Collaborative Design Method for Structural Performance of Integral Large-Scale Complex Thin-Walled Die-Cast Components

Abstract

The present application discloses a collaborative design method for the structural performance of an integrated large-scale complex thin-walled die-cast component, which relates to the field of artificial intelligence technology. The method realizes the full-automatic optimization of complex thin-walled components from conceptual design to performance verification through a collaborative process of multi-model topology optimization, machine learning-assisted classification, and experimental-simulation closed-loop verification. While ensuring computational efficiency, the system significantly improves the mechanical performance reliability and multi-objective collaborative ability of the design, and finally outputs a lightweight and high crashworthiness structural solution and a traceable complete performance report.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and particularly to a collaborative design method for the structural performance of an integrated large-scale complex thin-walled die-cast component. Background Art

[0002] In order to reduce carbon emissions, advanced die-casting manufacturing processes should be used. Lightweight design of automobiles can save fuel consumption. Large thin-walled castings such as the body-in-white and front engine compartment used in automobiles can be manufactured using integrated die-casting technology. However, the increase in the size and complexity of large castings has increased the difficulty of producing high-quality die-castings. High-strength materials are important for automotive safety. In addition to strength requirements, there are many other requirements that automotive components need to meet, such as vehicle dynamics static stiffness, NVH, driving comfort standards, and passive safety, etc.

[0003] For each requirement (such as NVH, statics, durability, and collision), there is a separate finite element model and different calculations are performed. Since each design requirement involves different commercial solvers and physical equations, most use independent models and adopt structural optimization (topology optimization) technology to derive structural changes to improve design accuracy. However, the separately designed models cannot be aligned, so the derived lightweight design parameters are not the optimal solutions, and multiple iterations are required among multiple design requirements, which increases the R & D cost. Summary of the Invention

[0004] The purpose of the present application is to provide a collaborative design method for the structural performance of an integrated large-scale complex thin-walled die-cast component.

[0005] To achieve the above purpose, the present application provides the following solutions:

[0006] In the first aspect, the present application provides a collaborative design method for the structural performance of an integrated large-scale complex thin-walled die-cast component, including:

[0007] Inputting the design parameters of the complex thin-walled part into a multi-model topology optimization framework to generate an initial load path optimization scheme;

[0008] Constructing a response surface prediction model based on the initial load path optimization scheme and generating a training data set through experimental design;

[0009] Inputting the training data set into a machine learning enhancement module to generate a design space classifier and clustering and grouping the simulation results;

[0010] Selecting the optimal design group that meets the preset constraint conditions according to the classifier and performing plastic deformation and damage failure simulations using the material constitutive model specified by the preset standard;

[0011] Perform multi-dimensional experimental tests on the samples in the optimal design group to obtain measured data for calibrating the failure parameters of the simulation model;

[0012] Execute a frontal collision test verification based on the calibrated simulation model and output the final design scheme that meets multi-performance constraints;

[0013] Integrate the optimization results of each stage in the final design scheme to generate an integrated structural performance report for the complex thin-walled part.

[0014] Optionally, the step of inputting the design parameters of the complex thin-walled part into the multi-model topology optimization framework to generate an initial load path optimization scheme includes:

[0015] Adjust the material distribution density through a density-based topology optimization algorithm to determine the optimal load path that meets static, NVH, and collision performance;

[0016] Establish a multi-disciplinary coupling optimization model, and the multi-disciplinary coupling optimization model balances the stiffness matrices of different finite element models through weight factors;

[0017] Map the design variables under multiple load conditions to a unified parameter space and output a set of candidate schemes including structural efficiency and performance indicators.

[0018] Optionally, the step of constructing a response surface prediction model based on the initial load path optimization scheme includes:

[0019] Extract the design variables and response variables from the set of candidate schemes and construct a second-order polynomial response surface function;

[0020] Generate a training data set through the Latin hypercube sampling method specified by a preset standard, and the training data set covers compression, tension, and shear stress states;

[0021] Use the training data set to fit the response surface prediction model and output the predicted values of stress, deformation, and damage factors.

[0022] Optionally, the step of inputting the training data set into the machine learning enhancement module includes:

[0023] Extract the features of the visualization data of the simulation results and mark the key stress concentration areas in the design space;

[0024] Use the K-means clustering algorithm to group the training data set and generate a classifier containing failure mode labels;

[0025] Couple the classifier with the response surface prediction model to establish a probability-driven design screening rule.

[0026] Optionally, the step of performing plastic deformation and damage failure simulation using the material constitutive model specified by the preset standard includes:

[0027] Call the MAT_PLASTICITY_COMPRESSION_TENSION_MAT_124 keyword to simulate the compression-tension dual-mode response of the material;

[0028] Calculate the dynamic yield stress under high strain rate conditions based on the Cowper-Symonds strain rate model;

[0029] Use the MAT_ADD_DAMAGE_DIEM keyword to evolve the damage factor, and the damage factor is iteratively updated through the equivalent plastic displacement increment.

[0030] Optionally, the step of performing multi-dimensional experimental tests on the samples in the optimal design group includes:

[0031] Perform metallographic inspection and CT scanning at the preset positions of the samples to obtain data on the microstructure and porosity distribution;

[0032] Perform quasi-static tensile tests and dynamic impact tests, and collect the stress-strain curves and fracture toughness parameters of the samples;

[0033] Establish the mapping relationship between the defect type and the simulation damage result through X-ray non-destructive testing and scanning electron microscope fracture analysis.

[0034] Optionally, the step of performing frontal collision test verification based on the calibrated simulation model includes:

[0035] Construct a vehicle collision finite element model, and embed the complex thin-walled part as a key component into the vehicle collision finite element model;

[0036] Set the collision initial velocity and boundary conditions specified by the preset standard, and calculate the deformation energy absorption of the complex thin-walled part;

[0037] Compare the simulation deformation mode with the measured data, verify the stiffness matching degree, and optimize the process feasibility of the final design scheme.

[0038] In a second aspect, the present application provides a device for collaborative design of the structural performance of an integrated large-scale complex thin-walled die-casting component, including:

[0039] A processing module for inputting the design parameters of the complex thin-walled part into a multi-model topology optimization framework to generate an initial load path optimization scheme;

[0040] Construct a response surface prediction model based on the initial load path optimization scheme, and generate a training data set through experimental design;

[0041] Input the training data set into the machine learning enhancement module to generate a design space classifier and cluster and group the simulation results;

[0042] Select the optimal design group that meets the preset constraint conditions according to the classifier, and perform plastic deformation and damage failure simulations using the material constitutive model specified by the preset standard;

[0043] Conduct multi-dimensional experimental tests on the samples in the optimal design group to obtain measured data for calibrating the failure parameters of the simulation model;

[0044] An output module, which is used to perform a frontal collision test verification based on the calibrated simulation model and output the final design scheme that meets multiple performance constraints;

[0045] Integrate the optimization results of each stage in the final design scheme to generate an integrated structural performance report for the complex thin-walled part.

[0046] Optionally, the processing module is further used for:

[0047] Adjust the material distribution density through a density-based topology optimization algorithm to determine the optimal load path that meets static, NVH, and collision performance;

[0048] Establish a multi-disciplinary coupling optimization model, and the multi-disciplinary coupling optimization model balances the stiffness matrices of different finite element models through weight factors;

[0049] Map the design variables under multiple load conditions to a unified parameter space and output a set of candidate solutions including structural efficiency and performance indicators.

[0050] Optionally, the processing module is further used for:

[0051] Extract the design variables and response variables from the set of candidate solutions and construct a second-order polynomial response surface function;

[0052] Generate a training data set through the Latin hypercube sampling method specified by the preset standard, and the training data set covers compression, tension, and shear stress states;

[0053] Use the training data set to fit the response surface prediction model and output the predicted values of stress, deformation, and damage factors.

[0054] Optionally, the processing module is further used for:

[0055] Extract the features of the visualization data of the simulation results and mark the key stress concentration areas in the design space;

[0056] Group the training data set using the K-means clustering algorithm to generate a classifier including failure mode labels;

[0057] Couple the classifier with the response surface prediction model to establish a probability-driven design screening rule.

[0058] Optionally, the processing module is further configured to:

[0059] Call the MAT_PLASTICITY_COMPRESSION_TENSION_MAT_124 keyword to simulate the compression-tension bimodal response of the material;

[0060] Calculate the dynamic yield stress under high strain rate conditions based on the Cowper-Symonds strain rate model;

[0061] Adopt the MAT_ADD_DAMAGE_DIEM keyword to evolve the damage factor, and the damage factor is iteratively updated through the equivalent plastic displacement increment.

[0062] Optionally, the processing module is further configured to:

[0063] Perform metallographic inspection and CT scanning at preset positions of the sample to obtain data on the microstructure and porosity distribution;

[0064] Perform quasi-static tensile tests and dynamic impact tests, and collect the stress-strain curves and fracture toughness parameters of the sample;

[0065] Establish a mapping relationship between the defect type and the simulation damage result through X-ray non-destructive testing and scanning electron microscope fracture analysis.

[0066] Optionally, the output module is further configured to:

[0067] Construct a finite element model for vehicle collision, and embed the complex thin-walled part as a key component into the finite element model for vehicle collision;

[0068] Set the initial collision velocity and boundary conditions specified by the preset standard, and calculate the deformation energy absorption of the complex thin-walled part;

[0069] Compare the simulation deformation mode with the measured data, verify the stiffness matching degree, and optimize the process feasibility of the final design scheme.

[0070] In a third aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the computer program to implement the steps of the integrated large-scale complex thin-walled die-casting component structural performance collaborative design method described in any one of the above.

[0071] Fourthly, the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the integrated large-scale complex thin-wall die-casting component structure performance collaborative design method described in any one of the above are implemented.

[0072] Fifthly, the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, the steps of the integrated large-scale complex thin-wall die-casting component structure performance collaborative design method described in any one of the above are implemented.

[0073] According to the specific embodiments provided by the present application, the following technical effects are disclosed in the present application:

[0074] The present application provides an integrated large-scale complex thin-wall die-casting component structure performance collaborative design method. Through the collaborative process of multi-model topology optimization, machine learning-assisted classification, and experiment-simulation closed-loop verification, the full-automatic optimization of complex thin-wall components from conceptual design to performance verification is realized. While ensuring the calculation efficiency, the system significantly improves the mechanical performance reliability and multi-objective collaborative ability of the design, and finally outputs a lightweight and high crashworthiness structural solution and a traceable complete performance report. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required to be used in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0076] Figure 1 It is a schematic flowchart of an integrated large-scale complex thin-wall die-casting component structure performance collaborative design method provided by an embodiment of the present application;

[0077] Figure 2 It is one of the schematic diagrams of the principle of an integrated large-scale complex thin-wall die-casting component structure performance collaborative design method provided by an embodiment of the present application;

[0078] Figure 3 It is another schematic diagram of the principle of an integrated large-scale complex thin-wall die-casting component structure performance collaborative design method provided by an embodiment of the present application;

[0079] Figure 4 It is yet another schematic diagram of the principle of an integrated large-scale complex thin-wall die-casting component structure performance collaborative design method provided by an embodiment of the present application;

[0080] Figure 5Schematic diagram of the functional modules of a collaborative design device for the structural performance of an integrated large complex thin-walled die-casting component provided by an embodiment of the present application;

[0081] Figure 6 Schematic diagram of the structure of a computer device provided by an embodiment of the present application. Specific embodiments

[0082] Next, the technical solutions in the embodiments of the present application will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0083] As Figure 1 shown, some embodiments of the present application provide a collaborative design method for the structural performance of an integrated large complex thin-walled die-casting component. In the embodiments of the present application, it includes:

[0084] Step 101: Input the design parameters of the complex thin-walled part into the multi-model topology optimization framework to generate an initial load path optimization scheme.

[0085] In the embodiments of the present application, a complex thin-walled part refers to an engineering component with a complex geometric shape and a relatively thin wall thickness, which is usually used to reduce weight and meet mechanical performance requirements. The design parameters include input variables such as geometric dimensions, material properties, and load conditions. The multi-model topology optimization framework is a computational platform that integrates multiple optimization algorithms and is used to automatically generate a structural design scheme under given constraints.

[0086] The computer terminal inputs the design parameters (such as boundary conditions, objective functions, and constraint conditions) of the complex thin-walled part defined by the user into the multi-model topology optimization framework. This framework generates an initial load path optimization scheme through iterative calculations (such as the variable density method or the level set method), and this scheme is presented in the form of the structural material distribution to ensure a preliminary balance between mechanical performance and the lightweight goal.

[0087] Specifically, topology optimization and response surface-based optimization are performed, and the response surface-based optimization is enhanced through expert simulation and clustering classification of machine learning. As Figure 2 shown.

[0088] The overall optimization problem can be expressed as a multi-model optimization problem, and the formulas (1) and (2) are as follows:

[0089] (1)

[0090] Wherein, the result of and (m) The Each load case is mapped to its corresponding finite element model m. Here, Define the objective function, is the inequality constraint, and are the lower and upper bounds of the th design variable, respectively.

[0091] (2)

[0092] Among them, the purpose of introducing the weight factor is to balance different load cases and derive various generative design suggestions. refers to the applied load; = 1, …, represents different load vectors, where is the number of load cases. Since the ligand mass conditions of each discipline are different, different finite element models may also be required, and each model is represented by a specific stiffness matrix denoted by, m = 1, …, where is the number of finite element models.

[0093] It can be seen that in this multi-model optimization framework, the design variables are the coupling parameters between each load case, model, or discipline. The best candidate design solutions are obtained through this multi-model optimization framework, as shown in Figure 3 .

[0094] Step 102, construct a response surface prediction model based on the initial load path optimization scheme, and generate a training data set through experimental design.

[0095] In the embodiment of the present application, the response surface prediction model is a surrogate model that approximately simulates the relationship between input parameters and output responses through a mathematical function. Experimental design refers to the strategy of planning training data points through sampling methods (such as Latin hypercube or full factorial design).

[0096] The computer constructs a response surface prediction model such as a polynomial or radial basis function based on the input-output relationship in the initial load path optimization scheme. The system generates uniformly distributed sample points in the parameter space through the experimental design method, calls the simulation module to calculate the corresponding mechanical responses, and forms a training data set to support model training.

[0097] Step 103, input the training data set into the machine learning enhancement module to generate a design space classifier and cluster and group the simulation results.

[0098] In the embodiments of the present application, the machine learning enhancement module refers to a software component integrating classification or regression algorithms, which is used to improve the efficiency of design space exploration. The design space classifier is a binary or multi-class discriminant model constructed through supervised learning. Clustering grouping is an operation of grouping similar simulation results in unsupervised learning.

[0099] The computer inputs the training data set into the machine learning enhancement module, trains the design space classifier using support vector machine or random forest algorithms to distinguish between feasible and infeasible designs. The system simultaneously performs K-means or hierarchical clustering on the simulation results, groups the design schemes according to mechanical property similarity to form an optimization candidate set.

[0100] Specifically, machine learning is added to the response surface optimization (RSM). Through machine learning, expert simulations are used to visually inspect and label each run, and clustering classification is used to classify runs with similar results, denoted as r(x). This will generate result groups. As Figure 4 shown, all runs are labeled to generate a classifier, which can be expressed as: , is a scalar, is the probability that r(x) belongs to .

[0101] Placing the classifier in the response surface-based optimization can be used to determine the optimal design belonging to a specific group, expressed as formula (3):

[0102] (3)

[0103] where the composite field is determined using the RSM itself, represents the minimum probability required for the result to belong to the group.

[0104] Step 104, screen out the optimal design group that meets the preset constraint conditions according to the classifier, and perform plastic deformation and damage failure simulations using the material constitutive model specified by the preset standard.

[0105] In the embodiments of the present application, the material constitutive model is a mathematical expression describing the stress-strain relationship of materials. Plastic deformation refers to the irreversible deformation behavior of materials beyond the elastic limit. Damage failure simulation is a numerical method for simulating the whole process of material from damage initiation to fracture.

[0106] The computer screens out the optimal design group that meets the constraint conditions according to the classifier, calls the finite element analysis module to load the material constitutive model specified by the preset standard (such as Johnson-Cook or Gurson model), and performs non-linear dynamic simulation to evaluate plastic deformation and damage failure behaviors and quantify the structural crashworthiness index.

[0107] Step 105: Conduct multi-dimensional experimental tests on the samples in the optimal design group to obtain measured data for calibrating the failure parameters of the simulation model.

[0108] In the embodiment of the present application, the multi-dimensional experimental tests include physical tests under different load conditions such as static compression and dynamic impact. The measured data refers to physical quantities such as displacement and strain collected by sensors. Failure parameter calibration is a process of making the simulation results match the experimental data through reverse optimization.

[0109] The computer-controlled testing machine conducts multi-condition mechanical tests on the samples in the optimal design group, and collects load-displacement curves and failure modes through force sensors and high-speed cameras. The system adjusts the failure parameters (such as fracture strain) in the simulation model based on the least squares method or genetic algorithm to ensure that the numerical prediction error is within the threshold compared with the measured data.

[0110] Step 106: Perform frontal collision test verification based on the calibrated simulation model, and output the final design scheme that meets multi-performance constraints.

[0111] In the embodiment of the present application, the frontal collision test verification is a dynamic response test that simulates the structure under axial impact load. The multi-performance constraints include comprehensive index requirements such as stiffness, energy absorption, and peak force.

[0112] The computer uses the calibrated simulation model to perform numerical simulation of the frontal collision condition, and extracts key indicators such as energy absorption and collision force waveform. The system screens the final design scheme that simultaneously meets constraints such as lightweight and crashworthiness through a multi-objective optimization algorithm (such as NSGA-II), and outputs a set of geometric and performance parameters.

[0113] Step 107: Integrate the optimization results of each stage in the final design scheme to generate an integrated structural performance report for the complex thin-walled part.

[0114] In the embodiment of the present application, the integrated structural performance report is a standardized document that summarizes the design iteration process and the comparison data between simulation and experiment.

[0115] The computer automatically integrates data such as topology optimization results, machine learning classification boundaries, and comparison curves between simulation and experiment, and generates a PDF format report including convergence analysis and robustness evaluation to support design decision-making and archiving.

[0116] The embodiment of the present application realizes the full-automatic optimization of complex thin-walled parts from conceptual design to performance verification through a collaborative process of multi-model topology optimization, machine learning-assisted classification, and experiment-simulation closed-loop verification. While ensuring the computational efficiency, the system significantly improves the mechanical performance reliability and multi-objective collaboration ability of the design, and finally outputs a lightweight and high-crashworthiness structural scheme and a traceable complete performance report.

[0117] Optionally, step 101 includes:

[0118] Step 1011: Adjust the material distribution density through a density-based topology optimization algorithm to determine the optimal load path that meets the static, NVH, and collision performance requirements.

[0119] In the embodiment of the present application, the density-based topology optimization algorithm is a numerical method for optimizing the structural performance by adjusting the material distribution density (0-1 continuous variable), where the density close to 1 represents solid material and the density close to 0 represents void. The static performance refers to the mechanical properties such as stiffness and strength of the structure under static loads. The NVH performance is a comprehensive evaluation index of noise, vibration, and harshness, reflecting the dynamic response characteristics of the structure. The collision performance refers to the crashworthiness indexes such as energy absorption, peak force, and deformation mode of the structure under impact loads. The optimal load path is the best distribution method of materials in the structure to maximize the target performance (such as stiffness and lightweight).

[0120] The computer uses a density-based topology optimization algorithm (such as the SIMP method) to minimize the structural compliance or maximize the natural frequency as the goal, and iteratively adjusts the material density distribution on the finite element model. The system calculates the influence of the design variables (element density) on the static, NVH, and collision performance through sensitivity analysis, generates the optimal load path that meets the multi-objective constraints, and outputs the optimized geometric configuration in STL or mesh format.

[0121] Step 1012: Establish a multidisciplinary coupling optimization model, and the multidisciplinary coupling optimization model balances the stiffness matrices of different finite element models through weight factors.

[0122] In the embodiment of the present application, the multidisciplinary coupling optimization model is a joint optimization framework integrating multiple disciplines (such as structural mechanics and acoustics), and realizes cross-disciplinary variable interaction through coupling equations. The weight factor is a coefficient used to adjust the contribution ratio of the objective functions of different disciplines to ensure that the optimization direction meets the global requirements. The stiffness matrix of the finite element model is a matrix describing the stiffness characteristics of the structural elements, and is used to calculate mechanical responses such as displacement and stress.

[0123] Based on the topology optimization results, the computer establishes a multidisciplinary coupling optimization model including static, NVH, and collision analyses. The system unifies the objective functions of each discipline (such as the eigenvalue of the stiffness matrix and the modal frequency) into a comprehensive objective through the weighted summation method, and uses a gradient optimization algorithm (such as MMA) to adjust the weight factors to balance the contributions of the stiffness matrices of different disciplines, and outputs a design variable update scheme that takes into account multiple performance requirements.

[0124] Step 1013: Map the design variables under multi-load conditions to a unified parameter space, and output a set of candidate solutions including structural efficiency and performance indicators.

[0125] In the embodiments of the present application, the multi-load condition is a combination of multiple loads (such as bending, torsion, and impact) that the structure bears under actual working conditions. The design variables are parameters that can be adjusted during the optimization process (such as thickness, material density). The unified parameter space is to normalize the design variables of different disciplines to the same mathematical space to facilitate interdisciplinary optimization. The structural efficiency is the performance indicator per unit mass (such as specific stiffness, specific strength). The performance indicator is a parameter that quantifies the structural characteristics (such as displacement, stress, natural frequency).

[0126] The computer maps the design variables (such as element density, thickness) under static, NVH, and collision conditions to a unified parameter space, and uses principal component analysis (PCA) or radial basis function (RBF) interpolation method to achieve data dimensionality reduction and correlation. The system evaluates the structural efficiency and performance indicators of each candidate solution through the Pareto front screening algorithm, and outputs a set of optimized solutions that meet multi-objective trade-offs for subsequent decision-making.

[0127] In the embodiments of the present application, the optimal material distribution is determined by a density-based topology optimization algorithm, and the stiffness, NVH, and collision performance are balanced by combining a multidisciplinary coupling model. Finally, candidate solutions with high structural efficiency are generated within the unified parameter space.

[0128] Optionally, step 102 includes:

[0129] Step 1021: Extract the design variables and response variables from the set of candidate solutions, and construct a second-order polynomial response surface function.

[0130] In the embodiments of the present application, the design variables are independent parameters that can be adjusted during the optimization process, such as material thickness, geometric dimensions, or topology optimization density distribution parameters. The response variables are output performance indicators determined by the design variables, such as stress, strain, displacement, or natural frequency. The second-order polynomial response surface function is a surrogate model based on quadratic polynomial regression, which is used to approximately describe the non-linear relationship between the design variables and the response variables.

[0131] The computer extracts the design variables (such as element density, thickness distribution) and the corresponding response variables (such as maximum stress, modal frequency) from the set of candidate solutions, and constructs a second-order polynomial response surface function. The system uses the least squares method to fit the polynomial coefficients and establish a mapping relationship from the design space to the performance space.

[0132] Step 1022: Generate a training data set through the Latin hypercube sampling method specified by a preset standard, and the training data set covers compression, tension, and shear stress states.

[0133] In the embodiments of the present application, the Latin hypercube sampling method: a hierarchical random sampling strategy that ensures that sample points are evenly distributed in the design space and have no repeated projections. The training data set is a data set containing input design variables and output response variables, and is used for model training and verification. Compressive, tensile, and shear stress states are classifications of the mechanical behavior of materials under unidirectional compression, unidirectional tension, and shear loadings.

[0134] The computer generates evenly distributed sample points in the design variable space according to the Latin hypercube sampling method specified by a preset standard (such as ISO 18404). The system calls the finite element analysis module, applies compressive, tensile, and shear loading conditions to each sample point, calculates the corresponding stress, strain, and damage factors, and forms a training data set covering multiple stress states. The data set is stored as a structured array, containing input variables (such as load magnitude, geometric parameters) and output variables (such as Von Mises stress, plastic strain).

[0135] Step 1023, use the training data set to fit the response surface prediction model, and output the predicted values of stress, deformation, and damage factors.

[0136] In the embodiments of the present application, the response surface prediction model is a surrogate model constructed by mathematical fitting, and is used to quickly predict the performance response of unsampled points. The stress prediction value is an estimated value of the internal stress distribution of the structure output by the model under the action of the load. The deformation prediction value is an estimated value of the structural displacement or shape change output by the model. The damage factor prediction value is an index that quantifies the risk of material failure, such as the Johnson-Cook damage parameter or equivalent plastic strain.

[0137] The computer uses the training data set to fit the second-order polynomial response surface model, and uses the cross-validation method to evaluate the model accuracy (such as R²≥0.95). The system realizes the rapid mapping from input design variables to output responses (stress, deformation, damage factors) by solving the polynomial coefficient matrix. For new design points, the model directly outputs the predicted values, replacing time-consuming high-fidelity simulations, and supporting subsequent optimization iterations.

[0138] The embodiments of the present application realize the rapid and high-precision prediction of complex mechanical responses by constructing a second-order polynomial response surface model, combining Latin hypercube sampling and multi-stress state training data. This technical solution significantly reduces the computational cost, avoids repeated calls to finite element analysis, and at the same time ensures the reliability of the surrogate model under typical working conditions such as compression, tension, and shear, providing efficient data-driven support for multi-objective optimization.

[0139] Optionally, step 103 includes:

[0140] Step 1031, extract features from the visualization data of the simulation results, and mark the key stress concentration areas in the design space.

[0141] In the embodiments of the present application, the visual data of the simulation results are graphical output data such as stress nephograms and deformation animations generated through post-processing of finite element analysis. Feature extraction is a computational process of identifying and quantifying key geometric or mechanical features from the visual data. The critical stress concentration region is a local area in the structure where the stress level is significantly higher than the average value, and it is usually the starting position of potential failure.

[0142] The computer analyzes the visual stress nephogram of the simulation results through image processing algorithms (such as edge detection and region growing method), and automatically identifies the regions with sudden changes in stress gradient. The system uses a threshold segmentation method to mark the stress concentration areas exceeding 80% of the material yield strength, and records their spatial coordinates, stress peaks and distribution ranges. These feature data are stored in a structured manner and used as input variables for subsequent clustering analysis.

[0143] Step 1032: Use the K-means clustering algorithm to group the training data set to generate a classifier containing failure mode labels.

[0144] In the embodiments of the present application, the K-means clustering algorithm is an unsupervised machine learning method based on distance measurement, which divides the data into K mutually exclusive subsets. The failure mode label is a classification mark (such as buckling, tearing, fracture) that identifies the typical failure forms of the structure. The classifier is a mathematical model that can automatically assign category labels to new data.

[0145] The computer uses feature parameters such as stress peaks and deformation energy density in the training data set as the input vectors of the K-means algorithm. The system presets the number of clusters K = 3 (corresponding to three typical failure modes), and completes data grouping by iteratively optimizing the centroid positions. Each cluster center is assigned a failure mode label with a clear physical meaning, forming a three-classifier with decision boundaries. This classifier can automatically label the simulation results of new design schemes.

[0146] Step 1033: Couple the classifier with the response surface prediction model to establish a probability-driven design screening rule.

[0147] In the embodiments of the present application, the probability-driven design screening rule is a scheme optimization criterion established based on statistical probability distributions. Model coupling is a process of data interaction between different mathematical models through interface protocols.

[0148] The computer couples the classifier with the response surface prediction model through the data bus interface to establish a joint evaluation framework. The system calculates the failure probability distribution of each design point in the prediction results of the response surface model, and combines the failure mode labels output by the classifier to generate a multi-dimensional screening matrix. For the candidate design solutions, when the probability of the main failure mode exceeds the preset threshold (such as the buckling probability > 30%), the system automatically excludes it from the optimization queue.

[0149] In the embodiment of the present application, through visual feature extraction, failure mode clustering and probability coupling analysis, intelligent classification and risk quantification evaluation of design solutions are realized. This technical solution establishes a closed-loop link from simulation data to design decisions, significantly improving the recognition accuracy of potential failure modes while ensuring computational efficiency, and providing data support for structural reliability optimization. The probability screening rules output by the system can effectively reduce the number of iterations in the later verification stage.

[0150] Optionally, step 104 includes:

[0151] Step 1041, call the MAT_PLASTICITY_COMPRESSION_TENSION_MAT_124 keyword to simulate the compression-tension dual-mode response of the material.

[0152] In the embodiment of the present application, the MAT_PLASTICITY_COMPRESSION_TENSION_MAT_124 keyword is a dual-mode elastoplastic constitutive model in the LS-DYNA material model, which is used to distinguish the mechanical behavior of the material in the compression and tension states. The compression-tension dual-mode response is that the material exhibits asymmetric yield strength and hardening characteristics under different stress states (compression / tension).

[0153] The computer calls the material model interface of the finite element solver to activate the MAT_124 constitutive relationship. The system inputs the elastic modulus, Poisson's ratio, yield strength and hardening curve parameters of the material in the compression and tension states respectively. During the calculation process, the program automatically switches between the compression or tension mode according to the current stress state of the element, and uses different plastic flow rules for stress update. This model can accurately simulate the asymmetric plastic behavior of metal materials under complex loads.

[0154] Step 1042, calculate the dynamic yield stress under high strain rate conditions based on the Cowper-Symonds strain rate model.

[0155] In the embodiment of the present application, the Cowper-Symonds strain rate model is an empirical formula describing the change of material yield strength with strain rate. The high strain rate condition is a dynamic loading condition where the strain rate exceeds 10^2 s^-1. The dynamic yield stress is the critical stress value at which the material begins to undergo plastic deformation under dynamic loads.

[0156] At each incremental step, the computer first obtains the current strain rate ε' through the central difference method. The system calls the Cowper-Symonds model parameters (material constants C and P) and combines the static yield stress σy to calculate the dynamic yield stress correction value in real time. This correction value is substituted into the J2 plastic flow criterion to update the equivalent stress of the current step. For strain rate sensitive materials (such as high-strength steel), this process can accurately reflect its dynamic strengthening effect.

[0157] Specifically, in order to accurately simulate the behavior of materials under different stress conditions, the Cowper-Symonds strain rate model and two load curves that scale the yield stress values in compression and tension respectively are used. Through the Cowper-Symonds strain rate model, the strain rate effect of the material is taken into account, thereby accurately simulating the response of the material under high strain rate conditions.

[0158] Step 1043, using the MAT_ADD_DAMAGE_DIEM keyword to evolve the damage factor, the damage factor is iteratively updated by the equivalent plastic displacement increment.

[0159] In the embodiment of the present application, MAT_ADD_DAMAGE_DIEM keyword: material extension option used in LS-DYNA to define damage accumulation and failure criteria. Equivalent plastic displacement increment: damage evolution control parameter based on plastic strain and characteristic length. Damage factor: scalar field variable that quantifies the degree of material damage (0 means no damage, 1 means complete failure).

[0160] The computer activates the DIEM damage model in the material properties and sets parameters such as the initial damage threshold and critical displacement. The system calculates the equivalent plastic displacement increment at each time step and adds it to the damage variable D. When D reaches the critical value D_crit, the program automatically reduces the unit stiffness until the failed unit is deleted. This process is implemented through an explicit iterative algorithm to ensure that the damage evolution and dynamic response are updated synchronously.

[0161] Specifically, the MAT_ADD_DAMAGE_DIEM keyword in LSDY is used to characterize material properties and evolve the damage failure behavior of materials. The DIEM fracture failure model is divided into shear criterion and forward criterion. The shear criterion formula is as follows (4):

[0162] (4)

[0163] In the formula, is the equivalent plastic strain when unstable deformation occurs in biaxial tension, is the equivalent plastic strain when unstable deformation occurs under biaxial compression, is the normalized shear stress, is the shear stress parameter during biaxial tension, is the shear stress parameter during biaxial compression, is the maximum shear stress, is the equivalent stress, is the equivalent plastic strain when the material undergoes instability deformation under different stress states, is a model parameter, and h represents a user-defined parameter.

[0164] The forward criterion is as follows in formula (5):

[0165] (5)

[0166] In the formula, β is the normalized principal stress, is the first principal stress, is the equivalent stress, is the equivalent plastic strain when the material undergoes instability deformation under different stress states, d, q, are model parameters.

[0167] In the DIEM fracture failure model, the damage factor D value is calculated using the plastic displacement, as shown in formula (6):

[0168] (6)

[0169] In the formula, ΔD is the damage factor increment, is the plastic strain increment, is the failure plastic displacement of the material under different stress states.

[0170] Through the synergistic effect of the compression-tension dual-mode constitutive, strain rate-sensitive strengthening, and progressive damage models in the embodiments of the present application, high-precision simulation of materials under complex dynamic loads is achieved. This technical solution can simultaneously reflect the stress state dependence, strain rate effect, and damage accumulation process of materials, providing a reliable theoretical framework for crashworthiness analysis and failure prediction.

[0171] Optionally, step 105 includes:

[0172] Step 1051, perform metallographic inspection and CT scanning at a preset position of the sample to obtain data on the microstructure and porosity distribution.

[0173] In the embodiments of the present application, metallographic inspection is an experimental method for observing the microstructural characteristics of materials through an optical microscope or an electron microscope, and is used to analyze parameters such as grain size and phase composition. CT scanning is a computed tomography technique that obtains three-dimensional structural information inside the material through X-ray transmission imaging, and can quantify the distribution characteristics of defects such as porosity and cracks. The microstructure is the structural characteristics of the material at the microscopic scale, such as grain morphology, phase distribution, and interface characteristics. The porosity distribution data is a quantitative description of the proportion of the pore volume in the total volume inside the material and its spatial distribution.

[0174] The computer-controlled metallographic microscope automatically focuses and acquires images at preset positions of the sample, and identifies microscopic features such as grain boundaries and precipitates through image processing algorithms. The system synchronously operates the industrial CT equipment to perform three-dimensional scanning at a resolution of 10 μm, uses a threshold segmentation algorithm to extract the pore structure, and outputs a distribution cloud map of the porosity varying with position. The detection data is stored in a structured format, providing basic input for material property analysis.

[0175] Step 1052: Perform a quasi-static tensile test and a dynamic impact test, and collect the stress-strain curve and fracture toughness parameters of the sample.

[0176] In the embodiments of the present application, the quasi-static tensile test is a uniaxial tensile test with a strain rate lower than 10^-3 s^-1, and is used to obtain basic mechanical parameters such as the elastic modulus and yield strength of the material. The dynamic impact test is a high-strain-rate (10^2~10^4 s^-1) loading test implemented through a Hopkinson bar or a drop hammer device, and is used to evaluate the dynamic response characteristics of the material. The stress-strain curve is a graphical expression of the relationship between stress and strain of the material under the action of an external force, reflecting its elastic, plastic, and fracture behaviors. The fracture toughness parameter is an index characterizing the ability of the material to resist crack propagation, such as the critical stress intensity factor KIC or the fracture energy Gf.

[0177] The computer controls the electronic universal testing machine to perform quasi-static tension at a strain rate of 0.001 s^-1, synchronously collects load-displacement data through a force sensor and an extensometer, and automatically generates an engineering stress-strain curve. The system then starts the split Hopkinson pressure bar device to perform a dynamic impact test at a strain rate of 500 s^-1, and calculates the dynamic stress-strain response using strain gauge signals and high-speed photography data. All test data is filtered and stored in the material database.

[0178] Step 1053: Establish a mapping relationship between the defect type and the simulation damage result through X-ray non-destructive testing and scanning electron microscope fracture analysis.

[0179] In the embodiments of the present application, radiographic non-destructive testing is a non-destructive testing technology that uses the principle of X-ray transmission to detect internal defects of materials. Scanning electron microscope fracture analysis is to observe the morphological characteristics of the fracture surface of materials through a scanning electron microscope, which is used to judge the fracture mechanism. The defect type is a classification description of discontinuous structures such as pores, inclusions, and microcracks existing in the material. The simulated damage result is the material damage distribution and failure mode predicted by finite element analysis.

[0180] The computer operates the X-ray flaw detector to perform a panoramic scan on the test sample after the test, and uses a convolutional neural network to automatically identify the defect types (such as pores, slag inclusions, etc.) and their spatial distributions. The system then collects the fracture morphology at a magnification of 5000 times under the scanning electron microscope, and determines the fracture mode (dimple, cleavage, etc.) through a feature matching algorithm. These measured defect data are spatially registered with the simulated damage parameters (such as the equivalent plastic strain distribution) to establish a quantitative mapping matrix of defect type - damage evolution.

[0181] In the embodiments of the present application, through the systematic comparison of multi-scale experimental tests and simulation data, the full-chain verification from the microscopic organizational structure to the macroscopic mechanical response is realized. This technical solution establishes a quantitative correlation model between the material defect characteristics and the damage evolution behavior, and significantly improves the accuracy of simulation prediction.

[0182] Optionally, step 106 includes:

[0183] Step 1061, construct a finite element model of vehicle crash, and embed the complex thin-walled part as a key component into the finite element model of vehicle crash.

[0184] In the embodiments of the present application, the finite element model of vehicle crash is a digital vehicle model composed of hundreds of thousands to millions of units, which contains the geometric and material property data of all key components such as the vehicle body and the chassis.

[0185] The computer imports the parametric vehicle geometric model, and generates a finite element mesh mainly composed of quadrilateral shell elements through an automatic mesh generation algorithm. The system embeds the optimized complex thin-walled part model into a specified position in the front cabin of the vehicle in the form of a component, and uses the multi-point constraint (MPC) method to realize the connection with adjacent components. The friction coefficient of 0.2 is defined for all contact interfaces for automatic surface-to-surface contact to ensure the continuity of the mechanical transmission path. The total degree of freedom scale of the model is controlled within 2 million to ensure the calculation efficiency.

[0186] Step 1062, set the initial collision velocity and boundary conditions specified by the preset standard, and calculate the deformation energy absorption of the complex thin-walled part.

[0187] In the embodiments of the present application, the initial collision velocity is the initial motion velocity of the vehicle at the moment of collision, which is usually set according to regulatory requirements (such as a 50 km / h frontal collision). The boundary conditions are the boundary settings that restrict the degrees of freedom of the model's motion, including fixed constraints, symmetric constraints, etc. The deformation energy absorption is the mechanical energy dissipated during the plastic deformation process of the structure, and it is the core index for measuring crashworthiness.

[0188] The computer sets the initial velocity condition of 56 km / h according to the GB 11551 standard and assigns the initial kinetic energy to the vehicle mass unit through the *INITIAL_VELOCITY keyword. The system uses the explicit central difference method to solve the dynamic equation, and the time step is automatically adjusted to ensure numerical stability. During the calculation process, the internal energy change curve of the complex thin-walled part is monitored in real time, and its deformation energy absorption is calculated by integrating the plastic strain energy density. The data sampling frequency is set to 10 kHz to ensure the result accuracy.

[0189] Step 1063: Compare the simulated deformation mode with the measured data, verify the stiffness matching degree, and optimize the process feasibility of the final design scheme.

[0190] In the embodiments of the present application, the simulated deformation mode is the deformation forms such as structural buckling and folding predicted by finite element analysis. The measured data is the result of a physical collision test collected by a high-speed camera or an optical measurement system. The stiffness matching degree is a quantitative evaluation index for the coincidence degree of the load-displacement curves of the simulation and the measurement. The process feasibility is an evaluation of the implementability of the design scheme in manufacturing processes such as stamping and welding.

[0191] The computer performs spatio-temporal registration on the deformation sequence of the thin-walled part output by the simulation and the measured image collected by the high-speed camera, and uses the image correlation coefficient (CC) algorithm to quantify the similarity of the deformation mode. The system automatically extracts the force-displacement data of the key measurement points and calculates the stiffness matching degree index (R²≥0.9 is qualified). For the unqualified areas, the optimization module is triggered to adjust the material thickness distribution or the layout of the stiffeners, and at the same time, the forming limit diagram (FLD) of the stamping is checked to ensure the process feasibility, and the iteration is carried out until all acceptance criteria are met.

[0192] In the embodiments of the present application, through the closed-loop verification of the vehicle-level collision simulation and test data, the systematic evaluation of the performance of complex thin-walled parts is realized. This technical solution ensures the precise matching of the component design with the vehicle safety requirements, and at the same time takes into account the manufacturing process constraints, forming a reliable conversion path from the digital model to the physical product.

[0193] Based on the same inventive concept, an embodiment of the present application further provides an integrated large and complex thin-walled die-casting component structural performance collaborative design device for implementing the above-mentioned integrated large and complex thin-walled die-casting component structural performance collaborative design method. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more of the following embodiments of the integrated large and complex thin-walled die-casting component structural performance collaborative design device can refer to the limitations on the integrated large and complex thin-walled die-casting component structural performance collaborative design method in the foregoing, and will not be elaborated herein.

[0194] In an exemplary embodiment, as Figure 5 shown, an integrated large and complex thin-walled die-casting component structural performance collaborative design device 20 is provided, including:

[0195] A processing module 201, configured to input the design parameters of the complex thin-walled part into a multi-model topology optimization framework to generate an initial load path optimization scheme;

[0196] Construct a response surface prediction model based on the initial load path optimization scheme, and generate a training data set through experimental design;

[0197] Input the training data set into a machine learning enhancement module to generate a design space classifier and perform clustering grouping on the simulation results;

[0198] Select the optimal design group that meets the preset constraint conditions according to the classifier, and perform plastic deformation and damage failure simulations using the material constitutive model specified by the preset standard;

[0199] Perform multi-dimensional experimental tests on the samples in the optimal design group to obtain measured data to calibrate the failure parameters of the simulation model;

[0200] An output module 202, configured to perform a frontal collision test verification based on the calibrated simulation model and output a final design scheme that meets multi-performance constraints;

[0201] Integrate the optimization results of each stage in the final design scheme to generate an integrated structural performance report for the complex thin-walled part.

[0202] Optionally, the processing module 201 is further configured to:

[0203] Adjust the material distribution density through a density-based topology optimization algorithm to determine the optimal load path that meets static, NVH, and collision performance;

[0204] Establish a multidisciplinary coupling optimization model, and the multidisciplinary coupling optimization model balances the stiffness matrices of different finite element models through weight factors;

[0205] Map the design variables under multi-load conditions to a unified parameter space, and output a set of candidate solutions including structural efficiency and performance indicators.

[0206] Optionally, the processing module 201 is further configured to:

[0207] Extract the design variables and response variables from the set of candidate solutions, and construct a second-order polynomial response surface function;

[0208] Generate a training data set by the Latin hypercube sampling method specified by a preset standard, where the training data set covers compression, tension, and shear stress states;

[0209] Use the training data set to fit the response surface prediction model, and output the predicted values of stress, deformation, and damage factors.

[0210] Optionally, the processing module 201 is further configured to:

[0211] Extract the features of the visualization data of the simulation results, and mark the key stress concentration areas in the design space;

[0212] Use the K-means clustering algorithm to group the training data set, and generate a classifier including failure mode labels;

[0213] Couple the classifier with the response surface prediction model to establish a probability-driven design screening rule.

[0214] Optionally, the processing module 201 is further configured to:

[0215] Call the MAT_PLASTICITY_COMPRESSION_TENSION_MAT_124 keyword to simulate the compression-tension bimodal response of the material;

[0216] Calculate the dynamic yield stress under high strain rate conditions based on the Cowper-Symonds strain rate model;

[0217] Use the MAT_ADD_DAMAGE_DIEM keyword to evolve the damage factor, and the damage factor is iteratively updated by the equivalent plastic displacement increment.

[0218] Optionally, the processing module 201 is further configured to:

[0219] Perform metallographic inspection and CT scanning at preset positions of the sample to obtain microstructural and porosity distribution data;

[0220] Perform quasi-static tensile tests and dynamic impact tests, and collect the stress-strain curves and fracture toughness parameters of the sample;

[0221] Establish the mapping relationship between the defect type and the simulation damage result through X-ray non-destructive testing and scanning electron microscope fracture analysis.

[0222] Optionally, the output module 201 is further configured to:

[0223] Construct a finite element model of vehicle collision, and embed the complex thin-walled part as a key component into the finite element model of vehicle collision;

[0224] Set the collision initial velocity and boundary conditions specified by the preset standard, and calculate the deformation energy absorption of the complex thin-walled part;

[0225] Compare the simulation deformation mode with the measured data, verify the stiffness matching degree and optimize the process feasibility of the final design scheme.

[0226] Through the collaborative process of multi-model topology optimization, machine learning-assisted classification, and experiment-simulation closed-loop verification in the embodiments of the present application, the full-automatic optimization of complex thin-walled parts from conceptual design to performance verification is realized. While ensuring the calculation efficiency, the system significantly improves the mechanical performance reliability and multi-objective collaborative ability of the design, and finally outputs a lightweight and high crashworthiness structural scheme and a traceable complete performance report.

[0227] In an exemplary embodiment, a computer device is provided. The computer device can be a server or a terminal, and its internal structure diagram can be as Figure 6 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the structural performance collaborative design data of an integrated large and complex thin-walled die-cast component. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a method for collaborative design of the structural performance of an integrated large and complex thin-walled die-cast component.

[0228] Those skilled in the art can understand, Figure 6The structure shown is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0229] In an exemplary embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0230] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0231] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0232] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0233] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the various embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0234] The databases involved in the various embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the various embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0235] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, 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, it should be considered to be within the scope described in this specification.

[0236] In this article, specific examples are used to elaborate on the principles and implementation manners of this application. The descriptions of the above embodiments are only used to help understand the method and its core idea of this application; at the same time, for those of ordinary skill in the art, according to the idea of this application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation on this application.

Claims

1. An integrated collaborative design method for the structural performance of large-scale complex thin-walled die-cast components, characterized in that, The collaborative design method for the structural performance of the integrated large-scale complex thin-walled die-cast component includes: Input the design parameters of the complex thin-walled component into a multi-model topology optimization framework to generate an initial load path optimization scheme; Construct a response surface prediction model based on the initial load path optimization scheme and generate a training data set through experimental design; Input the training data set into a machine learning enhancement module to generate a design space classifier and cluster and group the simulation results; Select the optimal design group that meets the preset constraint conditions according to the classifier and perform plastic deformation and damage failure simulations using the material constitutive model specified by the preset standard; Conduct multi-dimensional experimental tests on the samples in the optimal design group to obtain measured data to calibrate the failure parameters of the simulation model; Execute a frontal collision test verification based on the calibrated simulation model and output the final design scheme that meets multi-performance constraints; Integrate the optimization results of each stage in the final design scheme to generate an integrated structural performance report for the complex thin-walled component; The step of inputting the design parameters of the complex thin-walled component into a multi-model topology optimization framework to generate an initial load path optimization scheme includes: Adjust the material distribution density through a density-based topology optimization algorithm to determine the optimal load path that meets static, NVH, and collision performance; Establish a multi-disciplinary coupling optimization model, and the multi-disciplinary coupling optimization model balances the stiffness matrices of different finite element models through weight factors; Map the design variables under multi-load conditions to a unified parameter space and output a set of candidate schemes including structural efficiency and performance indicators; The step of constructing a response surface prediction model based on the initial load path optimization scheme includes: Extract the design variables and response variables from the set of candidate schemes to construct a second-order polynomial response surface function; Generate a training data set through the Latin hypercube sampling method specified by the preset standard, and the training data set covers compression, tension, and shear stress states; Use the training data set to fit the response surface prediction model and output the predicted values of stress, deformation, and damage factors.

2. The collaborative design method for the structural performance of an integrated large-scale complex thin-walled die-cast component according to claim 1, characterized in that The step of inputting the training data set into a machine learning enhancement module includes: Extract the features of the visualization data of the simulation results and mark the key stress concentration areas in the design space; Use the K-means clustering algorithm to group the training data set to generate a classifier including failure mode labels; Couple the classifier with the response surface prediction model to establish a probability-driven design screening rule.

3. The collaborative design method for the structural performance of an integral large-scale complex thin-walled die-cast component according to claim 1, characterized in that The step of performing plastic deformation and damage failure simulations using the material constitutive model specified by the preset standard includes: Call the MAT_PLASTICITY_COMPRESSION_TENSION_MAT_124 keyword to simulate the compression-tension dual-mode response of the material; Calculate the dynamic yield stress under high strain rate conditions based on the Cowper-Symonds strain rate model; Use the MAT_ADD_DAMAGE_DIEM keyword to evolve the damage factor, and the damage factor is iteratively updated through the equivalent plastic displacement increment.

4. The collaborative design method for the structural performance of an integrated large-scale complex thin-walled die-cast component according to claim 1, characterized in that, The steps of performing multi-dimensional experimental tests on the samples in the optimal design group include: Performing metallographic inspection and CT scanning at preset positions of the samples to obtain data on the microstructure and porosity distribution; Performing quasi-static tensile tests and dynamic impact tests, and collecting the stress-strain curves and fracture toughness parameters of the samples; Establishing the mapping relationship between the defect type and the simulation damage result through X-ray non-destructive testing and scanning electron microscope fracture analysis.

5. The collaborative design method for the structural performance of an integrated large-scale complex thin-walled die-cast component according to claim 1, wherein The steps of performing frontal collision test verification based on the calibrated simulation model include: Constructing a vehicle collision finite element model, and embedding the complex thin-walled part as a key component into the vehicle collision finite element model; Setting the collision initial velocity and boundary conditions specified by the preset standard, and calculating the deformation energy absorption of the complex thin-walled part; Comparing the simulation deformation mode with the measured data, verifying the stiffness matching degree, and optimizing the process feasibility of the final design scheme.

6. An integrated collaborative design device for the structural performance of large-scale complex thin-walled die-cast components, characterized in that, The integrated structural performance collaborative design device for the integral large-scale complex thin-walled die-casting component includes: A processing module, configured to input the design parameters of the complex thin-walled part into a multi-model topology optimization framework to generate an initial load path optimization scheme; Constructing a response surface prediction model based on the initial load path optimization scheme, and generating a training data set through experimental design; Inputting the training data set into a machine learning enhancement module to generate a design space classifier and clustering and grouping the simulation results; Selecting the optimal design group that meets the preset constraint conditions according to the classifier, and performing plastic deformation and damage failure simulations using the material constitutive model specified by the preset standard; Performing multi-dimensional experimental tests on the samples in the optimal design group to obtain measured data for calibrating the failure parameters of the simulation model; An output module, configured to perform frontal collision test verification based on the calibrated simulation model and output the final design scheme that meets multi-performance constraints; Integrating the optimization results of each stage in the final design scheme to generate an integrated structural performance report for the complex thin-walled part; The processing module is further configured to: Adjust the material distribution density through a density-based topology optimization algorithm to determine the optimal load path that meets static, NVH, and collision performance; Establishing a multi-disciplinary coupling optimization model, and the multi-disciplinary coupling optimization model balances the stiffness matrices of different finite element models through weight factors; Mapping the design variables under multi-load conditions to a unified parameter space, and outputting a set of candidate schemes including structural efficiency and performance indicators; Extracting the design variables and response variables in the set of candidate schemes, and constructing a second-order polynomial response surface function; Generating a training data set through the Latin hypercube sampling method specified by the preset standard, and the training data set covers compressive, tensile, and shear stress states; Fitting the response surface prediction model using the training data set, and outputting the predicted values of stress, deformation, and damage factors.

7. A computer device, comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the integrated large-scale complex thin-walled die-casting component structural performance collaborative design method according to any one of claims 1-6.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the integrated large and complex thin-walled die-casting component structural performance collaborative design method described in any one of claims 1-6.

Images