensions such as quality grade, surface flatness, edge uniformity, and roll plate deviation in historical process samples. The scoring output is achieved using linear regression or neural network algorithms. The output results are used to rank the performance and assign priority values ​​to all parameter groups.

[0010] Furthermore, the step of selecting optimized process parameters includes: S31. Perform high-dimensional feature encoding on all process parameters according to their process weight values; S32. Using the encoding result as the query condition, retrieve the corresponding parameter template from the optimized database; S33. Select the parameter template with the highest matching degree with the current board features through similarity calculation as the optimized process parameter.

[0011] Furthermore, the real-time monitoring of curvature distribution includes: acquiring real-time images of the edge of the sheet metal during the rolling process using a high-resolution image sensor, extracting edge lines through an edge detection algorithm, acquiring continuous edge coordinate points using a sliding window method, calculating the curvature distribution map based on the angle changes between discrete points, and inputting the results into the state recognition module for state determination.

[0012] Furthermore, the correction strategy includes: jointly fine-tuning parameters such as rolling force, rolling speed, and roll gap position according to the current state type. Specifically, when the plate is excessively bent, the rolling force is reduced and the feed speed is decreased; when the plate is in a transitional state, the roll pressure is appropriately increased and the rolling radius is reduced, while maintaining balanced pressure at the edges.

[0013] Furthermore, the corrective feedback fusion step includes: S61. Collect edge data before correction under abnormal conditions of the roll plate, and output its curvature distribution value; S62. After executing the correction strategy, collect the corrected edge data again and obtain the corresponding curvature distribution value; S63. Compare and analyze the curvature distribution results before and after the correction, and calculate the value of the change in curvature Δκ. S64. Input the Δκ value as a correction factor into the correction function model and generate dynamic fine-tuning parameters; S65. Update and integrate the fine-tuning parameters into the current process parameter group to form updated optimized parameters for subsequent use; S66. Establish an optimized process parameter library, record all parameter groups with "normal" feedback in a versioned manner, and build a parameter library containing process number, execution time, board information, final curvature result, etc., for subsequent process migration and quick call, to realize rapid optimization recommendation for the same type of board.

[0014] Furthermore, each set of parameters in the optimized process parameter library is equipped with a dynamic validity period label. The system periodically reviews and evaluates the usage frequency and stability indicators of the parameter sets. When a set of parameters has a low usage frequency or an increase in abnormal feedback within a specified time, it is marked as a historical invalid set and removed from the default recommendation list.

[0015] This application also provides an artificial intelligence-based cold working process parameter optimization and plate rolling control system for executing the aforementioned artificial intelligence-based cold working process parameter optimization and plate rolling control method, including: The process data acquisition module is used to collect historical parameters and sheet quality results and provide them to the evaluation model; The parameter evaluation module is used to construct evaluation functions and output process scores and process weight values; The process optimization module is used to select the optimal parameters and generate control commands. The curvature monitoring module is used to acquire images, calculate curvature, and determine the status of the rolled plate during the rolling process. The strategy control module is used to determine whether to execute a maintenance strategy or a correction strategy based on the roll plate status. The correction fusion module is used to collect edge data before and after correction and output correction factors; The process parameter library management module is used to record, manage, and eliminate optimized parameter groups.

[0016] The present invention also provides an electronic device, comprising: at least one processor and a memory, wherein the memory stores a computer program, and when the program is executed by the processor, the processor executes the aforementioned artificial intelligence-based cold working process parameter optimization and rolling plate control method, thereby realizing intelligent optimization, automatic control and correction feedback functions of cold working process parameters.

[0017] Beneficial effects Compared with existing technologies, the artificial intelligence-based method for optimizing cold working process parameters and controlling sheet rolling provided by this invention has the following advantages: 1. This invention uses an artificial intelligence model to evaluate and optimize historical process parameters, which can automatically select the optimal combination of coil parameters, effectively improving the accuracy of coiling and the consistency of sheet forming.

[0018] 2. By utilizing a real-time curvature monitoring and status recognition mechanism, rapid response and adaptive correction to abnormal coil conditions can be achieved, significantly reducing the defect rate and material waste.

[0019] 3. Build a process parameter knowledge base to enable long-term accumulation and reuse of process data, support rapid adaptation to different board types, improve production efficiency, and reduce reliance on manual experience.

[0020] In summary, by deeply integrating artificial intelligence technology into the optimization of cold working process parameters and the control of rolling plates, this invention not only effectively improves the system's intelligence level and rolling accuracy, but also significantly reduces the labor intensity of workers and manufacturing costs, demonstrating broad application prospects and significant industrial promotion value. Attached Figure Description

[0021] Figure 1 This is a schematic diagram of the method flow of the present invention. Detailed Implementation

[0022] To facilitate understanding of the present invention, a more detailed description of the invention is provided below with reference to specific embodiments. It should be understood that the following description is merely for illustrating specific implementations of the invention and is not intended to limit the scope of protection of the invention.

[0023] The specific embodiments of the present invention will now be described with reference to the accompanying drawings.

[0024] Example 1 like Figure 1 As shown, this embodiment provides a method for optimizing cold working process parameters and controlling sheet metal rolls based on artificial intelligence, including the following steps: S1. Obtain historical process data: Collect the actual process parameters of the cold working equipment in multiple past process batches and the corresponding sheet quality data; S2. Constructing a process evaluation function: Using process parameters and sheet quality as input variables, construct an evaluation function to quantify the execution quality of each set of process parameters; S3. Generate process weight values: Output the execution quality of each set of process parameters as a process score, and determine the corresponding process weight values ​​by sorting. S4. Optimize process parameters: Optimize and filter the process parameter set based on all process weight values, and import the filtering results into the parameter control module; S5. Real-time monitoring of curvature distribution: During the plate rolling process, image data of the plate edge is collected, and the curvature distribution curve is identified through the image processing and curvature calculation module; S6. Identify the state of the roll plate: Compare the curvature distribution with the preset evaluation range to identify the current state of the roll plate, including normal state, excessive bending state, and smooth transition state. S7. Output control strategy: Output control strategy based on recognition results, where the maintenance strategy is executed in normal state and the correction strategy is triggered in abnormal state. S8. Integration Correction Feedback: Collect edge data of the board before and after correction under abnormal conditions, calculate the edge change curvature distribution value, and integrate it into the current optimized process parameters as a correction factor.

[0025] Example 2 This embodiment is a further improvement on embodiment 1: The process evaluation function is a multidimensional regression model. Its model weights are obtained by training on dimensions such as quality grade, surface flatness, edge uniformity, and roll plate deviation in historical process samples. The scoring output is achieved by using linear regression or neural network algorithms. The output results are used to rank the performance and assign priority values ​​to all parameter groups.

[0026] The steps for selecting optimized process parameters include: S31. Perform high-dimensional feature encoding on all process parameters according to their process weight values; S32. Using the encoding result as the query condition, retrieve the corresponding parameter template from the optimized database; S33. Select the parameter template with the highest matching degree with the current board features through similarity calculation as the optimized process parameter.

[0027] The process of real-time monitoring of curvature distribution includes: using a high-resolution image sensor to acquire real-time images of the edge of the sheet during the rolling process, extracting edge lines through an edge detection algorithm, acquiring continuous edge coordinate points using a sliding window method, calculating the curvature distribution map based on the angle changes between discrete points, and inputting the results into the state recognition module for state determination.

[0028] The correction strategy includes: jointly fine-tuning parameters such as rolling force, rolling speed, and roll gap position according to the current state type. Specifically, when the plate is excessively bent, reduce the rolling force and reduce the feed speed; when the plate is in a transitional state, appropriately increase the roll pressure and reduce the rolling radius, while maintaining balanced pressure at the edges.

[0029] Example 3 This embodiment is a further improvement on embodiment 1: The correction feedback fusion step includes: S61. Collect edge data before correction under abnormal conditions of the roll plate, and output its curvature distribution value; S62. After executing the correction strategy, collect the corrected edge data again and obtain the corresponding curvature distribution value; S63. Compare and analyze the curvature distribution results before and after the correction, and calculate the value of the change in curvature Δκ. S64. Input the Δκ value as a correction factor into the correction function model and generate dynamic fine-tuning parameters; S65. Update and integrate the fine-tuning parameters into the current process parameter group to form updated optimized parameters for subsequent use; S66. Establish an optimized process parameter library, record all parameter groups with "normal" feedback in a versioned manner, and build a parameter library containing process number, execution time, board information, final curvature result, etc., for subsequent process migration and quick call, to realize rapid optimization recommendation for the same type of board.

[0030] Each parameter group in the optimized process parameter library is assigned a dynamic validity period label. The system periodically reviews and evaluates the usage frequency and stability indicators of the parameter groups. When a parameter group has a low usage frequency or an increase in abnormal feedback within a specified time, it is marked as a historical invalid group and removed from the default recommendation list.

[0031] Example 4 This embodiment provides an artificial intelligence-based method for optimizing cold working process parameters and controlling plate rolling, which is applicable to four-roll hydraulic plate rolling machines, and is particularly suitable for mass production of high-precision fan cylinder-type plate parts.

[0032] First, step S1 is executed to acquire historical process data. In this embodiment, data is collected from cold-worked sheet metal projects completed by a factory in the past year. The actual usage parameters of each project are extracted, including 12 variables such as sheet metal rolling force, feed speed, roll gap setting, and initial position of the upper roll. Quality data of each batch of finished sheet metal is also collected, such as curvature error, edge uniformity, and residual stress distribution. Finally, a structured process dataset with a sample size of no less than 500 groups is formed.

[0033] In step S2, a process evaluation function is constructed. This embodiment employs a multidimensional regression model based on a fusion of random forest and neural network, using the aforementioned historical data as training samples, process parameters as input variables, and sheet quality scores as outputs. The model is iteratively trained using cross-validation to ultimately obtain a scoring function that can output corresponding scores for any set of process parameters, reflecting the average performance quality of that parameter set in historical applications.

[0034] Execute step S3 to generate process weight values. After normalizing the score values ​​output by the model, establish a parameter priority list by sorting, and assign a unique weight value to each group of parameters to achieve quantitative classification of parameter groups.

[0035] Proceed to step S4 to filter and optimize process parameters. The system first encodes all weight values ​​in a high dimension, constructs an index number using a hash mapping, and then queries the optimized process database using process conditions such as sheet type (e.g., Q235, 16Mn), thickness, and target roll radius as search criteria. The system selects the parameter group with the highest matching degree to the current task as the initial process parameters for the current task.

[0036] In step S5, the curvature distribution of the sheet metal during the rolling process is monitored in real time. In this embodiment, a bidirectional line-scanning high-resolution industrial camera is installed at the discharge end of the rolling equipment. The edge contour of the sheet metal is extracted using an edge detection algorithm, and the coordinates of a discrete point every 5 mm are extracted using a sliding window. The local curvature is calculated using a three-point fitting method, ultimately forming a complete edge curvature distribution map of the sheet metal. This graphic data is transmitted to the control system in real time for status recognition.

[0037] In step S6, the state of the roll plate is identified. The system compares the curvature distribution map with the preset curvature standard range. When the curvature fluctuation value is within the set range, it is identified as "normal state"; if there is a significant high curvature concentration area, it is identified as "excessive bending state"; if the curvature continuous section is too flat, it is identified as "transitional flat state".

[0038] In step S7, a control strategy is output based on the identification result. For normal conditions, the system maintains the current process parameters; if an abnormal condition is identified, a correction strategy is triggered. For example, when excessive bending is identified, the system automatically reduces the upper roller feed pressure by 5% and reduces the rolling speed by 20%; when a smooth transition is identified, the system automatically tightens the roller gap by 0.8mm and appropriately increases the feed rate to enhance the bending force.

[0039] Proceed to step S8, where the correction feedback is integrated. The system collects two consecutive curvature distribution maps of the rolled plate before and after correction, compares and analyzes the difference, and calculates the edge curvature change Δκ(x). Δκ(x) is input into the correction function module, which outputs the rolled plate speed correction factor and pressure correction gain, and integrates them with the current parameters to form the parameters for the next round of rolled plate operation.

[0040] To enhance process reusability, this embodiment further establishes an optimized process parameter library, recording all parameter groups that receive "normal" feedback, including their process number, execution time, material and specifications, and the mean and variance of the final curvature. Each parameter group has a dynamic validity period label, and the system periodically evaluates its call frequency and feedback accuracy. If a parameter group receives three consecutive abnormal feedbacks or has not been used within three months, it is marked as a "historically invalid group" and automatically removed from the recommendation list.

[0041] The method described in this embodiment has been successfully applied to the cold rolling process of multiple batches of fan cylinders of different specifications, verifying that it has good automatic adjustment capability, parameter transfer capability and significant rolling accuracy improvement effect. The product qualification rate has increased from the original 92.4% to 98.7%, and the dependence on operators has been significantly reduced.

[0042] Example 5 This embodiment provides an artificial intelligence-based cold working process parameter optimization and plate rolling control system for executing the aforementioned artificial intelligence-based cold working process parameter optimization and plate rolling control method, including: The process data acquisition module is used to collect historical parameters and sheet quality results and provide them to the evaluation model; The parameter evaluation module is used to construct evaluation functions and output process scores and process weight values; The process optimization module is used to select the optimal parameters and generate control commands. The curvature monitoring module is used to acquire images, calculate curvature, and determine the status of the rolled plate during the rolling process; The strategy control module is used to determine whether to execute a maintenance strategy or a correction strategy based on the roll plate status. The correction fusion module is used to collect edge data before and after correction and output correction factors; The process parameter library management module is used to record, manage, and eliminate optimized parameter groups.

[0043] Example 6 This embodiment provides an artificial intelligence-based cold working process parameter optimization and plate rolling control system. The system is deployed on a four-roll hydraulic plate rolling machine and can realize intelligent parameter optimization, status monitoring, strategy control and process knowledge management for the entire cold working plate rolling process.

[0044] The system includes the following modules: 1. Process Data Acquisition Module This module connects the equipment's historical data interface to the quality inspection system database. It collects historical process parameters (such as sheet thickness, width, rolling force, rolling speed, and roll gap settings) from multiple batches of sheet rolling tasks, along with corresponding sheet quality results (such as curvature error, edge uniformity, and thickness consistency). This data is then structured and output to the subsequent evaluation model. In actual operation, this module synchronizes data every 24 hours, acquiring no fewer than 100 sets of valid historical samples.

[0045] 2. Parameter Evaluation Module This module incorporates a neural network regression model as the process evaluation function, with training samples consisting of process parameter-quality score pairs. The model is trained before deployment and can be dynamically fine-tuned in real-time using new data after deployment. Based on the input process parameters, the module outputs execution scores and generates process weights based on the score ranking, which guide the optimization module in parameter selection.

[0046] 3. Process Optimization Module This module sorts and hashes all available process parameter groups based on the process weight values ​​generated by the evaluation module, and matches the results with standard parameter templates in the process optimization database. The matching process calculates similarity and achieves optimal matching based on parameters such as the current sheet type, thickness, and target roll radius, ultimately generating structured control commands that are sent to the equipment control unit. This module supports online parameter fine-tuning and has high-speed response capabilities.

[0047] 4. Curvature Monitoring Module A high-resolution industrial camera and edge recognition sensor are installed at the equipment's output end. Combined with image processing algorithms, this module acquires real-time images of the sheet metal edges during the rolling process, extracts edge lines, and calculates the discrete curvature distribution. The module employs a three-point method and curvature fitting technology, with an error controlled within ±0.5%. The identified curvature distribution map is compared by the system with a preset evaluation interval to determine the current state of the rolled sheet.

[0048] 5. Strategy Control Module This module calls the control strategy mapping table based on the status results (normal, excessive bending, and smooth transition) output by the curvature monitoring module. When a normal state is identified, the module maintains the current control commands unchanged; if an abnormal state is identified, the module immediately triggers correction logic to adjust parameters such as rolling speed, pressure, and roll gap. The strategy control module supports real-time communication with the PLC system, with an adjustment delay of no more than 200ms.

[0049] 6. Improve the fusion module After the correction command is executed, this module calls the image sensor to re-acquire edge data of the board material, obtains the curvature distribution of the corresponding area before and after correction, and calculates the change value Δκ. This change value is input into the correction function model, and the output correction factor is used to dynamically adjust and optimize the parameters. This module also supports the recording and trend analysis of multiple correction actions, providing support for parameter fine-tuning.

[0050] 7. Process Parameter Library Management Module This module maintains a structured database of optimized process parameters. Each record contains information such as parameter group ID, applicable sheet material type, execution time, usage frequency, and curvature feedback. The module employs a dynamic validity judgment mechanism: when a parameter group consistently generates abnormal feedback or its usage frequency is too low within a set period, it is marked as a historical invalid parameter and removed from the recommendation list. Furthermore, the system supports exporting recommended parameter combinations for rapid initialization of new tasks.

[0051] By deploying the system described in this embodiment, the traditional cold-work coiling process can be upgraded from "experience-dependent" to "data-driven" intelligent control, significantly improving parameter selection efficiency, rolling accuracy, and equipment automation level. System tests show that after using the system of this invention, the first-piece pass rate increased from 92% to over 98%, the frequency of manual intervention decreased by more than 60%, and the system's ability to adapt to multiple sheet specifications was significantly enhanced, demonstrating good prospects for widespread application.

[0052] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for optimizing cold working process parameters and controlling sheet rolling based on artificial intelligence, characterized in that, Includes the following steps: S1. Obtain historical process data: Collect the actual process parameters of the cold working equipment in multiple past process batches and the corresponding sheet quality data; S2. Constructing a process evaluation function: Using process parameters and sheet quality as input variables, construct an evaluation function to quantify the execution quality of each set of process parameters; The process evaluation function is a multidimensional regression model. Its model weights are obtained by training on the quality grade, surface flatness, edge uniformity, and roll plate deviation in historical process samples. The scoring output is achieved by using linear regression or neural network algorithms. The output results are used to rank the performance and assign priority values ​​to all parameter groups. S3. Generate process weight values: Output the execution quality of each set of process parameters as a process score, and determine the corresponding process weight values ​​by sorting. S4. Optimize process parameters: Optimize and filter the process parameter set based on all process weight values, and import the filtering results into the parameter control module; The steps for selecting optimized process parameters include: S41. Perform high-dimensional feature encoding on all process parameters according to their process weight values; S42. Using the encoding result as the query condition, retrieve the corresponding parameter template from the optimization database; S43. Select the parameter template with the highest matching degree with the current board features through similarity calculation as the optimized process parameter; S5. Real-time monitoring of curvature distribution: Real-time images of the edge of the sheet metal are acquired using a high-resolution image sensor during the rolling process. Edge lines are extracted using an edge detection algorithm, and continuous edge coordinate points are obtained using a sliding window method. The curvature distribution map is calculated based on the angle changes between discrete points, and the results are input to the state recognition module for state determination. S6. Identify the state of the roll plate: Compare the curvature distribution with the preset evaluation range to identify the current state of the roll plate, including normal state, excessive bending state, and smooth transition state. S7. Output control strategy: Output control strategy based on recognition results, where the maintenance strategy is executed in normal state and the correction strategy is triggered in abnormal state. S8. Integration and Correction Feedback: Collect edge data of the board material before and after correction under abnormal conditions, calculate the edge curvature distribution value, and integrate it into the current optimized process parameters as a correction factor. The correction feedback integration step includes: S81. Collect edge data before correction under abnormal conditions of the roll plate, and output its curvature distribution value; S82. After executing the correction strategy, collect the corrected edge data again and obtain the corresponding curvature distribution value; S83. Compare and analyze the curvature distribution results before and after the correction, and calculate the value of the change in curvature Δκ. S84. Input the Δκ value as a correction factor into the correction function model and generate dynamic fine-tuning parameters; S85. Update and integrate the fine-tuning parameters into the current process parameter group to form updated optimized parameters for subsequent use; S86. Establish an optimized process parameter library, record all parameter groups with "normal" feedback in a versioned manner, and build a parameter library containing process number, execution time, sheet material information, and final curvature result for subsequent process migration and quick call.

2. The method for optimizing cold working process parameters and controlling plate rolling based on artificial intelligence according to claim 1, characterized in that, The correction strategy includes: jointly fine-tuning the rolling force, rolling speed, and roll gap position according to the current state type. Specifically, when the plate is excessively bent, reduce the rolling force and feed speed; when the plate is in a transitional state, appropriately increase the roll pressure and reduce the rolling radius, while maintaining balanced pressure at the edges.

3. The method for optimizing cold working process parameters and controlling plate rolling based on artificial intelligence according to claim 2, characterized in that, Each parameter group in the optimized process parameter library is assigned a dynamic validity period label. The system periodically reviews and evaluates the usage frequency and stability indicators of the parameter groups. When a parameter group has a low usage frequency or an increase in abnormal feedback within a specified time, it is marked as a historical invalid group and removed from the default recommendation list.

4. An artificial intelligence-based cold working process parameter optimization and plate rolling control system, used to execute the artificial intelligence-based cold working process parameter optimization and plate rolling control method according to any one of claims 1-3, characterized in that, include: The process data acquisition module is used to collect historical parameters and sheet quality results and provide them to the parameter evaluation module. The parameter evaluation module is used to construct evaluation functions and output process scores and process weight values; The process optimization module is used to select the optimal parameters and generate control commands. The curvature monitoring module is used to acquire images, calculate curvature, and determine the status of the rolled plate during the rolling process; The strategy control module is used to determine whether to execute a maintenance strategy or a correction strategy based on the roll plate status. The correction fusion module is used to collect edge data before and after correction and output correction factors; The process parameter library management module is used to record, manage, and eliminate optimized parameter groups.

5. An electronic device, characterized in that, include: At least one processor and a memory storing a computer program, which, when executed by the processor, causes the processor to perform the method according to any one of claims 1-3, thereby achieving intelligent optimization, automatic control, and correction feedback functions for cold working process parameters.

Images