A die casting parameter optimization method and related device

Abstract

The present application discloses a die-casting parameter optimization method and related devices, which relate to the field of die-casting optimization technology, including: obtaining multiple die-casting production history data of a target die-casting machine, determining the die-casting production target data corresponding to each die-casting production history data, generating a decision tree for the target die-casting machine based on the die-casting production target data corresponding to the multiple die-casting production history data, and adjusting and optimizing the die-casting parameter values ​​to be optimized through the decision tree. The present application uses a screening method based on quantitative analysis of intrinsic connections, which makes the target die-casting parameters more compatible with the target die-casting machine, and thus the decision tree is more compatible with the target die-casting machine. The parameter optimization results based on the decision tree improve the yield rate. The entire process does not require manual parameters, and the process adjustment process is more efficient, more reproducible, and more transparent and explainable.

Description

Technical Field

[0001] The present application relates to the field of die-casting optimization technology, and in particular to a die-casting parameter optimization method and related devices. Background Art

[0002] The die-casting parameters of the die-casting machine play a decisive role in the quality of product molding. The current method of setting die-casting parameters relies heavily on manual adjustment based on the operator's experience. Due to the lack of a systematic and structured parameter optimization process, there are significant differences in parameter adjustment strategies between different personnel, resulting in a large gap in the quality of product molding. In addition, the manual parameter adjustment method also has problems such as low process adjustment efficiency, poor replicability, and lack of transparent and explainable decision-making basis.

[0003] An existing method (CN119066817A) attempts to automatically optimize die-casting parameters. Based on a die-casting process knowledge base and die-casting production history data, the importance of die-casting parameters is calculated through a clustering algorithm to obtain a die-casting parameter set. A nonlinear mapping model between die-casting parameters and corresponding value ranges is constructed through a gradient boosting decision tree algorithm. Combined with the importance of die-casting parameters, an optimized level set of die-casting parameters is generated through a die-casting parameter optimization algorithm. An intelligent interactive test plan is generated through a preset orthogonal experimental design method, and the die-casting equipment is controlled to conduct multiple batch tests to obtain test data. The die-casting parameter configuration strategy is optimized through a deep reinforcement learning model to obtain the optimal die-casting parameter settings, and the optimal die-casting workpiece is produced through the die-casting equipment.

[0004] However, this method uses a clustering algorithm to calculate the importance of die-casting parameters. Because clustering algorithms are highly dependent on initial condition settings, the results are highly random and unstable. This can lead to different partitions when running the same data multiple times, making it difficult to ensure the consistency and reliability of importance assessment. In addition, this method focuses on discovering correlations between historical die-casting production data. Therefore, using clustering results as the basis for parameter importance can easily lead to incorrect identification of key parameters, affecting the effectiveness of subsequent parameter screening and optimization, and reducing the accuracy and practicality of the constructed model. Summary of the Invention

[0005] In view of the above problems, this application provides a die-casting parameter optimization method and related devices to achieve the purpose of automatically adjusting die-casting parameters without human intervention. The specific solution is as follows:

[0006] A first aspect of the present application provides a method for optimizing die-casting parameters, comprising:

[0007] Acquire a plurality of die-casting production history data of a target die-casting machine, wherein each die-casting production history data consists of a product quality grade and a corresponding die-casting parameter set, and the die-casting parameter set includes historical parameter values ​​of each of a plurality of die-casting parameters;

[0008] Determining die-casting production target data corresponding to each die-casting production history data, wherein the die-casting production target data consists of the product quality grade and a corresponding target die-casting parameter set, the target die-casting parameter set includes a historical parameter value of at least one target die-casting parameter, and the target die-casting parameter is obtained by quantitatively analyzing the intrinsic relationship between the die-casting parameter and the product quality grade;

[0009] generating a decision tree for the target die-casting machine according to the die-casting production target data respectively corresponding to the plurality of die-casting production history data;

[0010] The die casting parameter values ​​to be optimized are regulated and optimized using the decision tree.

[0011] In one possible implementation, the target die-casting parameter refers to a die-casting parameter among the multiple die-casting parameters, which can distinguish the product quality grade by adjusting the parameter value, and / or a die-casting parameter whose correlation with the product quality grade is higher than a preset correlation threshold.

[0012] In a possible implementation, determining the die-casting production target data corresponding to each die-casting production history data includes:

[0013] According to the plurality of die-casting production history data, a preset quantitative analysis method is used to screen out the at least one target die-casting parameter from the plurality of die-casting parameters, wherein the quantitative analysis method includes a correlation analysis method and / or a numerical statistics method;

[0014] The die casting production target data is determined from each of the die casting production history data according to the at least one target die casting parameter.

[0015] In a possible implementation, when the quantitative analysis method includes the numerical statistics method, screening out the at least one target die-casting parameter from the plurality of die-casting parameters using a preset quantitative analysis method based on the plurality of die-casting production history data includes:

[0016] For each die-casting parameter of the plurality of die-casting parameters:

[0017] Extracting the historical parameter value of the die-casting parameter and the product quality grade from each of the die-casting production history data, and forming a data point by the historical parameter value and the product quality grade extracted from each of the die-casting production history data as the data point corresponding to each of the die-casting production history data;

[0018] Obtaining a data distribution graph corresponding to the die-casting parameter from the data points respectively corresponding to the plurality of die-casting production history data;

[0019] To obtain data distribution diagrams corresponding to the plurality of die-casting parameters respectively;

[0020] The at least one target die-casting parameter is selected from the plurality of die-casting parameters according to the data distribution graphs respectively corresponding to the plurality of die-casting parameters.

[0021] In a possible implementation, when the quantitative analysis method includes the correlation analysis method, screening out the at least one target die-casting parameter from the plurality of die-casting parameters using a preset quantitative analysis method based on the plurality of die-casting production history data includes:

[0022] For each die-casting parameter of the plurality of die-casting parameters:

[0023] Extracting the historical parameter value of the die-casting parameter and the product quality grade from each of the die-casting production history data, and using the historical parameter value and the product quality grade extracted from each of the die-casting production history data as a to-be-processed value pair corresponding to each of the die-casting production history data;

[0024] Calculating, based on the to-be-processed value pairs corresponding to the plurality of die-casting production history data, a correlation between the die-casting parameter and the product quality grade as the correlation corresponding to the die-casting parameter;

[0025] To obtain the correlations corresponding to the plurality of die-casting parameters;

[0026] The at least one target die-casting parameter is selected from the plurality of die-casting parameters according to the respective correlations corresponding to the plurality of die-casting parameters.

[0027] In a possible implementation, the decision tree is any one of a classification and regression tree, an iterated binary tree 3, and a C4.5 decision tree.

[0028] A second aspect of the present application provides a die-casting parameter optimization device, comprising:

[0029] a historical data acquisition module, configured to acquire a plurality of die-casting production historical data of a target die-casting machine, wherein each of the die-casting production historical data comprises a product quality grade and a corresponding die-casting parameter set, wherein the die-casting parameter set comprises respective historical parameter values ​​of a plurality of die-casting parameters;

[0030] a die-casting parameter screening module, configured to determine die-casting production target data corresponding to each die-casting production history data, wherein the die-casting production target data is composed of the product quality grade and a corresponding target die-casting parameter set, the target die-casting parameter set including a historical parameter value of at least one target die-casting parameter, and the target die-casting parameter is obtained by quantitatively analyzing the intrinsic relationship between the die-casting parameter and the product quality grade;

[0031] a decision tree generating module, configured to generate a decision tree for the target die-casting machine according to the die-casting production target data respectively corresponding to the plurality of die-casting production history data;

[0032] The die-casting parameter tuning module is used to adjust and optimize the die-casting parameter values ​​to be optimized through the decision tree.

[0033] A third aspect of the present application provides a computer program product comprising computer-readable instructions, which, when executed on an electronic device, enables the electronic device to implement the die-casting parameter optimization method of the first aspect or any implementation of the first aspect.

[0034] A fourth aspect of the present application provides an electronic device, comprising at least one processor and a memory connected to the processor, wherein:

[0035] The memory is used to store computer programs;

[0036] The processor is used to execute the computer program so that the electronic device can implement the die-casting parameter optimization method of the above-mentioned first aspect or any implementation manner of the first aspect.

[0037] In a fifth aspect, the present application provides a computer storage medium, which carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement the die-casting parameter optimization method of the above-mentioned first aspect or any implementation method of the first aspect.

[0038] By means of the above technical solution, the die-casting parameter optimization method provided by the present application obtains multiple die-casting production history data of the target die-casting machine, determines the die-casting production target data corresponding to each die-casting production history data, generates a decision tree for the target die-casting machine based on the die-casting production target data corresponding to the multiple die-casting production history data, and adjusts and optimizes the die-casting parameter values ​​to be optimized through the decision tree. Considering that some of the multiple die-casting parameters contained in each die-casting production history data have an important impact on the die-casting quality of the products of the target die-casting machine, and the remaining parameters may have a very small impact on the die-casting quality of the products of the target die-casting machine, in order to be able to screen parameters with a higher degree of importance from the multiple die-casting parameters, the present application can quantitatively analyze the intrinsic relationship between the multiple die-casting parameters and the product quality grade. Since the intrinsic relationship is a stable relationship between the die-casting parameters and the product quality grade captured by the quantitative analysis, the screening result of the present application depends only on the die-casting production history data itself rather than external factors. Therefore, for the same batch of die-casting production history data, the screened target die-casting parameters will not change. At the same time, this inherently linked screening method allows for a higher degree of compatibility between the target die-casting parameters and the target die-casting machine. This, in turn, increases the compatibility of the decision tree with the target die-casting machine, making the decision tree more accurate and practical. Consequently, the parameter optimization results based on the decision tree result in a higher yield rate for products produced by the target die-casting machine. The entire process eliminates the need for manual parameter adjustments, making process adjustments more efficient, reproducible, transparent, and interpretable. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that the originals and elements are not necessarily drawn to scale.

[0040] Figure 1 A schematic flow chart of a die-casting parameter optimization method provided in this application;

[0041] Figure 2 (a) shows the data distribution corresponding to the average value of high-speed speed;

[0042] Figure 2(b) shows the data distribution corresponding to the cake thickness;

[0043] Figure 2 (c) shows the data distribution corresponding to the high-speed position;

[0044] Figure 2(d) shows the data distribution corresponding to the cycle time;

[0045] Figure 2 (e) shows the data distribution corresponding to the pressure buildup time;

[0046] Figure 2 (f) shows the data distribution corresponding to the filling distance;

[0047] Figure 2 (g) shows the data distribution corresponding to the filling time;

[0048] Figure 2 (h) shows the data distribution corresponding to the filling pressure;

[0049] Figure 2 (i) shows the data distribution corresponding to the ejection pressure;

[0050] Figure 2 (j) shows the data distribution corresponding to the highest speed position;

[0051] Figure 2 (k) is the data distribution diagram corresponding to the maximum speed of the injection curve;

[0052] Figure 2 (l) shows the data distribution corresponding to the maximum value of the filling pressure;

[0053] Figure 3 (a) shows the correlation between multiple die-casting parameters and product quality grades;

[0054] Figure 3 (b) is the correlation graph after removing the values ​​below the preset correlation threshold;

[0055] Figure 4 A schematic diagram of a decision tree constructed for this application;

[0056] Figure 5 A schematic structural diagram of a die-casting parameter optimization device provided in this application;

[0057] Figure 6 This is a schematic diagram of the structure of an electronic device provided in this application. DETAILED DESCRIPTION

[0058] The following describes the embodiments of the present application in conjunction with the accompanying drawings. The terms used in the implementation methods of the present application are only used to explain the specific embodiments of the present application and are not intended to limit the present application.

[0059] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0060] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, and this is merely a way of distinguishing the objects of the same attributes when describing them in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0061] In order to achieve data-based, interpretable and adaptable intelligent parameter adjustment optimization and solve the above-mentioned problems existing in the clustering algorithm, the present application provides the following die-casting parameter optimization method and related devices.

[0062] In order to enable those skilled in the art to better understand the present application, the die-casting parameter optimization method of the embodiment of the present application is described in detail below with reference to the accompanying drawings.

[0063] Reference Figure 1 , is a flow chart of a die casting parameter optimization method provided in this application, such as Figure 1 As shown, the die casting parameter optimization method may include:

[0064] Step S101: Acquire multiple die-casting production history data of a target die-casting machine.

[0065] Each die-casting production history data consists of a product quality grade and a corresponding die-casting parameter set, and the die-casting parameter set includes historical parameter values ​​of multiple die-casting parameters.

[0066] Considering that even within the same production site, different die-casting machines may differ in brand, model, control algorithm, and other aspects, resulting in inconsistent operating characteristics and parameter response patterns, this exacerbates the complexity of parameter optimization. Furthermore, the cost of a single die-casting machine is substantial, potentially reaching hundreds of millions. To ensure that such a high-cost die-casting machine can produce products with the highest possible yield, this embodiment optionally allows the target die-casting machine to be the single die-casting machine for die-casting parameter optimization.

[0067] It should be understood that in the die-casting production process of the target die-casting machine, the yield rate is affected by the comprehensive influence of multiple die-casting parameter factors. This embodiment can obtain multiple die-casting production history data of the target die-casting machine, so as to study and analyze the operating characteristics and parameter response laws of the target die-casting machine through multiple die-casting production history data, obtain optimized parameters that are more suitable for the target die-casting machine, and improve the yield rate of the target die-casting machine.

[0068] Die-casting parameters refer to a series of technical parameters that must be set and controlled during the die-casting process. These parameters directly impact the quality, production efficiency, and cost of the final product. In-depth research has identified die-casting parameters that influence yield and can be optimized and adjusted, including the target die-casting machine's process parameters and parameters related to environmental climate conditions.

[0069] To this end, optionally, the multiple die-casting parameters in each die-casting production history data include: process parameters of the target die-casting machine and parameters related to environmental climate conditions. Among them, process parameters play a decisive role in the product molding process. These parameters affect the flow state, pressure distribution and heat conduction process of the molten metal in the mold cavity, thereby largely determining the density and molding quality of the final product. Improper setting of process parameters can easily lead to common defects such as short shots, pores, cold shuts, and deformations. Ambient temperature and climate conditions also have a significant impact on the die-casting process, especially in areas with large fluctuations in humidity and heat. For example, some areas have significant differences in climate throughout the year, resulting in different thermal balance response conditions for die-casting equipment in different regions. This regional environmental difference makes the parameter adjustment experience accumulated in the long-term production process in various places highly localized, making it difficult to directly reuse or migrate applications.

[0070] Optionally, the process parameters of the target die-casting machine include one or more of the following parameters: average high-speed speed, cake thickness, high-speed starting position, cycle time, pressure building time, filling distance, filling time, filling pressure, ejection pressure, reaching the highest speed position, maximum speed of the injection curve and maximum value of the filling pressure.

[0071] Optionally, parameters related to environmental climate conditions include: the temperature of the day, date (if the historical parameter values ​​of the date are not much different, this application will not consider the date parameter; if the historical parameter values ​​of the date are greatly different, this application may consider the date parameter; the same applies to the temperature of the day).

[0072] Of course, the above die-casting parameters are merely examples and are not intended to limit the present application.

[0073] Optionally, the product quality level includes good products and defective products. For example, good products are represented by the number 1 and defective products are represented by the number 0.

[0074] Step S102: Determine the die-casting production target data corresponding to each die-casting production history data.

[0075] The die-casting production target data consists of a product quality grade and a corresponding target die-casting parameter set, and the target die-casting parameter set includes a historical parameter value of at least one target die-casting parameter.

[0076] In this embodiment, at least one target die-casting parameter is obtained by quantitatively analyzing the intrinsic relationships between multiple die-casting parameters and product quality grades. Because the intrinsic relationship is a stable relationship between the die-casting parameter and product quality grade captured through quantitative analysis, the screening results of this application depend solely on the die-casting production history data itself, rather than external factors. Therefore, for the same batch of die-casting production history data, the selected target die-casting parameters will not change. Furthermore, this screening method based on intrinsic relationships improves the compatibility of the target die-casting parameters with the target die-casting machine.

[0077] Step S103: Generate a decision tree for a target die-casting machine according to the die-casting production target data corresponding to the plurality of die-casting production history data.

[0078] The decision tree in this embodiment is essentially a decision model. This embodiment can construct a decision model with visualization path and logical judgment capabilities based on the die-casting production target data corresponding to multiple die-casting production history data, so that the subsequent adjustment and optimization process of the die-casting parameter values ​​to be optimized has stronger transparency and explainability.

[0079] Step S104: adjusting and optimizing the die-casting parameter values ​​to be optimized through a decision tree.

[0080] Specifically, in this embodiment, the die-casting parameter values ​​to be optimized can be input into a decision tree to obtain the decision tree's prediction results. If the prediction results indicate that the die-casting parameter values ​​to be optimized enable the target die-casting machine to produce good products, the die-casting parameter values ​​to be optimized are not adjusted and are directly output. If the prediction results indicate that the die-casting parameter values ​​to be optimized enable the target die-casting machine to produce defective products, the die-casting parameter values ​​to be optimized are adjusted and the adjusted die-casting parameter values ​​are output.

[0081] Optionally, the process of adjusting the die-casting parameter value to be optimized may include: adjusting the die-casting parameter value to be optimized based on a preset step size and / or a preset adjustment factor, and the adjustment direction may be determined according to the specific die-casting parameter, including upward adjustment and downward adjustment.

[0082] The die-casting parameter optimization method provided by the present application obtains multiple die-casting production history data of a target die-casting machine, determines the die-casting production target data corresponding to each die-casting production history data, generates a decision tree for the target die-casting machine based on the die-casting production target data corresponding to the multiple die-casting production history data, and adjusts and optimizes the die-casting parameter values ​​to be optimized through the decision tree. Considering that some of the multiple die-casting parameters contained in each die-casting production history data have an important impact on the die-casting quality of the products of the target die-casting machine, and the remaining parameters may have a very small impact on the die-casting quality of the products of the target die-casting machine, in order to be able to screen parameters with a higher degree of importance from multiple die-casting parameters, the present application can quantitatively analyze the intrinsic relationship between the multiple die-casting parameters and the product quality grade. Since the intrinsic relationship is a stable relationship between the die-casting parameters and the product quality grade captured by the quantitative analysis, the screening result of the present application depends only on the die-casting production history data itself rather than external factors. Therefore, for the same batch of die-casting production history data, the screened target die-casting parameters will not change. At the same time, the inherently linked screening method allows for a higher degree of compatibility between the target die-casting parameters and the target die-casting machine. Consequently, the decision tree is more compatible with the target die-casting machine. The parameter optimization results based on the decision tree result in a higher yield rate for products produced by the target die-casting machine. The entire process eliminates the need for manual parameter adjustments, making process adjustments more efficient, reproducible, transparent, and explainable.

[0083] In some embodiments of the present application, the target die-casting parameter refers to a die-casting parameter among multiple die-casting parameters, which can distinguish the product quality grade by adjusting the parameter value, and / or a die-casting parameter whose correlation with the product quality grade is higher than a preset correlation threshold.

[0084] Based on this, optionally, the process of the previous step S102 "determining the die-casting production target data corresponding to each die-casting production history data" may include: based on multiple die-casting production history data, using a preset quantitative analysis method to screen out at least one target die-casting parameter from multiple die-casting parameters, wherein the quantitative analysis method includes a correlation analysis method and / or a numerical statistics method; based on at least one target die-casting parameter, determining the die-casting production target data from each die-casting production history data.

[0085] In order to ensure data quality, optionally, before using the quantitative analysis method to screen the target die-casting parameters, multiple die-casting production history data can be cleaned and standardized to remove outliers and missing values ​​to obtain multiple pre-processed die-casting production history data, and then, based on the multiple pre-processed die-casting production history data, a quantitative analysis method can be used to screen out at least one target die-casting parameter from the multiple die-casting parameters.

[0086] In one possible implementation, when the quantitative analysis method includes a numerical statistics method, the process of "selecting at least one target die-casting parameter from multiple die-casting parameters using a preset quantitative analysis method based on multiple die-casting production history data" may include: for each die-casting parameter among the multiple die-casting parameters, extracting the historical parameter value and product quality grade of the die-casting parameter from each die-casting production history data, and forming a data point by the values ​​extracted from each die-casting production history data (i.e., the historical parameter value and product quality grade of the die-casting parameter), which serves as the data point corresponding to each die-casting production history data; obtaining a data distribution graph corresponding to the die-casting parameter from the data points respectively corresponding to the multiple die-casting production history data; and selecting at least one target die-casting parameter from the multiple die-casting parameters according to the data distribution graphs respectively corresponding to the multiple die-casting parameters.

[0087] For example, referring to Figure 2 (a) to Figure 2 (l), which are schematic diagrams of the distribution of multiple die-casting parameters at different product quality levels (i.e., data distribution diagrams corresponding to multiple die-casting parameters), Figure 2 (a) to Figure 2 (l) correspond to 500 pieces of die-casting production history data collected, of which 463 are good products and 37 are defective products. As shown in Figure 2 (a), the data distribution diagram corresponding to the average high-speed speed, Figure 2 (b) is the data distribution diagram corresponding to the cake thickness, Figure 2 (c) is the data distribution diagram corresponding to the high-speed starting position, Figure 2 (d) is the data distribution diagram corresponding to the cycle time, Figure 2 (e) is the data distribution diagram corresponding to the pressure buildup time, Figure 2 (f) is the data distribution diagram corresponding to the filling distance, Figure 2 (g) is the data distribution diagram corresponding to the filling time, Figure 2 (h) is the data distribution diagram corresponding to the filling pressure, Figure 2 (i) is the data distribution diagram corresponding to the ejection pressure, Figure 2 (j) is the data distribution diagram corresponding to the highest speed position, Figure 2 (k) is the data distribution diagram corresponding to the maximum speed of the injection curve, and Figure 2 (l) is the data distribution diagram corresponding to the maximum value of the filling pressure.

[0088] For Figure 2 (a) to Figure 2 (l), the box on the left side of each figure represents the numerical distribution of the corresponding die-casting parameters in good products, and the box on the right side represents the numerical distribution of the corresponding die-casting parameters in defective products. The closer the upper and lower boundaries are, that is, the flatter the box is, the more concentrated the numerical distribution is (stable, with small fluctuations).

[0089] Taking Figure 2 (a) as an example, we can see that the high-speed average value has a significant impact on the product quality grade. The upper and lower boundaries of good products are approximately in the range of 6.2-6.7, and the upper and lower boundaries of defective products are approximately in the range of 3.8-5.4. Therefore, the high-speed average value can be adjusted to between 6.2 and 6.7.

[0090] As can be seen from Figure 2 (a) to Figure 2 (l), the distribution of the average high-speed speed, pressure build-up time, filling pressure, ejection pressure, maximum speed of the injection curve, and maximum filling pressure in good and defective products is very different. Good and defective products can be distinguished by looking at any one of these parameters. Although there are certain differences in parameters such as cake thickness, high-speed starting position, cycle time, filling distance, filling time, and reaching the highest speed position between good and defective products, they are not enough to completely distinguish good and defective products. For example, if the filling time is less than 150, some good products can be distinguished, but if the filling time is greater than 150, it may be a good product or a defective product.

[0091] Based on this, this embodiment can screen at least one target die-casting parameter that can distinguish product quality grades by adjusting parameter values ​​from the multiple die-casting parameters according to the data distribution diagrams corresponding to the multiple die-casting parameters.

[0092] In another possible implementation, when the quantitative analysis method includes a correlation analysis method, the process of "selecting at least one target die-casting parameter from multiple die-casting parameters using a preset quantitative analysis method based on multiple die-casting production history data" may include: for each die-casting parameter among the multiple die-casting parameters, extracting the historical parameter value and product quality grade of the die-casting parameter from each die-casting production history data, and using the value extracted from each die-casting production history data (i.e., the historical parameter value and the product quality grade) as the to-be-processed value pair corresponding to each die-casting production history data; calculating the correlation between the die-casting parameter and the product quality grade based on the to-be-processed value pairs corresponding to the multiple die-casting production history data, as the correlation corresponding to the die-casting parameter; so as to obtain the correlations corresponding to the multiple die-casting parameters; and selecting at least one target die-casting parameter from the multiple die-casting parameters based on the correlations corresponding to the multiple die-casting parameters.

[0093] The correlation value is between -1 and 1, where -1 indicates a completely negative correlation, 0 indicates no correlation, and 1 indicates a completely positive correlation. The closer the correlation value is to -1 or 1, the stronger the relationship between the die-casting parameters and the product quality grade, meaning the higher the degree of influence of the die-casting parameters on the product quality grade.

[0094] The collection of multiple die-casting production history data is: Take this as an example to illustrate, , .

[0095] in, Represents a collection of multiple die-casting production history data. Indicates the number of historical data of die casting production, Indicates the number of die casting parameters in each die casting production history data, represents the set of historical parameter values ​​of all die-casting parameters in the i-th die-casting production history data, Represents the historical parameter value of the jth die-casting parameter in the i-th die-casting production history data, , represents the product quality level in the i-th die-casting production history data, Indicates good quality. Indicates defective product.

[0096] As mentioned above, in order to measure the correlation between the die-casting parameters in the die-casting production history data and the product quality level (this embodiment takes good and defective products as an example, and in actual applications, the product quality level can include several levels), the Pearson correlation coefficient can be used. The calculation formula is as follows:

[0097] Formula (1);

[0098] in, Indicates die casting parameters ( Represents the jth die-casting parameter among multiple die-casting parameters) and product quality level The corresponding Pearson correlation coefficient is, Indicates die casting parameters The average value of the historical parameter values ​​in all die casting production history data, It represents the average value of product quality grade in all die casting production history data. For die casting parameters For example, the value pair to be processed corresponds to the i-th die-casting production history data.

[0099] As mentioned above, the Pearson correlation coefficient The value range is [-1,1]. The closer the value is to 1 or -1, the The stronger the correlation with product quality level.

[0100] In this embodiment, the correlations corresponding to the multiple die-casting parameters can constitute a correlation matrix for subsequent feature screening. Feature screening can preset a correlation threshold, for example, only retaining die-casting parameters greater than the preset correlation threshold. That is, optionally, the process of "screening at least one target die-casting parameter from the multiple die-casting parameters based on the correlations corresponding to the multiple die-casting parameters" can include: for each die-casting parameter in the multiple die-casting parameters, if the correlation corresponding to the die-casting parameter is greater than or equal to the preset correlation threshold, then the die-casting parameter is determined as the target die-casting parameter; if the correlation corresponding to the die-casting parameter is less than the preset correlation threshold, then the die-casting parameter is eliminated.

[0101] Optionally, the correlation between each two die-casting parameters can also be calculated. Based on the correlation, the reliability of the correlation corresponding to the two die-casting parameters can be identified. In the previous screening, the die-casting parameters with low reliability can be ignored to avoid screening out the wrong target die-casting parameters, which will affect the subsequent decision tree construction process and parameter tuning process.

[0102] See Figure 3(a) for a correlation diagram between multiple die-casting parameters and product quality grades, and Figure 3(b) for a correlation diagram after removing values ​​below a preset correlation threshold. As shown in Figures 3(a) and 3(b), the correlations between multiple die-casting parameters and product quality grades form a correlation matrix, where only the lower triangular region and the diagonal region of the correlation matrix contain element values. As shown in Figure 3(b), after removing correlations below the preset correlation threshold, the resulting target die-casting parameters include: average high-speed speed, cycle time, filling time, filling pressure, ejection pressure, maximum value of the shot curve, and maximum filling pressure.

[0103] In another possible implementation, when the quantitative analysis method includes a numerical statistics method and a correlation analysis method, the target die-casting parameters screened out by the numerical statistics method and the correlation analysis method can be used as the target die-casting parameters finally screened out in this application.

[0104] In another possible implementation, when the quantitative analysis method includes the numerical statistics method and the correlation analysis method, the target die-casting parameters jointly screened out by the numerical statistics method and the correlation analysis method can be used as the target die-casting parameters finally screened out in this application. For example, when the numerical statistics method screens out the average value of high-speed speed, pressure building time, filling pressure, ejection pressure, maximum speed of the shot curve, and maximum value of filling pressure, and the correlation analysis method screens out the average value of high-speed speed, cycle time, filling time, filling pressure, ejection pressure, maximum value of the shot curve, and maximum value of filling pressure, the average value of high-speed speed, filling pressure, ejection pressure, maximum speed of the shot curve, and maximum value of filling pressure are used as target die-casting parameters.

[0105] In summary, the quantitative analysis method used in this application can accurately screen out the die-casting parameters that have a greater impact on product quality, so that subsequent parameter adjustments can be more accurate.

[0106] In other embodiments of the present application, the process of the aforementioned step S103 of "generating a decision tree of a target die-casting machine according to die-casting production target data respectively corresponding to a plurality of die-casting production history data" is introduced.

[0107] Optionally, the decision tree of the present application may be any one of a Classification and Regression Tree (CART), an Iterative Dichotomiser 3 (ID3), and a C4.5 Decision Tree (C4.5 Decision Tree).

[0108] Taking CART as an example, the optional process of "generating a decision tree for a target die-casting machine based on die-casting production target data corresponding to multiple die-casting production history data" may include: enumerating all possible segmentation values ​​of each target die-casting parameter to obtain a segmentation value set consisting of all possible segmentation values ​​of all target die-casting parameters; calculating the weighted Gini index corresponding to each segmentation value in the segmentation value set based on the die-casting production target data corresponding to multiple die-casting production history data, selecting the segmentation value with the smallest weighted Gini index and the target die-casting parameter corresponding to the segmentation value as the root node; removing all possible segmentation values ​​of the target die-casting parameter in the root node from the segmentation value set to obtain an updated segmentation value set (in some scenarios, this step can also be removed, and the updated segmentation value set is still the original segmentation value set); for the construction process of the left child node of the root node, the construction process of the root node can be referred to, that is, according to The die-casting production target data corresponding to multiple die-casting production history data (the die-casting production target data here refers to the die-casting production target data in the left child node split according to the root node) are calculated, and the weighted Gini index corresponding to each split value in the split value set is calculated, and the split value with the smallest weighted Gini index and the target die-casting parameters corresponding to the split value are selected as the left child node of the root node; for the construction process of the right child node of the root node, the construction process of the root node can refer to the construction process of the root node, that is, according to the die-casting production target data corresponding to multiple die-casting production history data (the die-casting production target data here refers to the die-casting production target data in the right child node split according to the root node), the weighted Gini index corresponding to each split value in the split value set is calculated, and the split value with the smallest weighted Gini index and the target die-casting parameters corresponding to the split value are selected as the right child node of the root node; and so on, until the preset construction end condition is reached.

[0109] Optionally, the construction end conditions include but are not limited to the following conditions: the samples in the node (one die casting production target data is one sample) belong to the same category, the number of node samples is less than the preset sample number threshold , the benefits brought by the partition (such as Gini index, information gain, etc.) are less than the preset expectation, and the tree depth reaches the preset tree depth threshold .

[0110] When any of the above construction end conditions is met, the recursive partitioning stops and the node becomes a leaf node.

[0111] Of course, the construction end condition can also be other, and this application does not make specific limitations.

[0112] In order to make those skilled in the art better understand the process of building the decision tree, the following is a detailed explanation. For the sake of convenience, the following will take multiple die-casting production target data in a node to be split as a sample set. For the introduction, the symbol j is also used to indicate a target die-casting parameter, but the value range of j may be narrowed, depending on how many parameters are eliminated during the parameter screening process.

[0113] For each Enumerate all possible split values , the sample set The corresponding nodes to be split are Divided into two subsets, left and right, representing the sample set The left child node of the corresponding node to be split and right child node .

[0114] in, express A cutoff value of express The set of all possible split values ​​of Represents a sample set The left child node (also referred to as ), Represents a sample set The right child node (also referred to as ), Represents the set of historical parameter values ​​corresponding to the target die-casting parameters in the node to be split, Represents the set of product quality levels corresponding to the node to be split.

[0115] In CART, the Gini index of a node measures the purity of the sample category in the node, and the calculation formula is as follows (2).

[0116] Formula (2);

[0117] in, Represents a sample set The corresponding Gini index of the node to be split, Indicates a category, e.g. , 0 represents defective products, 1 represents good products (It should be noted that the categories 0 and 1 here are just examples, and there can be other categories, for example, It can also be 0, 1, 2, etc.); Indicates the The sample ratio of each category is calculated as follows:

[0118] Formula (3);

[0119] in, represents the number of samples in the sample set, Indicates the first The product quality level in the samples, It means if and only if The dot in the string takes the value 1 when the condition is met, and takes the value 0 otherwise.

[0120] according to The split value is The calculation formula of the weighted Gini index when dividing the left child node and the right child node is as follows (4).

[0121] Formula (4);

[0122] in, Indicates that The split value is The weighted Gini index when dividing the left child node and the right child node, Indicates that The split value is The number of samples of the left child node of the partition, Indicates that The split value is The number of samples of the right child node of the partition, Indicates that The split value is The Gini index of the left child node of the partition, Indicates that The split value is Gini index of the right child node of the partition.

[0123] Thus, you can choose to smallest and ,Right now .in, Indicates smallest , represents the target die casting parameters selected (i.e., the sample set The target die-casting parameters in the corresponding node to be split), Indicates smallest (i.e., sample set The corresponding split value in the node to be split).

[0124] See also Figure 4 , which is a schematic diagram of a decision tree constructed for this application, Figure 4 The gini in each node represents the Gini index, samples represents the number of samples in the node, the numerical value on the left in value represents the number of defective products, and the numerical value on the right represents the number of good products. For example, value=[37,463] means there are 37 defective products and 463 good products. The class indicates whether the node corresponds to good or defective products. If the number of defective products in a node is greater than the number of good products, then the class in the node is defective. If the number of good products in a node is greater than the number of defective products, then the class in the node is good. If the number of defective products in a node is equal to the number of good products, then the class in the node is defective or good.

[0125] It should be noted that the above weighted Gini index is only an example. In other decision tree algorithms, the weighted Gini index can be replaced by other values.

[0126] For example, in ID3, the weighted Gini index can be replaced by information gain.

[0127] In ID3, the information entropy of the node is first calculated, which can measure the The uncertainty is as follows, and the calculation formula of information entropy is as follows:

[0128] Formula (5);

[0129] in, Represents a sample set The information entropy of the corresponding node, Indicates a category, e.g. , 0 represents defective products, 1 represents good products; Indicates the The sample ratio of each category is calculated using the formula (3) above.

[0130] Then calculate the conditional entropy as follows:

[0131] Formula (6);

[0132] in, Indicates that The split value is Conditional entropy when dividing the left child node and the right child node, Indicates that The split value is The information entropy of the left child node of the partition, Indicates that The split value is The information entropy of the right child node of the partition.

[0133] Information gain represents the reduction in information entropy before and after dividing the left child node and the right child node. The formula is as follows:

[0134] Formula (7);

[0135] in, Indicates that The split value is Information gain when partitioning the left and right child nodes.

[0136] Thus, you can choose to The largest and ,Right now .in, Indicates The largest , represents the target die casting parameters selected (i.e., the sample set The target die-casting parameters in the corresponding node to be split), Indicates The largest (i.e., sample set The corresponding split value in the node to be split).

[0137] Similarly, in C4.5, the weighted Gini index can be replaced by the information gain rate.

[0138] In C4.5, the information gain rate further considers the amount of information in the partition itself based on the information gain. First, the intrinsic value of the partition is defined as:

[0139] Formula (8);

[0140] in, Indicates that The split value is The intrinsic value when partitioning the left and right child nodes.

[0141] The information gain ratio is defined as the ratio of information gain to the partition intrinsic value, that is:

[0142] Formula (9);

[0143] in, Indicates that The split value is The information gain rate when partitioning the left and right child nodes.

[0144] Thus, you can choose to The largest and ,Right now .in, Indicates The largest , represents the target die casting parameters selected (i.e., the sample set The target die-casting parameters in the corresponding node to be split), Indicates The largest (i.e., sample set The corresponding split value in the node to be split).

[0145] This application constructs a decision-making model based on a decision tree, which can clarify the impact of various die-casting parameters on the quality of products produced by target die-casting parameters through visual paths and logical judgments, and assist in the tuning and setting of die-casting parameters and the feasibility of predicting parameter schemes, solving the problems existing in the existing technology such as reliance on experience-based adjustment, low efficiency, poor reusability, and opaque parameter optimization process.

[0146] In summary, this application provides a data-based, interpretable and adaptable die-casting parameter optimization method that can effectively integrate equipment characteristics, environmental conditions and historical experience, and realize the transformation of the die-casting process from "experience-driven" to "data-driven", thereby improving the yield rate, shortening the debugging cycle and accelerating the process introduction of new products and new equipment.

[0147] The above describes a die-casting parameter optimization method provided by an embodiment of the present application. The following describes an apparatus for executing the above die-casting parameter optimization method.

[0148] See also Figure 5 , Figure 5 This is a schematic diagram of the structure of a die casting parameter optimization device provided in an embodiment of the present application. Figure 5 As shown, the die casting parameter optimization device may include:

[0149] A historical data acquisition module 501 is used to acquire a plurality of die-casting production historical data of a target die-casting machine, wherein each die-casting production historical data is composed of a product quality grade and a corresponding die-casting parameter set, and the die-casting parameter set includes historical parameter values ​​of a plurality of die-casting parameters;

[0150] The die-casting parameter screening module 502 is configured to determine die-casting production target data corresponding to each die-casting production history data, wherein the die-casting production target data is composed of a product quality grade and a corresponding target die-casting parameter set. The target die-casting parameter set includes a historical parameter value of at least one target die-casting parameter. The target die-casting parameter is obtained by quantitatively analyzing the intrinsic relationship between the die-casting parameter and the product quality grade.

[0151] A decision tree generating module 503 is configured to generate a decision tree for a target die-casting machine based on die-casting production target data corresponding to a plurality of die-casting production history data;

[0152] The die-casting parameter tuning module 504 is used to adjust and optimize the die-casting parameter values ​​to be optimized through a decision tree.

[0153] It should be noted that the specific implementation of each module in the above-mentioned die-casting parameter optimization device can refer to the relevant introduction in the above-mentioned die-casting parameter optimization method, and will not be repeated here.

[0154] It should also be noted that each module in the die-casting parameter optimization device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0155] An embodiment of the present application further provides an electronic device, which may include at least one processor and a memory connected to the processor, wherein:

[0156] Memory is used to store computer programs;

[0157] The processor is used to execute a computer program so that the electronic device can implement any one of the die-casting parameter optimization methods provided in the embodiments of the present application.

[0158] refer to Figure 6 , which shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present application. The electronic device in the embodiments of the present application may include, but is not limited to, fixed terminals such as mobile phones, laptops, PDAs (personal digital assistants), PADs (tablet computers), desktop computers, etc. Figure 6 The electronic device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0159] like Figure 6 As shown, the electronic device may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 602 or programs loaded from a storage device 608 into a random access memory (RAM) 603. When the electronic device is powered on, the RAM 603 also stores various programs and data required for the operation of the electronic device. The processing device 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0160] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a memory card, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Figure 6 The electronic device is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead.

[0161] An embodiment of the present application also provides a computer program product including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements any one of the die-casting parameter optimization methods provided in the embodiments of the present application.

[0162] A computer-readable storage medium is also provided in an embodiment of the present application. The storage medium carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement any one of the die-casting parameter optimization methods provided in the embodiment of the present application.

[0163] It should also be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed across multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. In addition, in the drawings of the device embodiments provided in this application, the connection relationship between the modules indicates that there is a communication connection between them, which can be specifically implemented as one or more communication buses or signal lines.

[0164] Through the description of the above embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course can also be implemented by special hardware including application-specific integrated circuits, special CPUs, special memories, special components, etc. In general, all functions performed by computer programs can be easily implemented with corresponding hardware, and the specific hardware structures used to implement the same function can also be diverse, such as analog circuits, digital circuits or special circuits, etc. However, for the present application, software program implementation is a better implementation method in most cases. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer's floppy disk, USB flash drive, mobile hard disk, ROM, RAM, magnetic disk or optical disk, etc., and includes a number of instructions to enable a computer device (which can be a personal computer, training equipment, or network equipment, etc.) to execute the methods described in each embodiment of the present application.

[0165] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware, or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0166] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, a computer, a training device or a data center by wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode to another website, computer, training device or data center. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a training device, a data center that includes one or more available media integrations. The available medium can be a magnetic medium, (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid-state drive (SSD)).

Claims

1. A die casting parameter optimization method, characterized in that: include: Acquire a plurality of die-casting production history data of a target die-casting machine, wherein each die-casting production history data consists of a product quality grade and a corresponding die-casting parameter set, and the die-casting parameter set includes historical parameter values ​​of each of a plurality of die-casting parameters; Determining die-casting production target data corresponding to each die-casting production history data, wherein the die-casting production target data consists of the product quality grade and a corresponding target die-casting parameter set, the target die-casting parameter set includes a historical parameter value of at least one target die-casting parameter, the target die-casting parameter is obtained by quantitatively analyzing an intrinsic relationship between the die-casting parameter and the product quality grade, the target die-casting parameter refers to a die-casting parameter among the multiple die-casting parameters that can distinguish the product quality grade by adjusting the parameter value, and / or a die-casting parameter whose correlation with the product quality grade is higher than a preset correlation threshold; generating a decision tree for the target die-casting machine according to the die-casting production target data respectively corresponding to the plurality of die-casting production history data; Adjust and optimize the die-casting parameter values ​​to be optimized through the decision tree; The determining of the die-casting production target data corresponding to each die-casting production history data includes: According to the plurality of die-casting production history data, a preset quantitative analysis method is used to screen out the at least one target die-casting parameter from the plurality of die-casting parameters, wherein the quantitative analysis method includes a correlation analysis method and / or a numerical statistics method; The die casting production target data is determined from each of the die casting production history data according to the at least one target die casting parameter.

2. The die casting parameter optimization method according to claim 1, characterized in that: In the case where the quantitative analysis method includes the numerical statistics method, the step of selecting the at least one target die-casting parameter from the plurality of die-casting parameters using a preset quantitative analysis method based on the plurality of die-casting production history data includes: For each die-casting parameter of the plurality of die-casting parameters: Extracting the historical parameter value of the die-casting parameter and the product quality grade from each of the die-casting production history data, and forming a data point by the historical parameter value and the product quality grade extracted from each of the die-casting production history data as the data point corresponding to each of the die-casting production history data; Obtaining a data distribution graph corresponding to the die-casting parameter from the data points respectively corresponding to the plurality of die-casting production history data; To obtain data distribution diagrams corresponding to the plurality of die-casting parameters respectively; The at least one target die-casting parameter is selected from the plurality of die-casting parameters according to the data distribution graphs respectively corresponding to the plurality of die-casting parameters.

3. The die casting parameter optimization method according to claim 1, characterized in that: In the case where the quantitative analysis method includes the correlation analysis method, the step of selecting the at least one target die-casting parameter from the plurality of die-casting parameters using a preset quantitative analysis method based on the plurality of die-casting production history data includes: For each die-casting parameter of the plurality of die-casting parameters: Extracting the historical parameter value of the die-casting parameter and the product quality grade from each of the die-casting production history data, and using the historical parameter value and the product quality grade extracted from each of the die-casting production history data as a to-be-processed value pair corresponding to each of the die-casting production history data; Calculating, based on the to-be-processed value pairs corresponding to the plurality of die-casting production history data, a correlation between the die-casting parameter and the product quality grade as the correlation corresponding to the die-casting parameter; To obtain the correlations corresponding to the plurality of die-casting parameters; The at least one target die-casting parameter is selected from the plurality of die-casting parameters according to the respective correlations corresponding to the plurality of die-casting parameters.

4. The die casting parameter optimization method according to claim 1, characterized in that: The decision tree is any one of a classification and regression tree, an iterated binary tree 3, and a C4.5 decision tree.

5. A die casting parameter optimization device, characterized in that: include: a historical data acquisition module, configured to acquire a plurality of die-casting production historical data of a target die-casting machine, wherein each of the die-casting production historical data comprises a product quality grade and a corresponding die-casting parameter set, wherein the die-casting parameter set comprises respective historical parameter values ​​of a plurality of die-casting parameters; a die-casting parameter screening module, configured to determine die-casting production target data corresponding to each die-casting production history data, wherein the die-casting production target data is composed of the product quality grade and a corresponding target die-casting parameter set, the target die-casting parameter set including a historical parameter value of at least one target die-casting parameter, the target die-casting parameter being obtained by quantitatively analyzing the intrinsic relationship between the die-casting parameter and the product quality grade, the target die-casting parameter being a die-casting parameter among the multiple die-casting parameters that can distinguish the product quality grade by adjusting the parameter value, and / or a die-casting parameter whose correlation with the product quality grade is higher than a preset correlation threshold; a decision tree generating module, configured to generate a decision tree for the target die-casting machine according to the die-casting production target data respectively corresponding to the plurality of die-casting production history data; A die-casting parameter tuning module, configured to adjust and optimize the die-casting parameter values ​​to be optimized through the decision tree; The die-casting parameter screening module is specifically used to screen out the at least one target die-casting parameter from the multiple die-casting production history data using a preset quantitative analysis method, and determine the die-casting production target data from each of the die-casting production history data based on the at least one target die-casting parameter, wherein the quantitative analysis method includes a correlation analysis method and / or a numerical statistics method.

6. A computer program product, characterized in that The method comprises computer-readable instructions, which, when executed on an electronic device, enable the electronic device to implement the die-casting parameter optimization method according to any one of claims 1 to 4.

7. An electronic device, characterized in that: comprising at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is configured to execute the computer program so as to enable the electronic device to implement the die-casting parameter optimization method according to any one of claims 1 to 4.

8. A computer storage medium, characterized in that The storage medium carries one or more computer programs, and when the one or more computer programs are executed by an electronic device, the electronic device can implement the die-casting parameter optimization method according to any one of claims 1 to 4.

Images