Punching die parameter optimization method and system based on demand analysis

Abstract

The present invention discloses a method and system for optimizing sheet die parameters based on demand analysis, which relates to the technical field related to die optimization. The method comprises: receiving a sheet die demand instruction; performing variable coupling cleaning on A-dimensional sheet die parameter variables according to predetermined variable coupling constraint values; performing backtracking registration of sheet die parameters to generate a registered sheet die solution; performing variation optimization on the registered sheet die solution in combination with a sheet die variation optimization dual channel to generate a sheet die variation optimization domain; performing deep optimization according to a second sheet die optimization rule to determine a sheet die parameter optimization solution. The method solves the technical problems existing in existing die parameter optimization, such as inaccurate acquisition of die parameter variables and parameter mismatch, which lead to poor parameter optimization effect and unstable die performance quality, and optimizes die parameters to achieve the technical effect of improving die performance and stability.

Description

Technical Field

[0001] The present application relates to the field related to mold optimization technology, and specifically to a method and system for optimizing punching mold parameters based on demand analysis. Background Art

[0002] With the continuous advancement of industrial technology, punching dies, as key tools in the manufacturing field, have a direct impact on the performance and quality of products in terms of production efficiency, precision and cost. Parameter optimization of punching dies is a crucial technological innovation in the manufacturing industry. As modern industry continues to increase its requirements for product quality and production efficiency, performance optimization of punching dies is particularly critical. However, traditional punching die designs are often based on experience and trial and error, making it difficult to accurately meet complex and changing market demands, and unable to meet the high requirements for precision and stability of punching dies. On the other hand, existing dies are difficult to adapt to continuous high-speed production environments, resulting in a shortened service life of the dies.

[0003] Therefore, in the current technologies related to mold parameter optimization, there are technical problems such as inaccurate acquisition of mold parameter variables and parameter mismatch, which lead to poor parameter optimization effects and unstable mold performance and quality. Summary of the Invention

[0004] This application provides a punching die parameter optimization method and system based on demand analysis, and adopts technical means such as variable coupling cleaning and backtracking alignment to solve the technical problems of inaccurate mold parameter variable acquisition and parameter mismatch in existing mold parameter optimization, resulting in poor parameter optimization effect and unstable mold performance quality. It optimizes mold parameters and achieves the technical effect of improving mold performance and stability.

[0005] The present application provides a method for optimizing punching die parameters based on demand analysis, the method comprising: receiving a punching die demand instruction, wherein the punching die demand instruction includes punching die operation scene characteristic data, wherein the punching die operation scene characteristic data includes stamping process characteristic data, stamping material characteristic data and stamping process environment characteristic data; performing variable coupling cleaning on A-dimensional punching die parameter variables according to predetermined variable coupling constraint values to generate B-dimensional punching die parameter variables, wherein A and B are both positive integers greater than 1, and B is less than or equal to A; performing backtracking alignment of punching die parameters according to the punching die operation scene characteristic data and the B-dimensional punching die parameter variables to generate an aligned punching die scheme; performing variation optimization on the aligned punching die scheme according to a first punching die optimization rule and in combination with a punching die variation optimization dual channel to generate a punching die variation optimization domain; performing deep optimization on the punching die variation optimization domain according to a second punching die optimization rule to determine a punching die parameter optimization scheme.

[0006] In a possible implementation, variable coupling cleaning is performed on the A-dimensional punching die parameter variables according to a predetermined variable coupling constraint value to generate a B-dimensional punching die parameter variable, wherein A and B are both positive integers greater than 1, and B is less than or equal to A, and the following processing is performed: randomly extract the first punching die parameter variable and the second punching die parameter variable from the A-dimensional punching die parameter variable; perform variable coupling analysis on the first punching die parameter variable and the second punching die parameter variable to obtain a first die variable coupling index; determine whether the first die variable coupling index is less than / equal to the predetermined variable coupling constraint value; if the first die variable coupling index is less than / equal to the predetermined variable coupling constraint value, add the first die parameter variable and the second die parameter variable to the B-dimensional punching die parameter variable.

[0007] In a possible implementation, it is determined whether the first mold variable coupling index is less than / equal to the predetermined variable coupling constraint value, and the following processing is performed: if the first mold variable coupling index is greater than the predetermined variable coupling constraint value, a variable coupling warning signal is generated; the first punching mold parameter variable and the second punching mold parameter variable are subjected to variable fusion according to the variable coupling warning signal to generate a first fused punching mold parameter variable; the first fused punching mold parameter variable is added to the B-dimensional punching mold parameter variable.

[0008] In a possible implementation, the punching mold parameters are retrospectively aligned according to the punching mold operation scene feature data and the B-dimensional punching mold parameter variables to generate an aligned punching mold scheme, and the following processing is also performed: the punching mold parameter record library is retrieved, wherein the punching mold parameter record library includes multiple groups of punching mold parameter records, and each group of punching mold parameter records includes sample punching mold operation scene feature data and sample punching mold parameter schemes; based on the punching mold operation scene feature data, operation scene twin identification is performed on each sample punching mold operation scene feature data in the punching mold parameter record library to generate multiple mold operation scene twin coefficients; the winning mold operation scene twin coefficient is screened according to the multiple mold operation scene twin coefficients; based on the punching mold parameter record library, the winning sample punching mold parameter scheme is matched according to the winning mold operation scene twin coefficient, and the aligned punching mold scheme is feature fused according to the B-dimensional punching mold parameter variables to obtain the aligned punching mold scheme.

[0009] In a possible implementation, according to the first punching die optimization rule, the punching die variation optimization dual channel is combined to perform variation optimization on the registration punching die scheme to generate a punching die variation optimization domain, and the following processing is also performed: a mold operation scene fitness prediction module is built, wherein the mold operation scene fitness prediction module includes a multi-dimensional mold operation scene fitness prediction index, and the multi-dimensional mold operation scene fitness prediction index includes mold operation process fitness, mold operation material fitness and mold operation environment fitness; according to the mold operation scene fitness prediction module, a multi-dimensional fitness prediction is performed on the punching die operation scene feature data and the registration punching die scheme to obtain a first scheme fitness prediction result; it is judged whether the first scheme fitness prediction result meets the first punching die optimization rule, wherein the first punching die optimization rule includes a multi-dimensional mold operation scene fitness constraint, and the multi-dimensional mold operation scene fitness constraint includes a mold operation process fitness constraint, a mold operation material fitness constraint and a mold operation environment fitness constraint. Material fitness constraints and mold operating environment fitness constraints; if the fitness prediction result of the first scheme meets the first punching mold optimization rule, the registered punching mold scheme is used as the punching mold variation benchmark scheme, and the punching mold variation benchmark scheme is added to the punching mold variation optimization domain; activate the first punching mold variation optimization channel in the punching mold variation optimization dual channels, wherein the first punching mold variation optimization channel includes a first punching mold variation operator, and the first punching mold variation operator includes a first mold variation dimension threshold, a first mold variation asynchronous advancement threshold and a first mold variation capacity threshold; according to the first punching mold variation optimization channel, the punching mold variation benchmark scheme is mutated and adjusted to generate a first punching mold variation space; with the first punching mold optimization rule as the variation optimization target, the first punching mold variation space is iteratively optimized in combination with the mold operation scenario fitness prediction module to construct the punching mold variation optimization domain that meets the first optimization capacity constraint.

[0010] In a possible implementation, it is determined whether the fitness prediction result of the first scheme satisfies the first punching die optimization rule, and the following processing is also performed: if the fitness prediction result of the first scheme does not satisfy the first punching die optimization rule, the second punching die variation optimization channel in the punching die variation optimization dual channel is activated, wherein the second punching die variation optimization channel includes a second punching die variation operator, and the second punching die variation operator includes a second die variation dimension threshold, a second die asynchronous advancement threshold, and a second die variation capacity threshold, and the second die variation dimension threshold is greater than the first die variation dimension threshold, the second die asynchronous advancement threshold is greater than the first die asynchronous advancement threshold, and the second die variation capacity threshold is greater than the first die variation capacity threshold; the registration punching die scheme is mutated and adjusted according to the second punching die variation optimization channel, Generate a second punching die variation space; extract a first variation punching die scheme based on the second punching die variation space; perform multi-dimensional fitness prediction on the punching die operation scene feature data and the first variation punching die scheme according to the mold operation scene fitness prediction module to obtain a first variation scheme fitness prediction result; determine whether the first variation scheme fitness prediction result meets the first punching die optimization rule; if the first variation scheme fitness prediction result meets the first punching die optimization rule, use the first variation punching die scheme as the punching die variation benchmark scheme; if the first variation scheme fitness prediction result does not meet the first punching die optimization rule, continue to iteratively search the second punching die variation space according to the mold operation scene fitness prediction module and the first punching die optimization rule until the punching die variation benchmark scheme is generated.

[0011] In a possible implementation, the punching die variation optimization domain is deeply optimized according to the second punching die optimization rule to determine the punching die parameter optimization scheme, and the following processing is also performed: mold production quality prediction is performed according to the punching die variation optimization domain to generate multiple scheme mold quality prediction coefficients; based on the multiple scheme mold quality prediction coefficients, the punching die variation optimization domain is selected according to the second punching die optimization rule to obtain the punching die variation selection domain, wherein the second punching die optimization rule includes a mold quality constraint interval; mold production cost minimization analysis is performed according to the punching die variation selection domain to generate the punching die parameter optimization scheme.

[0012] This application also provides a punching die parameter optimization system based on demand analysis, including:

[0013] A demand instruction receiving module, the demand instruction receiving module is used to receive a punching die demand instruction, wherein the punching die demand instruction includes punching die operation scene feature data, wherein the punching die operation scene feature data includes stamping process feature data, stamping material feature data and stamping process environment feature data;

[0014] A variable coupling cleaning module, wherein the variable coupling cleaning module is used to perform variable coupling cleaning on the A-dimensional punching die parameter variables according to a predetermined variable coupling constraint value to generate a B-dimensional punching die parameter variable, wherein A and B are both positive integers greater than 1, and B is less than or equal to A;

[0015] A registration punching die solution generation module is configured to perform backtracking registration of punching die parameters based on the punching die operation scene feature data and the B-dimensional punching die parameter variables to generate a registration punching die solution;

[0016] A scheme variation optimization module is used to perform variation optimization on the registered punching die scheme according to the first punching die optimization rule and in combination with the punching die variation optimization dual channels to generate a punching die variation optimization domain;

[0017] The punching die parameter optimization solution determination module is used to perform deep optimization on the punching die variation optimization domain according to the second punching die optimization rule to determine the punching die parameter optimization solution.

[0018] The present application proposes a method and system for optimizing sheet die parameters based on demand analysis, which receives sheet die demand instructions; performs variable coupling cleaning on the A-dimensional sheet die parameter variables according to predetermined variable coupling constraint values; performs backtracking alignment of sheet die parameters to generate an aligned sheet die solution; combines the sheet die variation optimization dual-channel to perform variation optimization on the aligned sheet die solution to generate a sheet die variation optimization domain; performs deep optimization according to the second sheet die optimization rule to determine the sheet die parameter optimization solution. This solves the technical problems of inaccurate acquisition of die parameter variables and parameter mismatch in existing die parameter optimization, resulting in poor parameter optimization results and unstable die performance quality, and optimizes die parameters to achieve the technical effect of improving die performance and stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] To more clearly illustrate the technical solutions of the embodiments of the present disclosure, the accompanying drawings of the embodiments of the present disclosure are briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the systems according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in precise order. Instead, various steps may be processed in reverse order or simultaneously as needed. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0020] Figure 1 A schematic flow chart of a method for optimizing punching die parameters based on demand analysis provided in an embodiment of the present application;

[0021] Figure 2 Schematic diagram of the structure of the punching die parameter optimization system based on demand analysis provided in an embodiment of the present application.

[0022] Explanation of the reference numerals: demand instruction receiving module 10 , variable coupling cleaning module 20 , registration punching die solution generation module 30 , solution variation optimization module 40 , punching die parameter optimization solution determination module 50 . DETAILED DESCRIPTION

[0023] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0024] In order to make the purpose, technical solutions and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limiting this application. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0025] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict, and the terms “first\second” involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. The terms “including” and “having” and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs. The terms used herein are for the purpose of describing the embodiments of this application only.

[0026] The present application embodiment provides a method for optimizing punching die parameters based on demand analysis, such as Figure 1 As shown, the method includes:

[0027] Step S100, receiving a punching die requirement instruction, wherein the punching die requirement instruction includes punching die operation scene characteristic data, wherein the punching die operation scene characteristic data includes stamping process characteristic data, punched material characteristic data and stamping process environment characteristic data. Receive a punching die requirement instruction, wherein the punching die requirement instruction is used to clarify various requirements in the design, manufacturing and optimization process of the punching die, including the punching die operation scene characteristic data, wherein the punching die operation scene characteristic data refers to various parameters and conditions related to the punching die in the actual operation environment, including stamping process characteristic data, punched material characteristic data and stamping process characteristic data. Specifically, the stamping process characteristic data refers to various process parameters and technical requirements involved in the stamping process, such as stamping speed, punching force, blanking method, number of stamping times, etc., which directly determine the quality and efficiency of stamping. At the same time, the process characteristic data also includes the structural design of the mold, the shape and size of the male and female molds. etc., which have an important impact on the stamping performance and service life of the mold; the characteristic data of the stamped material mainly involves the physical and chemical properties of the material, such as the thickness, hardness, tensile strength, elongation, etc. of the material, which determines the adaptability of the material to the stamping process and the performance after forming. The composition and microstructure of the material will also affect the deformation behavior during the stamping process and the wear of the mold; the stamping processing environment characteristic data covers various environmental factors at the production site, such as temperature, humidity, vibration, noise, etc., which will affect the stability of the stamping process and the service life of the mold. For example, a high temperature environment may cause thermal expansion of the mold material, affecting the accuracy and stability of the mold; vibration and noise may interfere with the operator's judgment and operation, thereby affecting the stamping quality.

[0028] Step S200: Variable coupling cleaning is performed on the A-dimensional punching die parameter variables according to predetermined variable coupling constraint values to generate B-dimensional punching die parameter variables, wherein A and B are both positive integers greater than 1, and B is less than or equal to A. Variable coupling cleaning is performed on the A-dimensional punching die parameter variables according to predetermined variable coupling constraint values to generate B-dimensional punching die parameter variables, wherein the predetermined variable coupling constraint values are pre-set based on engineering experience or experimental results, and are used to quantify the constraint values of this coupling relationship, so as to identify key parameter combinations that have a significant impact on die performance. A represents the original number of dimensions of the punching die parameters, that is, the number of parameters initially considered. Parameter variables may include die geometry, material properties, heat treatment process parameters, etc.; variable coupling cleaning is to screen and organize the A-dimensional parameter variables according to predetermined constraint values to eliminate redundant or low-impact parameters, retain those parameters that play a key role in die performance, reduce the number of parameters, and simplify the subsequent optimization process. B represents the number of parameter dimensions retained after cleaning, which is less than or equal to A. Through variable coupling cleaning, the original A-dimensional parameter variables are simplified into B-dimensional parameter variables. These variables are more refined and more representative of the mold performance, which simplifies the design and optimization process of the punching mold and improves the design efficiency and mold performance.

[0029] In one possible implementation, step S200 further includes step S210, randomly extracting a first punching die parameter variable and a second punching die parameter variable from the A-dimensional punching die parameter variable. Randomly selecting two specific parameters from all considered die parameters as the first punching die parameter variable and the second punching die parameter variable. The method further includes step S220, performing a variable coupling analysis on the first punching die parameter variable and the second punching die parameter variable to obtain a first die variable coupling index. Variable coupling analysis refers to quantifying the degree of mutual influence or correlation between the first punching die parameter variable and the second punching die parameter variable, obtaining a quantitative indicator, namely the first die variable coupling index, which is used to represent the degree of coupling between the two die parameter variables. A larger first die variable coupling index indicates a higher degree of mutual influence and lower independence between the two die parameter variables. The method further includes step S230, determining whether the first die variable coupling index is less than or equal to the predetermined variable coupling constraint value. After obtaining the first die variable coupling index, it is necessary to compare it with the predetermined variable coupling constraint value. The method further includes step S240, where, if the first mold variable coupling index is less than or equal to the predetermined variable coupling constraint value, the first punching mold parameter variable and the second punching mold parameter variable are added to the B-dimensional punching mold parameter variable. If the first mold variable coupling index is less than or equal to the predetermined variable coupling constraint value, it can be considered that the degree of coupling between the two parameters is within the design allowable range and will not have a significant adverse effect on the performance of the mold, and the first punching mold parameter variable and the second punching mold parameter variable are added to the B-dimensional punching mold parameter variable.

[0030] In one possible implementation, step S230 further includes step S231: if the first mold variable coupling index is greater than the predetermined variable coupling constraint value, generating a variable coupling warning signal. If the first mold variable coupling index is greater than the predetermined variable coupling constraint value, it indicates that the degree of coupling between the two parameters exceeds the design allowable range and requires further analysis and adjustment to reduce their mutual influence and ensure the rationality of the mold design. A variable coupling warning signal is then generated, which can help promptly identify and address potential problems when parameter coupling exceeds the expected range. The process also includes step S232: performing variable fusion on the first punching die parameter variable and the second punching die parameter variable based on the variable coupling warning signal to generate a first fused punching die parameter variable. Variable fusion is a data processing technique used to merge multiple related or strongly coupled variables into a new variable. Through variable fusion, redundant information between the original variables can be eliminated or reduced while retaining information that has a significant impact on mold performance, thereby generating a first fused punching die parameter variable. The process also includes step S233: adding the first fused punching die parameter variable to the B-dimensional punching die parameter variable.

[0031] Step S300, based on the punching die operation scene characteristic data and the B-dimensional punching die parameter variables, the punching die parameters are retrospectively aligned to generate a registered punching die solution. In combination with the actual operation scene characteristic data, the generated B-dimensional punching die parameter variables are retrospectively analyzed and aligned to generate a punching die solution that meets the requirements of a specific operation scene. Specifically, retrospective alignment is to retrospectively analyze and adjust the existing design parameters to make them better adapt to the requirements of a specific operation scene. In this process, the operation scene characteristic data and the B-dimensional punching die parameter variables are comprehensively considered, and the performance of the current parameter variables in a specific operation scene is evaluated through simulation, analysis or experiment. If it is found that the performance does not meet the requirements or there is room for optimization, the parameter variables are retrospectively adjusted and the mold parameters are reconfigured to improve the performance of the mold or adapt to the new operation conditions. After retrospective alignment and adjustment, a new set of punching die parameter configurations that meet the requirements of the specific operation scene are obtained, which is the aligned punching die solution.

[0032] In one possible implementation, step S300 further includes step S310, retrieving a punching die parameter record library, wherein the punching die parameter record library includes multiple sets of punching die parameter records, each set of punching die parameter records including sample punching die operation scene feature data and sample punching die parameter schemes. Specifically, the punching die parameter record library is a database that stores a large number of punching die parameter records. The record library contains multiple sets of different punching die parameter records, each set of records represents a die parameter configuration scheme under a specific operation scene, and each set of punching die parameter records includes sample punching die operation scene feature data, which describes key information such as the operation environment, process requirements, and material properties of the die in actual application, as well as corresponding sample punching die parameter schemes, which are die parameter configurations under specific operation scenes. They have been verified by actual application and have certain reliability and effectiveness. It also includes step S320, based on the punching die operation scene feature data, performing operation scene twin recognition on each sample punching die operation scene feature data in the punching die parameter record library, and generating multiple die operation scene twin coefficients. The current die operation scene feature data is compared and matched with the sample die operation scene feature data in the die parameter record library to identify historical scenes similar to the current operation scene and generate corresponding twin coefficients. Specifically, the current operation scene feature data is compared with the historical scene data in the record library to discover similarities and differences between them. The die operation scene twin coefficient is a numerical indicator used to quantify the degree of similarity between the current operation scene and each sample scene in the record library, reflecting the similarity relationship between the current operation scene and multiple historical scenes. The method further includes step S330 of selecting a winning die operation scene twin coefficient based on the multiple die operation scene twin coefficients. The maximum value of the selected die operation scene twin coefficient is determined as the winning die operation scene twin coefficient. The method further includes step S340 of matching a winning sample die parameter solution based on the winning die operation scene twin coefficient based on the die parameter record library, and performing feature fusion on the registered die solution based on the B-dimensional die parameter variables to obtain the registered die solution. According to the twin coefficient of the selected winning mold operation scenario, the winning sample punching mold parameter scheme is matched in the punching mold parameter record library, and feature fusion is performed based on the B-dimensional punching mold parameter variable to obtain the matched punching mold scheme, which combines the advantages of the winning sample scheme and the current design parameter characteristics of the punching mold scheme.

[0033] Step S400, according to the first punching die optimization rule, combined with the punching die variation optimization dual channel, the said registration punching die scheme is subjected to variation optimization to generate the punching die variation optimization domain. Specifically, the first punching die optimization rule is a set of pre-set rules for guiding the optimization of punching die parameters, which is used to determine how to adjust the die parameters to optimize performance. The first punching die optimization rule may take into account a variety of factors, such as stamping efficiency, material utilization, die life, manufacturing cost, etc.; variation optimization is a method of searching for a better solution by introducing parameter variation. In the design of punching die, this means making a certain degree of random change or adjustment to the current die parameter configuration. Dual channels refer to the simultaneous consideration of two different parameter adjustment channels or paths during the variation optimization process, which may represent different The optimization direction or strategy of the two channels can be explored simultaneously to increase the possibility of finding the global optimal solution. Based on the dual channels of the first punching die optimization rule and the punching die variation optimization, the generated registration punching die scheme is mutated to generate a series of new die parameter configurations. These configurations may be different from the original scheme in performance, but may contain better solutions. After variation optimization, a set of multiple new die parameter configurations will be generated, which is called the punching die variation optimization domain. It represents the parameter range or space that can be achieved through variation optimization based on the current registration punching die scheme.

[0034] In one possible implementation, step S400 further includes step S410, which constructs a mold operation scenario adaptability prediction module, wherein the mold operation scenario adaptability prediction module includes multi-dimensional mold operation scenario adaptability prediction indicators, and the multi-dimensional mold operation scenario adaptability prediction indicators include mold operation process adaptability, mold operation material adaptability, and mold operation environment adaptability. A systematic module is created that can evaluate the adaptability of the mold in different operation scenarios. Based on a series of multi-dimensional prediction indicators, a comprehensive and integrated analysis of the performance of the mold in a specific operation environment is performed, including mold operation process adaptability, mold operation material adaptability, and mold operation environment adaptability. Specifically, mold operation process adaptability focuses on the adaptability and performance of the mold under specific process conditions, for example, whether the mold can meet process requirements such as stamping speed, number of stamping times, and pressure distribution, as well as the stability and durability of the mold under these process conditions; mold operation material adaptability mainly evaluates the mold's processing adaptability to materials of different types and properties. For example, whether the mold can effectively process materials of different hardness, thickness, and surface properties, as well as the wear and life of the mold during the processing of these materials; the mold operating environment adaptability focuses on the stability and reliability of the mold in different operating environments. The operating environment may include temperature, humidity, vibration, dust and other factors, all of which may affect the performance of the mold. It also includes step S420, which performs multi-dimensional fitness prediction on the punching mold operating scene feature data and the registered punching mold scheme according to the mold operating scene fitness prediction module to obtain the first scheme fitness prediction result. The punching mold operating scene feature data and the registered punching mold scheme are used as input data of the mold operating scene fitness prediction module to perform fitness evaluation prediction. For each prediction indicator, a fitness score will be output, which reflects the adaptability of the mold scheme under this indicator. Combining the fitness scores of all prediction indicators, the prediction module finally generates a comprehensive fitness prediction result, i.e., the first scheme fitness prediction result. It also includes step S430, judging whether the fitness prediction result of the first scheme satisfies the first punching die optimization rule, wherein the first punching die optimization rule includes a multi-dimensional mold operation scene fitness constraint, and the multi-dimensional mold operation scene fitness constraint includes a mold operation process fitness constraint, a mold operation material fitness constraint and a mold operation environment fitness constraint.Specifically, the mold operation process fitness constraint requires that the mold solution must be able to meet the operating requirements under specific process conditions. For example, the mold must be able to withstand specific process parameters such as stamping speed and pressure distribution, and maintain stable and efficient operation under these conditions. The mold operation material fitness constraint requires that the mold solution must be able to adapt to the processing requirements of different materials. The mold operation environment fitness constraint requires that the mold solution must be able to operate stably in different operating environments. The mold needs to be able to withstand the influence of environmental factors such as temperature, humidity, and vibration, and maintain the stability and reliability of its performance. The above three constraints are comprehensively considered and the fitness prediction result of the first solution is determined to be satisfied. The method also includes step S440. If the fitness prediction result of the first solution meets the first punching die optimization rule, the registered punching die solution is used as the punching die variation benchmark solution and is added to the punching die variation optimization domain. If the scores of the fitness prediction result of the first solution in all dimensions meet or exceed the corresponding constraint requirements, then it can be considered that the solution meets the first punching die optimization rule, the registered punching die solution is used as the punching die variation benchmark solution, and it is added to the punching die variation optimization domain. It also includes step S450, activating the first punching die variation optimization channel in the punching die variation optimization dual channels, wherein the first punching die variation optimization channel includes a first punching die variation operator, and the first punching die variation operator includes a first die variation dimension threshold, a first die variation asynchronous advancement threshold and a first die variation capacity threshold. A specific optimization channel is initiated, which focuses on finding a more optimal punching die solution through mutation operations. The first punching die mutation operator is used to guide how to perform mutation operations on the current punching die solution. The first die mutation dimension threshold limits the number or dimensions of die parameters that can be changed in each mutation operation. For example, if the dimension threshold is set to 3, then at most three die parameters can be changed in a single mutation operation. The first die asynchronous advancement threshold defines the maximum step size or amplitude that a die parameter can change during mutation, limiting the possible range of variation for each parameter. For example, if the first die asynchronous advancement threshold is 5%, the possible step sizes include 1%, 2%, 3%, 4%, and 5%. The first die mutation capacity threshold is used to limit the overall impact range or mutation capacity of the mutation operation, i.e., the number of solutions in the first punching die variation space. The method also includes step S460, in which the punching die variation benchmark solution is mutated and adjusted according to the first punching die variation optimization channel to generate a first punching die variation space. Using the mutation rules and parameters defined in the first punching die variation optimization channel, a series of mutation operations are performed on the pre-set punching die variation benchmark scheme to generate a space containing multiple possible better solutions, namely the first punching die variation space.The method further includes step S470, wherein the first punching die optimization rule is used as a variation optimization target, and the die operation scenario fitness prediction module is combined to iteratively optimize the first punching die variation space, thereby constructing the punching die variation optimization domain that satisfies a first optimization capacity constraint. Based on the first punching die optimization rule and the die operation scenario fitness prediction module, a series of iterative optimization processes are performed to search for an optimal punching die solution that meets the preset optimization rule in the first punching die variation space, and ultimately form a variation optimization domain that satisfies a specific capacity constraint, wherein the first optimization capacity constraint refers to a threshold value for the number of solutions in the punching die variation optimization domain.

[0035] In a possible implementation, step S430 further includes step S431, if the fitness prediction result of the first scheme does not meet the first punching die optimization rule, activating the second punching die variation optimization channel in the punching die variation optimization dual channel, wherein the second punching die variation optimization channel includes a second punching die variation operator, the second punching die variation operator includes a second die variation dimension threshold, a second die asynchronous advancement threshold and a second die variation capacity threshold, and the second die variation dimension threshold is greater than the first die variation dimension threshold, the second die asynchronous advancement threshold is greater than the first die asynchronous advancement threshold, and the second die variation capacity threshold is greater than the first die variation capacity threshold. The current die solution does not meet the preset requirements for adaptability to the operational scenario and requires further adjustment and optimization. The system then activates the second die solution variation optimization channel within the dual die solution variation optimization channel. The second die solution variation optimization channel uses different mutation operators and parameter settings to accommodate broader or deeper search requirements. It includes a second die solution variation operator with three key threshold parameters: a second die variation dimension threshold, a second die asynchronization threshold, and a second die variation capacity threshold. Specifically, if the second die variation dimension threshold is greater than the first die variation dimension threshold, each mutation operation in the second die solution variation optimization channel can change a greater number of die parameters or dimensions; if the second die asynchronization threshold is greater than the first die asynchronization threshold, the die parameter asynchronization duration or amplitude is greater, allowing for faster exit from a local optimal solution; and if the second die variation capacity threshold is greater than the first die variation capacity threshold, the mutation operation in the second channel has a greater impact on the overall die solution. The system also includes step S432, performing mutation adjustments on the registered die solution according to the second die solution variation optimization channel to generate a second die solution variation space. It also includes step S433, extracting the first variant punching die solution according to the second punching die variation space. From the set of punching die solutions generated after the variation adjustment of the second punching die variation optimization channel, one is selected as a starting or representative solution, and this solution is called the first variant punching die solution. It also includes step S434, performing multi-dimensional fitness prediction on the punching die operation scene feature data and the first variant punching die solution according to the mold operation scene fitness prediction module to obtain the fitness prediction result of the first variant solution. Using the pre-constructed mold operation scene fitness prediction module, the feature data of the punching die operation scene is combined with the first variant punching die solution obtained after the variation operation, and a multi-dimensional fitness evaluation is performed to obtain the fitness prediction result of the variant solution in the operation scene. It also includes step S435, judging whether the fitness prediction result of the first variant solution meets the first punching die optimization rule.It also includes step S436, if the fitness prediction result of the first variation scheme meets the first punching die optimization rule, the first variation punching die scheme is used as the punching die variation benchmark scheme. After multi-dimensional fitness prediction, if it is determined that the fitness of the first variation punching die scheme in the operation scenario has reached the preset optimization rule requirements, then the system will use this mutated scheme as a new benchmark scheme for subsequent punching die variation optimization. It also includes step S437, if the fitness prediction result of the first variation scheme does not meet the first punching die optimization rule, the second punching die variation space is continued to be iteratively searched according to the mold operation scenario fitness prediction module and the first punching die optimization rule until the punching die variation benchmark scheme is generated. When the first variation punching die scheme after mutation and fitness prediction fails to meet the preset optimization rule requirements, the system will re-enter the iterative search process and conduct a deeper search of the second punching die variation space until a punching die variation benchmark scheme that meets the conditions is found.

[0036] Step S500: Deeply search and optimize the variation optimization domain of the punching die according to the second punching die optimization rule to determine the punching die parameter optimization solution. According to the second punching die optimization rule, further deep search and optimization are performed in the variation optimization domain. Specifically, the second punching die optimization rule is often more specific than the first rule, and contains more detailed requirements on the performance, structure, material, etc. of the punching die. The variation optimization domain of the punching die is screened and evaluated more finely. Not only will the system search for possible excellent solutions in the larger variation space, but it will also conduct a more detailed search in the possible solution space. In the process of deep optimization, the system will continuously adjust and optimize the various parameters of the punching die, such as punch diameter, punching size, punch height, punch plate thickness, etc., until one or more parameter combinations that meet the second punching die optimization rule are found, forming a punching die parameter optimization solution.

[0037] In a possible implementation, step S500 further includes step S510, performing mold production quality prediction based on the punching die variation optimization domain, and generating multiple scheme mold quality prediction coefficients. Within the determined punching die variation optimization domain, the system evaluates the performance of each potential mold design scheme in actual production by performing production quality prediction on them, and generates corresponding mold quality prediction coefficients. Specifically, the mold quality prediction coefficient is used to quantitatively represent the quality level, stability, durability and other performance indicators of the mold during the production process. It also includes step S520, based on the multiple scheme mold quality prediction coefficients, selecting the punching die variation optimization domain according to the second punching die optimization rule to obtain the punching die variation selection domain, wherein the second punching die optimization rule includes a mold quality constraint interval. After obtaining the mold quality prediction coefficients of multiple solutions, the system further screens the punching mold variation optimization domain based on the mold quality constraint interval in the second punching mold optimization rule to obtain a punching mold variation selection domain that meets specific quality requirements. Specifically, the mold quality prediction coefficients of multiple solutions are analyzed to understand the advantages and disadvantages of each solution in terms of quality; the mold quality constraint interval defines the qualified range of mold quality prediction; based on the mold quality constraint interval, the system screens the solutions in the punching mold variation optimization domain. All solutions with quality prediction coefficients falling within the constraint interval will be retained, while solutions outside this interval will be excluded. After screening, a narrowed punching mold variation selection domain is obtained. It also includes step S530, performing mold production cost minimization analysis based on the punching mold variation selection domain to generate the punching mold parameter optimization solution. Within the selected punching die variation selection domain, the production cost of each die design scheme is further analyzed, and a punching die parameter optimization scheme that can minimize the production cost is determined, including a series of specific parameter adjustment suggestions, such as changing the structural design of the die, adjusting the punching force and punching speed, optimizing the size of the punch and punch plate, etc., to minimize the production cost while ensuring the quality of the die.

[0038] In the above, refer to Figure 1 The method for optimizing the parameters of the punching die based on demand analysis according to an embodiment of the present invention is described in detail. Figure 2 A punching die parameter optimization system based on demand analysis according to an embodiment of the present invention is described.

[0039] The punching die parameter optimization system based on demand analysis according to an embodiment of the present invention is used to solve the technical problems existing in existing mold parameter optimization, such as inaccurate acquisition of mold parameter variables and parameter mismatch, which lead to poor parameter optimization results and unstable mold performance and quality. The system optimizes mold parameters and achieves the technical effect of improving mold performance and stability. The punching die parameter optimization system based on demand analysis includes: a demand instruction receiving module 10, a variable coupling cleaning module 20, a punching die registration solution generation module 30, a solution variation optimization module 40, and a punching die parameter optimization solution determination module 50.

[0040] A demand instruction receiving module 10 is used to receive a punching die demand instruction, wherein the punching die demand instruction includes punching die operation scene feature data, wherein the punching die operation scene feature data includes stamping process feature data, stamping material feature data and stamping process environment feature data;

[0041] A variable coupling cleaning module 20 is used to perform variable coupling cleaning on the A-dimensional punching die parameter variables according to a predetermined variable coupling constraint value to generate a B-dimensional punching die parameter variable, wherein A and B are both positive integers greater than 1, and B is less than or equal to A;

[0042] A registration punching die solution generation module 30 is configured to perform backtracking registration of punching die parameters based on the punching die operation scene feature data and the B-dimensional punching die parameter variables to generate a registration punching die solution;

[0043] A scheme variation optimization module 40 is used to perform variation optimization on the registered punching die scheme according to the first punching die optimization rule and in combination with the punching die variation optimization dual channels to generate a punching die variation optimization domain;

[0044] The punching die parameter optimization solution determination module 50 is used to perform deep optimization on the punching die variation optimization domain according to the second punching die optimization rule to determine the punching die parameter optimization solution.

[0045] The specific configuration of the variable coupling cleaning module 20 will be described in detail below. The variable coupling cleaning module 20 further includes: randomly extracting a first punching die parameter variable and a second punching die parameter variable from the A-dimensional punching die parameter variable; performing a variable coupling analysis on the first punching die parameter variable and the second punching die parameter variable to obtain a first die variable coupling index; determining whether the first die variable coupling index is less than / equal to the predetermined variable coupling constraint value; and if the first die variable coupling index is less than / equal to the predetermined variable coupling constraint value, adding the first punching die parameter variable and the second punching die parameter variable to the B-dimensional punching die parameter variable.

[0046] The specific configuration of the variable coupling cleaning module 20 will be described in detail below. The variable coupling cleaning module 20 may further include: generating a variable coupling warning signal if the first die variable coupling index is greater than the predetermined variable coupling constraint value; performing variable fusion on the first punching die parameter variable and the second punching die parameter variable based on the variable coupling warning signal to generate a first fused punching die parameter variable; and adding the first fused punching die parameter variable to the B-dimensional punching die parameter variable.

[0047] The specific configuration of the registration punching die scheme generation module 30 will be described in detail below. The registration punching die scheme generation module 30 may further include: retrieving a punching die parameter record library, wherein the punching die parameter record library includes multiple groups of punching die parameter records, and each group of punching die parameter records includes sample punching die operation scene feature data and sample punching die parameter schemes; based on the punching die operation scene feature data, performing operation scene twin recognition on each sample punching die operation scene feature data in the punching die parameter record library, and generating multiple mold operation scene twin coefficients; screening a winning mold operation scene twin coefficient based on the multiple mold operation scene twin coefficients; based on the punching die parameter record library, matching a winning sample punching die parameter scheme according to the winning mold operation scene twin coefficient, and performing feature fusion on the registration punching die scheme according to the B-dimensional punching die parameter variable to obtain the registration punching die scheme.

[0048] The specific configuration of the scheme variation optimization module 40 will be described in detail below. The scheme variation optimization module 40 further includes: building a mold operation scene fitness prediction module, wherein the mold operation scene fitness prediction module includes a multi-dimensional mold operation scene fitness prediction index, and the multi-dimensional mold operation scene fitness prediction index includes mold operation process fitness, mold operation material fitness and mold operation environment fitness; performing multi-dimensional fitness prediction on the punching mold operation scene feature data and the registration punching mold scheme according to the mold operation scene fitness prediction module to obtain a first scheme fitness prediction result; judging whether the first scheme fitness prediction result satisfies the first punching mold optimization rule, wherein the first punching mold optimization rule includes a multi-dimensional mold operation scene fitness constraint, and the multi-dimensional mold operation scene fitness constraint includes a mold operation process fitness constraint, a mold operation material fitness constraint and a mold operation environment fitness constraint; if the first scheme is adapted The degree prediction result meets the first punching die optimization rule, the registered punching die scheme is used as the punching die variation benchmark scheme, and the punching die variation benchmark scheme is added to the punching die variation optimization domain; the first punching die variation optimization channel in the punching die variation optimization dual channel is activated, wherein the first punching die variation optimization channel includes a first punching die variation operator, and the first punching die variation operator includes a first die variation dimension threshold, a first die variation asynchronous advancement threshold and a first die variation capacity threshold; the punching die variation benchmark scheme is mutated and adjusted according to the first punching die variation optimization channel to generate a first punching die variation space; the first punching die optimization rule is used as the variation optimization target, and the first punching die variation space is iteratively optimized in combination with the mold operation scenario fitness prediction module to construct the punching die variation optimization domain that meets the first optimization capacity constraint.

[0049] The specific configuration of the scheme variation optimization module 40 will be described in detail below. The scheme variation optimization module 40 further includes: if the fitness prediction result of the first scheme does not meet the first punching die optimization rule, activating the second punching die variation optimization channel in the punching die variation optimization dual channel, wherein the second punching die variation optimization channel includes a second punching die variation operator, and the second punching die variation operator includes a second die variation dimension threshold, a second die asynchronous advancement threshold, and a second die variation capacity threshold, and the second die variation dimension threshold is greater than the first die variation dimension threshold, the second die asynchronous advancement threshold is greater than the first die asynchronous advancement threshold, and the second die variation capacity threshold is greater than the first die variation capacity threshold; according to the second punching die variation optimization channel, the registered punching die scheme is mutated and adjusted to generate a second punching die variation space; according to the Extract the first variant punching die scheme from the second punching die variation space; perform multi-dimensional fitness prediction on the punching die operation scene feature data and the first variant punching die scheme according to the mold operation scene fitness prediction module to obtain the fitness prediction result of the first variant scheme; judge whether the fitness prediction result of the first variant scheme meets the first punching die optimization rule; if the fitness prediction result of the first variant scheme meets the first punching die optimization rule, use the first variant punching die scheme as the punching die variation benchmark scheme; if the fitness prediction result of the first variant scheme does not meet the first punching die optimization rule, continue to iteratively search the second punching die variation space according to the mold operation scene fitness prediction module and the first punching die optimization rule until the punching die variation benchmark scheme is generated.

[0050] The specific configuration of the punching die parameter optimization solution determination module 50 will be described in detail below. The punching die parameter optimization solution determination module 50 may further include: performing mold production quality prediction based on the punching die variation optimization domain to generate multiple solution mold quality prediction coefficients; based on the multiple solution mold quality prediction coefficients, selecting the punching die variation optimization domain according to the second punching die optimization rule to obtain the punching die variation selection domain, wherein the second punching die optimization rule includes a mold quality constraint interval; performing mold production cost minimization analysis based on the punching die variation selection domain to generate the punching die parameter optimization solution.

[0051] The punching die parameter optimization system based on demand analysis provided by the embodiment of the present invention can execute the punching die parameter optimization method based on demand analysis provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0052] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other and are not used to limit the scope of protection of the present invention.

[0053] The above specific embodiments do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application shall be included within the scope of protection of this application.

Claims

1. A method for optimizing punching die parameters based on demand analysis, characterized in that: The method comprises: Receive a punching die requirement instruction, wherein the punching die requirement instruction includes punching die operation scene characteristic data, wherein the punching die operation scene characteristic data includes stamping process characteristic data, stamping material characteristic data, and stamping process environment characteristic data; Perform variable coupling cleaning on the A-dimensional punching die parameter variables according to the predetermined variable coupling constraint value to generate the B-dimensional punching die parameter variables, wherein A and B are both positive integers greater than 1, and B is less than or equal to A; The variable coupling cleaning is to screen and sort the A-dimensional parameter variables according to the predetermined constraint values to eliminate redundant or low-impact parameters, retain the parameters that play a key role in the mold performance, and reduce the number of parameters to simplify the subsequent optimization process; Performing backtracking registration of punching die parameters according to the punching die operation scene feature data and the B-dimensional punching die parameter variables to generate a registered punching die solution; According to the first punching die optimization rule, the punching die variation optimization dual channel is combined to perform variation optimization on the registered punching die solution, and a punching die variation optimization domain is generated, including: Establishing a mold operation scenario fitness prediction module, wherein the mold operation scenario fitness prediction module includes multi-dimensional mold operation scenario fitness prediction indicators, and the multi-dimensional mold operation scenario fitness prediction indicators include mold operation process fitness, mold operation material fitness, and mold operation environment fitness; Performing multi-dimensional fitness prediction on the punching die operation scene feature data and the registration punching die scheme according to the mold operation scene fitness prediction module to obtain a first scheme fitness prediction result; Determining whether the fitness prediction result of the first solution satisfies the first punching die optimization rule, wherein the first punching die optimization rule includes a multi-dimensional die operation scenario fitness constraint, and the multi-dimensional die operation scenario fitness constraint includes a die operation process fitness constraint, a die operation material fitness constraint, and a die operation environment fitness constraint; If the fitness prediction result of the first solution satisfies the first punching die optimization rule, the registered punching die solution is used as the punching die variation benchmark solution, and the punching die variation benchmark solution is added to the punching die variation optimization domain; Activate the first punching die variation optimization channel in the punching die variation optimization dual channels, wherein the first punching die variation optimization channel includes a first punching die variation operator, and the first punching die variation operator includes a first die variation dimension threshold, a first die variation asynchronous advancement threshold, and a first die variation capacity threshold; performing variation adjustment on the punching die variation benchmark solution according to the first punching die variation optimization channel to generate a first punching die variation space; Taking the first punching die optimization rule as the variation optimization target, and combining the die operation scenario fitness prediction module, iteratively optimize the first punching die variation space to construct the punching die variation optimization domain that satisfies the first optimization capacity constraint; The determining whether the fitness prediction result of the first solution satisfies the first punching die optimization rule includes: If the fitness prediction result of the first scheme does not meet the first punching die optimization rule, activate the second punching die variation optimization channel in the punching die variation optimization dual channel, wherein the second punching die variation optimization channel includes a second punching die variation operator, the second punching die variation operator includes a second die variation dimension threshold, a second die asynchronous advancement threshold, and a second die variation capacity threshold, and the second die variation dimension threshold is greater than the first die variation dimension threshold, the second die asynchronous advancement threshold is greater than the first die asynchronous advancement threshold, and the second die variation capacity threshold is greater than the first die variation capacity threshold; Perform variation adjustment on the registered punching die solution according to the second punching die variation optimization channel to generate a second punching die variation space; Extracting a first variant punching die solution according to the second punching die variation space; Performing multi-dimensional fitness prediction on the punching die operation scene feature data and the first variant punching die solution according to the die operation scene fitness prediction module to obtain a fitness prediction result of the first variant solution; Determining whether the fitness prediction result of the first variation scheme satisfies the first punching die optimization rule; If the fitness prediction result of the first variation scheme satisfies the first punching die optimization rule, the first variation punching die scheme is used as the punching die variation benchmark scheme; If the fitness prediction result of the first variation scheme does not satisfy the first punching die optimization rule, continue to iteratively search the second punching die variation space according to the mold operation scenario fitness prediction module and the first punching die optimization rule until the punching die variation benchmark scheme is generated; According to the second punching die optimization rule, the punching die variation optimization domain is deeply optimized to determine the punching die parameter optimization solution.

2. The method for optimizing punching die parameters based on demand analysis according to claim 1, characterized in that: According to the predetermined variable coupling constraint value, the A-dimensional punching die parameter variables are subjected to variable coupling cleaning to generate the B-dimensional punching die parameter variables, wherein A and B are both positive integers greater than 1, and B is less than or equal to A, including: Randomly extracting a first punching die parameter variable and a second punching die parameter variable from the A-dimensional punching die parameter variable; Performing a variable coupling analysis on the first punching die parameter variables and the second punching die parameter variables to obtain a first die variable coupling index; Determining whether the first mold variable coupling index is less than / equal to the predetermined variable coupling constraint value; If the first die variable coupling index is less than / equal to the predetermined variable coupling constraint value, the first punching die parameter variable and the second punching die parameter variable are added to the B-dimensional punching die parameter variable.

3. The method for optimizing punching die parameters based on demand analysis according to claim 2, characterized in that: Determining whether the first mold variable coupling index is less than / equal to the predetermined variable coupling constraint value includes: If the first mold variable coupling index is greater than the predetermined variable coupling constraint value, generating a variable coupling warning signal; Performing variable fusion on the first punching die parameter variable and the second punching die parameter variable according to the variable coupling warning signal to generate a first fused punching die parameter variable; The first fused punching die parameter variables are added to the B-dimensional punching die parameter variables.

4. The method for optimizing punching die parameters based on demand analysis according to claim 1, characterized in that: Performing backtracking registration of punching die parameters according to the punching die operation scene feature data and the B-dimensional punching die parameter variables to generate a registered punching die solution, including: Retrieving a punching die parameter record library, wherein the punching die parameter record library includes multiple sets of punching die parameter records, and each set of punching die parameter records includes sample punching die operation scene feature data and a sample punching die parameter solution; Based on the punching die operation scene feature data, each sample punching die operation scene feature data in the punching die parameter record library is respectively subjected to operation scene twin recognition to generate a plurality of die operation scene twin coefficients; Selecting a winning mold operation scenario twin coefficient according to the multiple mold operation scenario twin coefficients; Based on the punching die parameter record library, the winning sample punching die parameter scheme is matched according to the twin coefficient of the winning mold operation scenario, and the registered punching die scheme is feature fused according to the B-dimensional punching die parameter variables to obtain the registered punching die scheme.

5. The method for optimizing punching die parameters based on demand analysis according to claim 1, characterized in that: According to the second punching die optimization rule, the punching die variation optimization domain is deeply optimized to determine the punching die parameter optimization solution, including: Perform mold production quality prediction based on the punching mold variation optimization domain and generate mold quality prediction coefficients for multiple solutions; Based on the mold quality prediction coefficients of the multiple solutions, the punching mold variation optimization domain is selected according to the second punching mold optimization rule to obtain the punching mold variation selection domain, wherein the second punching mold optimization rule includes a mold quality constraint interval; A die production cost minimization analysis is performed based on the punching die variation selection domain to generate a punching die parameter optimization solution.

6. The punching die parameter optimization system based on demand analysis is characterized by: The system is used to implement the method for optimizing punching die parameters based on demand analysis according to any one of claims 1 to 5, and the system includes: A demand instruction receiving module, the demand instruction receiving module is used to receive a punching die demand instruction, wherein the punching die demand instruction includes punching die operation scene feature data, wherein the punching die operation scene feature data includes stamping process feature data, stamping material feature data and stamping process environment feature data; A variable coupling cleaning module, wherein the variable coupling cleaning module is used to perform variable coupling cleaning on the A-dimensional punching die parameter variables according to a predetermined variable coupling constraint value to generate a B-dimensional punching die parameter variable, wherein A and B are both positive integers greater than 1, and B is less than or equal to A; A registration punching die solution generation module is configured to perform backtracking registration of punching die parameters based on the punching die operation scene feature data and the B-dimensional punching die parameter variables to generate a registration punching die solution; A scheme variation optimization module is used to perform variation optimization on the registered punching die scheme according to the first punching die optimization rule and in combination with the punching die variation optimization dual channels to generate a punching die variation optimization domain; The punching die parameter optimization solution determination module is used to perform deep optimization on the punching die variation optimization domain according to the second punching die optimization rule to determine the punching die parameter optimization solution.

Images