Optimization method and device of automobile collision simulation model, medium and equipment

Abstract

The invention provides an optimization method and device for an automobile collision simulation model, a medium and equipment, and the method comprises the steps: building an initial model of a simulation vehicle based on the vehicle parameters of the simulation vehicle; performing preliminary training on the initial model to obtain a preliminary training model; training the initial training model again to obtain a target model of the simulation vehicle; according to the method, an initial model of a simulation vehicle is constructed, the initial model is preliminarily trained by using historical collision simulation sequence data, rapid training is performed by using simulation data with a large data size, so that the whole vehicle model rapidly reaches a certain precision, and the preliminary training model is further trained by using experimental test sequence data, so that the accuracy of the whole vehicle model is improved. According to the method, the precision of the whole vehicle model is improved by adopting the test data with small data volume, and the training precision of the initial model is improved by selecting the historical collision simulation sequence data with large correlation with the experimental test sequence data, so that the efficiency and effect of model training and optimization are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of automobile crash simulation, and in particular to an automobile crash simulation model optimization method, device, medium and equipment. BACKGROUND

[0002] The simulation of automobile whole vehicle crash scenes is mainly realized through computer simulation software, and the structure and restraint system are analyzed and optimized through simulation of vehicle body structure deformation data and the like when the vehicle is in a crash, so as to improve the safety of the vehicle and reduce the injury value of the passengers.

[0003] At present, the finite element method is mainly used for simulation of the safety of the whole vehicle structure. The more the number of meshes when the finite element method is used, the higher the simulation calculation precision. Therefore, the mesh scale of the whole vehicle model established by the current automobile engineers is often large, which leads to a long calculation time of the model. In addition, a large number of calculation examples are required for the whole vehicle structure benchmarking, which leads to an excessively large calculation amount of the simulation model of the whole vehicle structure safety, prolongs the construction time of the simulation model of the whole vehicle structure, and reduces the efficiency of automobile crash simulation. SUMMARY

[0004] In order to solve the above technical problems, the present application is proposed. Embodiments of the present application provide an automobile crash simulation model optimization method, device, medium and equipment.

[0005] According to one aspect of the present application, an automobile crash simulation model optimization method is provided, which includes: constructing an initial model of a simulation vehicle based on vehicle parameters of the simulation vehicle; inputting historical crash simulation sequence data into the initial model to preliminarily train the initial model, to obtain a preliminary training model; inputting test sequence data into the preliminary training model to retrain the preliminary training model, to obtain a target model of the simulation vehicle; and the correlation between the historical crash simulation sequence data and the test sequence data is greater than a preset correlation threshold.

[0006] In an embodiment, the inputting of the historical crash simulation sequence data into the initial model to preliminarily train the initial model to obtain the preliminary training model includes: inputting the historical crash simulation sequence data into the initial model to obtain a first output result; calculating a first loss value based on the first output result and an observation value corresponding to the historical crash simulation sequence data; if the first loss value is greater than a preset first loss value threshold, adjusting the parameters of the initial model until the first loss value is less than or equal to the first loss value threshold, to obtain the preliminary training model.

[0007] In an embodiment, the adjusting the parameters of the initial model comprises: calculating a target function value of a plurality of data in the historical collision simulation sequence data; wherein the target function represents a first loss value of the corresponding data; calculating an optimal target function value, a target function value mean and a target function value standard deviation of the historical collision simulation sequence data; calculating a parameter adjustment step based on the optimal target function value, the target function value mean and the target function value standard deviation; and adjusting the parameters of the initial model based on the parameter adjustment step.

[0008] In an embodiment, the calculating a parameter adjustment step based on the optimal target function value, the target function value mean and the target function value standard deviation comprises: a calculation formula of the parameter adjustment step is: ; wherein, is a parameter adjustment step, is a regularization function, is a target function value mean, is an optimal target function value, is a target function value standard deviation, is a set threshold value.

[0009] In an embodiment, the historical collision simulation sequence data comprises a plurality of; wherein the preliminary training of the initial model by inputting the historical collision simulation sequence data into the initial model to obtain an initial training model comprises: calculating a correlation between each of the historical collision simulation sequence data and the test sequence data; if the correlation is greater than a correlation threshold value, selecting the corresponding historical collision simulation sequence data as target collision simulation sequence data; and inputting the target collision simulation sequence data into the initial model to preliminarily train the initial model to obtain the initial training model.

[0010] In an embodiment, the retraining of the initial training model by inputting the test sequence data into the initial training model to obtain a target model of the simulation vehicle comprises: inputting the test sequence data into the initial training model to obtain a second output result; calculating a second loss value based on the second output result and an observation value corresponding to the test sequence data; if the second loss value is greater than a preset second loss value threshold value, adjusting parameters of the initial training model until the second loss value is less than or equal to the second loss value threshold value to obtain the target model.

[0011] In an embodiment, the adjusting the parameters of the initial training model comprises: adjusting a parameter value of the initial training model; calculating a parameter error variable of the initial training model; and calculating a parameter error of the target model based on the parameter error of the initial training model and the parameter error variable.

[0012] According to another aspect of the present application, there is provided an apparatus for optimizing a simulation model of a vehicle collision, comprising: a model construction module configured to construct an initial model of a simulation vehicle based on vehicle parameters of the simulation vehicle; a preliminary training module configured to input historical collision simulation sequence data into the initial model to preliminarily train the initial model to obtain a preliminary trained model; and a re-training module configured to input test sequence data into the preliminary trained model to re-train the preliminary trained model to obtain a target model of the simulation vehicle; wherein a correlation between the historical collision simulation sequence data and the test sequence data is greater than a preset correlation threshold.

[0013] According to another aspect of the present application, there is provided a computer readable storage medium storing a computer program for performing any of the methods described above.

[0014] According to another aspect of the present application, there is provided an electronic device comprising: a processor; a memory for storing instructions executable by the processor; and the processor configured to perform any of the methods described above.

[0015] The method, apparatus, medium and device for optimizing a simulation model of a vehicle collision provided by the present application, by constructing an initial model of a simulation vehicle based on vehicle parameters of the simulation vehicle; inputting historical collision simulation sequence data into the initial model to preliminarily train the initial model to obtain a preliminary trained model; inputting test sequence data into the preliminary trained model to re-train the preliminary trained model to obtain a target model of the simulation vehicle; wherein a correlation between the historical collision simulation sequence data and the test sequence data is greater than a preset correlation threshold; that is, by constructing an initial model of a simulation vehicle, and preliminarily training the initial model using historical collision simulation sequence data, to quickly train using simulation data with a large amount of data, so that the whole vehicle model quickly reaches a certain accuracy, and further training the preliminary trained model using test sequence data, to improve the accuracy of the whole vehicle model using test data with a small amount of data, and selecting historical collision simulation sequence data with a large correlation with the test sequence data, to improve the training accuracy of the initial model, and then improve the efficiency and effect of model training and optimization. BRIEF DESCRIPTION OF DRAWINGS

[0016] The above and other objects, features and advantages of the present application will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings in which: like reference characters refer to the like elements throughout the drawings. The drawings provided in the present application are used to provide further understanding of the embodiments of the present application, and constitute a part of the specification, and are used to explain the present application together with the embodiments of the present application, and do not constitute a limitation of the present application. In the drawings, the same reference numerals generally refer to the same parts or steps throughout the drawings.

[0017] Figure 1 This is a flowchart illustrating an exemplary embodiment of the method for optimizing a car collision simulation model provided in this application.

[0018] Figure 2 This is a schematic diagram of the structure of an optimization device for a car collision simulation model provided in an exemplary embodiment of this application.

[0019] Figure 3 This is a structural diagram of an electronic device provided in an exemplary embodiment of this application. Detailed Implementation

[0020] Hereinafter, exemplary embodiments according to this application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this application, and not all embodiments of this application. It should be understood that this application is not limited to the exemplary embodiments described herein.

[0021] Figure 1 This is a flowchart illustrating an exemplary embodiment of the method for optimizing a car collision simulation model provided in this application. Figure 1 As shown, the optimization method for this car crash simulation model includes the following steps: Step 110: Based on the vehicle parameters of the simulated vehicle, construct the initial model of the simulated vehicle.

[0022] This application is based on finite element software, which combines vehicle parameters of the simulated vehicle (such as vehicle type, shape, size and stiffness) to establish a whole vehicle model according to the collision conditions. The software includes, but is not limited to, Perimer, HyperWorks, ANSA, etc. The collision conditions include, but are not limited to, frontal 50 km / h 100% collision (50FRB), frontal 50 km / h 40% overlap deformable barrier collision (64ODB), frontal 50% overlap moving progressive deformable barrier collision test (50MPDB), etc.

[0023] Step 120: Input the historical collision simulation sequence data into the initial model to perform preliminary training on the initial model and obtain the initial trained model.

[0024] After constructing an initial model of the simulated vehicle, this application acquires historical collision simulation sequence data and inputs this data into the initial model for preliminary training, resulting in a pre-trained model. The training process may involve parameterizing the initial model to obtain a model function.

[0025] in, To input the observed numerical function, To pass through variables x The function equations of the initial model (x may be controllable variables (including size or shape of the product, etc.) and uncontrollable variables (including material properties, structural mass and stiffness, etc.), is an unknown regression coefficient, is a model bias or model error, is a measurement error (assuming Gaussian noise, which is x independent of everything else).

[0026] The present application can define = 1 to simplify the training process of the simulation model, and the simplified model function is: ; the present application improves the accuracy of the simulation model by controlling the error .

[0027] Step 130: input the test sequence data into the initial training model to retrain the initial training model, and obtain the target model of the simulation vehicle.

[0028] The correlation between the historical crash simulation sequence data and the test sequence data is greater than a preset correlation threshold. After the initial model is preliminarily trained by using the historical crash simulation sequence data, the initial training model is trained by using the test sequence data whose correlation with the historical crash simulation sequence data is greater than the preset correlation threshold, so as to improve the accuracy of the simulation model and obtain a simulation model with high accuracy.

[0029] The present application provides an optimization method of a vehicle crash simulation model. The initial model of a simulation vehicle is constructed based on the vehicle parameters of the simulation vehicle. The initial training model is obtained by preliminarily training the initial model by using the historical crash simulation sequence data. The target model of the simulation vehicle is obtained by retraining the initial training model by using the test sequence data. The correlation between the historical crash simulation sequence data and the test sequence data is greater than a preset correlation threshold. The initial model of the simulation vehicle is constructed, and the initial model is preliminarily trained by using the historical crash simulation sequence data, so that the simulation data with a large amount of data is used for rapid training, the whole vehicle model quickly reaches a certain accuracy, and the test sequence data is used for further training of the initial training model, so that the test data with a small amount of data is used to improve the accuracy of the whole vehicle model. The historical crash simulation sequence data with a large correlation with the test sequence data is selected to improve the training accuracy of the initial model, and then the efficiency and effect of the model training and optimization are improved.

[0030] In an embodiment, the specific implementation of the step 120 can be: inputting the historical collision simulation sequence data into the initial model to obtain a first output result; calculating a first loss value based on the first output result and the observation value corresponding to the historical collision simulation sequence data; if the first loss value is greater than a preset first loss value threshold, adjusting the parameters of the initial model until the first loss value is less than or equal to the first loss value threshold to obtain a preliminary trained model.

[0031] The application predicts the historical collision simulation sequence data by using the initial parameters of the initial model to obtain a first output result, then calculates the difference between the first output result and the observation value corresponding to the historical collision simulation sequence data to obtain a first loss value, adjusts the parameters of the initial model if the first loss value is large until the first output result and the observation value corresponding to the historical collision simulation sequence data are close, and then it is considered that the training of the initial model is completed. The calculation formula (i.e. the objective function) of the first loss value is:

[0032] Wherein, J the first loss value, the observation value corresponding to the historical collision simulation sequence data, the first output result, the error parameter to be adjusted (corresponding to the error), the number of historical collision simulation sequence data.

[0033] In an embodiment, the specific implementation of the step 120 can be: calculating the objective function values of a plurality of data in the historical collision simulation sequence data; wherein the objective function represents the first loss value of the corresponding data; calculating the optimal objective function value, the mean value of the objective function value and the standard deviation of the objective function value of the historical collision simulation sequence data; calculating the parameter adjustment step based on the optimal objective function value, the mean value of the objective function value and the standard deviation of the objective function value; adjusting the parameters of the initial model based on the parameter adjustment step.

[0034] The application calculates the objective function values of a plurality of data in the historical collision simulation sequence data, calculates the optimal objective function value, the mean value of the objective function value and the standard deviation of the objective function value of the historical collision simulation sequence data based on the objective function values, calculates the parameter adjustment step based on the optimal objective function value, the mean value of the objective function value and the standard deviation of the objective function value, and adjusts the parameters of the initial model according to the parameter adjustment step, thereby realizing the iterative updating of the parameters of the initial model.

[0035] In an embodiment, the specific implementation of the step 120 can be: the calculation formula of the parameter adjustment step is: ​​wherein, is a parameter adjustment step size, is a regularization function, is a target function value mean, is an optimal target function value, is a target function value standard deviation, is a set threshold value.

[0036] In an embodiment, the historical crash simulation sequence data comprises a plurality of; wherein the specific implementation manner of the step 120 can be: calculating the correlation between each historical crash simulation sequence data and the test test sequence data; if the correlation is greater than a correlation threshold value, the corresponding historical crash simulation sequence data is selected as the target crash simulation sequence data; and the target crash simulation sequence data is input into the initial model to preliminarily train the initial model to obtain a preliminary training model.

[0037] After obtaining a plurality of historical crash simulation sequence data, since the vehicle models and vehicle parameters corresponding to different historical crash simulation sequence data can be different, the application screens the obtained plurality of historical crash simulation sequence data to obtain the historical crash simulation sequence data closest to the simulation vehicle. Specifically, the application calculates the correlation between the historical crash simulation sequence data and the test test sequence data, and if the correlation is greater than a correlation threshold value, the corresponding historical crash simulation sequence data is selected as the target crash simulation sequence data, and all the target crash simulation sequence data screened is input into the initial model to preliminarily train the initial model to obtain a preliminary training model. The correlation calculation formula between the historical crash simulation sequence data and the test test sequence data is: ; wherein, is the correlation, and are the first values in the historical crash simulation sequence data and the test test sequence data, i and are the average values in the historical crash simulation sequence data and the test test sequence data, is the number of historical crash simulation sequence data. In an embodiment, the specific implementation manner of the step 130 can be: inputting the test test sequence data into the preliminary training model to obtain a second output result; based on the second output result and the observation value corresponding to the test test sequence data, a second loss value is calculated; if the second loss value is greater than a preset second loss value threshold value, the parameters of the preliminary training model are adjusted until the second loss value is less than or equal to the second loss value threshold value, and a target model is obtained.

[0038]

[0039] ​The application utilizes the initial training model to predict historical collision simulation sequence data to obtain a second output result, then calculates the difference between the second output result and the observation value corresponding to the test sequence data to obtain a second loss value, adjusts the parameter of the initial training model if the second loss value is large, and until the second output result and the observation value corresponding to the test sequence data are close, which indicates that the training of the initial training model is completed.

[0040] In an embodiment, the specific implementation of the above step 130 can be: adjusting the parameter value of the initial training model; calculating the parameter error variable of the initial training model; and calculating the parameter error of the target model based on the parameter error of the initial training model and the parameter error variable.

[0041] In the adjustment of the initial training model, the parameters of the initial training model are divided into parameter values and parameter errors, and the adjustment of the initial training model is realized by adjusting the parameter values and parameter errors of the initial training model. After the initial training model is trained, the parameter error of the initial training model is fixed when the initial training model is trained again by using the test sequence data, and the parameter error of the final target model is modified by the additional error (i.e. parameter error variable) generated in the test sequence data, i.e. the parameter error of the target model = the parameter error of the initial training model + the parameter error variable.

[0042] Figure 2 is a structural schematic diagram of an optimization device of a car collision simulation model provided by an exemplary embodiment of the application. As shown in Figure 2 The optimization device 20 of the car collision simulation model includes: a model construction module 21, configured to construct an initial model of a simulation vehicle based on vehicle parameters of the simulation vehicle; a preliminary training module 22, configured to input historical collision simulation sequence data into the initial model to preliminarily train the initial model to obtain an initial training model; and a retraining module 23, configured to input test sequence data into the initial training model to retrain the initial training model to obtain a target model of the simulation vehicle; wherein the correlation between the historical collision simulation sequence data and the test sequence data is greater than a preset correlation threshold.

[0043] The application provides an optimization device of a vehicle collision simulation model. An initial model of a simulation vehicle is constructed based on vehicle parameters of the simulation vehicle by a model construction module 21. A preliminary training module 22 inputs historical collision simulation sequence data into the initial model to preliminarily train the initial model, and obtains an initial training model. A retraining module 23 inputs test sequence data into the initial training model to retrain the initial training model, and obtains a target model of the simulation vehicle. The correlation between the historical collision simulation sequence data and the test sequence data is greater than a preset correlation threshold. The initial model of the simulation vehicle is constructed, and the initial model is preliminarily trained by using the historical collision simulation sequence data, so that the simulation data with a large amount of data is used for rapid training, the vehicle model reaches a certain precision quickly, the test sequence data is used to further train the initial training model, the test data with a small amount of data is used to improve the precision of the vehicle model, the historical collision simulation sequence data with a large correlation with the test sequence data is selected to improve the training precision of the initial model, and then the efficiency and effect of model training and optimization are improved.

[0044] In an embodiment, the preliminary training module 22 can be further configured to input the historical collision simulation sequence data into the initial model to obtain a first output result, calculate a first loss value based on the first output result and an observation value corresponding to the historical collision simulation sequence data, and adjust the parameters of the initial model until the first loss value is less than or equal to a preset first loss value threshold to obtain the initial training model if the first loss value is greater than the first loss value threshold.

[0045] In an embodiment, the preliminary training module 22 can be further configured to calculate target function values of a plurality of data in the historical collision simulation sequence data, wherein the target function represents a first loss value of the corresponding data, calculate an optimal target function value, a target function value mean and a target function value standard deviation of the historical collision simulation sequence data, calculate a parameter adjustment step based on the optimal target function value, the target function value mean and the target function value standard deviation, and adjust the parameters of the initial model based on the parameter adjustment step.

[0046] In an embodiment, the preliminary training module 22 can be further configured to have a calculation formula of the parameter adjustment step as follows: ; Wherein, is the parameter adjustment step, is a regularization function, is the target function value mean, is the optimal target function value, is the target function value standard deviation, is a preset threshold.

[0047] In one embodiment, the historical collision simulation sequence data includes multiple data sets; wherein, the aforementioned preliminary training module 22 can be further configured to: calculate the correlation between each historical collision simulation sequence data set and the experimental test sequence data; if the correlation is greater than the correlation threshold, select the corresponding historical collision simulation sequence data set as the target collision simulation sequence data set; input the target collision simulation sequence data set into the initial model to perform preliminary training on the initial model, thereby obtaining the initial training model.

[0048] In one embodiment, the retraining module 23 can be further configured to: input experimental test sequence data into the initial training model to obtain a second output result; calculate a second loss value based on the second output result and the observation value corresponding to the experimental test sequence data; if the second loss value is greater than a preset second loss value threshold, adjust the parameters of the initial training model until the second loss value is less than or equal to the second loss value threshold to obtain the target model.

[0049] In one embodiment, the retraining module 23 can be further configured to: adjust the parameter values ​​of the initial training model; calculate the parameter error variable of the initial training model; and calculate the parameter error of the target model based on the parameter error and parameter error variable of the initial training model.

[0050] Below, for reference Figure 3 This application describes an electronic device according to embodiments thereof. The electronic device may be either or both of a first device and a second device, or a standalone device independent of them, which may communicate with the first device and the second device to receive acquired input signals from them.

[0051] Figure 3 A block diagram of an electronic device according to an embodiment of this application is illustrated.

[0052] like Figure 3 As shown, the electronic device 10 includes one or more processors 11 and memory 12.

[0053] The processor 11 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

[0054] The memory 12 can include one or more computer program products that can include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory, for example, can include random access memory (RAM), cache memory, and / or the like. The non-volatile memory, for example, can include read only memory (ROM), hard disk drives, solid state drives, and / or the like. The computer-readable storage media can store one or more computer program instructions implementing the methods of the embodiments of the present application described above and / or other desired function. Various contents such as input signals, signal components, noise components, and the like can also be stored in the computer-readable storage media.

[0055] In one example, the electronic device 10 can further include an input device 13 and an output device 14, which are interconnected through a bus system and / or other forms of connection mechanisms (not shown).

[0056] When the electronic device is a stand-alone device, the input device 13 can be a communication network connector for receiving acquired input signals from the first device and the second device.

[0057] In addition, the input device 13 can further include, for example, a keyboard, a mouse, and the like.

[0058] The output device 14 can output various information including determined distance information, direction information, and the like to the outside. The output device 14 can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.

[0059] Of course, in order to simplify, Figure 3 Only some of the components in the electronic device 10 related to the present application are shown in FIG. 1, and components such as buses, input / output interfaces, and the like are omitted. In addition, the electronic device 10 can include any other appropriate components according to the specific application.

[0060] In addition to the above-described methods and devices, embodiments of the present application can be a computer program product including computer program instructions that, when executed by a processor, cause the processor to perform the steps of the methods according to the embodiments of the present application described in the above "Exemplary Methods" section of the specification.

[0061] The computer program product can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computing device, partly on the user's computing device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device or entirely on the remote computing device or server. The embodiments of the present application are not limited by the

[0062] In addition, an embodiment of the present application can also be a computer readable storage medium, which stores computer program instructions, and when the computer program instructions are run on a processor, the processor executes the steps of the methods according to various embodiments of the present application described in the above "Exemplary Methods" section of the specification.

[0063] The computer readable storage medium can be any combination of one or more computer readable media. The computer readable medium can be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any suitable combination of the above. More specific examples (a non-exhaustive list) of the computer readable storage medium include an electrical connection having one or more wires, a portable disc, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0064] The above describes the basic principles of the present application in combination with specific embodiments, but it should be noted that the advantages, advantages, effects and the like mentioned in the present application are only examples and are not limiting, and these advantages, advantages, effects and the like cannot be considered as the must-have of each embodiment of the present application. In addition, the above specific details are only for the purpose of example and understanding, and are not limiting, and the above details do not limit the present application to the must-have of the above specific details.

[0065] The block diagrams of devices, apparatuses, devices, and systems involved in this application are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0066] It should also be noted that in the apparatus, equipment, and methods of this application, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions of this application.

[0067] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this application. Therefore, this application is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0068] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this application to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A method of optimizing a car crash simulation model, characterized in that, The method comprises: constructing an initial model of a simulation vehicle based on vehicle parameters of the simulation vehicle; inputting historical crash simulation sequence data into the initial model to preliminarily train the initial model, to obtain an initial training model; inputting test sequence data into the initial training model to retrain the initial training model, to obtain a target model of the simulation vehicle; wherein a correlation between the historical crash simulation sequence data and the test sequence data is greater than a preset correlation threshold.

2. The method of optimizing an automotive crash simulation model according to claim 1, wherein, The method of inputting the historical crash simulation sequence data into the initial model to preliminarily train the initial model, to obtain an initial training model comprises: inputting the historical crash simulation sequence data into the initial model to obtain a first output result; calculating a first loss value based on the first output result and an observation value corresponding to the historical crash simulation sequence data; if the first loss value is greater than a preset first loss value threshold, adjusting parameters of the initial model until the first loss value is less than or equal to the first loss value threshold, to obtain the initial training model.

3. The method of optimizing an automotive crash simulation model of claim 2, wherein, The method of adjusting the parameters of the initial model comprises: calculating target function values of a plurality of data in the historical crash simulation sequence data; wherein the target function represents a first loss value of the corresponding data; calculating an optimal target function value, a target function value mean and a target function value standard deviation of the historical crash simulation sequence data; calculating a parameter adjustment step based on the optimal target function value, the target function value mean and the target function value standard deviation; adjusting the parameters of the initial model based on the parameter adjustment step.

4. The method of optimizing an automotive crash simulation model of claim 3, wherein, The method of calculating the parameter adjustment step based on the optimal target function value, the target function value mean and the target function value standard deviation comprises: a calculation formula of the parameter adjustment step is: ； wherein, is a parameter adjustment step size, is a regularization function, is a mean of objective function values, is an optimal objective function value, is a standard deviation of objective function values, is a set threshold value.

5. The method of optimizing an automotive crash simulation model of claim 1, wherein, The historical crash simulation sequence data comprises a plurality of historical crash simulation sequence data; wherein the method of inputting the historical crash simulation sequence data into the initial model to preliminarily train the initial model, to obtain an initial training model comprises: calculating a correlation between each of the historical crash simulation sequence data and the test sequence data; if the correlation is greater than the correlation threshold, selecting the corresponding historical crash simulation sequence data as target crash simulation sequence data; inputting the target crash simulation sequence data into the initial model to preliminarily train the initial model, to obtain the initial training model.

6. The method of optimizing an automotive crash simulation model of claim 1, wherein, The method of inputting the test sequence data into the initial training model to retrain the initial training model, to obtain a target model of the simulation vehicle comprises: inputting the test sequence data into the initial training model to obtain a second output result; calculating a second loss value based on the second output result and an observation value corresponding to the test sequence data; if the second loss value is greater than a preset second loss value threshold, adjusting parameters of the initial training model until the second loss value is less than or equal to the second loss value threshold, to obtain the target model.

7. The method of optimizing an automotive crash simulation model of claim 6, wherein, The method of adjusting the parameters of the initial training model comprises: adjusting parameter values of the initial training model; calculating a parameter error variable of the initial training model; Based on the parameter error of the initial training model and the parameter error variable, a parameter error of the target model is calculated.

8. An optimization device of a vehicle crash simulation model, characterized by, The method comprises the steps of: a model construction module, configured to construct an initial model of a simulation vehicle based on vehicle parameters of the simulation vehicle; an initial training module, configured to input historical collision simulation sequence data into the initial model to perform initial training on the initial model, to obtain an initial training model; a re-training module, configured to input test sequence data into the initial training model to perform re-training on the initial training model, to obtain a target model of the simulation vehicle; wherein a correlation between the historical collision simulation sequence data and the test sequence data is greater than a preset correlation threshold.

9. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, and the computer program is used for executing the method in any one of claims 1-7.

10. An electronic device, comprising: The method comprises the steps of: a processor; a memory for storing instructions executable by the processor; the processor is configured to execute the method in any one of claims 1-7.

Images