Automobile anti-collision optimization method, device and equipment and storage medium

Abstract

The invention provides an automobile anti-collision optimization method, device and equipment and a storage medium, and the method comprises the steps: generating an original scheme group of automobile part design through employing a bionics principle, taking the original scheme group as an initial solution of a genetic algorithm, and carrying out the solving through employing the genetic algorithm, and obtaining a simulation scheme group; using a computer-aided tool to emulate an automobile collision of the set of plans; a finite element analysis method is used for judging the collision degree corresponding to each simulation scheme after simulation, and the simulation scheme with the lowest collision degree serves as a final scheme; and inputting the material parameters in the final scheme into a pre-established classification model, outputting material name distribution including each part of the automobile, and replacing the material parameters in the final scheme with the material name distribution to obtain an anti-collision optimization result. The genetic algorithm initial solution of the automobile part design is generated by utilizing the bionics principle, so that the stability of the automobile structure is ensured; the automobile collision is simulated by means of a computer-aided tool, and the automobile structure is verified more strictly.

Description

Technical Field

[0001] The present invention relates to the technical field of automotive safety, and particularly to an automotive anti-collision optimization method, device, equipment and storage medium. Background Art

[0002] With the continuous progress of the modern automotive industry, vehicle safety standards have been continuously improved, making vehicle safety design one of the core elements of automotive R & D. In safety design, load-bearing components and energy absorbers play a crucial role. In particular, energy absorbers can effectively disperse collision energy and thus reduce the impact force.

[0003] In the related art, the automotive industry and academia have been exploring advanced design concepts and technologies, including using topology optimization algorithms to design key load-bearing components, which can find the optimal material distribution in a given design space. In the prior art, specific material names such as aluminum alloy are often directly output. Then, when new materials appear in the market or existing materials are unavailable, the model cannot be automatically adjusted, limiting the flexibility of automotive design. In addition, the optimization principle of natural biological structures inspires the structure of automotive components, but in the prior art, it is only mentioned that it is applied to the design of components, and no scientific and effective verification is carried out based on this.

[0004] Based on the above analysis of the development status of this technical field, the existing technology lacks a solution that generates an initial solution of a genetic algorithm based on the bionics principle and then matches the corresponding material name after determining the material parameter results. Summary of the Invention

[0005] The purpose of the present invention is to provide an automotive anti-collision optimization method, device, equipment and storage medium, aiming to solve the above problems in the prior art.

[0006] According to the first aspect of the embodiment of the present invention, an automotive anti-collision optimization method is provided, including:

[0007] Using the bionics principle to generate an original solution group for the design of automotive components, taking the original solution group as the initial solution of the genetic algorithm, and using the genetic algorithm to solve to obtain a simulation solution group, specifically including:

[0008] Based on bionic structures including bones, honeycombs and cell walls, generating the structures of load-bearing components and energy-absorbing components of the vehicle; randomly generating material parameters, geometric parameters of load-bearing components and geometric parameters of energy-absorbing components by using the random generation method;

[0009] Taking the load-bearing component structure, energy-absorbing component structure, material parameters, geometric parameters of load-bearing components and geometric parameters of energy-absorbing components as the original solutions, and generating a preset number of original solutions as the original solution group.

[0010] The process of the genetic algorithm is as follows:

[0011] Take the original solution group as the initial population, and calculate the sum of the weights of the individual bearing component structure and the energy absorption component structure as the fitness value;

[0012] Select parents from the initial population according to the fitness value;

[0013] Randomly perform crossover and mutation on the individuals in the parents to obtain an updated population. Take the updated population as the initial parents for the next round of iteration. Stop after reaching the maximum number of iterations, and obtain the finally solved simulation solution group according to the fitness value.

[0014] Randomly performing crossover and mutation on the individuals in the parents to obtain an updated population specifically includes:

[0015] Randomly select individuals from the parents for crossover, and exchange the bearing component structure, energy absorption component structure, material parameters, bearing component geometric parameters, or energy absorption component geometric parameters between two individuals to achieve crossover;

[0016] Randomly select individuals from the parents for mutation, and change the bearing component structure, energy absorption component structure, material parameters, bearing component geometric parameters, or energy absorption component geometric parameters of the individuals to achieve mutation.

[0017] Use computer-aided tools to simulate the vehicle collision of the solution group, specifically including:

[0018] Use the computer-aided tool CAE to perform vehicle collision simulation.

[0019] Use the finite element analysis method to judge the collision degree corresponding to each simulation solution after simulation, and take the simulation solution with the lowest collision degree as the final solution, specifically including:

[0020] Discretize the vehicle structure into individual finite elements;

[0021] Obtain the deformation amount received by the finite element and the energy absorption amount of the energy absorption component structure, and calculate the collision degree according to the deformation amount and the energy absorption amount.

[0022] Input the material parameters in the final solution into the pre-established classification model, and output the material name distribution of each vehicle component. Use the material name distribution to replace the material parameters in the final solution to obtain the anti-collision optimization result, specifically including:

[0023] Input the material parameters into the classification model in the form of a neural network, and output the material names of each component. Among them, the classification model is trained by a labeled training set, and label the material names in the final solution of the computer-aided tool to obtain the material name distribution.

[0024] According to the second aspect of the embodiments of the present invention, there is provided a vehicle anti-collision optimization device, including:

[0025] An initial solution module, which is used to generate an original solution group for the design of automotive components by using the bionics principle, use the original solution group as the initial solution of the genetic algorithm, and solve by using the genetic algorithm to obtain a simulation solution group, specifically used for:

[0026] Based on bionic structures including bones, honeycombs, and cell walls, generate the structures of the load-bearing components and energy-absorbing components of the vehicle; use the random generation method to randomly generate material parameters, geometric parameters of the load-bearing components, and geometric parameters of the energy-absorbing components;

[0027] Take the structures of the load-bearing components, the structures of the energy-absorbing components, the material parameters, the geometric parameters of the load-bearing components, and the geometric parameters of the energy-absorbing components as the original solutions, and generate a preset number of original solutions as the original solution group.

[0028] The process of the genetic algorithm is as follows:

[0029] Take the original solution group as the initial population, and calculate the sum of the weights of the structures of the individual load-bearing components and energy-absorbing components as the fitness value;

[0030] Select parents from the initial population according to the fitness value;

[0031] Randomly perform crossover and mutation on the individuals in the parents to obtain an updated population, take the updated population as the parents at the beginning of the next round of iteration, stop after reaching the maximum number of iterations, and obtain the finally solved simulation solution group according to the fitness value.

[0032] Randomly performing crossover and mutation on the individuals in the parents to obtain an updated population specifically includes:

[0033] Randomly select individuals from the parents for crossover, and exchange the structures of the load-bearing components, the structures of the energy-absorbing components, the material parameters, the geometric parameters of the load-bearing components, or the geometric parameters of the energy-absorbing components between two individuals to achieve crossover;

[0034] Randomly select individuals from the parents for mutation, and change the structures of the load-bearing components, the structures of the energy-absorbing components, the material parameters, the geometric parameters of the load-bearing components, or the geometric parameters of the energy-absorbing components of the individuals to achieve mutation.

[0035] A simulation module, which is used to simulate the vehicle collision of the solution group by using computer-aided tools, specifically used for:

[0036] Use the computer-aided tool CAE to perform vehicle collision simulation.

[0037] A finite element analysis module, which is used to judge the collision degree corresponding to each simulation solution after simulation by using the finite element analysis method, and take the simulation solution with the lowest collision degree as the final solution, specifically used for:

[0038] Discretize the vehicle structure into individual finite elements;

[0039] Obtain the deformation amount suffered by the finite element and the energy absorption amount of the energy absorption component structure, and calculate the collision degree according to the deformation amount and the energy absorption amount.

[0040] A material determination module is used to input the material parameters in the final solution into a pre-established classification model, output the material name distribution of each component of the vehicle, and replace the material parameters in the final solution with the material name distribution to obtain the anti-collision optimization result. Specifically, it is used for:

[0041] Input the material parameters into a classification model in the form of a neural network, output the material names of each component. Among them, the classification model is trained by a labeled training set, and label the material names in the final solution of the computer-aided tool to obtain the material name distribution.

[0042] According to the third aspect of the embodiments of the present invention, there is provided an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the computer program is executed by the processor, it implements the steps of the vehicle anti-collision optimization method provided in the first aspect of the present disclosure.

[0043] According to the fourth aspect of the embodiments of the present invention, there is provided a computer-readable storage medium, on which an implementation program for information transmission is stored. When the program is executed by the processor, it implements the steps of the vehicle anti-collision optimization method provided in the first aspect of the present disclosure.

[0044] The technical solutions provided by the embodiments of the present invention have the following beneficial effects: Using the bionics principle to generate the initial solution of the genetic algorithm for vehicle component design to ensure the stability of the vehicle structure, and on this basis, perform the genetic algorithm to obtain a solution for reducing vehicle weight; then simulate vehicle collisions with the help of computer-aided tools to obtain the optimal performance solution, which can verify the vehicle structure more strictly; and the material characteristics in the solution are initially represented as material parameters and finally mapped to the corresponding specific material names to improve the flexibility of material selection.

[0045] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. Description of the Drawings

[0046] In order to more clearly illustrate the technical solutions in one or more embodiments of this specification or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in this specification. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0047] Figure 1 is a flowchart of the vehicle collision avoidance optimization method according to an embodiment of the present invention;

[0048] Figure 2 is a schematic diagram of the first example of the bionic structure according to an embodiment of the present invention;

[0049] Figure 3 is a schematic diagram of the second example of the bionic structure according to an embodiment of the present invention;

[0050] Figure 4 is a schematic diagram of the vehicle collision avoidance optimization device according to an embodiment of the present invention;

[0051] Figure 5 is a schematic diagram of the electronic device according to an embodiment of the present invention. Detailed implementation manners

[0052] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the following will clearly and completely describe the technical solutions in one or more embodiments of this specification with reference to the accompanying drawings in one or more embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of this specification, rather than all the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this document.

[0053] Method embodiments

[0054] According to an embodiment of the present invention, a vehicle collision avoidance optimization method is provided. Figure 1 is a flowchart of the vehicle collision avoidance optimization method according to an embodiment of the present invention. As Figure 1 shown, the vehicle collision avoidance optimization method according to an embodiment of the present invention specifically includes:

[0055] In step S110, a set of original solutions for vehicle component design is generated using bionics principles, and the set of original solutions is used as the initial solution of the genetic algorithm. The genetic algorithm is used to solve and obtain a set of simulation solutions, which specifically includes:

[0056] Based on bionic structures including but not limited to bones, honeycombs, and cell walls, a load-bearing component structure and an energy-absorbing component structure of the vehicle are generated; Figure 2 is a schematic diagram of the first example of the bionic structure according to an embodiment of the present invention. As Figure 2 shown, it shows the cell wall structure of the bumper beam. Figure 3 is a schematic diagram of the second example of the bionic structure according to an embodiment of the present invention, showing the honeycomb structure of the energy absorber. Figure 2 and Figure 3 are only examples of a certain original solution, used to explain the application of bionic structures in vehicles;

[0057] The material parameters, the geometric parameters of the load-bearing components, and the geometric parameters of the energy-absorbing components are randomly generated by the random generation method; the geometric parameters are equivalent to the length, width, thickness, etc. of the component structure; after generating the geometric parameters and the component structure, the appearance and volume of the component can be determined. The material parameters refer to the relevant parameters of the material properties, such as the yield strength, density, etc. of the material;

[0058] The load-bearing components are the components that bear the main load and force transmission in the vehicle structure, and the energy-absorbing components are the components that effectively disperse the collision energy to reduce the impact force. The number of the above two types of components is not limited;

[0059] The load-bearing component structure, the energy-absorbing component structure, the material parameters, the geometric parameters of the load-bearing components, and the geometric parameters of the energy-absorbing components are used as the original scheme, and a preset number of original schemes are generated as the original scheme group.

[0060] The genetic algorithm process is as follows:

[0061] Taking the original scheme group as the initial population, calculate the sum of the weights of the load-bearing component structure and the energy-absorbing component structure of the individual as the fitness value. After determining the geometric parameters and the component structure, the volume can be obtained, and then the weight can be calculated in combination with the density information in the material parameters; in the embodiment of the present invention, since it is desired to reduce the weight while maintaining the strength of the vehicle body structure, and the strength is convenient to verify in the subsequent simulation, the weight value is used as the fitness value;

[0062] Select the parent generation from the initial population according to the fitness value, that is, select a certain amount of samples from the initial population as the parent generation according to the fitness value from high to low;

[0063] Randomly perform crossover and mutation on the individuals in the parent generation to obtain an updated population. Take the updated population as the parent generation at the beginning of the next round of iteration. Stop after reaching the maximum number of iterations, and obtain the finally solved simulation scheme group according to the fitness value.

[0064] Randomly performing crossover and mutation on the individuals in the parent generation to obtain an updated population specifically includes:

[0065] Randomly select individuals in the parent generation for crossover, and exchange the load-bearing component structure, the energy-absorbing component structure, the material parameters, the geometric parameters of the load-bearing components, or the geometric parameters of the energy-absorbing components between two individuals to achieve crossover. In the embodiment of the present invention, preferably, only the inconsistent parts between two individuals are exchanged. For example, if the load-bearing component structures of individual 1 and individual 2 are both honeycomb-shaped, randomly select one of the remaining four attributes for crossover;

[0066] Randomly select individuals in the parent generation for mutation, and change the load-bearing component structure, the energy-absorbing component structure, the material parameters, the geometric parameters of the load-bearing components, or the geometric parameters of the energy-absorbing components of the individual to achieve mutation.

[0067] In step S120, a computer-aided tool is used to simulate the vehicle collisions of the simulation scenario group, specifically including:

[0068] Use the computer-aided tool CAE to conduct vehicle collision simulations;

[0069] In the embodiments of the present invention, the collision simulations include four types: frontal collision, side collision, rear-end collision, and rollover collision. Preferably, in order to facilitate the statistical analysis of the collision severity, the same collision simulations are performed on all scenario individuals in the simulation scenario group, that is, the types of directions and impact forces are the same.

[0070] In step S130, the finite element analysis method is used to determine the collision severity corresponding to each simulation scenario after simulation, and the simulation scenario with the lowest collision severity is used as the final scenario, specifically including:

[0071] Discretize the vehicle structure into individual finite elements;

[0072] Obtain the deformation amount received by the finite elements and the energy absorption amount of the energy absorption component structure, and calculate the collision severity based on the deformation amount and the energy absorption amount;

[0073] Under the premise of the same impact force, the lower the deformation amount and the higher the energy absorption amount, the lower the collision severity and the stronger the anti-collision ability of the vehicle. In the embodiments of the present invention, the average method with threshold setting is used to calculate the collision severity, and it can also be replaced by other similar common methods;

[0074] The process of the average method with threshold setting is as follows: calculate the average deformation amount received by the finite elements within the collision area, match the level score in the pre-established deformation amount threshold rule according to the value, obtain the energy absorption value, and match the level score in the energy absorption threshold rule, and calculate the average value of the two level scores as the collision severity to screen out the final scenario;

[0075] It should be noted that during the process of establishing the threshold rule, the lower the deformation amount, the lower the level, and the higher the energy absorption amount, the lower the level.

[0076] In step S140, the material parameters in the final scenario are input into the pre-established classification model, and the output includes the material name distribution of each vehicle component. Use the material name distribution to replace the material parameters in the final scenario to obtain the anti-collision optimization result, specifically including:

[0077] Since the structure of the bearing component, the structure of the energy absorption component, the geometric parameters of the bearing component, and the geometric parameters of the energy absorption component in the final scenario are all in the final form of the anti-collision optimization result, only the material parameters are not clear enough, that is, only the material properties are obtained at this time, but the specific material names are unknown;

[0078] Input the material parameters into a classification model in the form of a neural network to output the material names of each component. Among them, the classification model is trained by a labeled training set. The input of the classification model is the features of the material parameters. Mark the material names in the final solution of the computer-aided tool to obtain the material name distribution.

[0079] Preferably, not all materials are suitable for automotive manufacturing design. Therefore, the training set only includes labels suitable for automotive manufacturing, so that the output result of the classification model not only approaches the numerical result in the material parameters, but also conforms to the automotive manufacturing industry standards as much as possible, avoiding the output of results with similar performance but too high price or other adverse situations.

[0080] In addition, in the field, the corresponding material is often matched according to the numerical value of the material parameter by using the numerical matching method, that is, the difference between each feature and the existing material is calculated in turn, and the material name to be obtained is the one with the smallest sum of differences. This method is prone to cause imbalance problems. For example, if one feature has a large difference from the corresponding material but other features have small differences, but the overall sum of differences is the smallest, making it the final result. If this feature is more important than other features in actual application, safety problems are likely to occur.

[0081] In the embodiment of the present invention, it is verified that new composite materials such as carbon fiber reinforced polymers and aluminum matrix composites can achieve better effects.

[0082] The method further includes:

[0083] In step S150, simulate the influence of the optimized result of vehicle collision prevention on environmental changes, such as temperature change, humidity change, ultraviolet radiation, etc., and conduct long-term load tests to simulate the continuous or intermittent loads that the vehicle may bear during daily use, and test the fatigue life and crack propagation of the vehicle structure.

[0084] In actual application, conduct intelligent monitoring and provide timely feedback to maintenance personnel when a collision is detected.

[0085] To sum up, aiming at the existing problems, the vehicle collision prevention optimization method of the present invention uses the bionics principle to generate the initial solution of the genetic algorithm for vehicle component design to ensure the stability of the vehicle structure. On this basis, the genetic algorithm is executed. The weight is used as the fitness value in the genetic algorithm to obtain a solution for reducing the vehicle weight; then, the computer-aided tool is used to simulate vehicle collisions to obtain the optimal performance solution, and the finite element analysis method is used to judge the degree of vehicle collision, which can verify the vehicle structure more strictly; and the material characteristics in the solution are initially represented as material parameters and finally mapped to the corresponding specific material names to improve the flexibility of material selection; overall, the safety performance of the vehicle in the event of a collision is improved.

[0086] Device Embodiment

[0087] According to an embodiment of the present invention, an anti-collision optimization device for an automobile is provided. Figure 4 It is a schematic diagram of the anti-collision optimization device for an automobile according to an embodiment of the present invention, as Figure 4 shown. The anti-collision optimization device for an automobile according to an embodiment of the present invention specifically includes:

[0088] An initial solution module 40, configured to generate an original solution group for the design of automobile components using the bionics principle, use the original solution group as the initial solution of the genetic algorithm, and solve using the genetic algorithm to obtain a simulation solution group. Specifically, it is used for:

[0089] Based on bionic structures including bones, honeycombs, and cell walls, generate the structures of the load-bearing components and energy-absorbing components of the automobile; use the random generation method to randomly generate material parameters, geometric parameters of the load-bearing components, and geometric parameters of the energy-absorbing components;

[0090] Take the structures of the load-bearing components, energy-absorbing components, material parameters, geometric parameters of the load-bearing components, and geometric parameters of the energy-absorbing components as the original solutions, and generate a preset number of original solutions as the original solution group.

[0091] The process of the genetic algorithm is as follows:

[0092] Take the original solution group as the initial population, and calculate the sum of the weights of the structures of the individual load-bearing components and energy-absorbing components as the fitness value;

[0093] Select the parent generation from the initial population according to the fitness value;

[0094] Randomly perform crossover and mutation on the individuals in the parent generation to obtain an updated population. Take the updated population as the parent generation at the beginning of the next round of iteration. Stop after reaching the maximum number of iterations, and obtain the finally solved simulation solution group according to the fitness value.

[0095] Randomly performing crossover and mutation on the individuals in the parent generation to obtain an updated population specifically includes:

[0096] Randomly select individuals in the parent generation for crossover, and exchange the structures of the load-bearing components, energy-absorbing components, material parameters, geometric parameters of the load-bearing components, or geometric parameters of the energy-absorbing components between two individuals to achieve crossover;

[0097] Randomly select individuals in the parent generation for mutation, and change the structures of the load-bearing components, energy-absorbing components, material parameters, geometric parameters of the load-bearing components, or geometric parameters of the energy-absorbing components of the individuals to achieve mutation.

[0098] A simulation module 42, configured to use a computer-aided tool to simulate the collision of the automobile in the simulation solution group. Specifically, it is used for:

[0099] Use the computer-aided tool CAE for vehicle collision simulation.

[0100] The finite element analysis module 44 is used to judge the collision degree corresponding to each simulation scheme after simulation by using the finite element analysis method, and take the simulation scheme with the lowest collision degree as the final scheme. Specifically, it is used for:

[0101] Discretize the vehicle structure into individual finite elements;

[0102] Obtain the deformation amount received by the finite element and the energy absorption amount of the energy absorption component structure, and calculate the collision degree according to the deformation amount and the energy absorption amount.

[0103] The material determination module 46 is used to input the material parameters in the final scheme into a pre-established classification model, output the material name distribution of each vehicle component, and replace the material parameters in the final scheme with the material name distribution to obtain the anti-collision optimization result. Specifically, it is used for:

[0104] Input the material parameters into the classification model in the form of a neural network, output the material names of each component. Among them, the classification model is trained by a labeled training set, and label the material names in the final scheme of the computer-aided tool to obtain the material name distribution.

[0105] In summary, in view of the existing problems, the vehicle anti-collision optimization device of the present invention generates the initial solution of the genetic algorithm for vehicle component design by using the bionics principle to ensure the stability of the vehicle structure. On this basis, execute the genetic algorithm, and use the weight as the fitness value in the genetic algorithm to obtain a scheme for reducing the vehicle weight; then simulate the vehicle collision with the help of a computer-aided tool to obtain the optimal performance scheme, and use the finite element analysis method to judge the vehicle collision degree, which can verify the vehicle structure more strictly; and the material characteristics in the scheme are initially represented as material parameters and finally mapped to the corresponding specific material names to improve the flexibility of material selection; the overall scheme improves the safety performance of the vehicle in the event of a collision.

[0106] Embodiment of the electronic device

[0107] Figure 5 It is a schematic diagram of the electronic device according to the embodiment of the present invention. The electronic device 500 may include at least one processor 510 and a memory 520. The processor 510 may execute instructions stored in the memory 520. The processor 510 is communicatively connected to the memory 520 through a data bus. In addition to the memory 520, the processor 510 may also be communicatively connected to an input device 530, an output device 540, and a communication device 550 through the data bus.

[0108] The processor 510 can be any conventional processor, such as a commercially available CPU. The processor can also include, for example, a Graphic Process Unit (GPU), a Field Programmable Gate Array (FPGA), a System on Chip (SOC), an Application Specific Integrated Circuit (ASIC), or a combination thereof.

[0109] The memory 520 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic memory, flash memory, magnetic disks, or optical disks.

[0110] In an embodiment of the present disclosure, executable instructions are stored in the memory 520. The processor 510 can read the executable instructions from the memory 520 and execute the instructions to implement all or part of the steps of the vehicle collision avoidance optimization method in any of the above exemplary embodiments.

[0111] Embodiment of computer-readable storage medium

[0112] In addition to the above methods and devices, an exemplary embodiment of the present disclosure can also be a computer program product or a computer-readable storage medium storing the computer program product. The computer product includes computer program instructions that can be executed by a processor to implement all or part of the steps described in the vehicle collision avoidance optimization method in any of the above exemplary embodiments.

[0113] The computer program product can be written in any combination of one or more programming languages for the program code to perform the operations of the embodiments of the present application. The programming languages include object-oriented programming languages, such as Java, C++, etc., and also include conventional procedural programming languages, such as the "C" language or similar programming languages, and scripting languages (e.g., Python). The program code can be executed entirely on the user computing device, partially on the user device, executed as a stand-alone software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0114] A computer-readable storage medium may adopt any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the readable storage medium include: a static random access memory (SRAM) with one or more electrically connected wires, an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic disk or an optical disk, or any suitable combination of the above.

[0115] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for optimizing vehicle collision avoidance, characterized in that: include: Generate an original solution group for automobile component design by using the bionics principle, use the original solution group as the initial solution of the genetic algorithm, and use the genetic algorithm to solve and obtain a simulation solution group; Using computer-aided tools to simulate the automobile collision of the simulation scenario group; Use the finite element analysis method to determine the collision degree corresponding to each simulation scheme after simulation, and take the simulation scheme with the lowest collision degree as the final scheme; The material parameters in the final solution are input into a pre-established classification model, and the output includes the material name distribution of each component of the automobile. The material name distribution is used to replace the material parameters in the final solution to obtain an anti-collision optimization result.

2. The method according to claim 1, characterized in that The original scheme group for generating automobile component design using bionic principles specifically includes: Generate the receiving component structure and energy absorbing component structure of the automobile based on the bionic structure including bones, honeycombs and cell walls; use the random generation method to randomly generate material parameters, receiving component geometric parameters and energy absorbing component geometric parameters; The receiving component structure, the energy absorbing component structure, the material parameters, the receiving component geometric parameters and the energy absorbing component geometric parameters are taken as original solutions, and a preset number of original solutions are generated as the original solution group.

3. The method according to claim 2, characterized in that The method of using a genetic algorithm to solve the simulation scheme group specifically includes: Taking the original solution group as the initial population, calculating the sum of the weights of the individual receiving component structures and the energy absorbing component structures as the fitness value; Selecting a parent from the initial population according to the fitness value; The individuals in the parent generation are randomly crossovered and mutated to obtain an updated population, and the updated population is used as the initial parent generation of the next round of iterations. The process stops after reaching a maximum number of iterations, and a final solution simulation solution group is obtained based on the fitness value.

4. The method according to claim 3, characterized in that The randomly performing crossover and mutation on the individuals in the parent generation to obtain the updated population specifically includes: Randomly select individuals in the parent generation for crossover, and exchange the receiving component structure, energy absorbing component structure, material parameters, receiving component geometric parameters or energy absorbing component geometric parameters between two individuals to achieve crossover; Individuals in the parent generation are randomly selected for mutation, and the receiving component structure, energy absorbing component structure, material parameters, receiving component geometric parameters or energy absorbing component geometric parameters of the individuals are changed to achieve mutation.

5. The method according to claim 1, characterized in that The using of computer-aided tools to simulate the automobile collision of the simulation scheme group specifically includes: using computer-aided tools CAE to perform automobile collision simulation.

6. The method according to claim 1, characterized in that The use of the finite element analysis method to determine the collision degree corresponding to each simulation scheme after simulation specifically includes: Discretize the vehicle structure into individual finite elements; The deformation amount of the finite element and the energy absorption amount of the energy absorbing component structure are obtained, and the collision degree is calculated according to the deformation amount and the energy absorption amount.

7. The method according to claim 1, characterized in that The material parameters in the final solution are input into a pre-established classification model, and the output includes the material name distribution of each component of the automobile, specifically including: The material parameters are input into a classification model in the form of a neural network, and the material names of the components are output, wherein the classification model is trained through a labeled training set, and the material names are annotated in a final solution of a computer-aided tool to obtain a material name distribution.

8. An automobile anti-collision optimization device, characterized in that: include: An initial solution module is used to generate an original solution group for automobile component design by using the bionics principle, and use the original solution group as the initial solution of the genetic algorithm to obtain a simulation solution group by using the genetic algorithm; A simulation module, used for simulating the automobile collision of the simulation scheme group using a computer-aided tool; A finite element analysis module is used to use the finite element analysis method to determine the collision degree corresponding to each simulation scheme after simulation, and take the simulation scheme with the lowest collision degree as the final scheme; The material determination module is used to input the material parameters in the final solution into a pre-established classification model, output the material name distribution of each component of the car, use the material name distribution to replace the material parameters in the final solution, and obtain the collision avoidance optimization result.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of the vehicle anti-collision optimization method as claimed in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an implementation program for information transmission, and when the program is executed by a processor, the steps of the vehicle anti-collision optimization method as described in any one of claims 1 to 7 are implemented.

Images