Spring stiffness characteristic simulation optimization method and system

Abstract

The invention relates to a spring stiffness characteristic simulation optimization method and system. The spring stiffness characteristic simulation optimization method comprises the steps of obtaining first stiffness characteristic curve data of a spring through multi-physical field simulation, and extracting and obtaining a first physical morphological characteristic of the spring based on the first stiffness characteristic curve data; establishing a prediction model between the spring input parameters and the first physical morphological characteristics; in robust design optimization iteration, according to the geometric design parameters and the uncertainty parameters and on the basis of the prediction model, corresponding second physical morphological characteristics are obtained, and on the basis of the second physical morphological characteristics, second rigidity characteristic curve data of the spring are obtained through reconstruction; and on the basis of statistical analysis of the second stiffness characteristic curve data, a robust performance evaluation result of the design scheme under the influence of uncertainty is obtained, and according to the robust performance evaluation result, the geometric design parameters are iteratively adjusted until the spring design scheme meeting the robust requirement is obtained.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of spring design optimization, and particularly relates to a spring stiffness characteristic simulation optimization method and system. BACKGROUND

[0002] In modern industrial design, springs as a kind of key elastic components, their performance directly affects the overall performance of the equipment. In order to ensure that the product can stably and reliably run under various complex working conditions, engineers usually use advanced simulation optimization systems to accurately predict and optimize the stiffness characteristics of the spring. However, when the design requirements are increasingly stringent, especially for precision springs under high speed, high frequency vibration and extreme temperature environment, the traditional simulation optimization method often encounters bottlenecks. These bottlenecks not only reflect the lack of consideration of material dynamic response and temperature influence, but also reflect the performance fluctuation of the theoretically perfect design in the actual product due to the tolerance and assembly deviation in actual production and manufacturing.

[0003] In the simulation optimization process of spring stiffness characteristics, when the mechanical response of the material during the force change process, the performance change of the material under different temperatures, and the influence of manufacturing tolerance and assembly deviation on the final performance need to be considered at the same time, how to efficiently perform robust design optimization becomes a technical problem to be solved.

[0004] Specifically, how to balance the simulation calculation accuracy of considering multiple physical phenomena (such as the influence of temperature on the structure) and the huge demand for calculation amount of statistical analysis methods such as Monte Carlo in evaluating uncertainty in optimization iteration. So in a limited time, find a spring design scheme that can not only meet the target stiffness characteristics, but also has good resistance to uncertainties in actual production and assembly, and avoid the situation that the optimization process cannot be practically applied due to too long calculation time, is the challenge faced by the current spring design optimization field. SUMMARY

[0005] The present application provides a spring stiffness characteristic simulation optimization method and system to at least solve the problem that the existing spring stiffness characteristic simulation optimization method is difficult to efficiently perform robust design optimization when considering material dynamic response, temperature influence, manufacturing tolerance and assembly deviation, and balance simulation calculation accuracy and uncertainty evaluation calculation amount in optimization iteration.

[0006] In a first aspect, the present application provides a spring stiffness characteristic simulation optimization method, the method comprising: obtaining first stiffness characteristic curve data of a spring through multi-physical field simulation, and extracting first physical morphology features of the spring based on the first stiffness characteristic curve data, wherein the multi-physical field simulation is based on material dynamic response and temperature influence of the spring; establishing a prediction model between spring input parameters and the first physical form feature, wherein the input parameters include geometric design parameters, working temperature range, manufacturing tolerance, and assembly deviation; In the robust design optimization iteration, a corresponding second physical form feature is obtained according to the geometric design parameters and the uncertainty parameters and based on the prediction model, and a second stiffness characteristic curve data of the spring is reconstructed based on the second physical form feature; Based on statistical analysis of the second stiffness characteristic curve data, a robust performance evaluation result of the design scheme under the influence of uncertainty is obtained, and the geometric design parameters are iteratively adjusted according to the robust performance evaluation result until a spring design scheme meeting the robustness requirement is obtained.

[0007] Optionally, in the robust design optimization iteration, a corresponding second physical form feature is obtained according to the geometric design parameters and the uncertainty parameters and based on the prediction model, and a second stiffness characteristic curve data of the spring is reconstructed based on the second physical form feature, comprising: According to the geometric design parameters and the expected service history information, the material cumulative damage state of the spring is estimated; According to the geometric design parameters and the uncertainty parameters, and based on the prediction model, the original physical form feature of the spring is obtained; According to the material cumulative damage state, the original physical form feature is corrected to obtain a corrected second physical form feature; Based on the second physical form feature, a second stiffness characteristic curve data of the spring is reconstructed.

[0008] Optionally, in the robust design optimization iteration, a corresponding second physical form feature is obtained according to the geometric design parameters and the uncertainty parameters and based on the prediction model, comprising: The spatial distribution density of the combination of the geometric design parameters and the uncertainty parameters in the prediction model training data is evaluated; When the spatial distribution density is lower than a preset density threshold, a new parameter sub-combination is generated according to the combination of the geometric design parameters and the uncertainty parameters; The parameter sub-combination is supplemented to the training data set of the prediction model, and the prediction model is locally retrained based on the supplemented training data set to obtain an updated prediction model; Based on the updated prediction model, a second physical form feature corresponding to the geometric design parameters and the uncertainty parameters is obtained.

[0009] Optionally, the first physical form feature of the spring is extracted based on the first stiffness characteristic curve data, comprising: determining a current service stage of the spring based on the first stiffness characteristic curve data and service history information of the spring; selecting a corresponding feature extraction strategy from a preset feature extraction strategy library for the current service stage, wherein the feature extraction strategy library contains feature extraction methods optimized for different service stages or the material cumulative damage state; analyzing the first stiffness characteristic curve data according to the selected feature extraction strategy, identifying and quantifying stiffness change features reflecting the evolution of the spring material microstructure, wherein the stiffness change features include nonlinear inflection point offset, hysteresis loop area change rate, and stiffness attenuation factor; combining the stiffness change features with other physical form features of the first stiffness characteristic curve data to obtain the first physical form features of the spring.

[0010] Optionally, the material cumulative damage state of the spring is estimated based on the geometric design parameters and expected service history information, comprising: performing consistency checking and missing data completion based on the expected service history information to obtain preprocessed service history information; dynamically selecting a damage evolution model according to the geometric design parameters and the preprocessed service history information, and calculating the material cumulative damage factor of the spring based on the damage evolution model; evaluating the material cumulative damage state of the spring based on the material cumulative damage factor.

[0011] Optionally, the current service stage of the spring is determined based on the first stiffness characteristic curve data and the service history information of the spring, comprising: standardizing the service history information data and preprocessing the standardized service history information, wherein the preprocessing includes timestamp alignment, interpolation completion, and data cleaning; extracting key parameters from the preprocessed service history information, wherein the key parameters include cumulative load cycle number, high temperature exposure time, and corrosion environment exposure time; comparing the key parameters with preset material damage thresholds and performance decay curves, and determining the current service stage of the spring according to the comparison results.

[0012] Optionally, the original physical form features are corrected according to the material cumulative damage state to obtain the corrected second physical form features, comprising: obtaining the estimation confidence information of the material cumulative damage state; when the estimation confidence is lower than a preset confidence threshold, determining a variation range of each of the original physical configuration features in a current damage state according to the material cumulative damage state; within the variation range, revising the original physical configuration features to obtain revised second physical configuration features; comparing the second physical configuration features with actual simulation results of a small number of key points, and correcting the second physical configuration features according to a comparison result.

[0013] Optionally, the first physical configuration features of the spring are extracted based on the first stiffness characteristic curve data, including: globally analyzing the first stiffness characteristic curve data to extract features describing overall trends and macro shapes of the first stiffness characteristic curve data to obtain global smooth features; running a local event detection algorithm to identify and quantify non-smooth local features on the first stiffness characteristic curve data to obtain local event features; combining the global smooth features and the local event features into a hybrid feature vector as the first physical configuration features of the spring.

[0014] In a second aspect, the present application provides a spring stiffness characteristic simulation optimization system, the system comprising: a feature acquisition module configured to acquire first stiffness characteristic curve data of a spring through multi-physics simulation, and extract first physical configuration features of the spring based on the first stiffness characteristic curve data, wherein the multi-physics simulation is based on material dynamic response and temperature influence of the spring; a model construction module configured to establish a prediction model between spring input parameters and the first physical configuration features, wherein the input parameters include geometric design parameters, working temperature range, manufacturing tolerance, and assembly deviation; a characteristic curve reconstruction module configured to, in a robust design optimization iteration, acquire corresponding second physical configuration features based on the geometric design parameters and uncertainty parameters and based on the prediction model, and reconstruct second stiffness characteristic curve data of the spring based on the second physical configuration features; a robust performance evaluation module configured to obtain a robust performance evaluation result of a design scheme under the influence of uncertainty based on statistical analysis of the second stiffness characteristic curve data, and iteratively adjust the geometric design parameters according to the robust performance evaluation result until a spring design scheme meeting the robustness requirement is obtained.

[0015] In a third aspect, the present application provides a computer readable storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the steps of the method provided in the first aspect.

[0016] Compared with the related art, the spring stiffness characteristic simulation optimization method and system provided by the present application has at least the following technical effects: Firstly, the present application obtains first stiffness characteristic curve data of the spring through multi-physics simulation, and extracts first physical morphology features based on the data, wherein the simulation considers material dynamic response and temperature influence. On this basis, a prediction model between spring input parameters (including geometric design parameters, working temperature range, manufacturing tolerance and assembly deviation) and the first physical morphology features is established. Subsequently, in the robust design optimization iteration, the second physical morphology features are obtained based on the prediction model according to the geometric design parameters and the uncertainty parameters, and the second stiffness characteristic curve data is reconstructed. Finally, the robust performance evaluation results are obtained based on the statistical analysis of the second stiffness characteristic curve data, and the geometric design parameters are iteratively adjusted until a spring design scheme meeting the robustness requirement is obtained.

[0017] The present application can effectively solve the problem in the prior art that it is difficult to efficiently balance the simulation calculation accuracy of multiple physical phenomena and the calculation amount of uncertainty evaluation in the spring stiffness characteristic simulation optimization process. The method of the present application comprehensively considers multiple complex factors such as material dynamic response, temperature influence, manufacturing tolerance and assembly deviation, and greatly reduces the huge demand of traditional Monte Carlo statistical analysis method for computing resources by constructing a prediction model and introducing robust design optimization iteration, thereby avoiding the problem that the optimization process cannot be practically applied due to too long calculation time. In summary, the present application can efficiently find a spring design scheme that can meet the target stiffness characteristic and has good resistance to uncertainty in actual production and assembly, thereby improving the efficiency and reliability of spring design.

[0018] The details of one or more embodiments of the present application are given in the following drawings and description, so that other features, objects and advantages of the present application are more apparent. BRIEF DESCRIPTION OF DRAWINGS

[0019] The drawings described herein are intended to provide further understanding of the present application, and constitute a part of the present application. The illustrative embodiments of the present application and their description serve to explain the present application, and do not constitute an improper limitation of the present application. In the drawings: Figure 1 is a flowchart of a spring stiffness characteristic simulation optimization method according to an exemplary embodiment.

[0020] Figure 2 is a flowchart of step S3 according to an exemplary embodiment.

[0021] Figure 3 is a flowchart of step S3 according to another exemplary embodiment.

[0022] Figure 4 is a flowchart of step S314 according to an exemplary embodiment.

[0023] Figure 5 is a flowchart of step S311 according to an exemplary embodiment.

[0024] Figure 6 is a flowchart of step S313 according to an exemplary embodiment.

[0025] Figure 7 is a partial flowchart of step S1 according to an exemplary embodiment.

[0026] Figure 8 is a block diagram of a spring rate characteristic simulation optimization system according to an exemplary embodiment. DETAILED DESCRIPTION

[0027] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and should not be used to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of the present application.

[0028] Obviously, the accompanying drawings in the following description are only some examples or embodiments of the present application, and for those of ordinary skill in the art, the present application can be applied to other similar scenarios without creative efforts based on these drawings. In addition, it can be understood that although the efforts made in this development process can be complex and lengthy, for those of ordinary skill in the art related to the content disclosed in the present application, some designs, manufacturing or production changes based on the technical content disclosed in the present application are only routine technical means and should not be understood as insufficient disclosure of the present application.

[0029] In the present application, "embodiment" means that the specific features, structures or characteristics described in conjunction with the embodiment can be included in at least one embodiment of the present application. The phrase appears at various places in the specification does not necessarily refer to the same embodiment, nor is it independent or alternative to other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in the present application can be combined with other embodiments without conflict.

[0030] Unless otherwise defined, the technical or scientific terms used in this application shall have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms “a,” “an,” “an,” “the,” and similar words used in this application do not indicate quantity limitation and may indicate singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units not listed, or may include other steps or units inherent to these processes, methods, products, or devices. The terms “connected,” “linked,” “coupled,” and similar words used in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. “Multiple” used in this application refers to two or more. “And / or” describes the relationship between related objects, indicating that three relationships may exist; for example, “A and / or B” can represent: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following objects are in an "or" relationship. The terms "first," "second," and "third" used in this application are merely to distinguish similar objects and do not represent a specific ordering of the objects.

[0031] In related technologies, a key challenge in spring design optimization is balancing the need for high-precision simulations that consider various physical phenomena (such as the effect of temperature on structure) with the computational demands of statistical analysis methods like Monte Carlo methods when assessing uncertainties. The goal is to find a spring design that satisfies the target stiffness characteristics while also exhibiting good resistance to uncertainties in actual production and assembly within a limited timeframe, avoiding the impracticality of the optimization process due to excessive computational time.

[0032] Based on the above, embodiments of the present invention provide a method and system for simulating and optimizing the stiffness characteristics of springs, which will be described in detail below with reference to specific embodiments and accompanying drawings.

[0033] Example 1 This invention provides a method for simulating and optimizing the stiffness characteristics of a spring. Figure 1 This is a flowchart illustrating a simulation optimization method for spring stiffness characteristics according to an exemplary embodiment. Figure 1 As shown, the method includes: S1. Obtain the first stiffness characteristic curve data of the spring through multiphysics simulation, and extract the first physical morphological features of the spring based on the first stiffness characteristic curve data. The multiphysics simulation is based on the material dynamic response and temperature influence of the spring. In this embodiment, multi-physics simulation is a simulation technique that can consider the interaction of multiple physical phenomena (such as mechanics, thermodynamics, electromagnetism, etc.) at the same time. In this application, multi-physics simulation is mainly used to simulate the material dynamic response and structural deformation of the spring under the influence of multiple factors such as force and temperature change, so as to obtain more accurate stiffness characteristic curve data.

[0034] The stiffness characteristic curve data refers to a set of stiffness response data of the spring under different loads or displacements, which is usually presented in the form of a curve, reflecting the elastic properties of the spring. In step S1, the first stiffness characteristic curve data is the data obtained by initial simulation or experiment. For example, finite element analysis (FEA) software can be used in combination with a thermal-mechanical coupling module to simulate the deformation and stress distribution of the spring under different load and temperature conditions, thereby obtaining its stiffness characteristic curve. When performing multi-physics simulation, different load steps and temperature gradients can be set to fully capture the mechanical response of the spring. For example, a cyclic load from zero to maximum working load can be applied to the spring, and its displacement is recorded at each load point, while considering the change of environmental temperature from normal temperature to extreme high temperature.

[0035] The physical morphology feature refers to the key parameters extracted from the spring stiffness characteristic curve data, which can quantitatively describe the physical state and performance of the spring. These features can be the slope of the curve, the nonlinear inflection point, the hysteresis loop area, etc., which can reflect the microstructure evolution and macroscopic mechanical behavior of the spring material. Based on the obtained first stiffness characteristic curve data, the first physical morphology feature of the spring is extracted. For example, the curve can be mathematically fitted to extract the slope of the linear segment as the initial stiffness, or the nonlinear inflection point position and amplitude in the curve can be identified.

[0036] S2, a prediction model between the input parameters of the spring and the first physical morphology feature is established, wherein the input parameters include geometric design parameters, working temperature range, manufacturing tolerance, and assembly deviation; In this embodiment, the prediction model refers to a mathematical model established through machine learning or other data-driven methods, which is used to describe the mapping relationship between the input parameters of the spring (such as geometric design parameters, working temperature range, manufacturing tolerance, assembly deviation, etc.) and the physical form features. The prediction model in step S2 can quickly predict the physical form features of the spring according to the given input parameters, avoiding time-consuming repeated simulation. Therefore, the prediction model can be constructed using various machine learning algorithms. For example, a support vector machine (SVM) or Gaussian process regression (GPR) model can be used, which is trained through a large amount of simulation data or experimental data. In the training process, the geometric design parameters (such as wire diameter, number of turns, free height), working temperature range, manufacturing tolerance (such as wire diameter tolerance, pitch tolerance), and assembly deviation (such as pre-tightening force deviation, installation angle deviation) are taken as input, and the extracted first physical form features are taken as output. For example, spring simulation data under different combinations of geometric design parameters can be collected, and the corresponding stiffness characteristic curves and extracted physical form features are recorded. These data are used to train a neural network model, so that it can learn the complex nonlinear relationship between the input parameters and the physical form features.

[0037] S3, in the robust design optimization iteration, the corresponding second physical form features are obtained according to the geometric design parameters and the uncertainty parameters based on the prediction model, and the second stiffness characteristic curve data of the spring is reconstructed based on the second physical form features; In this embodiment, the robust design optimization iteration refers to a design optimization process, which aims to find a design scheme that is not sensitive to uncertainty factors (such as manufacturing tolerance, assembly deviation, etc.). In this iteration process, the design parameters will be adjusted according to the robustness evaluation results until the pre-set robustness requirement is met. In the robust design optimization iteration, the Monte Carlo simulation method can be used to introduce the uncertainty parameters. For example, in each iteration, sample values of manufacturing tolerance and assembly deviation are randomly selected from the pre-set probability distribution, and are combined with the current geometric design parameters as the input of the prediction model. The prediction model will quickly output the corresponding second physical form features according to these input parameters. For example, in an iteration, the geometric design parameters are set to a group of initial values, and sample values of manufacturing tolerance and assembly deviation are randomly selected from a normal distribution. These parameters are input into the pre-trained prediction model, and the model will immediately output the predicted stiffness, nonlinear inflection point, and other second physical form features of the spring. Based on the obtained second physical form features, interpolation algorithms or curve fitting techniques can be used to reconstruct the second stiffness characteristic curve data of the spring. For example, if the physical form features include several key points on the curve and the overall trend parameters of the curve, these features can be converted into a complete stiffness characteristic curve through spline interpolation or polynomial fitting.

[0038] S4, based on the statistical analysis of the second stiffness characteristic curve data, obtaining the robust performance evaluation result of the design scheme under the influence of uncertainty, and iteratively adjusting the geometric design parameters according to the robust performance evaluation result until a spring design scheme meeting the robustness requirement is obtained; In this embodiment, the robust performance evaluation result can be obtained by statistical analysis of a large number of reconstructed second stiffness characteristic curve data. For example, the mean, standard deviation, and probability of exceeding the design margin of the spring stiffness characteristic curve under different combinations of uncertainty parameters can be calculated. These statistics can be used as indicators for robust performance evaluation. For example, in Monte Carlo simulation, the prediction model is run thousands of times, and each time the uncertainty parameters are randomly selected.

[0039] Then, statistical analysis is performed on all the reconstructed stiffness characteristic curves to calculate the average stiffness and fluctuation range within the target load range. If the fluctuation range is too large, it indicates that the robustness of the design scheme is insufficient. Based on the robust performance evaluation result, an optimization algorithm (such as genetic algorithm, particle swarm optimization algorithm) can be used to iteratively adjust the geometric design parameters. For example, if the evaluation result shows that the current design scheme has large stiffness fluctuation, the optimization algorithm will try to adjust the geometric design parameters such as wire diameter and number of turns to reduce the fluctuation while ensuring that other performance indicators are met. This iterative process will continue until a spring design scheme is found that has acceptable performance fluctuation under the influence of uncertainty.

[0040] The technical solutions of the above embodiments combine multi-physics simulation, prediction model, and robust design optimization iteration to form an efficient and accurate spring design optimization process. By introducing multi-physics simulation, the application can more accurately capture the material dynamic response and temperature influence of the spring under complex working conditions, improving the accuracy of the initial data. Based on this, by establishing a prediction model, the application converts time-consuming simulation calculations into fast model predictions, significantly improving the efficiency of optimization iteration. Subsequently, in the robust design optimization iteration, the application can systematically consider uncertainty factors, and finally, through statistical analysis, the robust performance of the design scheme is quantitatively evaluated to find a spring design scheme that has good resistance to uncertainty in actual production and assembly. Thus, the application not only improves the accuracy and reliability of spring design, but also significantly shortens the design cycle, providing an effective solution for precision spring design under complex working conditions.

[0041] A possible design, Figure 2 is a flowchart of step S3 according to an exemplary embodiment. Referring to the accompanying drawings Figure 2 Step S3 includes: S311, estimating the material cumulative damage state of the spring according to the geometric design parameters and the expected service history information; In this embodiment, the geometric design parameters refer to the structural dimensions, material types and other inherent properties of the spring; the expected service history information includes the number of load cycles, temperature variation range, corrosion medium exposure time and other information that the spring may experience in the actual working environment. By comprehensively analyzing these information, the degree of fatigue, creep, corrosion and other damage that may occur to the spring material during long-term use can be quantitatively evaluated, so as to obtain the material cumulative damage state.

[0042] S312, obtaining the original physical form feature of the spring according to the geometric design parameters and the uncertainty parameters and based on the prediction model; In this embodiment, the original physical form feature is based on the prediction result under the ideal state or without considering material damage, and reflects the theoretical physical form of the spring under specific input parameters.

[0043] S313, correcting the original physical form feature according to the material cumulative damage state to obtain a second physical form feature; In this embodiment, the correction process aims to take into account the influence of material damage on the physical form of the spring, for example, material damage may cause the effective stiffness of the spring to decrease, the geometric size to change microscopically, etc. By introducing the damage state for correction, the second physical form feature can more accurately reflect the true state of the spring under actual service conditions.

[0044] S314, reconstructing the second stiffness characteristic curve data of the spring based on the second physical form feature; In this embodiment, the reconstruction process uses the corrected physical form feature as input, and generates curve data that can reflect the actual stiffness response of the spring considering material damage through a specific mathematical model or simulation method.

[0045] The technical solutions of the above embodiments can significantly improve the accuracy and reliability of the spring stiffness characteristic simulation optimization results by introducing the estimation and correction mechanism of the material cumulative damage state. By incorporating the material cumulative damage state into the prediction model, the second physical form feature obtained can more truly reflect the performance degradation of the spring under long-term service conditions, thereby avoiding the prediction deviation caused by ignoring material damage. This not only helps to design a spring that can meet the performance requirements throughout its life cycle, but also effectively reduces the failure risk caused by material performance degradation, improves the robustness and reliability of the spring design, and provides more accurate data support for spring life prediction and maintenance strategy formulation.

[0046] In one example, it is assumed that a spring used in a car suspension system needs to be robustly designed and optimized. The spring will be subjected to periodic load and temperature variation during service.

[0047] First, the cumulative damage state of the spring material is estimated based on the geometric design parameters of the spring (e.g., wire diameter, number of turns, material grade) and the expected service history information (e.g., projected mileage, road type, environmental temperature range). The estimation can involve fatigue damage accumulation models and creep damage models to quantify the extent of fatigue crack initiation and propagation or the amount of plastic deformation accumulation of the material.

[0048] Next, based on the current geometric design parameters and uncertainty parameters (e.g., manufacturing tolerances, assembly deviations), and using a pre-trained prediction model, the original physical form features of the spring in an ideal state are obtained, such as its initial geometric dimensions, material elastic modulus, etc.

[0049] Subsequently, the above-mentioned original physical form features are corrected using the previously estimated cumulative damage state of the material. For example, if it is estimated that the material has a certain degree of fatigue damage, the effective elastic modulus of the material can be reduced or the effective number of turns of the spring can be adjusted according to the degree of damage, so as to obtain the second physical form features after correction.

[0050] Finally, based on these second physical form features after correction, the second stiffness characteristic curve data of the spring considering the material damage is reconstructed. For example, by inputting the corrected physical form features into a finite element analysis or analytical model, a stiffness-displacement curve closer to the actual service state is obtained. In this way, the designer can more accurately evaluate the performance of different design schemes under long-term service in the optimization iteration process, so as to select a more robust spring design scheme.

[0051] In another possible design, Figure 3 is a flowchart of step S3 according to another example embodiment. Referring to the accompanying drawings Figure 3 , step S3 includes: S321, evaluating the spatial distribution density of the combination of geometric design parameters and uncertainty parameters in the prediction model training data; In this embodiment, the evaluation of the spatial distribution density is quantified by statistical methods or machine learning techniques, such as Kernel Density Estimation (KDE), cluster analysis or nearest neighbor distance calculation, to quantify the sparsity of the current parameter combination in the existing training data distribution, so as to identify the areas where the prediction model may have prediction uncertainty or accuracy decline.

[0052] S322, when the spatial distribution density is lower than the preset density threshold, generating a new parameter sub-combination according to the combination of geometric design parameters and uncertainty parameters; In this embodiment, the preset density threshold can be set according to the actual application scenario, model accuracy requirement and available computing resource limit. Generating new parameter sub-combinations can be achieved in various ways, for example, small-scale random sampling near the current parameter combination, generating new data points based on Latin Hypercube Sampling (LHS) or Monte Carlo Sampling, or using Active Learning strategy to select new data points with the most information, thereby increasing the data coverage of the model in the sparse area.

[0053] S323, supplement the parameter sub-combinations to the training data set of the prediction model, and locally retrain the prediction model based on the supplemented training data set to obtain an updated prediction model; In this embodiment, local retraining refers to incremental training or fine-tuning of the prediction model using only the newly added parameter sub-combinations and part of the original training data near them, rather than training the entire model from scratch. Local retraining helps improve the prediction accuracy of the model in a specific area without significantly increasing the computing cost, so that the prediction model can better adapt to the new parameter space and improve its generalization ability.

[0054] S324, obtaining the second physical morphology feature corresponding to the geometric design parameter and the uncertainty parameter based on the updated prediction model; In this embodiment, by using the prediction model that has been locally retrained and updated, more accurate and reliable second physical morphology features can be obtained, thereby significantly improving the robustness and accuracy of the spring stiffness characteristic simulation optimization method.

[0055] The technical solutions of the above embodiments can significantly improve the robustness and accuracy of the spring stiffness characteristic simulation optimization method by dynamically evaluating the parameter space distribution density and adaptively locally retraining the prediction model. Specifically, by dynamically evaluating the spatial distribution density of the parameter combination and locally adaptively updating the prediction model, the deviation of the optimization result caused by inaccurate prediction of the prediction model in the sparse area of the training data is avoided. The second physical morphology feature obtained in the robust design optimization iteration is more accurate, which improves the reliability of subsequent spring second stiffness characteristic curve data reconstruction and the accuracy of the robust performance evaluation result.

[0056] In one example, assume that in the spring stiffness characteristic simulation optimization process, the prediction model is initially trained under a combination of a limited set of geometric design parameters (e.g., wire diameter, number of turns) and uncertainty parameters (e.g., material elastic modulus fluctuation range, manufacturing tolerance). When the optimization algorithm explores a new design point, for example, a spring design scheme with a thin wire diameter and a high number of turns, and a large material elastic modulus fluctuation range, this parameter combination may be very rare in the original training data set, resulting in a very low spatial distribution density.

[0057] At this time, the method of the present application will first evaluate the spatial distribution density of the new parameter combination in the prediction model training data. If it is found that its density is lower than the preset threshold, the system will automatically generate a series of parameter sub-combinations around the new parameter combination. For example, by adjusting the wire diameter, number of turns, and elastic modulus fluctuation range slightly, dozens of new parameter points can be generated around the thin wire diameter, high number of turns, and high fluctuation range. These new parameter sub-combinations are then supplemented to the training data set of the prediction model. Then, the prediction model will use these new data to perform local retraining to enhance its prediction ability in this specific area. In this way, the updated prediction model can more accurately predict the second physical morphology characteristics of the thin wire diameter, high number of turns spring under the influence of uncertainty, thereby ensuring that the subsequent robust performance evaluation results are more reliable, and avoiding potential design risks due to insufficient model extrapolation ability.

[0058] In one possible design, Figure 4 is a flowchart of step S314 according to an exemplary embodiment. Referring to the accompanying drawings Figure 4 Step S314 includes: S3141, based on the first stiffness characteristic curve data and the service history information of the spring, determining the current service stage of the spring; In this embodiment, the service history information is the data of various environmental and load conditions experienced by the spring during actual use, such as cumulative load cycle number, high temperature exposure time, corrosion environment exposure time, etc. By analyzing these historical data, the current service stage of the spring can be estimated, such as being in the initial running-in period, stable working period, fatigue damage accumulation period, or approaching failure period.

[0059] S3142, for the current service stage, selecting the corresponding feature extraction strategy from the preset feature extraction strategy library, wherein the feature extraction strategy library contains feature extraction methods optimized for different service stages or material cumulative damage states; In this embodiment, the feature extraction strategy library is a pre-established knowledge base that stores various feature extraction algorithms or models optimized for different service stages or material cumulative damage states. For example, for the initial running-in period, it may focus on identifying manufacturing defects or stiffness changes caused by initial stress relaxation; for the fatigue damage accumulation period, it may focus on capturing the stiffness nonlinear changes caused by micro-crack initiation and propagation.

[0060] S3143, analyze the first stiffness characteristic curve data according to the selected feature extraction strategy, identify and quantify the stiffness change features reflecting the evolution of the spring material microstructure, wherein the stiffness change features include nonlinear inflection point shift, hysteresis loop area change rate, and stiffness attenuation factor; In this embodiment, the stiffness change features are key indicators reflecting the evolution of the spring material microstructure. Specifically, the nonlinear inflection point shift refers to the change of the inflection point position in the stiffness characteristic curve from the linear region to the nonlinear region, which can indicate the change of the material plastic deformation or damage starting point; the hysteresis loop area change rate refers to the change of the hysteresis loop area formed by the stiffness characteristic curve under cyclic loading, which can reflect the change of the material internal energy dissipation and damping characteristics, and is closely related to the material internal damage accumulation; the stiffness attenuation factor directly quantifies the degree of decrease of the spring elastic modulus or overall stiffness during service. These features can reveal the microstructure changes of the spring material from different dimensions, such as dislocation movement, grain boundary slip, micro-pore formation or crack propagation, etc.

[0061] S3144, combine the stiffness change features with other physical form features of the first stiffness characteristic curve data to obtain the first physical form features of the spring; In this embodiment, combining the stiffness change features in step S3143 with other physical form features (such as geometric size, material type, surface treatment, etc.) of the first stiffness characteristic curve data of the spring can form a comprehensive first physical form feature vector for subsequent prediction model.

[0062] The technical solutions of the above embodiments realize adaptive and refined extraction of the first physical form features of the spring by introducing the concept of service history information and current service stage, and combining the feature extraction strategy library, significantly improve the accuracy and pertinence of the first physical form feature extraction of the spring, especially in the case of complex service history and material degradation of the spring, so that the prediction model can more accurately capture the real behavior of the spring, thereby improving the reliability and efficiency of the robust design optimization iteration.

[0063] In one possible design, Figure 5 is a flowchart of step S311 according to an exemplary embodiment. Referring to the accompanying drawings Figure 5 , step S311 includes: S3111、Based on the expected service history information, consistency check and missing data completion are performed to obtain preprocessed service history information; In this embodiment, the expected service history information refers to various working condition data that the spring may experience in actual use, such as load spectrum, temperature change, environmental corrosion, etc. Consistency check is performed on this information to identify and correct logical conflicts or abnormal values in the data, such as unreasonable peaks or valleys in the load data. Missing data completion refers to the reasonable filling of missing data by interpolation, regression or other statistical methods when part of the service history information is not recorded completely, so as to ensure the integrity and continuity of the data. Through these preprocessing steps, more accurate and reliable preprocessed service history information can be obtained.

[0064] S3112、According to the geometric design parameters and the preprocessed service history information, a damage evolution model is dynamically selected and calculated based on the damage evolution model to obtain the material cumulative damage factor of the spring; In this embodiment, the damage evolution model is a mathematical model describing the change of damage degree of the material with time or cycle number under specific load, temperature and environmental conditions. The model can be based on physical mechanism (such as fatigue damage model, creep damage model) or based on empirical statistics. Dynamic selection of damage evolution model is that the system intelligently selects the most suitable damage evolution model from the preset model library according to the geometric design parameters of the spring (such as material type, surface treatment) and the preprocessed service history information (such as main failure mode, service environment characteristics). For example, for a spring mainly subjected to cyclic load, a fatigue damage model may be selected; for a spring in high temperature environment for a long time, a creep damage model may be selected. Based on the selected model, the material cumulative damage factor of the spring can be quantitatively obtained, which reflects the damage degree of the spring in the service process.

[0065] S3113、Based on the material cumulative damage factor, the material cumulative damage state of the spring is evaluated; In this embodiment, the material cumulative damage factor is a quantitative index, which can be a value between 0 and 1, where 0 represents no damage and 1 represents complete failure. Based on the material cumulative damage factor, the material cumulative damage state of the spring can be evaluated. For example, the damage factor can be compared with a pre-set damage threshold to divide the damage state into different levels, such as “slight damage”, “moderate damage” or “severe damage”.

[0066] The technical solutions of the above embodiments effectively improve the quality and reliability of the input data by strictly checking the consistency of the expected service history information and completing the missing data, thereby avoiding estimation deviation caused by data defects. On this basis, a damage evolution model that best conforms to the actual damage mechanism is dynamically selected according to the geometric design parameters of the spring and the preprocessed service history information, thereby ensuring the scientificity and pertinence of damage calculation. Subsequently, the damage evolution model highly matches the actual working condition, so that the calculation result of the material cumulative damage factor can accurately reflect the actual damage degree of the spring. Finally, based on the accurate damage factor, the material cumulative damage state of the spring can be accurately evaluated.

[0067] In one example, it is assumed that a helical spring used in a car suspension system needs to be robustly designed and optimized. First, the expected service history information of the spring under different road conditions, loads and temperatures is collected, including the number of load cycles, maximum stress, environmental temperature and the like.

[0068] Specifically, when the consistency check is performed, it is identified that the load data in a certain time period has abnormal fluctuations, for example, a very high impact load is suddenly recorded under stable driving conditions, which may be caused by sensor failure or data transmission error. At this time, the system will mark the abnormal data and correct or exclude it according to the trend of the data before and after. For missing data completion, if the temperature data of a certain time period is missing, the system can interpolate and complete the missing data according to the temperature data of adjacent time points and in combination with an environmental temperature model, so as to ensure the continuity of the temperature data. After the preprocessing, a complete and reliable preprocessed service history information is obtained.

[0069] Subsequently, a damage evolution model is dynamically selected according to the material (for example, high-strength alloy steel) of the helical spring and the preprocessed service history information. For example, if the service history information shows that the spring mainly bears high-frequency cyclic loads, the system may select a fatigue damage accumulation model based on the Miner rule. If the spring is also exposed to a high-temperature environment for a long time, the system may further consider a creep damage model and couple it with the fatigue damage model. Based on the selected model, the system calculates the material cumulative damage factor of the spring in the entire expected service period, for example, the calculation result is 0.65.

[0070] Finally, based on the material cumulative damage factor 0.65, the system evaluates the material cumulative damage state of the spring. For example, the system can preset that a damage factor below 0.3 is slight damage, between 0.3 and 0.7 is moderate damage, and above 0.7 is severe damage. Therefore, the material cumulative damage state of the spring is evaluated as “moderate damage”. This accurate damage state information will be used to subsequently correct the original physical morphological characteristics of the spring, thereby ensuring that the influence of material damage on the performance of the spring can be fully considered in the robust design and optimization iteration.

[0071] In one possible design, step S3141 comprises: S31411, standardizing the service history information data and preprocessing based on the standardized service history information, wherein the preprocessing includes timestamp alignment, interpolation completion and data cleaning; In this embodiment, the service history information data is standardized to eliminate dimensional differences caused by different data sources or measurement units and ensure data consistency. On this basis, preprocessing is performed based on the standardized service history information to improve data quality and availability. Specifically, timestamp alignment is to synchronize data collected by different sensors or recording systems according to a unified time reference to ensure the accuracy of the time series of the data; interpolation completion is to calculate missing values according to known data points by mathematical methods (such as linear interpolation, spline interpolation, etc.) when there are missing values in the data sequence to maintain data continuity; data cleaning is to identify and correct or delete errors, outliers or inconsistent items in the data to improve the accuracy and reliability of the data.

[0072] S31412, extracting key parameters in the preprocessed service history information, wherein the key parameters include cumulative load cycle number, high-temperature exposure time and corrosion environment exposure time; In this embodiment, the key parameters are physical quantities or events that have a decisive influence on the service state of the spring. Specifically, the cumulative load cycle number is an important indicator to measure the degree of fatigue damage of the spring, reflecting the periodic load effect on the spring during service; the high-temperature exposure time refers to the cumulative time of the spring exceeding its designed working temperature range, which may cause material creep, oxidation or changes in organizational structure, thereby affecting its mechanical properties; the corrosion environment exposure time refers to the cumulative time of the spring in corrosive media (such as acid, alkali, salt spray, etc.), which may cause surface corrosion, stress corrosion cracking and other damage of the material. By quantifying the key parameters, the actual service condition and potential damage risk of the spring can be more accurately evaluated.

[0073] S31413, comparing the key parameters with the preset material damage threshold and performance decay curve, and determining the current service stage of the spring according to the comparison result; In this embodiment, the material damage threshold is the critical value at which the material performance begins to decline significantly or fail under different damage mechanisms, such as fatigue crack initiation threshold, creep strain threshold, etc. The performance degradation curve is a trend curve that describes the change of the spring's key performance such as stiffness, load-carrying capacity, etc. with time or load accumulation under different service conditions. For example, when the cumulative load cycle number exceeds a certain fatigue damage threshold, the spring may enter the fatigue damage accumulation stage; when the high temperature exposure time reaches a certain degree, it may enter the material aging stage. Through this comparison, the current service stage of the spring can be objectively and quantitatively determined.

[0074] The technical solutions of the above embodiments effectively solve the quality problems that may exist in the original data through systematic standardization and preprocessing of the service history information, ensuring the accuracy of subsequent analysis. Subsequently, by extracting key parameters directly related to spring material damage and comparing them with preset damage thresholds and performance degradation curves, the judgment of the current service stage of the spring is more scientific and quantitative. Thus, the damage state of the spring can be more accurately identified, such as whether it is in the initial wear, fatigue accumulation, material aging or critical failure stage.

[0075] In one possible design, Figure 6 is a flowchart of step S313 according to an exemplary embodiment. Referring to the accompanying drawings, Figure 6 Step S313 includes: S3131, obtaining estimated confidence information of the material cumulative damage state; In this embodiment, the completeness, accuracy, timeliness of the data source (such as service history information) used to estimate the material cumulative damage state and the applicability of the damage evolution model are comprehensively evaluated to quantitatively evaluate the results. The confidence information can be a percentage value, a probability value or a confidence interval to reflect the reliability of the current material cumulative damage state estimation. For example, when there is a lot of missing or noise in the service history data, the estimated confidence information will be low.

[0076] S3132, when the estimated confidence is lower than the preset confidence threshold, determining the change range of each original physical form feature under the current damage state according to the material cumulative damage state; In this embodiment, when the estimation confidence is lower than the pre-set confidence threshold, it means that there is a high uncertainty in the estimation of the current material cumulative damage state. The pre-set confidence threshold can be set according to the actual application scenario and the requirement for the accuracy of the results, for example, it can be set to 70% or 80%. When it is lower than the threshold, the system will start a more conservative or more refined correction strategy. Subsequently, based on the known material damage mechanism, empirical data or more detailed physical model, the reasonable fluctuation range of the original physical morphology feature that may occur under the given material cumulative damage state is predicted. For example, material fatigue damage may cause the spring stiffness to decrease, and the decrease amplitude will have an expected range. The change range can be a symmetric interval or an asymmetric interval, the purpose of which is to provide a reasonable boundary for subsequent correction, avoiding over-correction or under-correction.

[0077] S3133, correcting the original physical morphology feature within the change range to obtain a second physical morphology feature; In this embodiment, within the change range determined in step S3132, the original physical morphology feature is adjusted by interpolation, weighted average, sampling based on probability distribution or optimization algorithm, etc. For example, according to the estimation confidence information, weighted correction can be performed within the change range, and the lower the confidence, the greater the correction amplitude, or the correction result tends to be a conservative estimate.

[0078] S3134, comparing the second physical morphology feature with the actual simulation results of a small number of key points, and correcting the second physical morphology feature according to the comparison results; In this embodiment, in order to further verify and improve the accuracy of the correction results, a small number of key points of the spring under specific load, temperature or deformation conditions are selected for high-precision multi-physical field simulation to obtain the actual physical morphology features of these key points. Subsequently, the second physical morphology feature obtained through the above steps is compared with these actual simulation results, and if there is a deviation, the second physical morphology feature is fine-tuned or corrected according to the deviation size and direction, so as to locally verify and optimize the correction process by using high-precision simulation results, and ensure that the corrected feature is closer to the actual situation.

[0079] The technical solutions of the above embodiments introduce the evaluation of the estimation confidence of the material cumulative damage state, and use high-precision simulation data to locally verify and refine the correction results, thereby making up for the potential errors caused by the uncertainty of the damage state estimation, and further improving the accuracy of the correction results.

[0080] In one example, it is assumed that a spring has part of its service history information missing due to sensor failure or incomplete data recording during service, so that the estimation confidence of the material cumulative damage state estimated by the existing method is only 60%, which is lower than the pre-set 75% confidence threshold.

[0081] In this case, the solution of the present application will first obtain the estimated confidence information of 60%. Since the confidence is lower than the threshold, the possible variation range of the original physical configuration characteristics (e.g. wire diameter, number of turns, pitch, etc.) of the spring under light fatigue damage will be determined according to the current estimated material cumulative damage state (e.g. light fatigue damage), combined with the material property database and the empirical model. For example, the wire diameter may fluctuate within a range of ±0.5%, the number of turns may remain unchanged, and the pitch may fluctuate within a range of ±0.2%. Subsequently, the original physical configuration characteristics will be modified within these determined variation ranges, for example, by adjusting the original wire diameter to its expected average value under light fatigue damage through weighted averaging, to obtain the modified second physical configuration characteristics. Finally, in order to further verify the modification result, two key points of the spring under the maximum compression load and the minimum compression load will be selected for high-precision finite element simulation to obtain the actual physical configuration characteristics corresponding to the two key points. The modified second physical configuration characteristics are compared with the actual simulation results of the two key points. If it is found that the modified wire diameter still has a slight deviation under the maximum compression load, the second physical configuration characteristics will be fine-tuned according to the comparison results until they are highly consistent with the simulation results of the key points. Through this series of steps, even in the case of high uncertainty in damage state estimation, more accurate and reliable second physical configuration characteristics can be obtained.

[0082] In one possible design, Figure 7 is a partial flow chart of step S1 according to an exemplary embodiment. Referring to the accompanying drawings, Figure 7 Step S1 includes: S11, globally analyze the first stiffness characteristic curve data, extract features describing the overall trend and macroscopic shape of the first stiffness characteristic curve data, and obtain global smoothing features; In this embodiment, global analysis refers to macro-level examination of the entire first stiffness characteristic curve data, aiming to capture its overall trend, average level, fluctuation range, etc. For example, curve fitting (such as polynomial fitting, spline fitting), statistical moments (such as mean, variance, skewness, kurtosis), Fourier transform or wavelet transform, etc. can be used to extract parameters reflecting the overall characteristics of the curve. Thus, the global smoothing features refer to the features obtained by global analysis that can describe the overall trend and macroscopic shape of the first stiffness characteristic curve data. These features usually reflect the average stiffness, linearity, overall nonlinearity, etc. of the spring in different load or displacement ranges. For example, they can be the coefficients of the fitted curve, the values of the statistical moments, or the amplitudes of specific frequency components.

[0083] S12, run a local event detection algorithm to identify and quantify non-smooth local features on the first stiffness characteristic curve data to obtain local event features; In this embodiment, the local event detection algorithm refers to an algorithm for identifying specific local regions in the first stiffness characteristic curve data that do not conform to the overall trend or have significant changes. These algorithms can include but are not limited to peak and valley detection, inflection point detection, outlier detection, edge detection, etc., so as to accurately capture the discontinuity or discontinuity in the curve caused by material phase change, micro-crack initiation, local plastic deformation, etc.

[0084] Non-smooth local features refer to features of local regions that are identified by the local event detection algorithm and exhibit non-smoothness, discontinuity or significant changes on the first stiffness characteristic curve data. These features are usually closely related to the microstructure changes, damage accumulation or local response of the spring material under specific working conditions. For example, it can be a nonlinear inflection point of the stiffness curve, a starting point or an ending point of a hysteresis loop, a local stiffness drop or a local stiffness rise amplitude and position.

[0085] Local event features refer to the results of quantitatively describing non-smooth local features. For example, nonlinear inflection point offset, hysteresis loop area change rate, local stiffness attenuation factor, etc. These quantitative indicators can more accurately reflect the performance changes of the spring in a specific local region.

[0086] S13, combine the global smooth features and the local event features into a hybrid feature vector as the first physical form feature of the spring; In this embodiment, the hybrid feature vector refers to a comprehensive feature representation formed by effectively combining global smooth features and local event features. This combination can be simple splicing or weighted fusion, aiming to comprehensively and multi-dimensionally represent the first physical form feature of the spring.

[0087] The technical solutions of the above embodiments can not only grasp the macro stiffness characteristics of the spring, but also accurately capture the non-smooth local features caused by material damage, phase change, etc. by performing global analysis and local event detection on the first stiffness characteristic curve data. Therefore, the hybrid feature vector obtained can more completely represent the actual physical state of the spring.

[0088] In summary, the spring stiffness characteristic simulation optimization method provided by the embodiment of the application comprehensively considers various complex factors such as material dynamic response, temperature influence, manufacturing tolerance and assembly deviation, greatly reduces the huge demand of a traditional Monte Carlo statistical analysis method on computing resources by constructing a prediction model and introducing robust design optimization iteration, avoids the problem that the optimization process cannot be practically applied due to too long calculation time, and thus efficiently finds a spring design scheme that can meet the target stiffness characteristic and has good resistance to uncertainties in actual production and assembly, thereby improving the efficiency and reliability of spring design.

[0089] Embodiment 2 The embodiment 2 of the application provides a spring stiffness characteristic simulation optimization system. Figure 8 FIG. 1 is a block diagram of a spring stiffness characteristic simulation optimization system according to an exemplary embodiment. Referring to FIG. 1, the system includes: Figure 8 a feature acquisition module 01 configured to acquire first stiffness characteristic curve data of the spring through multi-physics field simulation, and extract first physical morphology features of the spring based on the first stiffness characteristic curve data, wherein the multi-physics field simulation is based on material dynamic response and temperature influence of the spring; a model construction module 02 configured to establish a prediction model between input parameters of the spring and the first physical morphology features, wherein the input parameters include geometric design parameters, a working temperature range, manufacturing tolerance and assembly deviation; a characteristic curve reconstruction module 03 configured to acquire corresponding second physical morphology features according to the geometric design parameters and uncertainty parameters and based on the prediction model in robust design optimization iteration, and reconstruct second stiffness characteristic curve data of the spring based on the second physical morphology features; a robust performance evaluation module 04 configured to obtain a robust performance evaluation result of the design scheme under the influence of uncertainties based on statistical analysis of the second stiffness characteristic curve data, and iteratively adjust the geometric design parameters according to the robust performance evaluation result until a spring design scheme meeting the robustness requirement is obtained.

[0090] In summary, the spring stiffness characteristic simulation optimization system provided by the embodiment of the application comprehensively considers various complex factors such as material dynamic response, temperature influence, manufacturing tolerance and assembly deviation, greatly reduces the huge demand of a traditional Monte Carlo statistical analysis method on computing resources by constructing a prediction model and introducing robust design optimization iteration, avoids the problem that the optimization process cannot be practically applied due to too long calculation time, and thus efficiently finds a spring design scheme that can meet the target stiffness characteristic and has good resistance to uncertainties in actual production and assembly, thereby improving the efficiency and reliability of spring design.

[0091] Embodiment 3​ Embodiment 3 of the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the method provided in Embodiment 1.

[0092] More specifically, the readable storage medium can include, but is not limited to, a portable disc, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0093] In possible implementation manners, the present application can also be implemented in the form of a program product, which includes program codes for causing a terminal device to perform the steps of the method provided in Embodiment 1 when the program product is run on the terminal device.

[0094] The program codes for implementing the present application can be written in any combination of one or more programming languages, and can be executed completely on a user device, partially on a user device, as a separate software package, partially on a user device and partially on a remote device, or completely on a remote device.

[0095] The technical features of the above embodiments can be combined in any manner. To make the description concise, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combinations of the technical features do not contradict each other, they should be considered within the scope of the present application.

[0096] The above embodiments only express several implementation manners of the present application, and the description is relatively specific and detailed, but it should not be understood as a limitation on the patent scope of the present application. It should be pointed out that, for ordinary skilled persons in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the patent protection scope of the present application should be subject to the appended claims.

Claims

1. A simulation optimization method for spring stiffness characteristics, characterized in that, The method includes: The first stiffness characteristic curve data of the spring is obtained by multiphysics simulation, and the first physical morphological characteristics of the spring are extracted based on the first stiffness characteristic curve data. The multiphysics simulation is based on the material dynamic response and temperature influence of the spring. A predictive model is established between the spring input parameters and the first physical morphological feature, wherein the input parameters include geometric design parameters, operating temperature range, manufacturing tolerances, and assembly deviations; In the robust design optimization iteration, based on the geometric design parameters and uncertainty parameters and the prediction model, the corresponding second physical morphological features are obtained, and based on the second physical morphological features, the second stiffness characteristic curve data of the spring is reconstructed. Based on the statistical analysis of the second stiffness characteristic curve data, the robust performance evaluation results of the design scheme under the influence of uncertainty are obtained. Based on the robust performance evaluation results, the geometric design parameters are iteratively adjusted until a spring design scheme that meets the robustness requirements is obtained.

2. The spring stiffness characteristic simulation optimization method according to claim 1, characterized in that, In the robust design optimization iteration, based on the geometric design parameters and uncertainty parameters and the prediction model, the corresponding second physical morphological features are obtained, and based on the second physical morphological features, the second stiffness characteristic curve data of the spring is reconstructed, including: Based on the geometric design parameters and expected service history information, estimate the cumulative material damage state of the spring; Based on the geometric design parameters and the uncertainty parameters, and based on the prediction model, the original physical morphological characteristics of the spring are obtained; The original physical morphological characteristics are corrected according to the cumulative damage state of the material to obtain the corrected second physical morphological characteristics; Based on the second physical morphological characteristics, the second stiffness characteristic curve data of the spring is reconstructed.

3. The spring stiffness characteristic simulation optimization method according to claim 1, characterized in that, In the robust design optimization iteration, based on the geometric design parameters and uncertainty parameters and the prediction model, the corresponding second physical morphological features are obtained, including: Evaluate the spatial distribution density of the combination of the geometric design parameters and the uncertainty parameters in the training data of the prediction model; When the spatial distribution density is lower than a preset density threshold, a new parameter sub-combination is generated based on the geometric design parameters and the combination of uncertainty parameters; The parameter sub-combinations are added to the training dataset of the prediction model, and the prediction model is locally retrained based on the supplemented training dataset to obtain an updated prediction model. Based on the updated prediction model, the second physical morphological features corresponding to the geometric design parameters and the uncertainty parameters are obtained.

4. The spring stiffness characteristic simulation optimization method according to claim 2, characterized in that, The extraction of the first physical morphological features of the spring based on the first stiffness characteristic curve data includes: Based on the first stiffness characteristic curve data and the service history information of the spring, the current service stage of the spring is determined; For the current service stage, a corresponding feature extraction strategy is selected from a preset feature extraction strategy library, wherein the feature extraction strategy library contains feature extraction methods optimized for different service stages or the material's cumulative damage state. Based on the selected feature extraction strategy, the data of the first stiffness characteristic curve is analyzed to identify and quantify the stiffness change characteristics that reflect the evolution of the microstructure of the spring material. The stiffness change characteristics include nonlinear inflection point offset, hysteresis loop area change rate, and stiffness decay factor. The stiffness variation characteristics are combined with other physical morphological characteristics of the first stiffness characteristic curve data to obtain the first physical morphological characteristics of the spring.

5. The spring stiffness characteristic simulation optimization method according to claim 2, characterized in that, The step of estimating the cumulative material damage state of the spring based on the geometric design parameters and expected service history information includes: Based on the expected service history information, consistency checks and missing data completion are performed to obtain preprocessed service history information; Based on the geometric design parameters and the preprocessed service history information, a damage evolution model is dynamically selected and calculated based on the damage evolution model to obtain the material cumulative damage factor of the spring. Based on the material cumulative damage factor, the material cumulative damage state of the spring is evaluated and obtained.

6. The spring stiffness characteristic simulation optimization method according to claim 4, characterized in that, The step of determining the current service stage of the spring based on the first stiffness characteristic curve data and the spring's service history information includes: The service history information data is standardized and then preprocessed based on the standardized service history information, wherein the preprocessing includes timestamp alignment, interpolation completion, and data cleaning. Key parameters are extracted from the preprocessed service history information, including the cumulative load cycle count, high temperature exposure duration, and corrosive environment exposure time. The key parameters are compared with preset material damage thresholds and performance degradation curves, and the current service stage of the spring is determined based on the comparison results.

7. The spring stiffness characteristic simulation optimization method according to claim 2, characterized in that, The step of correcting the original physical morphological features based on the cumulative damage state of the material to obtain the corrected second physical morphological features includes: Obtain the estimated confidence level information of the cumulative damage state of the material; When the estimated confidence level is lower than the preset confidence level threshold, the range of change of each original physical morphological feature under the current damage state is determined based on the material's cumulative damage state. Within the range of variation, the original physical morphological features are modified to obtain the modified second physical morphological features; The second physical morphological feature is compared with the actual simulation results of a small number of key points, and the second physical morphological feature is corrected based on the comparison results.

8. The spring stiffness characteristic simulation optimization method according to claim 1, characterized in that, The extraction of the first physical morphological features of the spring based on the first stiffness characteristic curve data includes: A global analysis of the first stiffness characteristic curve data is performed to extract features that describe the overall trend and macroscopic shape of the first stiffness characteristic curve data, resulting in global smoothing features. Run the local event detection algorithm to identify and quantify the non-smooth locality features on the first stiffness characteristic curve data to obtain local event features; The global smoothing feature and the local event feature are combined into a hybrid feature vector, which serves as the first physical morphological feature of the spring.

9. A simulation and optimization system for spring stiffness characteristics, characterized in that, The system includes: The feature acquisition module is used to acquire the first stiffness characteristic curve data of the spring through multiphysics simulation, and extract the first physical morphological features of the spring based on the first stiffness characteristic curve data, wherein the multiphysics simulation is based on the material dynamic response and temperature influence of the spring. The model building module is used to establish a predictive model between the spring input parameters and the first physical morphological features, wherein the input parameters include geometric design parameters, operating temperature range, manufacturing tolerances, and assembly deviations; The characteristic curve reconstruction module is used to obtain the corresponding second physical morphological features based on the geometric design parameters and uncertainty parameters and the prediction model during robust design optimization iteration, and to reconstruct the second stiffness characteristic curve data of the spring based on the second physical morphological features. The robust performance evaluation module is used to obtain the robust performance evaluation results of the design scheme under the influence of uncertainty based on the statistical analysis of the second stiffness characteristic curve data, and to iteratively adjust the geometric design parameters according to the robust performance evaluation results until a spring design scheme that meets the robustness requirements is obtained.

10. 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 method according to any one of claims 1 to 8.

Images