Vehicle collision test model optimization method based on multi-target constraint

Abstract

The embodiment of the invention discloses a vehicle collision test model optimization method based on multi-target constraint. The method comprises the following steps: firstly, determining the structural deformation similarity of an obtained structural deformation animation and a template collision animation based on a VIT model, then extracting curve characteristic values corresponding to determined physical characteristic curves, and carrying out multi-target constraint iterative optimization on a test matrix unit through an optimization algorithm model; and when the structural deformation similarity and each curve characteristic value constraint condition meet preset conditions, optimization is stopped, and a target vehicle collision test model at the moment is determined. Through the above optimization steps, the optimal target vehicle collision test model is automatically determined, multi-target constrained vehicle collision test model optimization is completed, the optimization efficiency is improved, and the VIT model is added to analyze the collision animation, so that the target vehicle collision test model is more accurate in simulation of the collision test. The simulation animation meets the corresponding template structure deformation requirements.

Description

Technical Field

[0001] One or more embodiments of the present specification relate to the field of vehicle safety technology, and in particular, to a vehicle collision test model optimization method based on multi-objective constraints. Background Art

[0002] With the rapid development of intelligent manufacturing technology in the automotive industry, various target experimental parameters in vehicle collision tests can affect multiple test results. There is an urgent need for a method that can optimize the vehicle collision test model based on multi-objective constraints in vehicle collision tests. However, the existing optimization methods can often only optimize the vehicle collision test model by using a simple optimization model based on the linear eigenvalues ​​calculated as constraints. When it comes to optimization based on the collision structure deformation animation, it can only rely on engineers with development experience to manually optimize based on experience or overlap and compare the simulation animations, and cannot automatically optimize based on the structural deformation image formed by the vehicle in the collision. Among them, manual optimization based on experience requires the final judgment of whether the structural deformation mode is the same, which has subjective judgment errors. The use of the simulation animation overlap comparison analysis method requires the two animation models to overlap, and the operation is cumbersome. Therefore, the existing vehicle collision test model optimization methods are not only inefficient in optimization, but also cannot meet the requirements of the optimized vehicle collision test model structure deformation. Summary of the invention

[0003] The embodiment of this specification provides a vehicle collision test model optimization method based on multi-objective constraints, and its technical solution is as follows: In a first aspect, an embodiment of the present specification provides a vehicle collision test model optimization method based on multi-objective constraints, the method comprising: Constructing a test parameter matrix based on the parameters to be tested of the vehicle collision test model; For any test matrix unit in the test parameter matrix, determining the solution result data corresponding to the test matrix unit based on the simulation solver, and performing data conversion on the solution result data to obtain an output target, wherein the output target includes a structural deformation animation and at least one physical characteristic curve; Determine the structural deformation similarity between the structural deformation animation and the template collision animation based on the VIT model, and extract the curve characteristic value corresponding to each of the physical characteristic curves; Based on the optimization algorithm model, the test matrix unit is subjected to multi-objective constrained iterative optimization, and a target vehicle collision test model after iterative optimization is determined, wherein the optimization objectives of the multi-objective constrained iterative optimization include the structural deformation similarity and the characteristic values ​​of each of the curves.

[0004] In a second aspect, a vehicle collision test model optimization device based on multi-objective constraints is provided, the device comprising: A processing module, used for constructing a test parameter matrix based on the parameters to be tested of the vehicle collision test model; A simulation module, for determining, for any test matrix unit in the test parameter matrix, solution result data corresponding to the test matrix unit based on a simulation solver, and performing data conversion on the solution result data to obtain an output target, wherein the output target includes a structural deformation animation and at least one physical characteristic curve; A determination module, used to determine the structural deformation similarity between the structural deformation animation and the template collision animation based on the VIT model, and extract the curve characteristic value corresponding to each of the physical characteristic curves; The optimization module is used to perform multi-objective constrained iterative optimization on the test matrix unit based on the optimization algorithm model, and determine the target vehicle collision test model after iterative optimization, wherein the optimization objectives of the multi-objective constrained iterative optimization include the structural deformation similarity and the characteristic values ​​of each curve.

[0005] In a third aspect, an electronic device is provided, including a device processor and a memory; The device processor is connected to the memory; The memory is used to store executable program code; The device processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the steps of the method provided in the first aspect or any possible implementation manner of the first aspect.

[0006] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and the computer-readable storage medium stores instructions, which, when the instructions are executed on a computer or a device processor, cause the computer or the device processor to execute the method provided in the first aspect or any possible implementation of the first aspect.

[0007] The beneficial effects brought by the technical solutions provided by some embodiments of this specification include at least: In one or more embodiments of the present specification, the structural deformation similarity between the obtained structural deformation animation and the template collision animation can be determined based on the VIT model, and then the curve eigenvalues ​​corresponding to each determined physical characteristic curve can be extracted, and the test matrix unit can be optimized iteratively with multi-objective constraints through the optimization algorithm model. When the structural deformation similarity and the constraints of each curve eigenvalue meet the preset conditions, the optimization is stopped and the target vehicle collision test model at this time is determined. Through the above optimization steps, the optimal target vehicle collision test model is automatically determined, and the vehicle collision test model optimization with multi-objective constraints is completed, which not only improves the optimization efficiency, but also by adding the VIT model to analyze the collision animation, the target vehicle collision test model simulates the collision test, and the simulation animation meets the corresponding template structural deformation requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0009] Figure 1 A schematic diagram of the system architecture of a vehicle collision test model optimization method based on multi-objective constraints provided in an embodiment of this specification; Figure 2 A flowchart of a vehicle collision test model optimization method based on multi-objective constraints provided in an embodiment of this specification; Figure 3 A schematic diagram of the structure of a vehicle collision test model optimization device based on multi-objective constraints provided in an embodiment of this specification; Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this specification. DETAILED DESCRIPTION

[0010] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0011] The terms "first", "second", "third", etc. in the description and claims of this specification and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0012] The following description provides examples and does not limit the scope, applicability or examples set forth in the claims. Changes may be made to the functions and arrangements of the elements described without departing from the scope of the present specification. Various processes or components may be appropriately omitted, substituted or added to each example. For example, the described method may be performed in an order different from the order described, and various steps may be added, omitted or combined. In addition, features described with respect to some examples may be combined in other examples.

[0013] See also Figure 1 , Figure 1 A schematic diagram of the system architecture of a vehicle collision test model optimization method based on multi-objective constraints provided in an embodiment of this specification is shown.

[0014] like Figure 1 As shown, the system architecture of the vehicle collision test model optimization method based on multi-objective constraints may at least include a terminal 10 , a server 20 and a network 30 .

[0015] The terminal 10 includes but is not limited to electronic devices such as smart phones, desktop computers, tablet computers, laptops, smart speakers, digital assistants, smart wearable devices, etc., and may also be software running on the above electronic devices, such as applications, etc. Optionally, the operating system running on the electronic device may include but is not limited to Android system, IOS system, Linux, Windows, etc. Optionally, the terminal 10 provides a vehicle collision test model optimization service to the user, and the terminal 10 may obtain a vehicle collision test model optimization instruction of an application program interface, and send a vehicle collision test model optimization request to the server 20.

[0016] The server 20 can provide background services for the terminal 10. According to the vehicle collision test model optimization request sent by the terminal 10, the server 20 will obtain a series of vehicle collision test model optimization instructions, and the server 20 transmits the vehicle collision test model optimization instructions to other terminals 10 through the network 30. Specifically, the server 20 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0017] The network 30 is used to provide a medium for a communication link between the terminal 10 and the server 20. The network 30 may include various connection types, such as wired or wireless communication links or optical fiber cables.

[0018] In addition, it should be noted that Figure 1 What is shown is only one system provided by the present disclosure. In practical applications, other systems may also be included, for example, more terminals may be included.

[0019] In the embodiments of the present specification, the terminal 10 and the server 20 may be directly or indirectly connected via wired or wireless communication, which is not limited in the present disclosure.

[0020] See next Figure 2 , Figure 2 An overall flow chart of a vehicle collision test model optimization method based on multi-objective constraints provided in an embodiment of this specification is shown. The vehicle collision test model optimization method based on multi-objective constraints can be used in the server 20.

[0021] like Figure 2 As shown, the vehicle collision test model optimization method based on multi-objective constraints may at least include the following steps: Step 201: construct a test parameter matrix based on the parameters to be tested of the vehicle collision test model.

[0022] In the embodiments of the present specification, in order to perform multi-objective optimization in the vehicle collision test, the target vehicle collision test model can be determined first. Optionally, common vehicle collision test models include frontal collision test models and side collision test models. Then, the variable range and level of the parameters to be tested are determined, such as the material and strength of the anti-collision beam, the thickness and length of different materials, etc. Further, the full factorial design, partial factorial design or response surface design in the experimental design (Design of Experiments, DOE) algorithm is used to design the experimental plan, and a corresponding test parameter matrix including different combinations of parameters to be tested is generated. In the test parameter matrix, the subsequent optimization iterative processing only needs to take any matrix unit to complete a certain optimization process.

[0023] In one possible implementation, the step of constructing a test parameter matrix based on the parameters to be tested of the vehicle collision test model includes: Obtaining parameters to be tested of the vehicle collision test model; The parameters to be tested are combined based on the full factor DOE algorithm to obtain a test parameter matrix.

[0024] In the embodiments of the present specification, all parameters to be tested of the target vehicle collision test model can be obtained first. As an example, when the target vehicle collision test model is a frontal collision test model, the parameters to be tested set by the target terminal may include the material structure, material type and material thickness of the barrier honeycomb aluminum. Among them, the material structure includes two types, A1 and A2, and the material types include four types, B1, B2, B3 and B4, and each material includes three material thicknesses, C1, C2 and C3. Furthermore, all the parameters to be tested can be combined through the full factor DOE algorithm, which can include a total of 2*4*3=24 test combinations, and all the single test combinations are used as test matrix units to obtain a test parameter matrix.

[0025] Step 202: for any test matrix unit in the test parameter matrix, determine the solution result data corresponding to the test matrix unit based on the simulation solver, and perform data conversion on the solution result data to obtain an output target.

[0026] Wherein, the output target includes a structural deformation animation and at least one physical characteristic curve.

[0027] In the embodiment of the present specification, in order to perform multi-objective constraint optimization on the vehicle collision test model, it is necessary to continuously change the parameters of the vehicle collision test model, and optimize the model parameters according to the comparison between the simulation results and the target results. Therefore, for a certain vehicle collision test, it is only necessary to take out any test matrix unit in the obtained test parameter matrix, and input the test parameter determination value corresponding to the test matrix unit into the simulation solver. Among them, for a certain parameter determination model, it can be pre-processed and converted into an information storage file, usually with a .K file extension. Then, the simulation solver is run to read the input file and calculate to solve the entire dynamic process of the simulation, and output the solution result data corresponding to the test matrix unit. Among them, the output solution result data can be output in the form of an output file, usually with a .d3plot file extension. Further, since the solution result data can include node displacement data and stress data, all solution result data can be converted, for example, node displacement data is converted into structural deformation animation, stress data is converted into each physical characteristic curve, and finally all conversions are completed to obtain the output target, and the output target can include structural deformation animation and multiple physical characteristic curves.

[0028] Among them, when performing simulation, you can choose from multiple simulation solvers such as LS-DYNA, ABAQUS, COMSOL Multiphysics and ANSYS. Each simulation solver has its own advantages and disadvantages. The LS-DYNA simulation solver is suitable for complex dynamic and nonlinear problems, supports explicit and implicit solvers, and can handle various material models and contact conditions, but the calculation cost is high, the hardware requirements are high, and professional technicians are required to operate. The ABAQUS simulation solver is suitable for a wide range of engineering applications, including structural, thermal, fluid and multi-physics field analysis, with powerful nonlinear processing capabilities and a wide range of material model libraries, but the interface is relatively complex and the calculation cost is high. The ANSYS simulation solver can provide a wide range of solvers, including structural, thermal, fluid, electromagnetic and multi-physics field analysis, with a user-friendly interface and support for multiple languages ​​and operating systems, but the software package is huge and contains many modules, and it takes a long time to familiarize yourself with all the functions. The COMSOL Multiphysics simulation solver can be used specifically for multi-physics field coupling analysis, providing an intuitive graphical interface, but compared with other general solvers, it focuses on specific types of multi-physics field problems.

[0029] In one possible implementation, for any test matrix unit in the test parameter matrix, determining the solution result data corresponding to the test matrix unit based on a simulation solver includes: For any test matrix unit in the test parameter matrix, convert the test matrix unit into an input file based on format conversion; The solution result data corresponding to the input file is determined based on the LS-DYNA simulation solver.

[0030] In the embodiment of the present specification, in order to determine the solution result data corresponding to the test matrix unit through the simulation solver, the parameter values ​​in the corresponding test matrix unit in the test parameter matrix can be first extracted, and an initial input file can be created using the pre-processing software, and the extracted parameter values ​​can be replaced with the corresponding parameter positions in the initial input file through format conversion to obtain the converted input file, and determine that the input file meets the file format requirements of the subsequent simulation solver. Then, since the vehicle collision test involves complex dynamic and nonlinear problems, the LS-DYNA simulation solver can be started first, and the input file can be imported into it. Then, the LS-DYNA simulation solver performs calculations and solutions based on the parameters and conditions in the input file, and finally outputs the corresponding solution result data.

[0031] In one possible implementation, the solution result data is converted to obtain an output target, and the output target includes a structural deformation animation and at least one physical characteristic curve, including: Classifying the solution result data based on data types to obtain a first data set and a second data set, wherein the first data set includes all continuous data in the solution result data, and the second data set includes all discrete data in the solution result data; Normalizing and plotting the first data set to obtain at least one physical characteristic curve; Performing LS-PrePost post-processing on the second data set to obtain a structural deformation animation; The structural deformation animation and the physical characteristic curves are integrated to obtain an output target.

[0032] In the embodiments of this specification, all the solution result data are first extracted from the output file of the LS-DYNA simulation solver, and all the solution result data are divided into a first data set and a second data set according to the data type and physical meaning purpose. Among them, the first data set includes all continuous data such as all stress, strain, displacement, etc., and the second data set includes all discrete data such as all node displacements and contact forces. Then, the first data set is normalized so that its normalized value falls between 0 and 1, and the normalized physical characteristic curves are drawn using drawing software such as Origin, MATLAB, etc. At the same time, the node displacement data in the second data set is converted into animation format data, and the structural deformation animation is created using LS-PrePost post-processing. Finally, the obtained structural deformation animation and each physical characteristic curve are sorted and merged, and the whole is defined as the output target.

[0033] Step 203: determining the structural deformation similarity between the structural deformation animation and the template collision animation based on the VIT model, and extracting the curve characteristic values ​​corresponding to each of the physical characteristic curves.

[0034] In the embodiments of the present specification, a trained Vision Transformer (VIT) VIT model can be first determined based on the collision test model, and the result deformation animation obtained by the simulation solver and the preset template collision animation are input into the trained VIT model, and a corresponding structural deformation similarity is output through the VIT model to indicate the similarity between the input structural deformation animation and the template collision animation. The structural deformation similarity is usually a value between 0 and 1, where 1 indicates complete similarity and 0 indicates complete dissimilarity. At the same time, by comparing each physical feature curve with the corresponding template curve, the corresponding curve feature value is obtained to indicate the deviation value between each physical feature curve and the template curve.

[0035] Among them, the VIT model is a deep learning model for image recognition tasks, which mainly includes a self-attention mechanism, which is used to process images not only to process local features but also to consider the relationship between different regions. The VIT model divides the input image into fixed-size image blocks (such as 16x16 pixel blocks), and in order to retain the spatial information of the image blocks, VIT adds position embedding to each image block and uses a standard Transformer encoder structure composed of multiple self-attention layers and feedforward networks. Each self-attention layer can process all image blocks at the same time and capture the global dependencies between them. After the Transformer encoder, VIT adds a classification head, usually a simple feedforward network, to convert the output of the encoder into the final classification result. The VIT model is suitable for a variety of visual tasks because it can effectively capture long-distance dependencies in images.

[0036] In one possible implementation, determining the structural deformation similarity between the structural deformation animation and the template collision animation based on the VIT model includes: The initial VIT model is trained based on the historical collision animation to obtain a trained VIT model; The structural deformation animation and the template collision animation are input into the trained VIT model to obtain the structural deformation similarity between the structural deformation animation and the template collision animation.

[0037] In the embodiments of the present specification, an initial VIT model can be constructed first, and the historical collision animations collected in the historical collision tests can include different types of collisions and different test conditions. Then, the collected historical collision animations are pre-processed by cropping, scaling, rotating, etc. to standardize the data format and improve the generalization ability of the model. Then, using the initial VIT model architecture, the historical collision animation data is used as input for model training, so that it can learn the characteristics of structural deformation during the collision process, and the VIT model parameters are adjusted through the model output to obtain a trained VIT model. Furthermore, the structural deformation animation and the template collision animation are input into the trained VIT model, and the VIT model outputs a structural deformation similarity to indicate the similarity between the input structural deformation animation and the template collision animation. When the structural deformation similarity is closer to 1, it means that the structural deformation animation is more similar to the template collision animation.

[0038] In one possible implementation, the extracting the curve characteristic value corresponding to each of the physical characteristic curves includes: Determine the curve features corresponding to each of the physical characteristic curves based on a feature extraction algorithm; Determine the template curve corresponding to each of the curve features based on the template database; Each of the physical characteristic curves is compared with each of the template curves to obtain a curve characteristic value corresponding to each of the physical characteristic curves.

[0039] In the embodiments of this specification, the curve features corresponding to each obtained physical characteristic curve can be first determined by a feature extraction algorithm, such as the acceleration features in the acceleration curve of a frontal collision test and the distance features in the deviation from the center curve of a side collision test. Then, in the template database, each type of curve feature corresponds to a template curve, so the template curve corresponding to each curve feature can be queried in the template database through each obtained curve feature type. Furthermore, each physical characteristic curve is compared with its corresponding template curve to obtain the deviation value between the corresponding physical characteristic curve and the template curve, and is defined as the curve feature value.

[0040] Step 204: performing multi-objective constraint iterative optimization on the test matrix unit based on the optimization algorithm model, and determining a target vehicle collision test model after iterative optimization.

[0041] Wherein, the optimization objectives of the multi-objective constrained iterative optimization include the structural deformation similarity and the characteristic values ​​of each of the curves.

[0042] In the embodiment of the present specification, an optimization algorithm model can be selected first, and the structural deformation similarity and each curve characteristic value generated by the test matrix unit can be judged whether they meet the corresponding multi-objective constraints. As long as one of the judgment results is characterized as not meeting the corresponding constraint conditions, a new test matrix unit is re-acquired and judged, and the optimization is iterated in this way until the judgment result represents that the multi-objective constraints all meet the constraint conditions, that is, the structural deformation similarity and each curve characteristic value are within the preset constraint range. Further, the corresponding target matrix unit is output at this time, and according to the corresponding parameter configuration in the target matrix unit, the simulated collision test results are close to the expected effects of each template, thereby determining the optimal target vehicle collision test model, and completing the optimization of the vehicle collision test model with multi-objective constraints.

[0043] Among them, the optimization algorithm can be selected from MEGO, genetic algorithm, particle swarm and other optimization algorithms.

[0044] In one possible implementation, the test matrix unit is subjected to multi-objective constrained iterative optimization based on the optimization algorithm model, and a target vehicle collision test model after iterative optimization is determined, wherein the optimization objectives of the multi-objective constrained iterative optimization include the structural deformation similarity and each of the curve eigenvalues, including: Based on the preset structural deformation similarity constraint, a first target constraint result corresponding to the structural deformation similarity is determined, and based on the preset curve characteristic value constraint, a second target constraint result corresponding to each curve characteristic value is determined; Iteratively optimizing the test matrix unit based on the MEGO optimization algorithm model until both the first target constraint result and the second target constraint result are characterized as satisfying the constraint condition; The target matrix unit after iterative optimization is obtained, and a target vehicle collision test model is determined based on the target matrix unit.

[0045] In the embodiment of the present specification, a pre-set structural deformation similarity constraint can be obtained through the target terminal, for example, the similarity is greater than 0.9. When the structural deformation similarity obtained based on the VIT model is greater than 0.9, the first target constraint result corresponding to this time is characterized as satisfying the constraint condition, and the first target constraint result corresponding to other cases is characterized as not satisfying the constraint condition. Similarly, the pre-set characteristic value constraints of each curve are obtained. For example, when the characteristic curve is an acceleration curve, the curve characteristic value constraint is that the curve acceleration is greater than 0.85. Then, when the curve characteristic value obtained based on the VIT model is greater than 0.85, the second target constraint result corresponding to this time is characterized as satisfying the constraint condition, and the second target constraint result corresponding to other cases is characterized as not satisfying the constraint condition. Next, the MEGO optimization algorithm model is used to iteratively optimize the test matrix unit. The maximum number of iterations of the optimization algorithm model can be set to 200 times. When only one of the first target constraint result and the second target constraint result is characterized as not satisfying the corresponding constraint condition, a new test matrix unit is re-acquired and judged. The optimization is iteratively performed until both the first target constraint result and the second target constraint result are characterized as satisfying the corresponding constraint condition. The corresponding target matrix unit is output at this time, and according to the corresponding parameter configuration in the target matrix unit, the simulated collision test results are close to the expected effects of each template, thereby determining the optimal target vehicle collision test model and completing the vehicle collision test model optimization with multi-objective constraints.

[0046] Optionally, the characteristic curve may include multiple curves, and the corresponding curve characteristic value constraints also include multiple constraints. Only when all the curve characteristic value constraints meet the requirements, the second target constraint result is characterized as meeting the constraint conditions.

[0047] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0048] See next Figure 3 , Figure 3The schematic diagram of the structure of a vehicle collision test model optimization device based on multi-objective constraints provided in the embodiment of this specification is shown. It should be noted that: Figure 3 The vehicle collision test model optimization device based on multi-objective constraints is used to implement the present application Figure 2 For the convenience of explanation, only the part related to the embodiment of the present application is shown. For the specific technical details not disclosed, please refer to the present application. Figure 2 The embodiment shown.

[0049] like Figure 3 As shown, the vehicle collision test model optimization device based on multi-objective constraints may at least include: The processing module 301 is used to construct a test parameter matrix based on the parameters to be tested of the vehicle collision test model; A simulation module 302 is used to determine the solution result data corresponding to any test matrix unit in the test parameter matrix based on a simulation solver, and perform data conversion on the solution result data to obtain an output target, wherein the output target includes a structural deformation animation and at least one physical characteristic curve; A determination module 303 is used to determine the structural deformation similarity between the structural deformation animation and the template collision animation based on the VIT model, and to extract curve characteristic values ​​corresponding to each of the physical characteristic curves; The optimization module 304 is used to perform multi-objective constrained iterative optimization on the test matrix unit based on the optimization algorithm model, and determine the target vehicle collision test model after iterative optimization, wherein the optimization objectives of the multi-objective constrained iterative optimization include the structural deformation similarity and the characteristic values ​​of each curve.

[0050] In one possible implementation, the processing module 301 is specifically used for: Obtaining parameters to be tested of the vehicle collision test model; The parameters to be tested are combined based on the full factor DOE algorithm to obtain a test parameter matrix.

[0051] In one possible implementation, the simulation module 302 is specifically used for: For any test matrix unit in the test parameter matrix, convert the test matrix unit into an input file based on format conversion; The solution result data corresponding to the input file is determined based on the LS-DYNA simulation solver.

[0052] In one possible implementation, the simulation module 302 is further configured to: Classifying the solution result data based on data types to obtain a first data set and a second data set, wherein the first data set includes all continuous data in the solution result data, and the second data set includes all discrete data in the solution result data; Normalizing and plotting the first data set to obtain at least one physical characteristic curve; Performing LS-PrePost post-processing on the second data set to obtain a structural deformation animation; The structural deformation animation and the physical characteristic curves are integrated to obtain an output target.

[0053] In one possible implementation, the determination module 303 is specifically configured to: The initial VIT model is trained based on the historical collision animation to obtain a trained VIT model; The structural deformation animation and the template collision animation are input into the trained VIT model to obtain the structural deformation similarity between the structural deformation animation and the template collision animation.

[0054] In one possible implementation, the determination module 303 is further configured to: Determine the curve features corresponding to each of the physical characteristic curves based on a feature extraction algorithm; Determine the template curve corresponding to each of the curve features based on the template database; Each of the physical characteristic curves is compared with each of the template curves to obtain a curve characteristic value corresponding to each of the physical characteristic curves.

[0055] In one possible implementation, the optimization module 304 is specifically used to: Based on the preset structural deformation similarity constraint, a first target constraint result corresponding to the structural deformation similarity is determined, and based on the preset curve characteristic value constraint, a second target constraint result corresponding to each curve characteristic value is determined; Iteratively optimizing the test matrix unit based on the MEGO optimization algorithm model until both the first target constraint result and the second target constraint result are characterized as satisfying the constraint condition; The target matrix unit after iterative optimization is obtained, and a target vehicle collision test model is determined based on the target matrix unit.

[0056] Those skilled in the art can clearly understand that the technical solutions of the embodiments of the present application can be implemented with the help of software and / or hardware. The "unit" and "module" in this specification refer to software and / or hardware that can independently complete or cooperate with other components to complete specific functions, where the hardware can be, for example, a field programmable gate array (FPGA), an integrated circuit (IC), etc.

[0057] Each processing unit and / or module of the embodiments of the present application may be implemented by an analog circuit that implements the functions described in the embodiments of the present application, or may be implemented by software that executes the functions described in the embodiments of the present application.

[0058] See next Figure 4 , Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this specification is shown.

[0059] like Figure 4 As shown, the electronic device 400 may include: at least one device processor 401 , at least one network interface 404 , a user interface 403 , a memory 405 , and at least one communication bus 402 .

[0060] The communication bus 402 may be used to realize the connection and communication among the above-mentioned components.

[0061] The user interface 403 may include buttons, and the optional user interface may also include a standard wired interface or a wireless interface.

[0062] The network interface 404 may include, but is not limited to, a Bluetooth module, an NFC module, a Wi-Fi module, etc.

[0063] Among them, the device processor 401 may include one or more processing cores. The device processor 401 uses various interfaces and lines to connect various parts within the entire electronic device 400, and executes various functions and processes data of the electronic device 400 by running or executing instructions, programs, code sets or instruction sets stored in the memory 405, and calling data stored in the memory 405. Optionally, the device processor 401 can be implemented in at least one hardware form of DSP, FPGA, and PLA. The device processor 401 can integrate one or a combination of CPU, GPU, modem, etc. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to handle wireless communications. It can be understood that the above-mentioned modem may not be integrated into the device processor 401, and it can be implemented separately through a chip.

[0064] The memory 405 may include a RAM or a ROM. Optionally, the memory 405 includes a non-transitory computer-readable medium. The memory 405 may be used to store instructions, programs, codes, code sets or instruction sets. The memory 405 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area may store data involved in the above-mentioned method embodiments, etc. The memory 405 may optionally be at least one storage device located away from the aforementioned device processor 401. As Figure 4 As shown, the memory 405 as a computer storage medium may include an operating system, a network communication module, a user interface module, and program instructions.

[0065] Specifically, the device processor 401 may be used to call the vehicle collision test model optimization application based on multi-objective constraints stored in the memory 405, and specifically perform the following operations: Constructing a test parameter matrix based on the parameters to be tested of the vehicle collision test model; For any test matrix unit in the test parameter matrix, determining the solution result data corresponding to the test matrix unit based on the simulation solver, and performing data conversion on the solution result data to obtain an output target, wherein the output target includes a structural deformation animation and at least one physical characteristic curve; Determine the structural deformation similarity between the structural deformation animation and the template collision animation based on the VIT model, and extract the curve characteristic value corresponding to each of the physical characteristic curves; Based on the optimization algorithm model, the test matrix unit is subjected to multi-objective constrained iterative optimization, and a target vehicle collision test model after iterative optimization is determined, wherein the optimization objectives of the multi-objective constrained iterative optimization include the structural deformation similarity and the characteristic values ​​of each of the curves.

[0066] As an option of the embodiment of this specification, the test parameter matrix is ​​constructed based on the parameters to be tested of the vehicle collision test model, including: Obtaining parameters to be tested of the vehicle collision test model; The parameters to be tested are combined based on the full factor DOE algorithm to obtain a test parameter matrix.

[0067] As an optional embodiment of this specification, for any test matrix unit in the test parameter matrix, determining the solution result data corresponding to the test matrix unit based on the simulation solver includes: For any test matrix unit in the test parameter matrix, convert the test matrix unit into an input file based on format conversion; The solution result data corresponding to the input file is determined based on the LS-DYNA simulation solver.

[0068] As an optional embodiment of this specification, the solution result data is converted to obtain an output target, and the output target includes a structural deformation animation and at least one physical characteristic curve, including: Classifying the solution result data based on data types to obtain a first data set and a second data set, wherein the first data set includes all continuous data in the solution result data, and the second data set includes all discrete data in the solution result data; Normalizing and plotting the first data set to obtain at least one physical characteristic curve; Performing LS-PrePost post-processing on the second data set to obtain a structural deformation animation; The structural deformation animation and the physical characteristic curves are integrated to obtain an output target.

[0069] As an option of the embodiment of this specification, the determining the structural deformation similarity between the structural deformation animation and the template collision animation based on the VIT model includes: The initial VIT model is trained based on the historical collision animation to obtain a trained VIT model; The structural deformation animation and the template collision animation are input into the trained VIT model to obtain the structural deformation similarity between the structural deformation animation and the template collision animation.

[0070] As an option of the embodiment of this specification, the extracting the curve characteristic value corresponding to each of the physical characteristic curves includes: Determine the curve features corresponding to each of the physical characteristic curves based on a feature extraction algorithm; Determine the template curve corresponding to each of the curve features based on the template database; Each of the physical characteristic curves is compared with each of the template curves to obtain a curve characteristic value corresponding to each of the physical characteristic curves.

[0071] As an optional embodiment of this specification, the test matrix unit is subjected to multi-objective constraint iterative optimization based on the optimization algorithm model, and the target vehicle collision test model after iterative optimization is determined, and the optimization objectives of the multi-objective constraint iterative optimization include the structural deformation similarity and each of the curve eigenvalues, including: Based on the preset structural deformation similarity constraint, a first target constraint result corresponding to the structural deformation similarity is determined, and based on the preset curve characteristic value constraint, a second target constraint result corresponding to each curve characteristic value is determined; Iteratively optimizing the test matrix unit based on the MEGO optimization algorithm model until both the first target constraint result and the second target constraint result are characterized as satisfying the constraint condition; The target matrix unit after iterative optimization is obtained, and a target vehicle collision test model is determined based on the target matrix unit.

[0072] The embodiments of this specification also provide a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of the above method are implemented. The computer-readable storage medium may include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a micro drive, and a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0073] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0074] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0075] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0076] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0077] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0078] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk and other media that can store program codes.

[0079] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by entering a program to instruct related hardware. The program may be stored in a computer-readable memory, which may include a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0080] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A vehicle collision test model optimization method based on multi-objective constraints, characterized in that: The method comprises: Constructing a test parameter matrix based on the parameters to be tested of the vehicle collision test model; For any test matrix unit in the test parameter matrix, determining the solution result data corresponding to the test matrix unit based on the simulation solver, and performing data conversion on the solution result data to obtain an output target, wherein the output target includes a structural deformation animation and at least one physical characteristic curve; Determine the structural deformation similarity between the structural deformation animation and the template collision animation based on the VIT model, and extract the curve characteristic value corresponding to each of the physical characteristic curves; Based on the optimization algorithm model, the test matrix unit is subjected to multi-objective constrained iterative optimization, and a target vehicle collision test model after iterative optimization is determined, wherein the optimization objectives of the multi-objective constrained iterative optimization include the structural deformation similarity and the characteristic values ​​of each of the curves.

2. The method according to claim 1, characterized in that The test parameter matrix is ​​constructed based on the parameters to be tested of the vehicle collision test model, including: Obtaining parameters to be tested of the vehicle collision test model; The parameters to be tested are combined based on the full factor DOE algorithm to obtain a test parameter matrix.

3. The method according to claim 1, characterized in that The step of determining, for any test matrix unit in the test parameter matrix, solution result data corresponding to the test matrix unit based on a simulation solver comprises: For any test matrix unit in the test parameter matrix, convert the test matrix unit into an input file based on format conversion; The solution result data corresponding to the input file is determined based on the LS-DYNA simulation solver.

4. The method according to claim 1, characterized in that: The data conversion is performed on the solution result data to obtain an output target, wherein the output target includes a structural deformation animation and at least one physical characteristic curve, including: Classifying the solution result data based on data types to obtain a first data set and a second data set, wherein the first data set includes all continuous data in the solution result data, and the second data set includes all discrete data in the solution result data; Normalizing and plotting the first data set to obtain at least one physical characteristic curve; Performing LS-PrePost post-processing on the second data set to obtain a structural deformation animation; The structural deformation animation and the physical characteristic curves are integrated to obtain an output target.

5. The method according to claim 1, characterized in that: The determining the structural deformation similarity between the structural deformation animation and the template collision animation based on the VIT model includes: The initial VIT model is trained based on the historical collision animation to obtain a trained VIT model; The structural deformation animation and the template collision animation are input into the trained VIT model to obtain the structural deformation similarity between the structural deformation animation and the template collision animation.

6. The method according to claim 1, characterized in that The extracting of curve characteristic values ​​corresponding to each of the physical characteristic curves includes: Determine the curve features corresponding to each of the physical characteristic curves based on a feature extraction algorithm; Determine the template curve corresponding to each of the curve features based on the template database; Each of the physical characteristic curves is compared with each of the template curves to obtain a curve characteristic value corresponding to each of the physical characteristic curves.

7. The method according to claim 1, characterized in that The test matrix unit is subjected to multi-objective constraint iterative optimization based on the optimization algorithm model, and the target vehicle collision test model after iterative optimization is determined, wherein the optimization objectives of the multi-objective constraint iterative optimization include the structural deformation similarity and each of the curve characteristic values, including: Based on the preset structural deformation similarity constraint, a first target constraint result corresponding to the structural deformation similarity is determined, and based on the preset curve characteristic value constraint, a second target constraint result corresponding to each curve characteristic value is determined; Iteratively optimizing the test matrix unit based on the MEGO optimization algorithm model until both the first target constraint result and the second target constraint result are characterized as satisfying the constraint condition; The target matrix unit after iterative optimization is obtained, and a target vehicle collision test model is determined based on the target matrix unit.

8. A vehicle collision test model optimization device based on multi-objective constraints, characterized in that: The device comprises: A processing module, used for constructing a test parameter matrix based on the parameters to be tested of the vehicle collision test model; A simulation module, for determining, for any test matrix unit in the test parameter matrix, solution result data corresponding to the test matrix unit based on a simulation solver, and performing data conversion on the solution result data to obtain an output target, wherein the output target includes a structural deformation animation and at least one physical characteristic curve; A determination module, used to determine the structural deformation similarity between the structural deformation animation and the template collision animation based on the VIT model, and extract the curve characteristic value corresponding to each of the physical characteristic curves; The optimization module is used to perform multi-objective constrained iterative optimization on the test matrix unit based on the optimization algorithm model, and determine the target vehicle collision test model after iterative optimization, wherein the optimization objectives of the multi-objective constrained iterative optimization include the structural deformation similarity and the characteristic values ​​of each curve.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, wherein the computer-readable storage medium has instructions stored therein, and when the instructions are executed on a computer or a processor, the computer or the processor executes the steps of the method according to any one of claims 1 to 7.

Images