Intelligent optimization method and system for aluminum alloy die casting forming process

Abstract

The application relates to the technical field of aluminum alloy die casting, and provides an intelligent optimization method and system for an aluminum alloy die casting forming process, the method comprising the following steps: acquiring basic information of an aluminum alloy die casting; setting an optimization fitness function; performing optimization analysis on die casting processing parameters to generate aluminum alloy die casting processing parameters; performing failure analysis on a die casting die to obtain a failure evaluation result; when the failure evaluation result belongs to a non-failure state, generating a die casting processing instruction; and controlling the aluminum alloy die casting forming process based on the aluminum alloy die casting processing parameters according to the die casting processing instruction. The technical problem that the production efficiency and quality are both low due to unreasonable die casting processing parameter setting and insufficient precision of die casting die inspection in the aluminum alloy die casting production process can be solved. The effect of improving the production efficiency and quality of the aluminum alloy die casting can be achieved.

Description

Technical Field

[0001] This application relates to the field of aluminum alloy die casting technology, specifically to an intelligent optimization method and system for the forming process of aluminum alloy die casting parts. Background Technology

[0002] Aluminum alloy die casting is a process that organically combines and comprehensively utilizes three major elements: die casting machine, die casting mold, and die casting alloy. The process of metal filling the mold cavity during die casting involves dynamically balancing process factors such as pressure, speed, temperature, and time. These factors are both mutually restrictive and complementary; only by correctly selecting and adjusting these factors to achieve harmony can the desired results be obtained.

[0003] Currently, the die-casting processing parameters in the production process of aluminum alloy die-casting parts are usually set manually without comprehensive analysis. This results in a long production time and, due to insufficient inspection of the die-casting molds, the aluminum alloy die-casting parts produced often fail to meet quality standards.

[0004] In summary, existing technologies suffer from low production efficiency and quality in aluminum alloy die casting production due to unreasonable die casting processing parameter settings and insufficient precision in die casting mold inspection. Summary of the Invention

[0005] Therefore, it is necessary to provide an intelligent optimization method and system for the forming process of aluminum alloy die casting to address the above-mentioned technical problems.

[0006] A smart optimization method for aluminum alloy die casting forming process includes: acquiring basic information of the aluminum alloy die casting; setting an optimization fitness function; based on the optimization fitness function, optimizing and analyzing die casting processing parameters according to the basic information of the aluminum alloy die casting to generate aluminum alloy die casting processing parameters; extracting features from the die casting mold image information to obtain mold defect features, wherein the mold defect features include crack feature information and trace feature information; performing failure analysis on the die casting mold according to the crack feature information and the trace feature information to obtain failure evaluation results, wherein the failure evaluation results include a non-failure state or a failure state; when the failure evaluation result is a non-failure state, generating a die casting processing instruction; and controlling the aluminum alloy die casting forming process according to the die casting processing instruction and the aluminum alloy die casting processing parameters.

[0007] In one embodiment, it further includes: a particle mass assessment formula:

[0008]

[0009] Where, m i(k) represents the particle mass parameter of the i-th particle in the k-th evaluation dimension, f i (k) represents the matching degree of the i-th particle in the k-th evaluation dimension, minf j (k) represents the minimum matching degree, maxf j (k) represents the maximum matching degree, f j (M) represents the matching degree of the j-th particle in the k-th evaluation dimension;

[0010] Formula for obtaining dimensional quality assessment:

[0011]

[0012] Among them, M i (k) represents the dimensional mass parameter of the i-th particle in the k-th evaluation dimension, L represents the total number of particles used for screening, and m j (k) represents the particle mass parameter of the j-th particle in the k-th evaluation dimension;

[0013] Obtain the formula for evaluating single-dimensional gravity:

[0014]

[0015] Where G represents the preset gravitational constant of the k-th dimension, and F represents the degree of emphasis on the k-th dimension. i (k) characterizes the gravitational force of the k-th dimension on the i-th particle;

[0016] Obtain the comprehensive gravitational assessment formula:

[0017]

[0018] Among them, F i The sum of gravity of the i-th particle is represented by N, the total number of evaluation dimensions is represented by N, and rand represents a random number in the range [0,1].

[0019] In one embodiment, the step of optimizing and analyzing the die-casting processing parameters based on the basic information of the aluminum alloy die-casting part according to the optimization fitness function to generate aluminum alloy die-casting processing parameters further includes: obtaining optimization evaluation dimensions and processing parameter indicators; the basic information of the aluminum alloy die-casting part includes die-casting mold model information, casting geometric feature information, and casting material feature information; using the die-casting mold model information, the casting geometric feature information, and the casting material feature information as scene data, and using the processing parameter indicators and the optimization evaluation dimensions as target data, collecting die-casting processing logs to generate die-casting processing record data; and optimizing and filtering the die-casting processing record data based on the optimization fitness function to generate the aluminum alloy die-casting processing parameters.

[0020] In one embodiment, the step of optimizing and filtering the die-casting processing record data based on the optimized fitness function to generate the aluminum alloy die-casting processing parameters further includes: obtaining the matching degree of the k-th evaluation dimension of the i-th particle according to the die-casting processing record data; inputting the matching degree of the k-th evaluation dimension of the i-th particle into the optimized fitness function to generate the comprehensive gravity of the i-th particle; filtering the comprehensive gravity of the i-th particle and the comprehensive gravity of the (i-1)-th particle by the larger value to generate the comparison winner; determining whether the number of comparisons meets the comparison number threshold; if it does, setting the comparison winner as the aluminum alloy die-casting processing parameter.

[0021] In one embodiment, obtaining the matching degree of the k-th evaluation dimension of the i-th particle based on the die-casting processing record data further includes: obtaining the i-th particle based on the die-casting processing record data, wherein the i-th particle represents any set of processing parameter index feature values; obtaining the k-th evaluation dimension and the preset feature value of the k-th evaluation dimension based on the optimized evaluation dimension; analyzing the k-th evaluation dimension based on the i-th particle to obtain the feature value of the k-th evaluation dimension of the i-th particle; and calculating the difference between the preset feature value of the k-th evaluation dimension and the feature value of the k-th evaluation dimension of the i-th particle to generate the matching degree of the k-th evaluation dimension of the i-th particle.

[0022] In one embodiment, the step of performing failure analysis on the die-casting mold based on the crack feature information and the trace feature information to obtain a failure evaluation result, wherein the failure evaluation result includes a non-failure state or a failure state, further includes: performing failure analysis on the die-casting mold based on the crack feature information to generate a first-level failure evaluation result; when the first-level failure evaluation result is a non-failure state, retrieving the aluminum alloy die-casting processing parameters, performing failure analysis based on the trace feature information to generate a second-level failure evaluation result; when the second-level failure evaluation result is a non-failure state, determining that the failure evaluation result is a non-failure state.

[0023] In one embodiment, the method further includes: acquiring crack feature record data and crack failure identification data, and training a crack failure assessment model; acquiring trace feature record data and trace failure identification data, and training a trace failure assessment model; processing the crack feature information using the crack failure assessment model to obtain the first-level failure evaluation result; and processing the aluminum alloy die-casting processing parameters and the trace feature information according to the trace failure assessment model to obtain the second-level failure evaluation result.

[0024] An intelligent optimization system for aluminum alloy die casting process includes:

[0025] Basic information acquisition module, which is used to acquire basic information of aluminum alloy die castings;

[0026] An optimization fitness function setting module is used to set the optimization fitness function;

[0027] A processing parameter generation module is used to optimize and analyze the die casting processing parameters based on the optimization fitness function and the basic information of the aluminum alloy die casting, and generate aluminum alloy die casting processing parameters.

[0028] A mold defect feature acquisition module is used to extract features from die-casting mold image information to acquire mold defect features, wherein the mold defect features include crack feature information and trace feature information;

[0029] The failure evaluation result acquisition module is used to perform failure analysis on the die casting mold based on the crack feature information and the trace feature information, and to acquire failure evaluation results, wherein the failure evaluation results include a non-failure state or a failure state.

[0030] A die casting processing instruction generation module is used to generate a die casting processing instruction when the failure evaluation result is in a non-failure state.

[0031] A forming process control module is used to control the forming process of aluminum alloy die casting parts according to the die casting processing instructions and based on the aluminum alloy die casting processing parameters.

[0032] The aforementioned intelligent optimization method and system for aluminum alloy die casting forming process can solve the technical problems of low production efficiency and quality caused by unreasonable die casting processing parameters and insufficient accuracy in die casting mold inspection during aluminum alloy die casting production. By setting an optimization fitness function to optimize and analyze the die casting processing parameters, aluminum alloy die casting processing parameters are generated; feature extraction is performed on the die casting mold image information to obtain mold defect features; further, failure analysis is performed on the die casting mold based on the mold defect features to obtain failure evaluation results; when the failure evaluation result indicates a non-failure state, the aluminum alloy die casting forming process is controlled according to the aluminum alloy die casting processing parameters. This can improve the production efficiency and quality of aluminum alloy die castings.

[0033] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0034] Figure 1This application provides a flowchart illustrating an intelligent optimization method for the forming process of aluminum alloy die casting.

[0035] Figure 2 This application provides a flowchart illustrating the optimization analysis of die-casting processing parameters in an intelligent optimization method for aluminum alloy die-casting forming process.

[0036] Figure 3 This application provides a flowchart illustrating the generation of aluminum alloy die casting processing parameters in an intelligent optimization method for aluminum alloy die casting forming process.

[0037] Figure 4 This application provides a structural schematic diagram of an intelligent optimization system for the forming process of aluminum alloy die casting.

[0038] Figure labeling: 1. Basic information acquisition module; 2. Optimization fitness function setting module; 3. Processing parameter generation module; 4. Mold defect feature acquisition module; 5. Failure evaluation result acquisition module; 6. Die casting processing instruction generation module; 7. Molding process control module. Detailed Implementation

[0039] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0040] like Figure 1 As shown, this application provides an intelligent optimization method for the forming process of aluminum alloy die casting, including:

[0041] Step S100: Obtain basic information about the aluminum alloy die casting;

[0042] Step S200: Set the optimization fitness function;

[0043] In one embodiment, step S200 of this application further includes:

[0044] Step S210: Particle mass assessment formula:

[0045]

[0046] Where, m i (k) represents the particle mass parameter of the i-th particle in the k-th evaluation dimension, f i (k) represents the matching degree of the i-th particle in the k-th evaluation dimension, minf j (k) represents the minimum matching degree, maxf j (k) represents the maximum matching degree, f j(M) represents the matching degree of the j-th particle in the k-th evaluation dimension;

[0047] Step S220: Obtain the dimensional quality assessment formula:

[0048]

[0049] Among them, M i (k) represents the dimensional mass parameter of the i-th particle in the k-th evaluation dimension, L represents the total number of particles used for screening, and m j (k) represents the particle mass parameter of the j-th particle in the k-th evaluation dimension;

[0050] Step S230: Obtain the single-dimensional gravity assessment formula:

[0051]

[0052] Where G represents the preset gravitational constant of the k-th dimension, and F represents the degree of emphasis on the k-th dimension. i (k) characterizes the gravitational force of the k-th dimension on the i-th particle;

[0053] Step S240: Obtain the comprehensive gravitational assessment formula:

[0054]

[0055] Among them, F i The sum of gravity of the i-th particle is represented by N, the total number of evaluation dimensions is represented by N, and rand represents a random number in the range [0,1].

[0056] Specifically, by querying data on aluminum alloy die castings, basic information about the aluminum alloy die castings is obtained. This basic information includes the type of casting material, wall thickness, dimensions and shape of the casting, and the model of the die casting mold. An optimization fitness function is then set, which includes a particle mass evaluation formula. Where m i (k) represents the particle mass parameter of the i-th particle in the k-th evaluation dimension, f i (k) represents the matching degree of the i-th particle in the k-th evaluation dimension, minf j (k) represents the minimum matching degree, maxf j (k) represents the maximum matching degree, f j (k) represents the matching degree of the j-th particle in the k-th evaluation dimension; dimensional quality evaluation formula Where M i (k) represents the dimensional mass parameter of the i-th particle in the k-th evaluation dimension, L represents the total number of particles used for screening, and m j (k) represents the particle mass parameter of the j-th particle in the k-th evaluation dimension, M i(k) can be based on m i (k) is obtained through calculation. Single-dimensional gravity assessment formula. Where G represents the pre-defined gravitational constant of the k-th dimension, m represents the degree of emphasis on the k-th dimension, and m i (k) and M i (k) is the pre-parameter, F i (k) represents the gravitational force of the k-th dimension on the i-th particle; the larger the value, the higher the fitness of the i-th particle in the k-th dimension; (Comprehensive Gravitational Evaluation Formula) Among them, F i The summation of gravity for the i-th particle is represented by F, N represents the total number of evaluation dimensions, and rand represents a random number in the range [0,1]. i A higher value indicates a higher overall fitness for the i-th particle. The optimized fitness function, obtained by combining the actual scenario of this embodiment, provides support for the next step of optimizing the die-casting processing parameters.

[0057] Step S300: Based on the optimized fitness function, the die casting processing parameters are optimized and analyzed according to the basic information of the aluminum alloy die casting to generate aluminum alloy die casting processing parameters;

[0058] like Figure 2 As shown, in one embodiment, step S300 of this application further includes:

[0059] Step S310: Obtain the optimization evaluation dimensions and processing parameter indicators;

[0060] Step S320: The basic information of the aluminum alloy die casting includes die casting mold model information, casting geometric feature information, and casting material feature information;

[0061] Step S330: Using the die casting mold model information, the casting geometric feature information, and the casting material feature information as scene data, and the processing parameter index and the optimization evaluation dimension as target data, collect die casting processing logs to generate die casting processing record data;

[0062] Specifically, the process involves acquiring optimization evaluation dimensions and processing parameter indicators. The optimization evaluation dimensions include processing time parameters, processing cost parameters, and processing energy consumption parameters. The processing parameter indicators include preset temperature parameters, preset time parameters, pouring temperature parameters, coating spraying volume, and die-casting pressure parameters. The basic information of the aluminum alloy die-casting part includes die-casting mold model information, casting geometric feature information, and casting material feature information. Using the die-casting mold model information, casting geometric feature information, and casting material feature information as scenario constraints, the following conditions are set: the die-casting mold models are identical; the casting geometric features are within a preset deviation range (which can be customized); and the casting material features conform to a material type dataset containing various common aluminum alloy materials (which can also be customized). Processing logs are collected from the processing parameter indicators and target data in the optimization evaluation dimensions. The target data refers to the specific data of the parameters in the processing parameter indicators and optimization evaluation dimensions, such as a processing time of 3 minutes and a pouring temperature of 900 degrees Celsius, generating die-casting processing record data.

[0063] Step S340: Based on the optimized fitness function, optimize and filter the die-casting processing record data to generate the aluminum alloy die-casting processing parameters.

[0064] like Figure 3 As shown, in one embodiment, step S340 of this application further includes:

[0065] Step S341: Based on the die-casting processing record data, obtain the matching degree of the k-th evaluation dimension of the i-th particle;

[0066] In one embodiment, step S341 of this application further includes:

[0067] Step S3411: Obtain the i-th particle based on the die-casting processing record data, wherein the i-th particle represents any set of processing parameter index feature values;

[0068] Step S3412: Based on the optimized evaluation dimension, obtain the k-th evaluation dimension and the preset feature value of the k-th evaluation dimension;

[0069] Step S3413: Analyze the k-th evaluation dimension based on the i-th particle to obtain the feature value of the k-th evaluation dimension of the i-th particle;

[0070] Step S3414: Calculate the difference between the preset feature value of the k-th evaluation dimension and the feature value of the k-th evaluation dimension of the i-th particle to generate the matching degree of the k-th evaluation dimension of the i-th particle.

[0071] Step S342: Input the matching degree of the k-th evaluation dimension of the i-th particle into the optimization fitness function to generate the comprehensive gravity of the i-th particle;

[0072] Step S343: Select the larger value from the combined gravitational force of the i-th particle and the combined gravitational force of the (i-1)-th particle to generate the superior particle for comparison;

[0073] Step S344: Determine whether the number of alignments meets the alignment threshold;

[0074] Step S345: If satisfied, set the superior particle in the comparison as the aluminum alloy die-casting processing parameter.

[0075] Specifically, based on the die-casting processing record data, the i-th particle is obtained. The i-th particle refers to any set of processing parameter index feature values, which are the specific data of each index in the processing parameters. Then, based on the optimization evaluation dimension, the k-th evaluation dimension and the preset feature value of the k-th evaluation dimension are obtained. The k-th evaluation dimension refers to any evaluation parameter in the evaluation dimension. The preset feature value of the k-th evaluation dimension can be customized based on the degree of improvement to be achieved. For example, if the k-th evaluation dimension is a processing time parameter, assuming that the processing time for an aluminum alloy die-casting part was previously 3 minutes, and now the production efficiency is to be improved by setting the processing time to 2 minutes, then the preset feature value of the k-th evaluation dimension is 2 minutes. Based on the i-th particle, the k-th evaluation dimension is analyzed to obtain the feature value of the i-th particle in the k-th evaluation dimension. The feature value of the i-th particle in the k-th evaluation dimension refers to the specific data of the i-th particle in the k-th evaluation dimension. For example, if the k-th evaluation dimension is a processing time, and the processing time parameter in the i-th particle is 3 minutes, then the feature value of the i-th particle in the k-th evaluation dimension is 3 minutes. The difference between the preset feature value of the k-th evaluation dimension and the feature value of the i-th particle in the k-th evaluation dimension is the matching degree of the i-th particle in the k-th evaluation dimension. The matching degree of the i-th particle in the k-th evaluation dimension is input into the optimized fitness function to generate the comprehensive gravity of the i-th particle. The larger the comprehensive gravity, the greater the comprehensive fitness of the particle, and thus the larger the value. The comprehensive gravity of the i-th particle and the comprehensive gravity of the (i-1)-th particle are compared, and the particle with the larger comprehensive gravity is selected as the winning particle. A preset comparison number threshold is set, which can be customized based on particle accuracy. When the comparison number is greater than or equal to the comparison number threshold, the winning particle is set as the aluminum alloy die-casting processing parameter. The aluminum alloy die-casting processing parameters are obtained based on the optimized fitness function. Because this optimized fitness function has strong global search capabilities, it can fit fitness information in multiple dimensions and has a fast convergence speed, saving computation time and thus improving the efficiency and accuracy of obtaining the aluminum alloy die-casting processing parameters.

[0076] Step S400: Extract features from the die-casting mold image information to obtain mold defect features, wherein the mold defect features include crack feature information and trace feature information;

[0077] Step S500: Based on the crack feature information and the trace feature information, perform failure analysis on the die casting mold and obtain failure evaluation results, wherein the failure evaluation results include a non-failure state or a failure state;

[0078] In one embodiment, step S500 of this application further includes:

[0079] Step S510: Perform failure analysis on the die-casting mold based on the crack feature information to generate a first-level failure evaluation result;

[0080] In one embodiment, step S510 of this application further includes:

[0081] Step S511: Obtain crack feature record data and crack failure identification data, and train the crack failure assessment model;

[0082] Step S512: Obtain trace feature record data and trace failure identification data, and train the trace failure assessment model;

[0083] Step S513: Process the crack feature information using the crack failure assessment model to obtain the first-level failure assessment result;

[0084] Step S514: Process the aluminum alloy die-casting processing parameters and the trace feature information according to the trace failure assessment model to obtain the secondary failure evaluation result.

[0085] Step S520: When the first-level failure evaluation result is in a non-failure state, retrieve the aluminum alloy die-casting processing parameters, perform failure analysis based on the trace feature information, and generate a second-level failure evaluation result;

[0086] Step S530: When the secondary failure evaluation result is in a non-failure state, it is determined that the failure evaluation result is in a non-failure state.

[0087] Specifically, an image acquisition device is used to acquire images of the die-casting mold, obtaining image information of the die-casting mold. Then, mold crack feature information and mold trace feature information are extracted from the die-casting mold image information. The mold crack feature information refers to the crack features on the die-casting surface, including crack size, crack location, crack shape, and crack depth. The mold trace feature information refers to mold scribing marks and electrical discharge machining marks, including mark size, mark location, and mark shape. Based on big data technology, relevant data of the die-casting mold is queried to obtain crack feature record data and crack failure identification data. The crack feature record data refers to the crack features on the die-casting surface, including crack size, location, shape, and depth. The crack failure identification data includes failure state and non-failure state. The failure state indicates that the die-casting part produced by the die-casting mold is a defective product and cannot be used. The non-failure state indicates that the die-casting part produced by the die-casting mold is a qualified product and can be used. A sample feature dataset is constructed, which includes the crack feature record data and the crack failure identification data. A crack failure assessment model is constructed based on a backpropagation (BP) neural network. This model is a neural network model that can be iteratively optimized in machine learning, and is obtained through supervised training using a training dataset. The sample feature set is divided into a training set and a validation set according to a preset data partitioning ratio. The training set data is input into the crack failure assessment model. When the model output results tend to converge, the validation set data is input into the model. A preset accuracy index is set. When the accuracy of the model output results exceeds the preset accuracy index, the trained crack failure assessment model is obtained. Trace feature recording data, trace failure identification data, and aluminum alloy die-casting processing parameters are acquired. The trace feature recording data refers to the trace features of the die-casting surface, such as the size, shape, and position of scribing marks and the size, shape, and position of electrical discharge machining marks. The trace failure identification data includes the failure state and the non-failure state. The aluminum alloy die-casting processing parameters refer to historical processing parameters. The trace feature recording data and the trace failure identification data have a corresponding relationship. A trace sample dataset is constructed, comprising trace feature recording data, aluminum alloy die-casting processing parameters, and trace failure identification data. A trace failure assessment model is built based on a backpropagation neural network, and supervised learning is performed using the same method described above to obtain the trace failure assessment model. The crack feature information is input into the crack failure assessment model, and the failure assessment result, i.e., the first-level failure evaluation result, is output. When the first-level failure evaluation result indicates a failure state, the failure evaluation result is determined to be a failure state.When the primary failure evaluation result is in a non-failure state, the aluminum alloy die-casting processing parameters are retrieved. The trace feature information and the aluminum alloy die-casting processing parameters are input into the trace failure assessment model, and the failure assessment result, i.e., the secondary failure assessment result, is output. If the secondary failure evaluation result is in a failure state, then the failure evaluation result is determined to be in a failure state; if the secondary failure evaluation result is in a non-failure state, then the failure evaluation result is determined to be in a non-failure state. By constructing crack failure assessment models and trace failure assessment models to evaluate the failure characteristics of the mold defects and obtain failure evaluation results, the probability of product quality defects caused by defects in the die-casting mold can be reduced, thereby improving the production quality of aluminum alloy castings.

[0088] Step S600: When the failure evaluation result is in a non-failure state, generate a die-casting processing instruction;

[0089] Step S700: Control the forming process of aluminum alloy die casting parts according to the die casting processing instructions and the aluminum alloy die casting processing parameters.

[0090] Specifically, when the failure evaluation result is in a non-failure state, meaning the surface defects of the die-casting mold do not affect product quality, a die-casting processing instruction is generated and sent to the aluminum alloy die-casting machine. The machine then controls the forming process of the aluminum alloy die-casting part according to the specified processing parameters. This method solves the technical problem of low production efficiency and quality caused by unreasonable die-casting processing parameter settings and insufficient precision in die-casting mold inspection during aluminum alloy die-casting production, thereby improving the production efficiency and quality of aluminum alloy die-casting parts.

[0091] In one embodiment, such as Figure 4 The system provided is an intelligent optimization system for the forming process of aluminum alloy die casting, including: a basic information acquisition module 1, an optimization fitness function setting module 2, a processing parameter generation module 3, a mold defect feature acquisition module 4, a failure evaluation result acquisition module 5, a die casting processing instruction generation module 6, and a forming process control module 7. wherein:

[0092] Basic information acquisition module 1, the basic information acquisition module 1 is used to acquire basic information of aluminum alloy die castings;

[0093] The fitness function setting module 2 is used to set the fitness function.

[0094] The processing parameter generation module 3 is used to optimize and analyze the die casting processing parameters based on the optimization fitness function and the basic information of the aluminum alloy die casting, and generate aluminum alloy die casting processing parameters.

[0095] The mold defect feature acquisition module 4 is used to extract features from the die casting mold image information and acquire mold defect features, wherein the mold defect features include crack feature information and trace feature information.

[0096] The failure evaluation result acquisition module 5 is used to perform failure analysis on the die casting mold based on the crack feature information and the trace feature information, and to obtain failure evaluation results, wherein the failure evaluation results include a non-failure state or a failure state.

[0097] Die casting processing instruction generation module 6, which is used to generate die casting processing instructions when the failure evaluation result is in a non-failure state;

[0098] The forming process control module 7 is used to control the forming process of aluminum alloy die casting parts according to the die casting processing instructions and based on the aluminum alloy die casting processing parameters.

[0099] In one embodiment, the system further includes:

[0100] The particle mass assessment formula module refers to the particle mass assessment formula:

[0101]

[0102] Where, m i (k) represents the particle mass parameter of the i-th particle in the k-th evaluation dimension, f i (k) represents the matching degree of the i-th particle in the k-th evaluation dimension, minf j (k) represents the minimum matching degree, maxf j (k) represents the maximum matching degree, f j (k) represents the matching degree of the j-th particle in the k-th evaluation dimension;

[0103] A module for obtaining dimensional quality assessment formulas, used to obtain dimensional quality assessment formulas:

[0104]

[0105] Among them, M i (k) represents the dimensional mass parameter of the i-th particle in the k-th evaluation dimension, L represents the total number of particles used for screening, and m j (k) represents the particle mass parameter of the j-th particle in the k-th evaluation dimension;

[0106] A single-dimensional gravity assessment formula acquisition module, wherein the single-dimensional gravity assessment formula acquisition module is used to acquire the single-dimensional gravity assessment formula:

[0107]

[0108] Where G represents the preset gravitational constant of the k-th dimension, and F represents the degree of emphasis on the k-th dimension. i (k) characterizes the gravitational force of the k-th dimension on the i-th particle;

[0109] A comprehensive gravity assessment formula acquisition module is used to acquire the comprehensive gravity assessment formula:

[0110]

[0111] Among them, F i The sum of gravity of the i-th particle is represented by N, the total number of evaluation dimensions is represented by N, and rand represents a random number in the range [0,1].

[0112] In one embodiment, the system further includes:

[0113] The data acquisition module is used to acquire optimization evaluation dimensions and processing parameter indicators;

[0114] The basic information module refers to the basic information of the aluminum alloy die casting, including die casting mold model information, casting geometric feature information, and casting material feature information.

[0115] The processing log collection module is used to collect die casting processing logs using the die casting mold model information, the casting geometric feature information, and the casting material feature information as scene data, and the processing parameter indicators and the optimization evaluation dimensions as target data, to generate die casting processing record data.

[0116] The data optimization and filtering module is used to optimize and filter the die-casting processing record data based on the optimization fitness function to generate the aluminum alloy die-casting processing parameters.

[0117] In one embodiment, the system further includes:

[0118] A matching degree acquisition module is used to acquire the matching degree of the i-th particle in the k-th evaluation dimension based on the die-casting processing record data.

[0119] The i-th particle comprehensive gravity generation module is used to input the matching degree of the k-th evaluation dimension of the i-th particle into the optimization fitness function to generate the comprehensive gravity of the i-th particle.

[0120] A comparison superior particle generation module is used to filter the larger value between the comprehensive gravitational force of the i-th particle and the comprehensive gravitational force of the (i-1)-th particle to generate a comparison superior particle.

[0121] A comparison count determination module is used to determine whether the comparison count meets the comparison count threshold.

[0122] A processing parameter acquisition module is used to set the superior particle in the comparison as the processing parameter of the aluminum alloy die casting if the condition is met.

[0123] In one embodiment, the system further includes:

[0124] The i-th particle acquisition module is used to acquire the i-th particle based on the die casting processing record data, wherein the i-th particle represents any set of processing parameter index feature values;

[0125] The k-th evaluation information acquisition module is used to obtain the k-th evaluation dimension and the preset feature value of the k-th evaluation dimension according to the optimized evaluation dimension;

[0126] The i-th particle k-th evaluation dimension feature value acquisition module is used to analyze the k-th evaluation dimension based on the i-th particle to obtain the i-th particle k-th evaluation dimension feature value.

[0127] The matching degree generation module for the k-th evaluation dimension of the i-th particle is used to calculate the difference between the preset feature value of the k-th evaluation dimension and the feature value of the k-th evaluation dimension of the i-th particle to generate the matching degree of the k-th evaluation dimension of the i-th particle.

[0128] In one embodiment, the system further includes:

[0129] A failure analysis module is used to perform failure analysis on the die-casting mold based on the crack feature information and generate a first-level failure evaluation result.

[0130] The secondary failure evaluation result generation module is used to retrieve the aluminum alloy die-casting processing parameters and perform failure analysis based on the trace feature information when the primary failure evaluation result is in a non-failure state, and generate the secondary failure evaluation result.

[0131] The non-failure state determination module is used to determine that the failure evaluation result is in a non-failure state when the secondary failure evaluation result is in a non-failure state.

[0132] In one embodiment, the system further includes:

[0133] A crack failure assessment model training module is used to acquire crack feature record data and crack failure identification data, and to train a crack failure assessment model.

[0134] The trace failure assessment model training module is used to acquire trace feature record data and trace failure identification data, and train the trace failure assessment model.

[0135] A first-level failure evaluation result acquisition module is used to process the crack feature information by the crack failure assessment model to obtain the first-level failure evaluation result.

[0136] The secondary failure evaluation result acquisition module is used to process the aluminum alloy die casting processing parameters and the trace feature information according to the trace failure assessment model to obtain the secondary failure evaluation result.

[0137] In summary, this application provides an intelligent optimization method and system for the forming process of aluminum alloy die casting, which has the following technical effects:

[0138] 1. This invention solves the technical problems of low production efficiency and quality in aluminum alloy die casting production caused by unreasonable die casting processing parameter settings and insufficient precision in die casting mold inspection. It can improve the production efficiency and quality of aluminum alloy die castings.

[0139] 2. The aluminum alloy die-casting processing parameters are obtained based on the optimized fitness function. Since the optimized fitness function has strong global search capability, it can fit fitness information in multiple dimensions. At the same time, the convergence speed is fast, which can save computation time, thereby improving the efficiency and accuracy of obtaining the aluminum alloy die-casting processing parameters.

[0140] 3. By constructing crack failure assessment models and trace failure assessment models to evaluate the failure characteristics of mold defects and obtain failure evaluation results, the probability of product quality failure caused by defects in die-casting molds can be reduced, thereby improving the production quality of aluminum alloy castings.

[0141] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0142] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A smart optimization method for the forming process of aluminum alloy die casting parts, characterized in that, include: Obtain basic information about aluminum alloy die castings; Define an optimal fitness function; Based on the optimized fitness function, the die casting processing parameters are optimized and analyzed according to the basic information of the aluminum alloy die casting, and aluminum alloy die casting processing parameters are generated. Feature extraction is performed on the image information of the die casting mold to obtain mold defect features, wherein the mold defect features include crack feature information and trace feature information; Based on the crack feature information and the trace feature information, a failure analysis is performed on the die casting mold to obtain a failure evaluation result, wherein the failure evaluation result includes a non-failure state or a failure state. If the failure evaluation result indicates a non-failure state, a die-casting processing instruction is generated. Based on the die-casting processing instructions and the aluminum alloy die-casting processing parameters, the forming process of aluminum alloy die-casting parts is controlled. The optimized fitness function includes: Particle mass assessment formula: ； in, The particle mass parameter characterizing the i-th particle in the k-th evaluation dimension. Characterizes the matching degree of the i-th particle in the k-th evaluation dimension. Characterizing the minimum matching degree, Characterizes the maximum matching degree. Characterizes the matching degree of the j-th particle in the k-th evaluation dimension; Formula for obtaining dimensional quality assessment: ； in, The dimensional mass parameter representing the i-th particle in the k-th evaluation dimension, and L representing the total number of particles used for screening. The particle mass parameter characterizing the j-th particle in the k-th evaluation dimension; Obtain the formula for evaluating single-dimensional gravity: ； in, The predefined gravitational constant representing the k-th dimension, and the degree of emphasis on the k-th dimension. Characterizes the gravitational force of the k-th dimension on the i-th particle; Obtain the comprehensive gravitational assessment formula: ； in, Characterizing the combined gravitational force of the i-th particle. Total number of dimensions for characterization and evaluation Represents a random number in the range [0,1].

2. The method as described in claim 1, characterized in that, Based on the optimized fitness function, the die-casting processing parameters are optimized and analyzed according to the basic information of the aluminum alloy die-casting parts to generate aluminum alloy die-casting processing parameters, including: Obtain optimization evaluation dimensions and processing parameter indicators; The basic information of the aluminum alloy die casting includes die casting mold model information, casting geometric feature information, and casting material feature information; Using the die-casting mold model information, the casting geometric feature information, and the casting material feature information as scene data, and the processing parameter indicators and the optimization evaluation dimensions as target data, die-casting processing logs are collected to generate die-casting processing record data; Based on the optimized fitness function, the die-casting processing record data is optimized and filtered to generate the aluminum alloy die-casting processing parameters.

3. The method as described in claim 2, characterized in that, The step of optimizing and filtering the die-casting processing record data based on the optimized fitness function to generate the aluminum alloy die-casting processing parameters includes: Based on the die-casting processing record data, obtain the matching degree of the k-th evaluation dimension of the i-th particle; Input the matching degree of the k-th evaluation dimension of the i-th particle into the optimization fitness function to generate the comprehensive gravity of the i-th particle; The larger value of the combined gravitational force of the i-th particle and the combined gravitational force of the (i-1)-th particle is selected to generate the superior particle for comparison. Determine whether the number of comparisons meets the comparison threshold; If the conditions are met, the superior particle in the comparison is set as the processing parameter for the aluminum alloy die casting.

4. The method as described in claim 3, characterized in that, The step of obtaining the matching degree of the k-th evaluation dimension of the i-th particle based on the die-casting processing record data includes: Based on the die-casting processing record data, the i-th particle is obtained, wherein the i-th particle represents any set of processing parameter index feature values; Based on the optimized evaluation dimension, obtain the k-th evaluation dimension and the preset feature value of the k-th evaluation dimension; Based on the analysis of the i-th particle on the k-th evaluation dimension, the feature value of the i-th particle in the k-th evaluation dimension is obtained; The difference between the preset feature value of the k-th evaluation dimension and the feature value of the k-th evaluation dimension of the i-th particle is calculated to generate the matching degree of the k-th evaluation dimension of the i-th particle.

5. The method as described in claim 1, characterized in that, The failure analysis of the die-casting mold is performed based on the crack feature information and the trace feature information to obtain a failure evaluation result, wherein the failure evaluation result includes a non-failure state or a failure state, including: Based on the crack characteristic information, a failure analysis is performed on the die-casting mold to generate a first-level failure evaluation result; When the first-level failure evaluation result is in a non-failure state, the aluminum alloy die-casting processing parameters are retrieved, and failure analysis is performed based on the trace feature information to generate a second-level failure evaluation result. If the secondary failure evaluation result is in a non-failure state, the failure evaluation result is determined to be in a non-failure state.

6. The method as described in claim 5, characterized in that, include: Acquire crack feature record data and crack failure identification data, and train a crack failure assessment model; Acquire trace feature record data and trace failure identification data, and train a trace failure assessment model; The crack failure assessment model is used to process the crack feature information to obtain the first-level failure assessment result; The aluminum alloy die-casting processing parameters and the trace feature information are processed according to the trace failure assessment model to obtain the secondary failure evaluation results.

7. An intelligent optimization system for aluminum alloy die casting forming process, characterized in that, include: Basic information acquisition module, which is used to acquire basic information of aluminum alloy die castings; An optimization fitness function setting module is used to set the optimization fitness function; The particle mass assessment formula module refers to the particle mass assessment formula: ； in, The particle mass parameter characterizing the i-th particle in the k-th evaluation dimension. Characterizes the matching degree of the i-th particle in the k-th evaluation dimension. Characterizes the minimum matching degree. Characterizes the maximum matching degree. Characterizes the matching degree of the j-th particle in the k-th evaluation dimension; A module for obtaining dimensional quality assessment formulas, used to obtain dimensional quality assessment formulas: ； in, The dimensional mass parameter representing the i-th particle in the k-th evaluation dimension, and L representing the total number of particles used for screening. The particle mass parameter characterizing the j-th particle in the k-th evaluation dimension; A single-dimensional gravity assessment formula acquisition module, wherein the single-dimensional gravity assessment formula acquisition module is used to acquire the single-dimensional gravity assessment formula: ； in, The predefined gravitational constant representing the k-th dimension, and the degree of emphasis on the k-th dimension. Characterizes the gravitational force of the k-th dimension on the i-th particle; A comprehensive gravity assessment formula acquisition module is used to acquire the comprehensive gravity assessment formula: ； in, Characterizing the combined gravitational force of the i-th particle. Total number of dimensions for characterization and evaluation Represents a random number in the range [0,1]. A processing parameter generation module is used to optimize and analyze the die casting processing parameters based on the optimization fitness function and the basic information of the aluminum alloy die casting, and generate aluminum alloy die casting processing parameters. A mold defect feature acquisition module is used to extract features from die-casting mold image information to acquire mold defect features, wherein the mold defect features include crack feature information and trace feature information; The failure evaluation result acquisition module is used to perform failure analysis on the die casting mold based on the crack feature information and the trace feature information, and to acquire failure evaluation results, wherein the failure evaluation results include a non-failure state or a failure state. A die casting processing instruction generation module is used to generate a die casting processing instruction when the failure evaluation result is in a non-failure state. A forming process control module is used to control the forming process of aluminum alloy die casting parts according to the die casting processing instructions and based on the aluminum alloy die casting processing parameters.

Images