Intelligent punching control method and system of high-precision numerical control punching machine, medium and computer equipment

Abstract

The invention relates to the technical field of numerical control punching machines, in particular to an intelligent punching control method and system of a high-precision numerical control punching machine, a medium and computer equipment. According to the method, the initial parameters are acquired, the coupling model is constructed, the complex coupling relationship among the parameters is quantitatively analyzed, the interaction among the parameters is accurately captured, and the weighted value is dynamically adjusted to realize multi-parameter collaborative optimization, so that the globality and stability of the optimization process are ensured, and the optimization efficiency is improved. An improved particle swarm optimization algorithm is adopted to solve a collaborative optimization objective function, optimization efficiency and precision are effectively improved, an optimization scheme is verified through a virtual stamping test and real-time data acquisition, it is ensured that the optimization scheme can keep a low parameter fluctuation index in the actual stamping process, and the optimization efficiency and precision are improved. Through construction and dynamic optimization of the multi-parameter coupling model, the problem that the global optimal solution is difficult to realize due to the fact that mutual influence among parameters cannot be fully considered in single-parameter adjustment in the prior art is effectively solved.

Description

Technical Field

[0001] The present invention relates to the technical field of CNC punching machines, and in particular to an intelligent punching control method, system, medium and computer equipment for a high-precision CNC punching machine. Background Art

[0002] The stamping of a high-precision CNC punch press refers to a stamping machine tool controlled by a CNC system, which is used to perform processing operations such as punching, cutting, and forming on metals, plastics and other materials. It has a high level of precision and automation, and can accurately control parameters such as speed, pressure, and position during the stamping process, thereby achieving high-precision and high-efficiency production.

[0003] At present, the existing technology for intelligent stamping control of high-precision CNC punching machines mainly uses adaptive parameter adjustment control method to dynamically adjust stamping parameters according to real-time processing status to avoid processing defects. However, during the stamping process, multiple parameters (punch speed, pressure, stroke depth, plate positioning accuracy, etc.) affect each other. Adjustment of a single parameter may trigger a chain reaction, making it difficult for the system to find the global optimal solution, and instead reducing processing stability. Summary of the Invention

[0004] The main purpose of the present invention is to provide an intelligent stamping control method for a high-precision CNC punching machine, aiming to solve the technical problems in the prior art.

[0005] The present invention proposes an intelligent stamping control method for a high-precision CNC punch press, comprising: Acquire multiple initial parameter values ​​of a high-precision CNC punch press under a preset punching working condition, and construct a multi-parameter coupling model based on each of the initial parameter values; Quantitatively analyzing the coupling relationship between the initial parameters according to the multi-parameter coupling model to obtain a parameter coupling coefficient matrix, and setting a dynamic weight value for each initial parameter value according to the parameter coupling coefficient matrix; Constructing a multi-parameter collaborative optimization objective function according to the plurality of dynamic weight values, and solving the multi-parameter collaborative optimization objective function using an improved particle swarm optimization algorithm to obtain an initial parameter optimization solution; Inputting the initial parameter optimization scheme into a CNC punch press simulation system to perform a virtual punching test and collecting real-time data of multiple parameters during the virtual punching process; Obtaining a parameter fluctuation index based on the real-time data of the plurality of parameters, and determining whether the parameter fluctuation index is less than a preset fluctuation threshold; If the parameter fluctuation index is less than the preset fluctuation threshold, the initial parameter optimization scheme is used as a candidate optimization scheme; If the parameter fluctuation index is not less than the preset fluctuation threshold, the multi-parameter coupling model is corrected according to the real-time parameter data, and the process returns to the step of quantitatively analyzing the coupling relationship between the initial parameters according to the multi-parameter coupling model until the parameter fluctuation index is less than the preset fluctuation threshold, and the initial parameter optimization scheme at this time is used as a candidate optimization scheme.

[0006] Preferably, the step of constructing a multi-parameter coupling model according to each of the initial parameter values ​​comprises: Constructing a parameter sample set according to the multiple initial parameter values, wherein the parameter sample set includes multiple sample points; Using principal component analysis to perform dimensionality reduction processing on the parameter sample set and extract multiple main components, and constructing a multi-parameter coupling initial model based on the multiple main components; Dividing the parameter sample set into training parameter samples and testing parameter samples; The multi-parameter coupling initial model is trained and tested according to the training parameter samples and the test parameter samples until the mean square error of the multi-parameter coupling initial model is less than a preset error threshold, thereby obtaining the multi-parameter coupling initial model.

[0007] Preferably, the step of performing quantitative analysis on the coupling relationship between the initial parameters according to the multi-parameter coupling model to obtain a parameter coupling coefficient matrix includes: Constructing a deep belief network according to the initial parameter values ​​of the multi-parameter coupling model, and inputting the normalized initial parameter values ​​in the multi-parameter coupling model into a visible layer of the deep belief network; The hidden layer of the deep belief network is trained layer by layer through a greedy algorithm, and the activation probability of the hidden layer is obtained based on the data of the visible layer; Obtain the reconstructed visible layer data based on the activation probability of the hidden layer, and update the network weights and biases based on the difference between the reconstructed visible layer data and the original visible layer data; Extracting the weight matrix of each layer of the deep belief network after training is completed, and obtaining the parameter coupling coefficient according to each weight matrix; Arrange multiple parameter coupling coefficients in parameter order to construct a parameter coupling coefficient matrix.

[0008] Preferably, the step of solving the multi-parameter collaborative optimization objective function to obtain an initial parameter optimization solution includes: Inputting each of the initial parameter values ​​into the multi-parameter collaborative optimization objective function to obtain multiple fitness values, and selecting the initial parameter value corresponding to the minimum fitness value from the multiple fitness values ​​as the individual optimal position; Selecting an initial parameter value corresponding to the minimum fitness value from the multiple individual optimal positions as the global optimal position, and obtaining a global optimal position deviation based on the global optimal position and the individual optimal position; Obtaining a historical optimal position of the initial parameter value corresponding to each of the individual optimal positions, and obtaining an individual optimal position deviation based on the historical optimal position and the individual optimal position; Obtaining the current speed of the initial parameter value corresponding to each of the individual optimal positions, and obtaining the update speed of the corresponding initial parameter value according to the current speed, the individual optimal position deviation, and the global optimal position deviation; An updated position is obtained according to the update speed and the individual optimal position, and an initial parameter optimization solution is obtained according to the update position and the update speed.

[0009] Preferably, the step of obtaining a parameter fluctuation index based on the real-time data of the plurality of parameters comprises: Preprocessing the real-time data of each parameter to obtain corresponding standard parameter data; Obtaining multiple initial parameter values ​​in the initial parameter optimization scheme, and obtaining corresponding parameter deviation values ​​according to each of the initial parameter values ​​and standard parameter data; A parameter deviation square sum is obtained according to the plurality of parameter deviation values, and a parameter fluctuation index is obtained according to the parameter deviation square sum.

[0010] Preferably, the step of correcting the multi-parameter coupling model according to the real-time parameter data includes: Inputting each of the initial parameter values ​​into a multi-parameter coupling model to obtain first predicted parameter data, and obtaining corresponding parameter residuals based on the first predicted parameter data and parameter real-time data; The parameter residuals are fitted using the least squares method to obtain a residual model, and the residual model is added to the multi-parameter coupling initial model to obtain a revised multi-parameter coupling model; Inputting each of the initial parameter values ​​into the modified multi-parameter coupling model to obtain second prediction parameter data; Obtaining an actual parameter value of each of the initial parameter values ​​under a preset stamping working condition, and obtaining a corresponding absolute deviation based on each of the actual parameter values ​​and the second predicted parameter data; Obtaining a root mean square error according to the multiple absolute deviations, and determining whether the root mean square error is greater than a preset error threshold; If the root mean square error is greater than the preset error threshold, it is determined that the modified multi-parameter coupling model verification fails, and the process returns to the step of fitting the parameter residuals using the least squares method to obtain a residual model until the root mean square error is no greater than the preset error threshold; If the root mean square error is not greater than the preset error threshold, it is determined that the modified multi-parameter coupling model has passed the verification.

[0011] The present application also provides an intelligent stamping control system for a high-precision CNC punch press, comprising: A construction module is used to obtain multiple initial parameter values ​​of the high-precision CNC punch press under a preset punching working condition, and to construct a multi-parameter coupling model according to each of the initial parameter values; a quantitative analysis module, configured to perform a quantitative analysis on the coupling relationship between the initial parameters according to the multi-parameter coupling model, obtain a parameter coupling coefficient matrix, and set a dynamic weight value for each initial parameter value according to the parameter coupling coefficient matrix; A solution module is used to construct a multi-parameter collaborative optimization objective function according to the multiple dynamic weight values, and use an improved particle swarm optimization algorithm to solve the multi-parameter collaborative optimization objective function to obtain an initial parameter optimization solution; A test module, used for inputting the initial parameter optimization scheme into a CNC punch press simulation system to perform a virtual punching test and collect real-time data of multiple parameters during the virtual punching process; a judgment module, configured to obtain a parameter fluctuation index based on the real-time data of the plurality of parameters, and to judge whether the parameter fluctuation index is less than a preset fluctuation threshold; If the parameter fluctuation index is less than the preset fluctuation threshold, the initial parameter optimization scheme is used as a candidate optimization scheme; If the parameter fluctuation index is not less than the preset fluctuation threshold, the multi-parameter coupling model is corrected according to the real-time parameter data, and the process returns to the step of quantitatively analyzing the coupling relationship between the initial parameters according to the multi-parameter coupling model until the parameter fluctuation index is less than the preset fluctuation threshold, and the initial parameter optimization scheme at this time is used as a candidate optimization scheme.

[0012] Preferably, the building blocks include: A first constructing unit is configured to construct a parameter sample set according to the multiple initial parameter values, wherein the parameter sample set includes multiple sample points; The second construction unit is used to perform dimensionality reduction processing on the parameter sample set by using a principal component analysis method and extract a plurality of main components, and construct a multi-parameter coupling initial model based on the plurality of main components; A division unit, configured to divide the parameter sample set into training parameter samples and testing parameter samples; The training unit is used to train and test the multi-parameter coupling initial model according to the training parameter samples and the test parameter samples until the mean square error of the multi-parameter coupling initial model is less than a preset error threshold, thereby obtaining the multi-parameter coupling initial model.

[0013] The present invention also provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned intelligent stamping control method for the high-precision CNC punching machine when executing the computer program.

[0014] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the intelligent stamping control method for the high-precision CNC punching machine.

[0015] The beneficial effects of the present invention are as follows: the present invention obtains initial parameters and constructs a coupling model, quantitatively analyzes the complex coupling relationship between parameters, accurately captures the interaction between parameters, and dynamically adjusts weight values ​​to achieve multi-parameter collaborative optimization, avoiding the chain reaction that may be caused by relying solely on a single parameter adjustment in traditional technologies, ensuring the globality and stability of the optimization process, and solving the collaborative optimization objective function by adopting an improved particle swarm optimization algorithm, effectively improving the optimization efficiency and accuracy, verifying the optimization scheme through virtual stamping tests and real-time data acquisition, ensuring that the optimization scheme can maintain a low parameter fluctuation index in the actual stamping process, and significantly improving the stability and accuracy of the stamping process. The present invention effectively solves the problem in the prior art that single parameter adjustment cannot fully consider the mutual influence between parameters, resulting in difficulty in achieving the global optimal solution, through the construction and dynamic optimization of a multi-parameter coupling model. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 Schematic diagram of a method flow according to an embodiment of the present invention.

[0017] Figure 2 FIG. 1 is a schematic diagram of a system structure according to an embodiment of the present invention.

[0018] Figure 3 This is a schematic diagram of the internal structure of a computer device according to an embodiment of the present application.

[0019] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0020] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0021] like Figure 1-Figure 3 As shown, the present application provides an intelligent stamping control method for a high-precision CNC punch press, comprising: S1. Acquire multiple initial parameter values ​​of a high-precision CNC punch press under a preset punching working condition, and construct a multi-parameter coupling model according to each of the initial parameter values; S2. quantifying the coupling relationship between the initial parameters according to the multi-parameter coupling model to obtain a parameter coupling coefficient matrix, and setting a dynamic weight value for each initial parameter value according to the parameter coupling coefficient matrix; S3. Constructing a multi-parameter collaborative optimization objective function according to the multiple dynamic weight values, and using an improved particle swarm optimization algorithm to solve the multi-parameter collaborative optimization objective function to obtain an initial parameter optimization solution; S4, inputting the initial parameter optimization scheme into the CNC punch press simulation system to perform a virtual punching test and collecting real-time data of multiple parameters during the virtual punching process; S5. Obtaining a parameter fluctuation index based on the real-time data of the plurality of parameters, and determining whether the parameter fluctuation index is less than a preset fluctuation threshold; If the parameter fluctuation index is less than the preset fluctuation threshold, the initial parameter optimization scheme is used as a candidate optimization scheme; If the parameter fluctuation index is not less than the preset fluctuation threshold, the multi-parameter coupling model is corrected according to the real-time parameter data, and the process returns to the step of quantitatively analyzing the coupling relationship between the initial parameters according to the multi-parameter coupling model until the parameter fluctuation index is less than the preset fluctuation threshold, and the initial parameter optimization scheme at this time is used as a candidate optimization scheme.

[0022] As described in the above steps S1-S5, the multiple initial parameter values ​​refer to a combined group of multiple different parameter values, and each combined group includes the core stamping parameters of the high-precision CNC punch press, such as the punch initial speed, initial pressure, initial stroke depth, and initial positioning accuracy of the plate. The dynamic weight value is set for each initial parameter value according to the parameter coupling coefficient matrix. It is mainly based on each element in the parameter coupling coefficient matrix (indicating the degree of mutual influence between the two parameters), and quantifying the influence weight of each initial parameter in the overall coupling relationship. The larger the absolute value of the coupling coefficient, the more significant the influence of the parameter on other parameters, and the higher the initial weight value. The adaptive weight allocation algorithm dynamically updates the weight according to the real-time change of the parameter coupling coefficient. When the sum of the coupling coefficients of a parameter and other parameters increases, its weight value is automatically increased (such as adjusted from 0.3 to 0.5); when the sum of the coupling coefficients decreases, the weight value is correspondingly reduced to ensure that the weight allocation always reflects the dominant position of the parameter in the current coupling relationship; The step of constructing a multi-parameter collaborative optimization objective function according to a plurality of dynamic weight values ​​includes determining the weight coefficients of stamping accuracy, stamping efficiency, and energy consumption, the sum of the weight coefficients being 1, and determining the weight coefficients of each indicator by means of a hierarchical analysis method. The steps of the hierarchical analysis method are as follows: constructing a judgment matrix, wherein the elements in the judgment matrix represent the relative importance of each indicator, and the relative importance is assigned using a 1-9 scaling method; calculating the maximum eigenvalue and the corresponding eigenvector of the judgment matrix, normalizing the eigenvector, and obtaining the weight coefficient of each indicator; performing a consistency test, and when the consistency ratio is less than 0.1, the judgment matrix is ​​consistent, otherwise the judgment matrix is ​​reconstructed; constructing a stamping accuracy sub-objective function ( ;in, Indicates the number of parameters that affect stamping accuracy, Indicates the Dynamic weight values ​​of parameters, Indicates the actual value of the parameter, represents the theoretical value of the parameter, Indicates the parameter number that affects stamping accuracy), stamping efficiency sub-objective function (the negative of the ratio of the number of stamping times completed per unit time to the unit time. The negative number indicates that the indicator is the maximization target. The higher the efficiency, the smaller the function value, which is consistent with the overall optimization goal) and energy consumption sub-objective function (the ratio of the power consumed by the stamping process per unit time to the unit time). Based on the weighted sum of the stamping accuracy sub-objective function, the stamping efficiency sub-objective function and the energy consumption sub-objective function, a multi-parameter collaborative optimization objective function is constructed to achieve collaborative optimization of stamping accuracy, efficiency and energy consumption, avoid the chain reaction caused by a single parameter adjustment, and lead to the global optimal solution; The present invention obtains multiple initial parameter values ​​of a high-precision CNC punch press under preset stamping conditions and constructs a multi-parameter coupling model based on each initial parameter value. By obtaining multiple initial parameter values ​​(such as punch speed, pressure, stroke depth, plate positioning accuracy, etc.) under the preset stamping conditions, it can truly reflect multiple physical parameters in the stamping process under actual working conditions. This not only improves the representativeness of the data, but also ensures that the data source for model training is close to actual operation, avoiding the errors of purely theoretical or hypothetical data. Existing technologies often rely on oversimplified models or single parameters to adjust equipment. The present invention, by comprehensively collecting multi-dimensional data, covers the complex relationships between multiple parameter changes, providing a more accurate and comprehensive foundation for subsequent optimization models. The present invention establishes a multi-parameter coupling model to fully consider the interactions between various stamping parameters, avoiding the problem of traditional methods focusing only on single parameter optimization. The coupling model can comprehensively analyze the mutual influence between different parameters, making the optimization process more realistic. Existing technologies generally use a single optimization parameter and ignore the complex coupling relationships between multiple parameters. The present invention, through the multi-parameter coupling model, can achieve more efficient optimization and avoid performance degradation or instability caused by the coupling effects between parameters. The coupling relationship between the initial parameters is quantitatively analyzed by a multi-parameter coupling model to obtain a parameter coupling coefficient matrix, and a dynamic weight value is set for each initial parameter value according to the parameter coupling coefficient matrix. By quantifying the coupling relationship between the parameters, the contribution of each parameter to the overall performance can be clearly understood, thereby providing a quantitative basis for subsequent optimization schemes, which can help identify which parameters are most critical to stamping accuracy and stability, and focus on adjusting these parameters during optimization. The existing technology often simply adjusts a single parameter or adjusts based on experience, lacking a systematic analysis of the parameter coupling relationship. The present invention, by constructing a coupling coefficient matrix, can more accurately identify which parameters need to be collaboratively optimized, avoiding the "local optimum" problem that may occur in traditional optimization methods. The present invention sets a dynamic weight value for each initial parameter, which means that each parameter has different importance under different stamping conditions. Dynamic adjustment of the weight value can adjust the optimization focus according to the real-time changes of the stamping process, thereby achieving more accurate optimization results. Traditional optimization methods usually use static weights or fixed parameter importance evaluations, which often lead to inflexible adjustment under different working conditions. The present invention, through the dynamic weight value method, can perform personalized optimization according to different production environments and working conditions, and better adapt to changing production needs. A multi-parameter collaborative optimization objective function is constructed through multiple dynamic weight values, and an improved particle swarm optimization algorithm is used to solve the multi-parameter collaborative optimization objective function to obtain an initial parameter optimization scheme. In the multi-parameter collaborative optimization objective function, the introduction of dynamic weights makes the optimization processes of different parameters coordinated with each other, and the overall performance will not be unstable due to extreme changes in a single parameter. The objective function can comprehensively consider the influence of multiple parameters to ensure that both the process requirements can be met and the stability of the system can be improved during optimization. The optimization in traditional technologies often focuses on the improvement of a single parameter and ignores the influence of changes in other related parameters on the overall system. The present invention not only optimizes each parameter through multi-parameter collaborative optimization, but also ensures that each parameter The coordination between them effectively avoids system instability or performance degradation. Particle swarm optimization is an efficient global optimization method. The improved particle swarm optimization algorithm can overcome some limitations of traditional particle swarm optimization, such as slow convergence speed and easy falling into local optimality. The improved algorithm improves the accuracy and speed of optimization and can obtain a more ideal initial parameter optimization solution in a relatively short time. The existing technology may adopt traditional optimization algorithms, such as genetic algorithms or gradient descent methods, but these methods may perform poorly in processing multiple parameters and complex constraints. The present invention can better cope with complex multi-objective optimization problems through the improved particle swarm optimization algorithm, and has strong global search capabilities, which can avoid falling into local optimal solutions. By inputting the initial parameter optimization scheme into the CNC punch press simulation system for a virtual punching test and collecting real-time data of multiple parameters in the virtual punching process in real time, the parameter fluctuation index is obtained through the real-time data of multiple parameters. By conducting a virtual punching test in the CNC punch press simulation system, the effectiveness of the initial parameter optimization scheme can be verified without actually performing a punching operation. This not only saves production costs, but also avoids risks in actual operations and identifies potential problems in advance. Traditional methods usually rely on actual processing tests to verify the optimization scheme, which may lead to waste of resources and production interruptions. The virtual simulation test of the present invention can be verified multiple times in a safe and low-cost environment to ensure the feasibility of the final optimization scheme. By collecting real-time data in the virtual stamping process, parameter fluctuations can be monitored in real time to ensure that the optimization scheme does not cause excessive fluctuations or instability in actual stamping. This method not only improves control accuracy, but also can adjust and correct the optimization scheme in real time to avoid large errors in the production process. The existing technology may rely on regular inspections or batch control, while the present invention can make dynamic adjustments at any time through real-time data feedback, thereby improving the response speed and stability of the system. By judging whether the parameter fluctuation index is less than the preset fluctuation threshold, if the parameter fluctuation index is less than the preset fluctuation threshold, the initial parameter optimization scheme is used as a candidate optimization scheme; if the parameter fluctuation index is not less than the preset fluctuation threshold, the multi-parameter coupling model is corrected according to the real-time parameter data, and the process returns to the step of quantitatively analyzing the coupling relationship between the initial parameters according to the multi-parameter coupling model, until the parameter fluctuation index is less than the preset fluctuation threshold, and the initial parameter optimization scheme at this time is used as a candidate optimization scheme. By setting a fluctuation threshold, it is judged whether the optimization effect meets the standard, ensuring that the parameter fluctuation does not exceed the preset range, thereby ensuring the stability and accuracy of the stamping process. If the fluctuation exceeds the threshold, it can be corrected in time. This mechanism improves the adaptability of the stamping process. Traditional technology The optimization and control of intraoperative parameters often rely on fixed standards and are difficult to flexibly adjust according to real-time conditions. The present invention, by setting a fluctuation threshold, can judge the effect in real time after each round of optimization, thereby adjusting the system more accurately and improving process control capabilities. By correcting the multi-parameter coupling model according to real-time data, the model can be dynamically adjusted to ensure that the model is consistent with the actual situation. Each time the model is corrected through parameter data feedback, the accuracy of the model can be gradually improved, making the optimization results more accurate and reliable. Existing technologies often rely on fixed models and rules for optimization and lack a dynamic adjustment mechanism. The present invention corrects the coupling model through real-time data feedback, making the entire optimization process more flexible and able to continuously adapt to changes in the production environment, ultimately obtaining a more stable and accurate optimization solution.

[0023] In one embodiment, the step S1 of constructing a multi-parameter coupling model according to each of the initial parameter values ​​includes: S11. Constructing a parameter sample set according to the multiple initial parameter values, wherein the parameter sample set includes multiple sample points, each sample point being a normalized initial parameter value; S12, performing dimensionality reduction processing on the parameter sample set and extracting a plurality of main components using a principal component analysis method, and constructing a multi-parameter coupling initial model based on the plurality of main components; S13, dividing the parameter sample set into training parameter samples and testing parameter samples; S14. Training and testing the multi-parameter coupling initial model are performed according to the training parameter samples and the test parameter samples until the mean square error of the multi-parameter coupling initial model is less than a preset error threshold, thereby obtaining the multi-parameter coupling initial model.

[0024] As described in the above steps S11-S14, before constructing the parameter sample set according to the multiple initial parameter values, the initial parameters need to be normalized, the parameter values ​​are mapped to the interval [0, 1], and the input layer and hidden layer of the multi-parameter coupling initial model are constructed according to the extracted main components. The number of neurons in the input layer is determined by the number of main components extracted (that is, the number of main components obtained by the principal component analysis method). The number of layers and the number of neurons in each layer of the hidden layer are empirical structural designs based on the scale of the input layer. The number of neurons in the input layer is the number of main components. The hidden layer includes 2-3 layers, and each layer of neurons The number of neurons is 1.5-2 times the number of neurons in the input layer. The training samples are 70%-80% of the sample set, and the test samples are 20%-30% of the sample set. The learning rate is set to 0.01-0.1, and the number of training iterations is 1000-5000. The main components are extracted through dimensionality reduction to solve the problem of high dimension and strong correlation of the original parameters, providing concise and complete features for model input. The input layer directly uses the number of main components as the dimension, and the hidden layer is designed based on the scale of the input layer. The coupling relationship between the main components is learned through a multi-layer network, and finally an initial model that can reflect the association of multiple parameters is constructed; The present invention constructs a parameter sample set through multiple initial parameter values, wherein the parameter sample set includes multiple sample points, each sample point is a normalized initial parameter value, and the first step in constructing the parameter sample set is to form a sample set through multiple initial parameter values. The key to this process is to collect enough initial parameter data to cover the diversity of the system and avoid relying on a single working condition or set parameter, thereby improving the system's adaptability to different processing conditions. This is different from the prior art that usually relies on a single set value, and can fully capture the variable factors in the stamping process. This method helps to build a more comprehensive model and enhance the generalization ability and Robustness. The normalization step aims to unify parameter values ​​of different dimensions or ranges into a standard scale, eliminating numerical deviations caused by dimensional differences between different parameters. Since the stamping process involves multiple parameters (such as punch speed, pressure, stroke depth, plate positioning accuracy, etc.), the value ranges of these parameters may vary greatly. If normalization is not performed, some parameters with a large numerical range may dominate the subsequent calculations, thereby affecting the stability and accuracy of the model. After normalization, the contribution weights of all parameters tend to be consistent, making the impact of each parameter on the dimensionality reduction analysis more balanced, thereby improving the overall performance and accuracy of the model; By using principal component analysis to reduce the dimensionality of the parameter sample set and extract multiple main components, principal component analysis can map high-dimensional data sets to low-dimensional space through linear transformation, thereby reducing redundant information in the data, improving computational efficiency, and retaining the main features of the original data. In the stamping control system, the multiple parameters involved may have strong correlations, and these correlations may lead to multicollinearity problems, making it difficult for traditional methods to handle them effectively. Principal component analysis can extract a group of unrelated principal components, representing the direction of the maximum variance in the data, thereby simplifying the complexity of the model and improving the computational efficiency of the model when processing high-dimensional data. Compared with the traditional single parameter adjustment method in the existing technology, principal component analysis can not only extract the most important features, but also reduce the computational time. The calculation amount makes the multi-parameter coupling model more efficient, avoids the problem of high computational complexity, and constructs a multi-parameter coupling initial model based on multiple main components. The multi-parameter coupling initial model based on multiple main components can effectively reduce the dimension and complexity of the model while retaining most of the information. By taking multiple main components as input, a model integrating the influence of multiple parameters is constructed, which can capture the interaction between the various parameters in the stamping process. Compared with the existing technology of adjusting a single parameter one by one, this method can simultaneously consider the comprehensive influence of multiple parameters on the stamping process, thereby avoiding the chain reaction caused by the adjustment of a single parameter. This multi-parameter coupling model can find more accurate solutions in a higher-dimensional control space, thereby improving the stability and processing accuracy of the system; By dividing the parameter sample set into training parameter samples and test parameter samples, the multi-parameter coupling initial model is trained and tested by the training parameter samples and the test parameter samples until the mean square error of the multi-parameter coupling initial model is less than the preset error threshold, and the multi-parameter coupling initial model is obtained. Dividing the data set into training samples and test samples is a standard step in the machine learning and modeling process. By dividing the data into training sets and test sets, overfitting can be effectively avoided to ensure that the model does not only remember the noise of the data during training, but can learn the potential laws of the data. The training samples are used to adjust the parameters of the model, and the test samples are used to evaluate the generalization ability of the model. This step ensures the consistency of the model's performance on different data sets and improves the reliability and applicability of the model. In the traditional single parameter adjustment method, due to the lack of an effective test verification process, it may lead to over-reliance on specific parameter values ​​and inability to fully adapt to different working conditions. The performance of the multi-parameter coupling model is continuously optimized through the training and testing process until the mean square error of the model is lower than the preset error threshold. The mean square error is commonly used in regression analysis. The measurement index can effectively evaluate the prediction accuracy of the model in practical applications. In this step, by continuously optimizing and adjusting the model parameters, it can ensure that the model maintains a high accuracy under the interaction of multiple parameters, thereby improving the stability and quality of the stamping control system. Unlike the adjustment method in the existing technology that relies only on intuition and experience, this step adopts a scientific training and verification mechanism to ensure that the output of the model is more reliable and avoids system fluctuations or failures caused by improper parameter adjustment. By continuously iterating training and testing until the model error is lower than the preset threshold, it can ensure that the model can give more accurate predictions and adjustment suggestions under all possible working conditions. This iterative optimization process can gradually approach the global optimal solution of the system, thereby avoiding the error accumulation and system instability caused by local parameter optimization in traditional methods. In the control of high-precision CNC punching machines, it is crucial to ensure the prediction accuracy of each step and the stability of the adjustment strategy. Through multiple rounds of training, the model can not only adapt to a single working condition, but also cope with complex multi-parameter coupling scenarios, thereby greatly improving the processing capability of the system.

[0025] In one embodiment, the step S2 of performing quantitative analysis on the coupling relationship between the initial parameters according to the multi-parameter coupling model to obtain a parameter coupling coefficient matrix includes: S21, constructing a deep belief network according to the initial parameter values ​​of the multi-parameter coupling model, and inputting the normalized initial parameter values ​​in the multi-parameter coupling model into the visible layer of the deep belief network; S22. Train the hidden layer of the deep belief network layer by layer through a greedy algorithm, and obtain the activation probability of the hidden layer based on the data of the visible layer; S23. Obtain reconstructed visible layer data according to the activation probability of the hidden layer, and update the network weights and bias according to the difference between the reconstructed visible layer data and the original visible layer data; S24, extracting the weight matrix of each layer of the deep belief network after training is completed, and calculating the parameter coupling coefficient according to each weight matrix, wherein the calculation formula is: ; =1,2,,,, , k≠j;

[0026] in, Representation parameters The parameter coupling coefficient with parameter j, Representation parameters and the weight value of parameter j in the weight matrix, Representation parameters With parameters (All other parameters) The maximum value among the weight values ​​in the weight matrix is ​​used for normalization to eliminate the dimension effect. i, j, and k all represent the parameter numbers; S25. Arrange the multiple parameter coupling coefficients in parameter order to construct a parameter coupling coefficient matrix.

[0027] As described in the above steps S21-S25, the structure of the initialized deep belief network includes 1 visible layer and 3-5 hidden layers. The number of neurons in the visible layer is the total number of initial parameters, and the number of neurons in the hidden layer decreases layer by layer. The number of neurons in each layer is 0.5-0.8 times that of the previous layer to achieve layer-by-layer extraction and compression of parameter features; the training parameters of the deep belief network are set, and the training parameters include a learning rate of 0.001-0.01, which is used to control the step size of the network parameter update to avoid convergence oscillation or too slow, and a training batch size of 32-64. The input data is divided into multiple batches for training to balance training efficiency and model stability. Qualitatively, the number of training iterations is 500-1000 times to ensure that the network fully learns the coupling characteristics between parameters until the model converges; the hidden layer is trained layer by layer through the greedy algorithm, and only the connection parameters of the current layer and the previous layer are trained each time, ignoring the influence of other layers, so as to achieve hierarchical optimization. During the training process, the contrast divergence algorithm is used to update the network parameters. The steps of the contrast divergence algorithm are: first, the activation probability of the hidden layer is calculated according to the visible layer data (implemented by the Sigmoid activation function, which is used for depth information). The function of calculating the hidden layer activation probability during the deep belief network training process is to map the input value to the interval [0,1] to quantify the correlation strength between the parameters), and then reversely reconstruct the visible layer data according to the activation probability of the hidden layer, simulate the reverse transmission of the parameter features, and finally calculate the difference (error value) between the original visible layer data and the reconstructed visible layer data, and update the network weights and biases based on the difference by gradient descent method to minimize the reconstruction error. In the weight matrix of each layer of the deep belief network, the weight matrix reflects the connection strength between different parameters. Each element represents the connection strength between the corresponding two parameters (or features). The larger the value, the better. The more significant the coupling relationship between the two, each element in the parameter coupling coefficient matrix represents the degree of mutual influence between the corresponding two parameters. Among them, the coupling coefficient between the punch speed and the pressure is calculated by the ratio of the punch speed change to the pressure change. The coupling coefficient between the pressure and the stroke depth is determined by the product of the pressure fluctuation value and the stroke depth deviation value. The coupling coefficient between the stroke depth and the plate positioning accuracy is calculated by the difference between the actual value and the theoretical value of the stroke depth and the mean square error of the plate positioning accuracy. Each element in the parameter coupling coefficient matrix intuitively reflects the degree of mutual influence between the corresponding two parameters, thereby completing the quantitative analysis of the coupling relationship between the initial parameters. The present invention constructs a deep belief network through the initial parameter values ​​of the multi-parameter coupling model, and inputs the normalized initial parameter values ​​in the multi-parameter coupling model into the visible layer of the deep belief network. In the existing CNC punching machine intelligent control system, it usually relies on a single control parameter or a combination of certain parameters to adjust the system performance. However, there is a complex coupling relationship between multiple parameters (such as punch speed, pressure, stroke depth, etc.) in the stamping process. It is difficult for traditional control methods to integrate the multi-dimensional information of these parameters and optimize the combination of each parameter to ensure the acquisition of the global optimal solution. The present invention uses the initial parameter values ​​of the multi-parameter coupling model as input to construct a deep belief network, which can be trained The network is trained to simultaneously consider the mutual influence of multiple parameters, thereby avoiding the chain reaction that may be caused by the adjustment of a single parameter, thereby improving the system's overall optimization ability for the coupling of multiple parameters and providing higher stability and reliability. Through normalization, the initial parameter values ​​will be converted to a unified scale, which can avoid the unnecessary impact of dimensional differences of different parameters on network training. The normalized data helps to accelerate the training process and improve the convergence speed and accuracy of the network. Since the parameters involved in the punching operation vary greatly, this process ensures that the deep belief network can effectively capture the complex relationship between parameters, thereby reducing the error caused by data inconsistency; The hidden layers of a deep belief network are trained layer by layer using a greedy algorithm. This is a common strategy in deep belief network training. In each layer, the greedy algorithm first trains the connection from the visible layer to the hidden layer, thus avoiding the gradient vanishing problem in complex backpropagation training. For the intelligent control of high-precision CNC punching machines, greedy algorithm layer-by-layer training can better capture the hierarchical structure between each layer and gradually extract high-order features from the data. Compared with traditional end-to-end training methods, this strategy reduces training time and improves model stability and accuracy. It can effectively avoid model overfitting, especially when dealing with complex parameter coupling problems. Obtaining the activation probability of the hidden layer based on the visible layer data, and obtaining the reconstructed visible layer data through the hidden layer activation probability, and obtaining the activation probability of the hidden layer through the visible layer data, means that the deep belief network does more than just predict or reconstruct; it can also reflect the "confidence" or "importance" of each layer of the network when processing data. In the application scenario of high-precision CNC punching machines, obtaining the activation probability of the hidden layer provides key data support for subsequent parameter optimization. For example, the impact of some stamping parameters may not be significant, while others may have a significant impact on the final stamping result. The activation probability system can more intelligently focus on those parameters that have a greater impact on stamping accuracy, thereby improving the intelligent adjustment capability during the processing process. By obtaining the reconstructed visible layer data, the system can self-correct and optimize parameter adjustment. The reconstruction error (i.e., the difference between the original visible layer data and the reconstructed data) can identify error sources and potential problems in parameter adjustment. In the existing technology, due to the lack of an effective error feedback mechanism, minor processing defects may occur during the stamping process, and these defects cannot be discovered in real time. However, by using the reconstruction error, the deep belief network can optimize stamping parameters in real time during each process, reducing error accumulation and maintaining processing accuracy. The network weights and biases are updated by reconstructing the difference between the visible layer data and the original visible layer data, and the network weights and biases are updated by the error, so that the network can learn a more accurate parameter coupling relationship. In the control of high-precision punching machines, small errors in parameter adjustment may lead to processing instability or defects. Existing control methods often ignore the comprehensive influence of multiple parameters. This parameter update method based on error feedback allows the system to adjust each parameter in real time to obtain better stamping performance. Unlike the existing technology that adjusts each parameter separately, the feedback update method based on the deep belief network can more accurately optimize the interaction between multiple parameters, thereby achieving a global optimal solution. By extracting the weight matrix of each layer of the deep belief network after training is completed, and calculating the parameter coupling coefficient according to each weight matrix, the control methods in the existing technology mostly rely on manually set rules or empirical formulas, and lack dynamic adjustment capabilities. The present invention uses the training of the deep belief network and the weight matrix The extraction can automatically obtain the coupling coefficients between different parameters, which reflect the dependency between the parameters. Compared with the traditional fixed rule method, the deep belief network can self-learn and dynamically adjust the parameter coupling coefficients according to the real-time processing data, so that the punching system can achieve optimal performance under different working conditions. By arranging multiple parameter coupling coefficients in parameter order, a parameter coupling coefficient matrix is ​​constructed. In high-precision CNC punching machines, the interaction between multiple parameters is difficult to describe and optimize through traditional single control parameters. The present invention constructs a parameter coupling coefficient matrix. When facing a variety of complex stamping conditions, the system can directly use these coefficients to adjust the parameter settings, thereby improving the stability and precision of the processing. Compared with the potential chain reaction brought about by the adjustment of a single parameter in the prior art, the present invention can optimize the global performance of the system, reduce processing defects, and improve stamping stability on the basis of considering the mutual influence of multiple parameters.

[0028] In one embodiment, the step S3 of solving the multi-parameter collaborative optimization objective function to obtain an initial parameter optimization solution includes: S31, inputting each of the initial parameter values ​​into the multi-parameter collaborative optimization objective function to obtain multiple fitness values, and selecting the initial parameter value corresponding to the minimum fitness value from the multiple fitness values ​​as the individual optimal position; S32, selecting an initial parameter value corresponding to the minimum fitness value from the multiple individual optimal positions as the global optimal position, and obtaining a global optimal position deviation based on the global optimal position and the individual optimal position; S33, obtaining a historical optimal position of the initial parameter value corresponding to each of the individual optimal positions, and obtaining an individual optimal position deviation based on the historical optimal position and the individual optimal position; S34, obtaining the current speed of the initial parameter value corresponding to each individual optimal position, and obtaining the update speed of the corresponding initial parameter value according to the current speed, the individual optimal position deviation and the global optimal position deviation; S35. Obtain an updated position according to the update speed and the individual optimal position, and obtain an initial parameter optimization solution according to the updated position and the update speed.

[0029] As described in the above steps S31-S35, before each of the initial parameter values ​​is input into the multi-parameter collaborative optimization objective function, it is necessary to determine the position and velocity of the initialized particle group. The position vector of the particle (initial parameter value) represents a set of parameter combinations to be optimized (clusters), namely, the core punching parameters of high-precision CNC punching machines such as the initial speed of the punch, the initial pressure, the initial stroke depth, and the initial positioning accuracy of the plate. The velocity vector of the particle is used to represent the rate of parameter adjustment. Since the initial parameter value is a high-precision combination of the initial speed of the punch, the initial pressure, the initial stroke depth, and the initial positioning accuracy of the plate, The cluster of core parameters of the punching machine is a collection of dense CNC punch presses. Therefore, when the multi-parameter collaborative optimization objective function is input, the fitness value corresponding to each core punching parameter will be obtained. The smaller the fitness value, the closer the parameter combination corresponding to the particle is to the global optimal solution. The current fitness value of each particle is compared with the historical fitness value, and the position corresponding to the minimum fitness value is determined as the individual optimal position of the particle. Among the individual optimal positions of all particles, the position with the minimum fitness value is selected as the global optimal position. Based on the output fitness value results, the preliminary screening of local and global optimality is completed, providing direction for subsequent parameter iteration; The formula for update speed is: ;in, Indicates the At the first iteration, The particle in The speed in the parameter dimension, represents the inertia weight, Indicates the current iteration number, Indicates the At the first iteration, The particle in The current position in the parameter dimension, represents the first learning factor, represents the second learning factor, represents the first random number in the interval [0, 1], represents the second random number in the interval [0, 1], which guides the particles to move towards the individual optimal and global optimal directions respectively. Indicates the The particle in The optimal position of an individual in the parameter dimension, Indicates that all particles in The global optimal position in the parameter dimension; The formula for updating the position is: ; Adjust the particle position based on the updated speed to achieve iterative optimization of the parameter combination. The updated position is the superposition of the current position of the particle and the new speed. The essence is to convert the parameter adjustment trend represented by the speed into an actual parameter value change, so that the particle moves to a better position in the parameter space. Before the step of obtaining the updated position according to the updated speed and the individual optimal position, it is also necessary to judge the iteration termination condition. Specifically, if the current number of iterations reaches the preset maximum value, the iteration is stopped, and the parameter combination corresponding to the global optimal position is output as the initial parameter optimization solution. If the termination condition is not met, return to recalculate the fitness value and repeat the iterative steps until the termination condition is met. The present invention obtains multiple fitness values ​​by inputting each initial parameter value into the multi-parameter collaborative optimization objective function. Compared with the traditional single parameter adjustment method, the present invention can more comprehensively consider the relationship and influence between each parameter by inputting multiple parameters into the collaborative optimization objective function, avoiding system instability or local optimal solution that may be caused by single parameter adjustment. Traditional technology often takes a certain parameter as the main optimization target and ignores the linkage effect of other parameters. The present invention solves the chain reaction problem caused by single parameter adjustment by considering multiple parameters at the same time, so that the system can more comprehensively and accurately find the optimal parameter combination, and select the initial parameter value corresponding to the minimum fitness value from multiple fitness values ​​as the individual optimal position. By evaluating multiple fitness values, the initial parameter value corresponding to the minimum fitness value is selected as the individual optimal position, which ensures that the system can always move towards the minimization target during the optimization process, thereby improving optimization efficiency and accuracy. Traditional optimization methods may fall into local optimality, but the present invention avoids this situation by selecting the minimum fitness value, which helps to ultimately find the global optimal solution; By selecting the initial parameter value corresponding to the minimum fitness value from multiple individual optimal positions as the global optimal position, and obtaining the global optimal position deviation based on the global optimal position and the individual optimal position, the present invention ensures the acquisition of the global optimal solution by selecting the parameter with the minimum fitness value from multiple individual optimal positions. Compared with the traditional method that may only consider the local optimum of the individual, the present invention can integrate the information of all individuals and improve the stability and performance of the overall system. By selecting the global optimal position, the system can achieve collaborative optimization in multiple dimensions, avoiding the limitations of a single dimension. The deviation between the global optimal position and the individual optimal position is calculated, so that the optimization process can compare the difference between the global and local optima, and further refine the optimization path. This deviation calculation can guide the adjustment pace in the optimization process, making the parameter adjustment more precise and efficient. Through the calculation and feedback of the deviation, the pace can be dynamically adjusted in the optimization process to avoid over-adjustment or slow adjustment, thereby improving the convergence speed of the optimization algorithm. By obtaining the historical optimal position of the initial parameter value corresponding to each individual optimal position, and obtaining the individual optimal position deviation based on the historical optimal position and the individual optimal position, by introducing the data of the historical optimal position, past optimization experience can be utilized to make the current optimization process more intelligent and reduce the possibility of blind adjustment. This is more efficient than the existing method of simply relying on real-time data. By considering the historical optimal position, the optimization algorithm not only relies on the current optimization state, but also can balance past successful experience, thereby avoiding overfitting or local optimal phenomena under certain special conditions. By obtaining the current speed of the initial parameter value corresponding to each individual optimal position, and obtaining the update speed of the corresponding initial parameter value based on the current speed, the individual optimal position deviation and the global optimal position deviation, the present invention calculates the update speed by combining the current speed, the individual optimal deviation and the global optimal deviation, thereby ensuring the flexibility and adaptability of parameter adjustment. Compared with the traditional fixed update step size method, the present invention can automatically adjust the optimization speed according to the real-time situation, making the parameter update more accurate and reducing the instability caused by too large or too small step size. By adjusting the update speed, the problem of system oscillation or low optimization efficiency caused by improper update step size is avoided, thereby improving the overall optimization stability. The updated position is obtained by updating the speed and the individual optimal position, and the initial parameter optimization scheme is obtained according to the updated position and the update speed. By combining the update speed and the individual optimal position for position update, the final value of each parameter can be further optimized, so that the optimization process not only depends on the global optimum, but also takes into account the influence of each local optimal position, thereby avoiding the adverse effects that may be caused by the local optimum. The present invention ensures that the dynamic characteristics of the speed adjustment are taken into account when obtaining the updated position, thereby avoiding the limitations of a single static optimization method, and enabling the final optimization scheme to remain efficient and stable during long-term operation. Compared with the traditional adaptive parameter adjustment control method, the multi-parameter collaborative optimization method of the present invention avoids the chain reaction problem caused by a single parameter adjustment by comprehensively considering the mutual influence between multiple parameters and the dynamic adjustment mechanism, so that the system can find the global optimal solution and significantly improve the processing stability. By combining factors such as the historical optimal position, the current speed, the deviation between the local and global optimality, the present invention can effectively improve the optimization efficiency, avoid overfitting or local optimality, and ultimately achieve more efficient and stable intelligent stamping control.

[0030] In one embodiment, the step S5 of obtaining the parameter fluctuation index according to the real-time data of the plurality of parameters includes: S51, preprocessing the real-time data of each parameter to obtain corresponding standard parameter data; S52, obtaining multiple initial parameter values ​​in the initial parameter optimization solution, and obtaining corresponding parameter deviation values ​​according to each of the initial parameter values ​​and the standard parameter data; S53. Obtain a parameter deviation square sum according to the plurality of parameter deviation values, and obtain a parameter fluctuation index according to the parameter deviation square sum.

[0031] As described in the above steps S51-S53, wherein the fluctuation index is the square root of the sum of squares of parameter deviations, the present invention obtains corresponding standard parameter data by preprocessing the real-time data of each parameter. The preprocessing of real-time data can effectively filter out interference factors caused by changes in the external environment or the noise of the equipment itself, thereby ensuring the accuracy and reliability of the data. By converting real-time data into standard parameter data, a stable benchmark can be provided for the subsequent optimization process. Compared with the existing technology, it avoids the direct use of unprocessed real-time data, which may cause fluctuations or deviations in the calculation results. Therefore, the accuracy of the system can be improved through preprocessing, and the error caused by unstable data in the stamping process can be reduced, which effectively improves the processing accuracy. By obtaining multiple initial parameter values ​​in the initial parameter optimization scheme, and obtaining corresponding parameter deviation values ​​according to each initial parameter value and the standard parameter data, multiple initial parameters are obtained. The purpose of the present invention is to ensure that all possible parameter ranges are covered in the optimization process, rather than relying solely on a single initial value. By introducing multiple initial parameter values, the present invention provides a variety of options for parameter adjustment during the optimization process, thereby avoiding the local optimal problem, increasing the probability of finding the global optimal solution, and improving the comprehensive performance of the stamping control. The deviation value between each initial parameter value and the standard parameter data is obtained by quantifying the deviation to measure the gap between the current system state and the target state, so that the system can accurately track the impact of each parameter on the final processing result. Compared with the traditional adaptive control method, a single parameter adjustment often ignores the relationship between the parameters, which can easily lead to inaccurate adjustment and non-optimal control effects. By obtaining the deviation value of each parameter in real time, the present invention can more accurately analyze and diagnose the impact of each parameter on the stamping process, thereby providing a refined basis for subsequent adjustments.The sum of squares of parameter deviations is obtained through multiple parameter deviation values, and the parameter fluctuation index is obtained based on the sum of squares of parameter deviations. The sum of squares of parameter deviations is calculated through multiple parameter deviation values. The use of the sum of squares method can more comprehensively reflect the overall deviation between parameters, avoid the excessive influence of a single parameter on the overall performance, not only consider the deviation of individual parameters, but also comprehensively consider the influence of multiple parameters, and can optimize the overall state of the system. In the prior art, many methods simply rely on the adjustment of a key parameter, which may ignore the influence of other parameters, resulting in an imbalance in the optimization results. Through the sum of squares method, the present invention provides a method that comprehensively considers the interaction of all parameters, which can more effectively balance multiple variables in the stamping process, reduce system imbalance caused by local adjustments, and the parameter fluctuation index. This method can quantify the fluctuations of the entire system. As a key indicator of stamping stability, the value of the fluctuation index can reflect the stability of the system in real time. By monitoring its changing trend, it can respond promptly to abnormal fluctuations in the stamping process. Traditional adaptive control systems often rely too much on the fluctuation of a single parameter and ignore the overall fluctuation of multiple parameters. The present invention combines the fluctuations of multiple parameters into a single overall indicator through the fluctuation index, which can more comprehensively and accurately monitor and adjust the stability of the stamping process, effectively avoiding processing defects caused by parameter fluctuations and improving processing quality. By comprehensively considering the deviations and fluctuations of all parameters, it achieves comprehensive optimization at the system level, ensures the coordination between multiple parameters, and effectively improves the processing stability of high-precision CNC punching machines.

[0032] In one embodiment, the step S5 of correcting the multi-parameter coupling model according to the real-time parameter data includes: S54: Input each of the initial parameter values ​​into a multi-parameter coupling model to obtain first predicted parameter data, and obtain corresponding parameter residuals based on the first predicted parameter data and parameter real-time data; S55, fitting the parameter residuals using the least squares method to obtain a residual model, and adding the residual model to the multi-parameter coupling initial model to obtain a revised multi-parameter coupling model; S56, inputting each of the initial parameter values ​​into the modified multi-parameter coupling model to obtain second prediction parameter data; S57, obtaining an actual parameter value of each of the initial parameter values ​​under a preset stamping working condition, and obtaining a corresponding absolute deviation based on a difference between each of the actual parameter values ​​and the second predicted parameter data; S58. Obtain a root mean square error according to the multiple absolute deviations, and determine whether the root mean square error is greater than a preset error threshold; If the root mean square error is greater than the preset error threshold, it is determined that the modified multi-parameter coupling model verification fails, and the process returns to the step of fitting the parameter residuals using the least squares method to obtain a residual model until the root mean square error is no greater than the preset error threshold; If the root mean square error is not greater than the preset error threshold, it is determined that the modified multi-parameter coupling model has passed the verification.

[0033] As described in the above steps S54-S58, the present invention obtains first predicted parameter data by inputting each initial parameter value into the multi-parameter coupling model, and obtains corresponding parameter residuals based on the first predicted parameter data and the parameter real-time data. The present invention comprehensively considers multiple interacting parameters (such as punch speed, pressure, stroke depth, plate positioning accuracy, etc.) through the multi-parameter coupling model, and more accurately reflects the multi-dimensional dynamic characteristics of the entire stamping process. This approach can avoid the chain reaction that may be caused by the adjustment of a single parameter, provide more comprehensive preliminary prediction results, and break the bottleneck of traditional methods being limited to single parameter optimization. The residual is generated by comparing the first predicted parameter data with the real-time data. The residual reflects the deviation between the prediction and the actual result, can directly reflect the deviation size of the current model, and provides a basis for subsequent model adjustment by quantizing the error. Traditional adaptive control methods may only focus on real-time correction of a single parameter without fully considering the complex interactive relationship between multiple parameters. The residual calculation of the present invention enables us to capture these complex deviations and provides a basis for more accurate correction; The residual model is obtained by fitting the parameter residuals using the least squares method, and the residual model is added to the multi-parameter coupling initial model to obtain the revised multi-parameter coupling model. The residuals are fitted using the least squares method, which can accurately obtain the optimal parameters of the revised model, minimize the residuals, and further improve the prediction accuracy. Unlike the simple linear or empirical models that may be used in traditional methods, the least squares method can adapt to the multivariate errors of complex systems through a rigorous mathematical optimization process, ensuring the efficiency and accuracy of model correction. By combining the differences between the preliminary predictions and the actual observations, a revised model that is closer to the actual working conditions is generated. Compared with the local correction of traditional methods, this correction method has stronger global adaptability and can dynamically adjust the overall model according to the mutual influence of multiple parameters, thereby effectively improving the control accuracy and avoiding the instability caused by the adjustment of a single parameter. By inputting each initial parameter value into the revised multi-parameter coupling model to obtain the second predicted parameter data, by obtaining the actual parameter value of each initial parameter value under the preset stamping working condition, and obtaining the corresponding absolute deviation according to the difference between each actual parameter value and the second predicted parameter data, the revised model is input for new prediction, which can verify the effect of the model adjustment. Through continuous correction and prediction verification, it is ensured that the revised model can adapt to changes in actual production. Compared with the "adjust parameter and use" mode of the traditional method, the present invention uses the revised model for re-prediction, fully considering the variability of the system and the complexity between multiple parameters, so that the prediction result is more accurate and better reflects the actual working condition. By comparing the predicted value with the actual value, the deviation of the model prediction can be accurately quantified. Unlike the traditional method that only adjusts the control strategy based on a single error threshold, this step provides a specific adjustment basis for each parameter by calculating the actual deviation, so that each parameter can be independently adjusted and monitored in real time, thereby achieving refined control, enhancing the adaptability of the model, and enabling the system to cope with different working condition changes, avoiding the system instability caused by the inability to accurately control each parameter in the traditional method; The root mean square error is obtained through multiple absolute deviations, and it is determined whether the root mean square error is greater than the preset error threshold. If the root mean square error is greater than the preset error threshold, the modified multi-parameter coupling model is determined to have failed verification, and the process returns to the step of fitting the parameter residuals using the least squares method to obtain the residual model, until the root mean square error is not greater than the preset error threshold. If the root mean square error is not greater than the preset error threshold, the modified multi-parameter coupling model is determined to have passed verification. The root mean square error is obtained through multiple absolute deviations, which can more comprehensively evaluate the accuracy of the model. Compared with the single deviation method, the root mean square error can better reflect the overall deviation of the model in multiple parameters, avoiding the wrong judgment caused by a single deviation being too large. As a comprehensive evaluation indicator, the root mean square error can more accurately reflect the actual error range of the model, thereby providing a scientific standard to judge whether the model is accurate enough, and ensure that the model is accurate in each iteration through error judgment and control. After that, the preset accuracy requirements can be achieved. Different from the traditional method, the present invention dynamically verifies the effectiveness of the correction model and uses the root mean square error to evaluate the correction effect in real time, avoiding the potential risks that may exist when the model is put into use directly after correction, ensuring that the model can be strictly verified after each adjustment, improving the accuracy and stability of the process, and avoiding the defect of the traditional method that the model is not further verified once adjusted. The model is adjusted by continuous iteration until the root mean square error reaches the preset error threshold, and finally ensuring that the corrected model can fully adapt to the actual working conditions. Different from the fixed parameter adjustment of the traditional method, the present invention provides a dynamic correction process, which enables the model to be continuously optimized and ensures high-precision stability under different working conditions. Each adjustment is precisely controlled within the error range, which can avoid over-correction while ensuring that each correction minimizes the error to the greatest extent, thereby improving the stability and accuracy of the stamping process.

[0034] The present application also provides an intelligent stamping control system for a high-precision CNC punch press, comprising: A construction module is used to obtain multiple initial parameter values ​​of the high-precision CNC punch press under a preset punching working condition, and to construct a multi-parameter coupling model according to each of the initial parameter values; a quantitative analysis module, configured to perform a quantitative analysis on the coupling relationship between the initial parameters according to the multi-parameter coupling model, obtain a parameter coupling coefficient matrix, and set a dynamic weight value for each initial parameter value according to the parameter coupling coefficient matrix; A solution module is used to construct a multi-parameter collaborative optimization objective function according to the multiple dynamic weight values, and use an improved particle swarm optimization algorithm to solve the multi-parameter collaborative optimization objective function to obtain an initial parameter optimization solution; A test module, used for inputting the initial parameter optimization scheme into a CNC punch press simulation system to perform a virtual punching test and collect real-time data of multiple parameters during the virtual punching process; a judgment module, configured to obtain a parameter fluctuation index based on the real-time data of the plurality of parameters, and to judge whether the parameter fluctuation index is less than a preset fluctuation threshold; If the parameter fluctuation index is less than the preset fluctuation threshold, the initial parameter optimization scheme is used as a candidate optimization scheme; If the parameter fluctuation index is not less than the preset fluctuation threshold, the multi-parameter coupling model is corrected according to the real-time parameter data, and the process returns to the step of quantitatively analyzing the coupling relationship between the initial parameters according to the multi-parameter coupling model until the parameter fluctuation index is less than the preset fluctuation threshold, and the initial parameter optimization scheme at this time is used as a candidate optimization scheme.

[0035] In one embodiment, the building block comprises: A first constructing unit is configured to construct a parameter sample set according to the multiple initial parameter values, wherein the parameter sample set includes multiple sample points; The second construction unit is used to perform dimensionality reduction processing on the parameter sample set by using a principal component analysis method and extract a plurality of main components, and construct a multi-parameter coupling initial model based on the plurality of main components; A division unit, configured to divide the parameter sample set into training parameter samples and testing parameter samples; The training unit is used to train and test the multi-parameter coupling initial model according to the training parameter samples and the test parameter samples until the mean square error of the multi-parameter coupling initial model is less than a preset error threshold, thereby obtaining the multi-parameter coupling initial model.

[0036] It should be noted that each module and unit in the intelligent stamping control system of the high-precision CNC punch press corresponds one-to-one to the steps in the intelligent stamping control method of the high-precision CNC punch press.

[0037] like Figure 3 As shown, the present application also provides a computer device, which can be a server, and its internal structure can be as shown in FIG. Figure 3As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. The processor of the computer design is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store all data required for the process of the intelligent stamping control method of the high-precision CNC punching machine. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the intelligent stamping control method of the high-precision CNC punching machine is realized.

[0038] Those skilled in the art will understand that Figure 3 The structure shown in is merely a block diagram of a portion of the structure related to the present application solution and does not constitute a limitation on the computer device to which the present application solution is applied.

[0039] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, any one of the above-mentioned intelligent stamping control methods for a high-precision CNC punch press is implemented.

[0040] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided in this application and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct RAM bus dynamic RAM (DRDRAM), and RAM bus dynamic RAM (RDRAM).

[0041] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, apparatus, article, or method comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, apparatus, article, or method. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, apparatus, article, or method comprising the element.

[0042] The above description is only a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. An intelligent stamping control method for a high-precision CNC punch press, characterized in that: include: Acquire multiple initial parameter values ​​of a high-precision CNC punch press under a preset punching working condition, and construct a multi-parameter coupling model based on each of the initial parameter values; Quantitatively analyzing the coupling relationship between the initial parameters according to the multi-parameter coupling model to obtain a parameter coupling coefficient matrix, and setting a dynamic weight value for each initial parameter value according to the parameter coupling coefficient matrix; Constructing a multi-parameter collaborative optimization objective function according to the plurality of dynamic weight values, and solving the multi-parameter collaborative optimization objective function using an improved particle swarm optimization algorithm to obtain an initial parameter optimization solution; Inputting the initial parameter optimization scheme into a CNC punch press simulation system to perform a virtual punching test and collecting real-time data of multiple parameters during the virtual punching process; Obtaining a parameter fluctuation index based on the real-time data of the plurality of parameters, and determining whether the parameter fluctuation index is less than a preset fluctuation threshold; If the parameter fluctuation index is less than the preset fluctuation threshold, the initial parameter optimization scheme is used as a candidate optimization scheme; If the parameter fluctuation index is not less than the preset fluctuation threshold, the multi-parameter coupling model is corrected according to the real-time parameter data, and the process returns to the step of quantitatively analyzing the coupling relationship between the initial parameters according to the multi-parameter coupling model until the parameter fluctuation index is less than the preset fluctuation threshold, and the initial parameter optimization scheme at this time is used as a candidate optimization scheme.

2. The intelligent stamping control method for a high-precision CNC punch press according to claim 1, characterized in that: The step of constructing a multi-parameter coupling model according to each of the initial parameter values ​​comprises: Constructing a parameter sample set according to the multiple initial parameter values, wherein the parameter sample set includes multiple sample points; Using principal component analysis to perform dimensionality reduction processing on the parameter sample set and extract multiple main components, and constructing a multi-parameter coupling initial model based on the multiple main components; Dividing the parameter sample set into training parameter samples and testing parameter samples; The multi-parameter coupling initial model is trained and tested according to the training parameter samples and the test parameter samples until the mean square error of the multi-parameter coupling initial model is less than a preset error threshold, thereby obtaining the multi-parameter coupling initial model.

3. The intelligent stamping control method for a high-precision CNC punch press according to claim 1, characterized in that: The step of performing quantitative analysis on the coupling relationship between the initial parameters according to the multi-parameter coupling model to obtain a parameter coupling coefficient matrix includes: Constructing a deep belief network according to the initial parameter values ​​of the multi-parameter coupling model, and inputting the normalized initial parameter values ​​in the multi-parameter coupling model into a visible layer of the deep belief network; The hidden layer of the deep belief network is trained layer by layer through a greedy algorithm, and the activation probability of the hidden layer is obtained based on the data of the visible layer; Obtain the reconstructed visible layer data based on the activation probability of the hidden layer, and update the network weights and biases based on the difference between the reconstructed visible layer data and the original visible layer data; Extracting the weight matrix of each layer of the deep belief network after training is completed, and obtaining the parameter coupling coefficient according to each weight matrix; Arrange multiple parameter coupling coefficients in parameter order to construct a parameter coupling coefficient matrix.

4. The intelligent stamping control method for a high-precision CNC punch press according to claim 1, characterized in that: The step of solving the multi-parameter collaborative optimization objective function to obtain an initial parameter optimization solution includes: Inputting each of the initial parameter values ​​into the multi-parameter collaborative optimization objective function to obtain multiple fitness values, and selecting the initial parameter value corresponding to the minimum fitness value from the multiple fitness values ​​as the individual optimal position; Selecting an initial parameter value corresponding to the minimum fitness value from the multiple individual optimal positions as the global optimal position, and obtaining a global optimal position deviation based on the global optimal position and the individual optimal position; Obtaining a historical optimal position of the initial parameter value corresponding to each of the individual optimal positions, and obtaining an individual optimal position deviation based on the historical optimal position and the individual optimal position; Obtaining the current speed of the initial parameter value corresponding to each of the individual optimal positions, and obtaining the update speed of the corresponding initial parameter value according to the current speed, the individual optimal position deviation, and the global optimal position deviation; An updated position is obtained according to the update speed and the individual optimal position, and an initial parameter optimization solution is obtained according to the update position and the update speed.

5. The intelligent stamping control method for a high-precision CNC punch press according to claim 1, characterized in that: The step of obtaining a parameter fluctuation index based on the real-time data of the plurality of parameters comprises: Preprocessing the real-time data of each parameter to obtain corresponding standard parameter data; Obtaining multiple initial parameter values ​​in the initial parameter optimization scheme, and obtaining corresponding parameter deviation values ​​according to each of the initial parameter values ​​and standard parameter data; A parameter deviation square sum is obtained according to the plurality of parameter deviation values, and a parameter fluctuation index is obtained according to the parameter deviation square sum.

6. The intelligent stamping control method for a high-precision CNC punch press according to claim 1, characterized in that: The step of correcting the multi-parameter coupling model according to the real-time parameter data includes: Inputting each of the initial parameter values ​​into a multi-parameter coupling model to obtain first predicted parameter data, and obtaining corresponding parameter residuals based on the first predicted parameter data and parameter real-time data; The parameter residuals are fitted using the least squares method to obtain a residual model, and the residual model is added to the multi-parameter coupling initial model to obtain a revised multi-parameter coupling model; Inputting each of the initial parameter values ​​into the modified multi-parameter coupling model to obtain second prediction parameter data; Obtaining an actual parameter value of each of the initial parameter values ​​under a preset stamping working condition, and obtaining a corresponding absolute deviation based on each of the actual parameter values ​​and the second predicted parameter data; Obtaining a root mean square error according to the multiple absolute deviations, and determining whether the root mean square error is greater than a preset error threshold; If the root mean square error is greater than the preset error threshold, it is determined that the modified multi-parameter coupling model verification fails, and the process returns to the step of fitting the parameter residuals using the least squares method to obtain a residual model until the root mean square error is no greater than the preset error threshold; If the root mean square error is not greater than the preset error threshold, it is determined that the modified multi-parameter coupling model has passed the verification.

7. An intelligent stamping control system for a high-precision CNC punch press, characterized in that: include: A construction module is used to obtain multiple initial parameter values ​​of the high-precision CNC punch press under a preset punching working condition, and to construct a multi-parameter coupling model according to each of the initial parameter values; a quantitative analysis module, configured to perform a quantitative analysis on the coupling relationship between the initial parameters according to the multi-parameter coupling model, obtain a parameter coupling coefficient matrix, and set a dynamic weight value for each initial parameter value according to the parameter coupling coefficient matrix; A solution module is used to construct a multi-parameter collaborative optimization objective function according to the multiple dynamic weight values, and use an improved particle swarm optimization algorithm to solve the multi-parameter collaborative optimization objective function to obtain an initial parameter optimization solution; A test module, used for inputting the initial parameter optimization scheme into a CNC punch press simulation system to perform a virtual punching test and collect real-time data of multiple parameters during the virtual punching process; a judgment module, configured to obtain a parameter fluctuation index based on the real-time data of the plurality of parameters, and to judge whether the parameter fluctuation index is less than a preset fluctuation threshold; If the parameter fluctuation index is less than the preset fluctuation threshold, the initial parameter optimization scheme is used as a candidate optimization scheme; If the parameter fluctuation index is not less than the preset fluctuation threshold, the multi-parameter coupling model is corrected according to the real-time parameter data, and the process returns to the step of quantitatively analyzing the coupling relationship between the initial parameters according to the multi-parameter coupling model until the parameter fluctuation index is less than the preset fluctuation threshold, and the initial parameter optimization scheme at this time is used as a candidate optimization scheme.

8. The intelligent stamping control system for a high-precision CNC punch press according to claim 7, characterized in that: The building blocks include: A first constructing unit is configured to construct a parameter sample set according to the multiple initial parameter values, wherein the parameter sample set includes multiple sample points; The second construction unit is used to perform dimensionality reduction processing on the parameter sample set by using a principal component analysis method and extract a plurality of main components, and construct a multi-parameter coupling initial model based on the plurality of main components; A division unit, configured to divide the parameter sample set into training parameter samples and testing parameter samples; The training unit is used to train and test the multi-parameter coupling initial model according to the training parameter samples and the test parameter samples until the mean square error of the multi-parameter coupling initial model is less than a preset error threshold, thereby obtaining the multi-parameter coupling initial model.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images