Integrated die-casting process parameter optimization method and device, medium and equipment

Abstract

The invention provides an integrated die-casting process parameter optimization method and device, a medium and equipment. The method comprises the following steps: acquiring an initial parameter combination of integrated die-casting process parameters; converting the initial parameter combination into a corresponding fuzzy parameter combination; based on the fuzzy parameter combination, calculating to obtain an evaluation value of the initial parameter combination; if the evaluation value of the initial parameter combination is inferior to a preset evaluation threshold value, updating the initial parameter combination to obtain an updated parameter combination; calculating to obtain an evaluation value of the updated parameter combination based on the updated parameter combination; if the evaluation value of the updated parameter combination is superior to an evaluation threshold value, determining that the updated parameter combination is a target parameter combination; the specific parameter values of the process parameters are converted into the fuzzy parameters, and the process parameters are evaluated and updated based on the fuzzy parameters, so that the target parameter combination is obtained through rapid iteration, and the optimization efficiency of the process parameters is effectively improved.

Description

Technical Field

[0001] The present application relates to the technical field of integrated die-casting process, and specifically to an integrated die-casting process parameter optimization method, device, medium and equipment. Background Art

[0002] Integrated die casting (such as integrated die casting of vehicle bodies) is a manufacturing technology that integrates multiple parts into one, which can simplify the number of parts, reduce costs and improve production efficiency. In the integrated die casting process, due to the extremely large size of the casting and the mold, the process is complicated and the production cost is extremely high. During the die casting process, the forming conditions and performance of different areas vary greatly. The unreasonable design of the pouring and overflow system will lead to poor filling of the casting, which seriously affects the quality of the product. Therefore, the process parameters need to be optimized before integrated die casting.

[0003] Existing die-casting process parameter optimization methods mainly use simulation to predict the flow of molten metal, the solidification process, and the distribution of defects. However, since integrated die-casting involves complex material flow and temperature control, as well as complex structures and large volumes, the workload of process parameter optimization will increase exponentially with the increase in the number of process factors considered. The simulation calculation is large, the optimization time is long, and the analysis is difficult, which increases the R&D cost. Therefore, there is an urgent need for a method that can quickly achieve process parameter optimization for integrated die-casting. Summary of the invention

[0004] In order to solve the above technical problems, the present application is proposed. The embodiments of the present application provide an integrated die-casting process parameter optimization method, device, medium and equipment.

[0005] According to one aspect of the present application, a method for optimizing integrated die-casting process parameters is provided, comprising: obtaining an initial parameter combination of integrated die-casting process parameters; wherein the initial parameter combination includes initial parameter values ​​of all process parameters; converting the initial parameter combination into a corresponding fuzzy parameter combination; wherein the fuzzy parameter combination represents the parameter level at which the initial parameter value in the initial parameter combination is located; based on the fuzzy parameter combination, calculating an evaluation value of the initial parameter combination; the evaluation value of the initial parameter combination represents the integrated die-casting result level corresponding to the initial parameter combination; if the evaluation value of the initial parameter combination is worse than a preset evaluation threshold, updating the initial parameter combination to obtain an updated parameter combination; based on the updated parameter combination, calculating an evaluation value of the updated parameter combination; the evaluation value of the updated parameter combination represents the integrated die-casting result level corresponding to the updated parameter combination; if the evaluation value of the updated parameter combination is better than the evaluation threshold, determining the updated parameter combination as the target parameter combination.

[0006] In one embodiment, the parameter levels include low level, medium level and high level; wherein, converting the initial parameter combination into the corresponding fuzzy parameter combination includes: using a triangular membership function to divide each of the initial parameters to obtain the fuzzy parameter combination; wherein the fuzzy parameter combination includes the parameter level of each process parameter.

[0007] In one embodiment, the evaluation value includes multiple integrated die-casting result indicators; wherein, if the evaluation value of the updated parameter combination is better than the evaluation threshold, determining the updated parameter combination as the target parameter combination includes: if multiple integrated die-casting result indicators in the evaluation value of the updated parameter combination are better than the evaluation threshold, determining the updated parameter combination as the target parameter combination.

[0008] In one embodiment, updating the initial parameter combination to obtain the updated parameter combination includes: using a genetic algorithm to update the initial parameter combination to obtain the updated parameter combination.

[0009] In one embodiment, the use of a genetic algorithm to update the initial parameter combination to obtain the updated parameter combination includes: using a genetic algorithm to iteratively update the initial parameter combination to obtain multiple groups of updated parameter combinations; dividing the multiple groups of updated parameter combinations into multiple non-dominated combinations; calculating the non-dominated combinations of the same level to obtain a Pareto front; calculating the crowding distance of each non-dominated combination on the corresponding Pareto front; wherein the crowding distance represents the distance from the non-dominated combination to the line connecting the preceding non-dominated combination and the subsequent non-dominated combination; based on the crowding distance and the Pareto front, determining the optimal non-dominated combination as the updated parameter combination.

[0010] In one embodiment, the evaluation value includes multiple integrated die-casting result indicators; wherein, if the evaluation value of the updated parameter combination is better than the evaluation threshold, determining the updated parameter combination as the target parameter combination includes: if there are multiple updated parameter combinations with evaluation values ​​better than the evaluation threshold, calculating the Jacobian matrix of the updated parameter combination; wherein the vector in the Jacobian matrix represents the Jacobian determinant of the multiple integrated die-casting result indicators for each process parameter; calculating the sum of the absolute values ​​of each element in the Jacobian matrix corresponding to a single process parameter to obtain the sensitivity of the single process parameter; selecting the updated parameter combination corresponding to the Jacobian matrix with the lowest sensitivity as the target parameter combination.

[0011] In one embodiment, before the evaluation value of the initial parameter combination is calculated based on the fuzzy parameter combination, the integrated die-casting process parameter optimization method further includes: calculating the sum of squares of differences between the predicted value and the actual value of the fuzzy logic model to obtain a residual sum of squares; wherein the actual value is the actual result of the input value corresponding to the fuzzy predicted value; calculating the sum of squares of differences between the average value of the actual value and the actual value to obtain a total sum of squares; calculating the accuracy of the fuzzy logic model based on the residual sum of squares and the total sum of squares; if the accuracy of the fuzzy logic model is lower than or equal to a preset accuracy threshold, continuing to train the fuzzy logic model until the accuracy of the fuzzy logic model is higher than the accuracy threshold; the calculation of the evaluation value of the initial parameter combination based on the fuzzy parameter combination includes: inputting the fuzzy parameter combination into the fuzzy logic model to calculate the evaluation value of the initial parameter combination.

[0012] According to another aspect of the present application, an integrated die-casting process parameter optimization device is provided, including: an initial parameter acquisition module, used to acquire an initial parameter combination of integrated die-casting process parameters; wherein the initial parameter combination includes initial parameter values ​​of all process parameters; a fuzzy parameter conversion module, used to convert the initial parameter combination into a corresponding fuzzy parameter combination; wherein the fuzzy parameter combination represents the parameter level at which the initial parameter value in the initial parameter combination is located; an initial parameter evaluation module, used to calculate an evaluation value of the initial parameter combination based on the fuzzy parameter combination; the evaluation value of the initial parameter combination represents the integrated die-casting result level corresponding to the initial parameter combination; a parameter combination updating module, used to update the initial parameter combination to obtain an updated parameter combination if the evaluation value of the initial parameter combination is inferior to a preset evaluation threshold; an updated parameter evaluation module, used to calculate an evaluation value of the updated parameter combination based on the updated parameter combination; the evaluation value of the updated parameter combination represents the integrated die-casting result level corresponding to the updated parameter combination; a target parameter determination module, used to determine the updated parameter combination as a target parameter combination if the evaluation value of the updated parameter combination is better than the evaluation threshold.

[0013] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the storage medium stores a computer program, and the computer program is used to execute any of the above methods.

[0014] According to another aspect of the present application, an electronic device is provided, comprising: a processor; a memory for storing instructions executable by the processor; and the processor is used to execute any of the above-described methods.

[0015] The present application provides an integrated die-casting process parameter optimization method, device, medium and equipment, which obtains an initial parameter combination of integrated die-casting process parameters; wherein the initial parameter combination includes initial parameter values ​​of all process parameters; converts the initial parameter combination into a corresponding fuzzy parameter combination; wherein the fuzzy parameter combination represents the parameter level where the initial parameter value in the initial parameter combination is located; based on the fuzzy parameter combination, an evaluation value of the initial parameter combination is calculated; the evaluation value of the initial parameter combination represents the integrated die-casting result level corresponding to the initial parameter combination; if the evaluation value of the initial parameter combination is worse than a preset evaluation threshold, the initial parameter combination is updated to obtain an updated parameter combination; based on the updated parameter combination, an evaluation value of the updated parameter combination is calculated; the evaluation value of the updated parameter combination represents the integrated die-casting result level corresponding to the updated parameter combination; if the evaluation value of the updated parameter combination is better than the evaluation threshold, the updated parameter combination is determined to be a target parameter combination; that is, by converting the specific parameter values ​​of the process parameters into fuzzy parameters, and evaluating and updating the process parameters based on the fuzzy parameters, the target parameter combination is obtained by rapid iteration, thereby effectively improving the optimization efficiency of the process parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0017] Figure 1 It is a flow chart of an integrated die-casting process parameter optimization method provided by an exemplary embodiment of the present application.

[0018] Figure 2 It is a structural schematic diagram of the triangular membership function of the input parameters of the integrated die-casting process parameter optimization method provided by an exemplary embodiment of the present application.

[0019] Figure 3 It is a structural schematic diagram of the triangular membership function of the output result of the integrated die-casting process parameter optimization method provided by an exemplary embodiment of the present application.

[0020] Figure 4 It is a structural schematic diagram of an integrated die-casting process parameter optimization device provided by an exemplary embodiment of the present application.

[0021] Figure 5 It is a structural diagram of an electronic device provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0022] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0023] Figure 1 FIG. 1 is a flow chart of an integrated die-casting process parameter optimization method provided by an exemplary embodiment of the present application. Figure 1 As shown, the integrated die-casting process parameter optimization method includes the following steps:

[0024] Step 110: Obtaining an initial parameter combination of integrated die-casting process parameters.

[0025] The initial parameter combination includes the initial parameter values ​​of all process parameters. By setting the initial parameter combination of the integrated die-casting process parameters, such as setting empirical values, the efficiency of process parameter optimization can be improved.

[0026] Step 120: Convert the initial parameter combination into a corresponding fuzzy parameter combination.

[0027] The fuzzy parameter combination represents the parameter level where the initial parameter value in the initial parameter combination is located. The present application converts the initial parameter combination into a fuzzy parameter combination, for example, according to the parameter level where each initial parameter value in the initial parameter combination is located, the initial parameter value is converted into a corresponding parameter level, including a low level, a medium level, a high level, etc., thereby converting a plurality of initial parameter values ​​into a smaller number of parameter levels, so as to reduce the data volume and thus improve the efficiency of process parameter optimization.

[0028] Step 130: Based on the fuzzy parameter combination, an evaluation value of the initial parameter combination is calculated.

[0029] The evaluation value of the initial parameter combination represents the integrated die-casting result level corresponding to the initial parameter combination. The present application obtains the corresponding evaluation value based on the fuzzy parameter combination calculation, that is, obtains the evaluation value of the initial parameter combination, so as to judge whether the initial parameter combination meets the process parameter requirements of the integrated die-casting.

[0030] Step 140: If the evaluation value of the initial parameter combination is worse than a preset evaluation threshold, the initial parameter combination is updated to obtain an updated parameter combination.

[0031] If the calculated evaluation value is worse than the evaluation threshold, it means that the initial parameter combination cannot meet the requirements of the integrated die-casting process. At this time, the values ​​of the process parameters are updated based on the initial parameter combination to obtain an updated parameter combination.

[0032] Step 150: Based on the updated parameter combination, an evaluation value of the updated parameter combination is calculated.

[0033] Among them, the evaluation value of the updated parameter combination represents the integrated die-casting result level corresponding to the updated parameter combination. After the updated parameter combination is updated, the evaluation value of the updated parameter combination is calculated again. At this time, the updated parameter combination can also be converted into a fuzzy parameter combination and the corresponding evaluation value is calculated to determine whether the updated parameter combination meets the process parameter requirements of the integrated die-casting.

[0034] Step 160: If the evaluation value of the updated parameter combination is better than the evaluation threshold, the updated parameter combination is determined to be the target parameter combination.

[0035] If the calculated evaluation value is better than the evaluation threshold, it means that the updated parameter combination meets the requirements of the integrated die-casting process. At this time, the updated parameter combination is used as the target parameter combination, that is, the various parameter values ​​in the updated parameter combination are used as the target values ​​of the process parameters, so as to optimize the process parameters and ensure the results of the integrated die-casting process.

[0036] The present application provides an integrated die-casting process parameter optimization method, which obtains an initial parameter combination of integrated die-casting process parameters; wherein the initial parameter combination includes initial parameter values ​​of all process parameters; converts the initial parameter combination into a corresponding fuzzy parameter combination; wherein the fuzzy parameter combination represents the parameter level where the initial parameter value in the initial parameter combination is located; based on the fuzzy parameter combination, an evaluation value of the initial parameter combination is calculated; the evaluation value of the initial parameter combination represents the integrated die-casting result level corresponding to the initial parameter combination; if the evaluation value of the initial parameter combination is worse than a preset evaluation threshold, the initial parameter combination is updated to obtain an updated parameter combination; based on the updated parameter combination, an evaluation value of the updated parameter combination is calculated; the evaluation value of the updated parameter combination represents the integrated die-casting result level corresponding to the updated parameter combination; if the evaluation value of the updated parameter combination is better than the evaluation threshold, the updated parameter combination is determined to be a target parameter combination; that is, by converting the specific parameter values ​​of the process parameters into fuzzy parameters, and evaluating and updating the process parameters based on the fuzzy parameters, the target parameter combination can be obtained by rapid iteration, thereby effectively improving the optimization efficiency of the process parameters.

[0037] In one embodiment, the parameter levels include low level, medium level and high level; wherein, the specific implementation method of the above step 120 may be: using a triangular membership function to divide each initial parameter to obtain a fuzzy parameter combination; wherein the fuzzy parameter combination includes the parameter level of each process parameter.

[0038] like Figure 2As shown, the present application can divide parameter levels into low level, medium level and high level, and use triangular membership function to divide each initial parameter to obtain fuzzy parameter combination. For example, the parameter value corresponding to the low level is 1-2, the parameter value corresponding to the medium level is 1-3, and the parameter value corresponding to the high level is 2-3. There is an intersection between the low level, the medium level and the high level. When determining which level a certain parameter value belongs to, the coordinate point corresponding to the parameter value (the point on the horizontal axis) can be extended along the vertical axis to obtain the level corresponding to the higher intersection point of the triangular membership function of the low level, the medium level and the high level as the level corresponding to the parameter value. For example, the level corresponding to the parameter value 1.2 is the low level, and the level corresponding to 1.8 is the medium level.

[0039] In one embodiment, the evaluation value includes multiple integrated die-casting result indicators; wherein, the specific implementation method of the above step 160 may be: if multiple integrated die-casting result indicators in the evaluation value of the updated parameter combination are better than the evaluation threshold, then the updated parameter combination is determined to be the target parameter combination.

[0040] This application can use multi-indicator evaluation, that is, use multiple integrated die-casting result indicators to evaluate the updated parameter combination at the same time. If all indicator evaluation results are better than the corresponding evaluation threshold, it means that the updated parameter combination at this time can meet the requirements of the integrated die-casting process. At this time, the updated parameter combination is used as the target parameter combination. For example, using solidification time, maximum grain size and minimum yield strength as evaluation indicators, the optimal parameter combination is generated by the following formula:

[0041] Minimize{f1(T init ,T wall ),f2(T init ,T wall ),f3(T init ,T wall )};

[0042] Among them, f1(T init ,T wall ) is the solidification time, f1(T init ,T wall ) is the grain size, f1(T init ,T wall ) is -min (yield strength), T init and T wall They are pouring temperature and initial mold temperature respectively.

[0043] Specifically, Figure 3As shown, the present application can divide the evaluation values ​​into extremely low level, low level, medium level, high level and extremely high level, and use the triangular membership function to divide each evaluation value to obtain a fuzzy evaluation result. For example, the parameter value corresponding to the extremely low level is 1-2, the parameter value corresponding to the low level is 1-3, the parameter value corresponding to the medium level is 2-4, the parameter value corresponding to the high level is 3-5, and the parameter value corresponding to the extremely high level is 4-5. There are intersections among the extremely low level, low level, medium level, high level and extremely high level. When determining which level a certain evaluation value belongs to, the coordinate point corresponding to the evaluation value (the point on the horizontal axis) can be extended along the vertical axis to obtain the level corresponding to the higher intersection point of the triangular membership function of the extremely low level, low level, medium level, high level and extremely high level as the level corresponding to the evaluation value. For example, the level corresponding to the evaluation value of 1.2 is the extremely low level, and the level corresponding to 1.8 is the low level.

[0044] It should be understood that the present application may also select only a single integrated die-casting result indicator as the main evaluation indicator, and use the evaluation value of the evaluation indicator as a measure of the quality of the updated parameter combination.

[0045] In one embodiment, the specific implementation of the above step 140 may be: using a genetic algorithm to update the initial parameter combination to obtain an updated parameter combination.

[0046] The present application adopts a genetic algorithm to update the initial parameter combination to obtain an updated parameter combination. Specifically, the first generation population is randomly initialized, and the evaluation value of each individual in the first generation population is calculated to determine the update direction of the optimization target, and individuals with higher evaluation values ​​are selected to perform selection, crossover and mutation operations to generate the next generation population. The optimization is stopped until the evaluation value of an individual is better than the evaluation threshold, or the number of iterative updates reaches a preset number (for example, 100 times).

[0047] In one embodiment, the specific implementation method of the above step 140 can be: based on the initial parameter combination, a genetic algorithm is used for updating and iterating to obtain multiple groups of updated parameter combinations; the multiple groups of updated parameter combinations are divided into multiple non-dominated combinations; the non-dominated combinations of the same level are calculated to obtain the Pareto front; the crowding distance of each non-dominated combination on the corresponding Pareto front is calculated; wherein the crowding distance represents the distance from the non-dominated combination to the line connecting the previous non-dominated combination and the subsequent non-dominated combination; based on the crowding distance and the Pareto front, the optimal non-dominated combination is determined as the updated parameter combination.

[0048] This application uses a non-dominated sorting genetic algorithm to divide the population into multiple non-dominated combination levels (i.e., Pareto fronts), and calculates the crowding distance of each non-dominated combination on the corresponding Pareto front to retain the diversity of the population. According to the crowding distance of the non-dominated combination on the corresponding Pareto front and the corresponding Pareto front, the individual with the highest fitness (i.e., non-dominated combination) is selected as the optimized parameter combination.

[0049] In one embodiment, the evaluation value includes multiple integrated die-casting result indicators; wherein, the specific implementation method of the above step 160 may be: if there are multiple updated parameter combinations whose evaluation values ​​are better than the evaluation threshold, then the Jacobian matrix of the updated parameter combination is calculated; wherein, the vector in the Jacobian matrix represents the Jacobian determinant of multiple integrated die-casting result indicators for each process parameter; the sum of the absolute values ​​of each element in the Jacobian matrix corresponding to a single process parameter is calculated to obtain the sensitivity of the single process parameter; and the updated parameter combination corresponding to the Jacobian matrix with the lowest sensitivity is selected as the target parameter combination.

[0050] The optimal parameter combination generated by the genetic algorithm can quantify the sensitivity of the output of all Pareto optimal solutions to each input based on the local sensitivity analysis of the process parameters, and select the stable optimal solution with lower input sensitivity. For a function with input x∈Rn (i.e., n-dimensional vector) and output f∈Rm (i.e., m-dimensional vector), the m×n-dimensional Jacobian matrix is ​​defined as:

[0051]

[0052] Where 1≤i≤m, 1≤j≤n. At a given point x, the local sensitivity of f to each input can be defined as the Jacobian matrix at that point: J f (x). Then, the sum of the absolute values ​​of the components of the Jacobian matrix is ​​used as a single scalar metric to quantify the local sensitivity, and the stable optimal solution with lower input sensitivity is selected as the target parameter combination.

[0053] In one embodiment, before step 130, the above-mentioned integrated die-casting process parameter optimization method may further include: calculating the sum of squares of the differences between the predicted value and the actual value of the fuzzy logic model to obtain the residual sum of squares; wherein the actual value is the actual result of the input value corresponding to the fuzzy predicted value; calculating the sum of squares of the differences between the average value of the actual value and the actual value to obtain the total sum of squares; based on the residual sum of squares and the total sum of squares, calculating the accuracy of the fuzzy logic model; if the accuracy of the fuzzy logic model is lower than or equal to a preset accuracy threshold, continuing to train the fuzzy logic model until the accuracy of the fuzzy logic model is higher than the accuracy threshold; correspondingly, the specific implementation method of the above-mentioned step 130 may be: inputting the fuzzy parameter combination into the fuzzy logic model, and calculating the evaluation value of the initial parameter combination.

[0054] This application adopts the orthogonal design method to design 18 sets of experimental data, where the process parameters include pouring temperature, filling time, injection pressure, initial mold temperature and punch speed. The parameter values ​​of each process parameter are converted into parameter levels to obtain the experimental data matrix shown in the following table:

[0055]

[0056]

[0057] The above 18 groups of experimental data and the corresponding evaluation results (corresponding evaluation values) are used as samples to construct a fuzzy logic model. The fuzzy logic model includes four parts: knowledge base, fuzzifier, inference engine and defuzzifier. The knowledge base includes a database and a rule base, which are used to store variable data such as input and output, rule data between input and output, etc. The fuzzifier converts input parameters into input fuzzy variables according to the fuzzy rules of the knowledge base, and the inference engine generates output fuzzy variables according to the fuzzy rules and input fuzzy variables. The defuzzifier converts the output fuzzy variables into a scalar of the target value (i.e., the evaluation value). The fuzzy logic model can use the Mamdani reasoning system and use the centroid method to convert the fuzzy output into the predicted value of the actual integrated die-casting molding result.

[0058] After constructing the fuzzy logic model, the present application calculates the sum of squares of the difference between the predicted value and the actual value of the fuzzy logic model to obtain the residual sum of squares SSR; and calculates the sum of squares of the difference between the average value of the actual value and the actual value to obtain the total sum of squares SST; based on the residual sum of squares and the total sum of squares, the accuracy of the fuzzy logic model is calculated; if the accuracy of the fuzzy logic model is lower than or equal to the preset accuracy threshold, the fuzzy logic model is continuously trained until the accuracy of the fuzzy logic model is higher than the accuracy threshold; wherein, the accuracy of the fuzzy logic model can be calculated using the following formula:

[0059]

[0060] Among them, R is the accuracy.

[0061] Compared with the traditional optimization method, the integrated die-casting process parameter optimization method provided in this application has the following advantages:

[0062] 1. Reduce optimization time and reduce costs. Traditional optimization methods take several hours to several days to simulate once, while this application uses a fuzzy logic model with less data to give the best process parameters in a short time, greatly reducing optimization time and R&D time, and reducing R&D costs. By combining genetic algorithms with fuzzy logic models, the evaluation values ​​under the optimization parameter combination can be quickly predicted, thereby improving optimization efficiency.

[0063] 2. Improve the accuracy of process parameters, reduce the defect rate, and improve product quality. Common defects in integrated die-casting include pores, cold shuts, shrinkage holes, and warping, which directly affect the strength and appearance of the product. The traditional optimization method is to adjust the process parameters based on the prediction results of numerical simulations and the experience of workers. The process parameters determined by the results of a limited number of numerical simulations and the experience of workers are inaccurate. This application uses a fuzzy logic model to quickly obtain the results corresponding to different process parameters (such as pouring speed, mold temperature, casting pressure, etc.), and uses an optimization algorithm to quickly obtain the optimal process parameters, which can effectively reduce or eliminate these defects, improve the overall quality of the product, and meet the requirements of high strength and high precision.

[0064] 3. Ability to meet multiple requirements. Integrated die casting is often used in the automotive field. Based on production and safety, the input process parameters must meet many requirements: high strength, low defect rate, low shrinkage rate, etc. Traditional optimization methods cannot optimize process parameters by taking into account multiple objectives. This application can consider multiple conflicting objectives at the same time and find the best balance between the objectives, so as to comprehensively consider and achieve the best process parameter optimization.

[0065] Figure 4 Schematic diagram of the structure of an integrated die-casting process parameter optimization device provided by an exemplary embodiment of the present application. Figure 4 As shown, the integrated die-casting process parameter optimization device 40 includes: an initial parameter acquisition module 41, which is used to obtain the initial parameter combination of the integrated die-casting process parameters; wherein the initial parameter combination includes the initial parameter values ​​of all process parameters; a fuzzy parameter conversion module 42, which is used to convert the initial parameter combination into a corresponding fuzzy parameter combination; wherein the fuzzy parameter combination represents the parameter level where the initial parameter value in the initial parameter combination is located; an initial parameter evaluation module 43, which is used to calculate the evaluation value of the initial parameter combination based on the fuzzy parameter combination; wherein the evaluation value of the initial parameter combination represents the integrated die-casting result level corresponding to the initial parameter combination; a parameter combination updating module 44, which is used to update the initial parameter combination to obtain an updated parameter combination if the evaluation value of the initial parameter combination is inferior to a preset evaluation threshold; an updated parameter evaluation module 45, which is used to calculate the evaluation value of the updated parameter combination based on the updated parameter combination; wherein the evaluation value of the updated parameter combination represents the integrated die-casting result level corresponding to the updated parameter combination; a target parameter determination module 46, which is used to determine the updated parameter combination as the target parameter combination if the evaluation value of the updated parameter combination is better than the evaluation threshold.

[0066] The present application provides an integrated die-casting process parameter optimization device, which obtains the initial parameter combination of the integrated die-casting process parameters through the initial parameter acquisition module 41; wherein the initial parameter combination includes the initial parameter values ​​of all process parameters; the fuzzy parameter conversion module 42 converts the initial parameter combination into the corresponding fuzzy parameter combination; wherein the fuzzy parameter combination represents the parameter level of the initial parameter value in the initial parameter combination; the initial parameter evaluation module 43 calculates the evaluation value of the initial parameter combination based on the fuzzy parameter combination; the evaluation value of the initial parameter combination represents the integrated die-casting result level corresponding to the initial parameter combination; if the evaluation value of the initial parameter combination is worse than the expected value, the initial parameter combination is converted into the corresponding fuzzy parameter combination; the fuzzy parameter conversion module 42 converts the initial parameter combination into the corresponding fuzzy parameter combination; the fuzzy parameter conversion ...2 converts the initial parameter combination into the corresponding fuzzy parameter combination; the fuzzy parameter conversion module 42 converts the initial parameter combination into the corresponding fuzzy parameter combination; the fuzzy parameter conversion module 42 converts the initial parameter combination into the corresponding fuzzy parameter combination; the fuzzy parameter conversion module 42 converts the initial parameter combination into the corresponding fuzzy parameter combination; the fuzzy parameter conversion module 42 converts the fuzzy parameter combination into the corresponding fuzzy parameter combination; the fuzzy parameter conversion module 42 converts the fuzzy parameter combination into the corresponding fuzzy parameter combination; the fuzzy parameter conversion module 42 convert The evaluation threshold is set, the parameter combination updating module 44 updates the initial parameter combination to obtain an updated parameter combination; the updated parameter evaluation module 45 calculates the evaluation value of the updated parameter combination based on the updated parameter combination; the evaluation value of the updated parameter combination represents the integrated die-casting result grade corresponding to the updated parameter combination; if the evaluation value of the updated parameter combination is better than the evaluation threshold, the target parameter determination module 46 determines the updated parameter combination as the target parameter combination; that is, by converting the specific parameter values ​​of the process parameters into fuzzy parameters, and evaluating and updating the process parameters based on the fuzzy parameters, the target parameter combination can be obtained by rapid iteration, thereby effectively improving the optimization efficiency of the process parameters.

[0067] In one embodiment, the parameter levels include low level, medium level and high level; wherein the fuzzy parameter conversion module 42 can be further configured to: divide each initial parameter using a triangular membership function to obtain a fuzzy parameter combination; wherein the fuzzy parameter combination includes the parameter level of each process parameter.

[0068] In one embodiment, the evaluation value includes multiple integrated die-casting result indicators; wherein the above-mentioned target parameter determination module 46 can be further configured as: if multiple integrated die-casting result indicators in the evaluation value of the updated parameter combination are better than the evaluation threshold, then the updated parameter combination is determined to be the target parameter combination.

[0069] In one embodiment, the parameter combination updating module 44 may be further configured to: update the initial parameter combination using a genetic algorithm to obtain an updated parameter combination.

[0070] In one embodiment, the parameter combination updating module 44 can be further configured as follows: based on the initial parameter combination, a genetic algorithm is used for updating iteration to obtain multiple groups of updated parameter combinations; the multiple groups of updated parameter combinations are divided into multiple non-dominated combinations; the non-dominated combinations of the same level are calculated to obtain the Pareto front; the crowding distance of each non-dominated combination on the corresponding Pareto front is calculated; wherein the crowding distance represents the distance from the non-dominated combination to the line connecting the preceding non-dominated combination and the subsequent non-dominated combination; based on the crowding distance and the Pareto front, the optimal non-dominated combination is determined as the updated parameter combination.

[0071] In one embodiment, the evaluation value includes multiple integrated die-casting result indicators; wherein, the above-mentioned target parameter determination module 46 can be further configured as: if there are multiple updated parameter combinations whose evaluation values ​​are better than the evaluation threshold, then the Jacobian matrix of the updated parameter combination is calculated; wherein, the vector in the Jacobian matrix represents the Jacobian determinant of multiple integrated die-casting result indicators for each process parameter; the sum of the absolute values ​​of each element in the Jacobian matrix corresponding to a single process parameter is calculated to obtain the sensitivity of the single process parameter; and the updated parameter combination corresponding to the Jacobian matrix with the lowest sensitivity is selected as the target parameter combination.

[0072] In one embodiment, the above-mentioned integrated die-casting process parameter optimization device can be further configured as follows: calculating the sum of squares of the differences between the predicted value and the actual value of the fuzzy logic model to obtain the residual sum of squares; wherein the actual value is the actual result of the input value corresponding to the fuzzy predicted value; calculating the sum of squares of the differences between the average value of the actual value and the actual value to obtain the total sum of squares; based on the residual sum of squares and the total sum of squares, calculating the accuracy of the fuzzy logic model; if the accuracy of the fuzzy logic model is lower than or equal to a preset accuracy threshold, continuing to train the fuzzy logic model until the accuracy of the fuzzy logic model is higher than the accuracy threshold; correspondingly, the above-mentioned initial parameter evaluation module 43 can be further configured as follows: inputting the fuzzy parameter combination into the fuzzy logic model, and calculating the evaluation value of the initial parameter combination.

[0073] Below, reference Figure 5 The electronic device according to the embodiment of the present application is described. The electronic device may be any one or both of the first device and the second device, or a stand-alone device independent of them, and the stand-alone device may communicate with the first device and the second device to receive the collected input signal from them.

[0074] Figure 5 A block diagram of an electronic device according to an embodiment of the present application is illustrated.

[0075] like Figure 5 As shown, the electronic device 10 includes one or more processors 11 and a memory 12 .

[0076] The processor 11 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

[0077] The memory 12 may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The non-volatile memory may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 11 may run the program instructions to implement the methods of the various embodiments of the present application described above and / or other desired functions. Various contents such as input signals, signal components, noise components, etc. may also be stored in the computer-readable storage medium.

[0078] In one example, the electronic device 10 may further include: an input device 13 and an output device 14, and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0079] When the electronic device is a stand-alone device, the input device 13 may be a communication network connector, which is used to receive the collected input signals from the first device and the second device.

[0080] In addition, the input device 13 may also include, for example, a keyboard, a mouse, etc.

[0081] The output device 14 can output various information to the outside, including the determined distance information, direction information, etc. The output device 14 can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.

[0082] Of course, to simplify, Figure 5 Only some of the components related to the present application in the electronic device 10 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application situations, the electronic device 10 may also include any other appropriate components.

[0083] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the method according to various embodiments of the present application described in the above-mentioned "Exemplary Method" section of this specification.

[0084] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0085] In addition, an embodiment of the present application may also be a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes the steps of the method according to various embodiments of the present application described in the above "Exemplary Method" section of this specification.

[0086] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0087] The basic principles of the present application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present application. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, not for limitation, and the above details do not limit the present application to being implemented by adopting the above specific details.

[0088] The block diagrams of the devices, apparatuses, equipment, and systems involved in this application are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The words "such as" used here refer to the phrase "such as but not limited to", and can be used interchangeably with them.

[0089] It should also be noted that in the apparatus, device and method of the present application, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0090] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0091] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. An integrated die-casting process parameter optimization method, characterized in that: include: Acquire an initial parameter combination of integrated die-casting process parameters; wherein the initial parameter combination includes initial parameter values ​​of all process parameters; Converting the initial parameter combination into a corresponding fuzzy parameter combination; wherein the fuzzy parameter combination represents the parameter level at which the initial parameter value in the initial parameter combination is located; Based on the fuzzy parameter combination, an evaluation value of the initial parameter combination is calculated; the evaluation value of the initial parameter combination represents the integrated die-casting result grade corresponding to the initial parameter combination; If the evaluation value of the initial parameter combination is worse than a preset evaluation threshold, updating the initial parameter combination to obtain an updated parameter combination; Based on the update parameter combination, an evaluation value of the update parameter combination is calculated; the evaluation value of the update parameter combination represents the integrated die-casting result grade corresponding to the update parameter combination; If the evaluation value of the updated parameter combination is better than the evaluation threshold, the updated parameter combination is determined to be the target parameter combination.

2. The integrated die-casting process parameter optimization method according to claim 1, characterized in that: The parameter levels include low level, medium level and high level; wherein, converting the initial parameter combination into a corresponding fuzzy parameter combination includes: Each of the initial parameters is divided by using a triangular membership function to obtain the fuzzy parameter combination; wherein the fuzzy parameter combination includes a parameter level of each process parameter.

3. The integrated die-casting process parameter optimization method according to claim 1, characterized in that: The evaluation value includes a plurality of integrated die-casting result indicators; wherein, if the evaluation value of the updated parameter combination is better than the evaluation threshold, determining the updated parameter combination as the target parameter combination includes: If a plurality of the integrated die-casting result indicators in the evaluation values ​​of the updated parameter combination are better than the evaluation threshold, the updated parameter combination is determined to be the target parameter combination.

4. The integrated die-casting process parameter optimization method according to claim 1, characterized in that: The updating of the initial parameter combination to obtain the updated parameter combination comprises: The initial parameter combination is updated by using a genetic algorithm to obtain the updated parameter combination.

5. The integrated die-casting process parameter optimization method according to claim 4, characterized in that: The adopting of a genetic algorithm to update the initial parameter combination to obtain the updated parameter combination comprises: Based on the initial parameter combination, a genetic algorithm is used to update and iterate to obtain multiple groups of updated parameter combinations; Dividing the plurality of update parameter combinations into a plurality of non-dominated combinations; Calculate the non-dominated combinations of the same level to obtain the Pareto front; Calculating the crowding distance of each non-dominated combination on the corresponding Pareto front; wherein the crowding distance represents the distance from the non-dominated combination to the line connecting the preceding non-dominated combination and the subsequent non-dominated combination; Based on the crowding distance and the Pareto front, an optimal non-dominated combination is determined as the update parameter combination.

6. The integrated die-casting process parameter optimization method according to claim 5, characterized in that: The evaluation value includes a plurality of integrated die-casting result indicators; wherein, if the evaluation value of the updated parameter combination is better than the evaluation threshold, determining the updated parameter combination as the target parameter combination includes: If there are multiple update parameter combinations whose evaluation values ​​are better than the evaluation threshold, the Jacobian matrix of the update parameter combination is calculated; wherein the vectors in the Jacobian matrix represent the Jacobian determinant of the multiple integrated die-casting result indicators for each process parameter; Calculating the sum of the absolute values ​​of the elements in the Jacobian matrix corresponding to the single process parameter to obtain the sensitivity of the single process parameter; The update parameter combination corresponding to the Jacobian matrix with the lowest sensitivity is selected as the target parameter combination.

7. The integrated die-casting process parameter optimization method according to claim 1, characterized in that: Before calculating the evaluation value of the initial parameter combination based on the fuzzy parameter combination, the integrated die-casting process parameter optimization method further includes: Calculate the sum of squares of the differences between the predicted value and the actual value of the fuzzy logic model to obtain the residual sum of squares; wherein the actual value is the actual result of the input value corresponding to the fuzzy predicted value; Calculate the average of the actual values ​​and the sum of squares of differences between the actual values ​​to obtain a total sum of squares; Calculating the accuracy of the fuzzy logic model based on the residual sum of squares and the total sum of squares; If the accuracy of the fuzzy logic model is lower than or equal to a preset accuracy threshold, continue to train the fuzzy logic model until the accuracy of the fuzzy logic model is higher than the accuracy threshold; The step of calculating the evaluation value of the initial parameter combination based on the fuzzy parameter combination includes: The fuzzy parameter combination is input into the fuzzy logic model, and the evaluation value of the initial parameter combination is calculated.

8. An integrated die-casting process parameter optimization device, characterized in that: include: An initial parameter acquisition module, used to acquire an initial parameter combination of integrated die-casting process parameters; wherein the initial parameter combination includes initial parameter values ​​of all process parameters; A fuzzy parameter conversion module, used to convert the initial parameter combination into a corresponding fuzzy parameter combination; wherein the fuzzy parameter combination represents the parameter level where the initial parameter value in the initial parameter combination is located; An initial parameter evaluation module, used to calculate an evaluation value of the initial parameter combination based on the fuzzy parameter combination; the evaluation value of the initial parameter combination represents the integrated die-casting result grade corresponding to the initial parameter combination; A parameter combination updating module, configured to update the initial parameter combination to obtain an updated parameter combination if the evaluation value of the initial parameter combination is worse than a preset evaluation threshold; An update parameter evaluation module, used to calculate an evaluation value of the update parameter combination based on the update parameter combination; the evaluation value of the update parameter combination represents the integrated die-casting result grade corresponding to the update parameter combination; The target parameter determination module is used to determine the updated parameter combination as a target parameter combination if the evaluation value of the updated parameter combination is better than the evaluation threshold.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program is used to execute the method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is used to execute the method described in any one of claims 1 to 7.

Images