A prediction method for damage evaluation index of automobile collision dummy

Through the prediction method of vehicle collision dummy damage evaluation index based on simulation and neural network, the problem of dummy design in the prior art is solved, and a rapid prediction and occupant constraint system for damage situations of multiple populations is realized. The optimized design reduces cost and time.

CN118296913BActive Publication Date: 2024-11-05CHINA AUTOMOTIVE TECH & RES CENT CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410666411.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-05-28
Publication Date
2024-11-05
Estimated Expiration
2044-05-28

AI Technical Summary

Technical Problem

In existing automobile collision tests, it is difficult for the designed dummies to accurately characterize the injuries caused by human bodies with diverse body shapes during the collision, resulting in the inability of vehicle occupants to comprehensively protect multiple groups of people, and the development of new dummies is expensive and simulated. The model parameterized transformation costs are low.

Method used

The damage evaluation index prediction method of automobile collision dummy based on simulation and neural network is adopted. By inputting multiple sets of collision dummy sign parameters, the damage evaluation index is obtained, and the neural network is trained to build a prediction model to realize the damage prediction of dummy with different sign parameters.

Benefits of technology

It realizes rapid prediction of damage situations in multiple populations, guides the optimization design of the occupant constraint system, improves the comprehensive protection ability of vehicles to multiple populations, reduces manpower and material resources, and reduces simulation experiment time.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118296913B_ABST
    Figure CN118296913B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of automobile safety collision simulation, and in particular, to a method for predicting damage evaluation indicators of automobile collision dummies. The method comprises: inputting multiple groups of collision dummy physical sign parameters into a simulation system to obtain damage evaluation indicators corresponding to each group of collision dummy physical sign parameters; the damage evaluation indicators include damage evaluation indicators of multiple target parts and comprehensive damage evaluation indicators; using the physical sign parameters and the damage evaluation indicators to train a neural network to construct a damage evaluation indicator prediction model; inputting the physical sign parameters of the collision dummy to be tested into the prediction model to obtain a predicted value of the damage evaluation indicator. The method is based on simulation and neural networks, and can obtain the correlation between the physical sign parameters of the collision dummy and the damage evaluation indicators, and can then predict the damage conditions of dummies with different physical sign parameters.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the field of automobile safety collision simulation, and in particular to a method for predicting damage evaluation indicators of automobile collision dummies. Background Art

[0002] With the continuous development of the automobile industry and technology, the safety performance of automobiles has received more and more attention. How to reduce the damage caused by traffic accidents to passengers in the car and improve the safety performance of automobiles is the focus of research in today's automobile industry.

[0003] At present, the dummies that are widely used in automobile collision tests are designed based on the 5th, 50th or 95th percentile human body signs, which makes it difficult to accurately characterize the injuries of people of other percentiles or other body types during automobile collisions. People have different body shapes and characteristics. This approach cannot fully take into account the needs and safety performance of all people, and cannot accurately predict the injuries caused by people of diverse body types during collisions. As a result, the vehicle occupant restraint system can only provide the greatest protection for people of a specific percentile, without comprehensively measuring the protection for people of various body types. In addition, since it is very expensive to develop a new dummy, and each dummy can only represent a group of people with one physical sign, the cost of parameterizing the finite element model through mesh deformation technology is relatively low, and the occupant's physical signs can be changed by changing the physical sign parameters of different parts of the dummy. Therefore, based on the simulation model, the intrinsic relationship between the dummy's physical sign parameters and its injury indicators is explored, and then a prediction method for the correlation between the physical sign parameters and injury indicators of a car collision dummy is developed. This can predict the damage to key parts of the dummy when the physical sign parameters change, which is of great significance for guiding the design of the occupant restraint system and improving the comprehensive protection capability of the restraint system for various groups of people.

[0004] In view of this, the present invention is proposed. Summary of the invention

[0005] The purpose of the present invention is to provide a prediction method for automobile collision dummy damage evaluation indexes. The method is based on simulation and neural network, and can obtain the correlation between the collision dummy's physical sign parameters and the damage evaluation index, and then can predict the damage of dummies with different physical sign parameters.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] In a first aspect, the present invention provides a method for predicting damage evaluation indicators of a vehicle collision dummy, comprising:

[0008] Inputting multiple groups of collision dummy body sign parameters into the simulation system, and obtaining damage evaluation indicators corresponding to each group of collision dummy body sign parameters; the damage evaluation indicators include damage evaluation indicators of multiple target parts and a comprehensive damage evaluation indicator;

[0009] Using the physical sign parameters and the damage evaluation index to train a neural network and construct a damage evaluation index prediction model;

[0010] The body sign parameters of the collision dummy to be tested are input into the prediction model to obtain the predicted value of the damage evaluation index.

[0011] As a further preferred technical solution, the multiple groups of collision dummy body sign parameters are input into the simulation system to obtain the damage evaluation index corresponding to each group of collision dummy body sign parameters, including:

[0012] Input multiple groups of collision dummy body sign parameters into the simulation system to obtain the change curves of target indicators of multiple groups of collision dummies during the collision process;

[0013] According to the change curve of the target index, the damage evaluation index and the comprehensive damage evaluation index of the target part are determined respectively.

[0014] As a further preferred technical solution, the multiple groups of collision dummy physical sign parameters are input into the simulation system to obtain the change curves of the target indicators of the multiple groups of collision dummies during the collision process, including:

[0015] Inputting multiple groups of collision dummy physical sign parameters into the simulation system;

[0016] According to the physical sign parameters, key nodes corresponding to the physical sign parameters are driven to change positions, thereby completing the construction of multiple groups of finite element dummies;

[0017] Primer is called to perform H-point alignment, sitting posture adjustment, seat foam compression, and seat belt setting; Lsdyna is called to perform simulation calculations to obtain the change curves of target indicators of multiple groups of collision dummies during the collision process.

[0018] As a further preferred technical solution, the comprehensive damage evaluation index is calculated using the following formula:

[0019] ;

[0020] Among them, WIC is the comprehensive damage evaluation index, HIC 15 is the head injury index, a 3ms N is the head's accumulated 3ms synthetic acceleration value. ijis the neck injury index, s1 is the chest compression deformation, VC is the chest viscosity index, F1 is the thigh compression force, s2 is the knee sliding displacement, TI is the tibia index, and F2 is the calf compression force; α1, α2, α3, α4, α5, α6, α7, α8, and α9 represent the weights of each evaluation index, satisfying α1+α2+α3+α4+α5+α6+α7+α8+α9=1, 0≤α1,α2,α3,α4,α5,α6,α7,α8,α9≤1.

[0021] As a further preferred technical solution, the use of the physical sign parameters and the injury assessment index to train a neural network and construct an injury assessment index prediction model includes:

[0022] Divide the multiple groups of physical sign parameters and the injury assessment indicators into three parts: a training set, a validation set and a test set; the training set accounts for 60%, the validation set accounts for 20%, and the test set accounts for 20%;

[0023] Inputting the physical sign parameters and the damage assessment index in the training set to train the BP neural network;

[0024] The physical sign parameters and the injury assessment indexes in the validation set are used to test whether the prediction model meets the accuracy requirements; if the accuracy requirements are met, the prediction model is confirmed to be successfully constructed; if the accuracy requirements are not met, back propagation is performed until a prediction model that meets the accuracy requirements is obtained.

[0025] As a further preferred technical solution, when training the BP neural network, forward propagation is first performed, and the function of the output layer is:

[0026] ;

[0027] Among them, s k is the predicted output value of the damage index of each target part, ψ is the activation function, and w ky is the weight from the hidden layer to the output layer, q k is the output value of the hidden layer, c k is the bias from the hidden layer to the output layer, t is the number of groups of vital sign parameters in the validation set;

[0028] The function of the hidden layer is:

[0029] ;

[0030] Among them, q k is the output value of the hidden layer, ψ is the activation function, w ik is the weight from the input layer to the hidden layer, a i is the value of the ith neuron, h j is the bias from the input layer to the hidden layer, and t is the number of groups of vital sign parameters in the validation set.

[0031] As a further preferred technical solution, the expected error E is used to determine whether the prediction model is successfully constructed:

[0032] ;

[0033] Among them, e k is the kth group of damage evaluation indicators in the validation set, s k is the injury assessment index learned through the kth group of physical sign parameters in the validation set, and t is the number of groups of physical sign parameters in the validation set;

[0034] If E<δ, it is confirmed that the prediction model is successfully constructed, and δ is the accuracy.

[0035] As a further preferred technical solution, in the back propagation process, the error is reduced by updating the weights and biases, and the weights are updated in the following manner:

[0036] ;

[0037] Among them, w ijhou is the updated weight from the input layer to the hidden layer, w ijqian is the weight from the input layer to the hidden layer before updating, w jk is the weight from the hidden layer to the input layer, q k is the output value of the hidden layer, e k is the kth group of damage evaluation indicators in the validation set, s k is the injury assessment index learned through the kth group of physical sign parameters in the validation set, a i is the value of the ith neuron, η is the learning rate, and t is the number of groups of sign parameters in the validation set;

[0038] The bias update method is:

[0039] ;

[0040] Among them, h jhou is the updated bias from the input layer to the hidden layer, h jqian is the bias from the input layer to the hidden layer before updating, η is the learning rate, q k is the output value of the hidden layer, w ky is the weight from the hidden layer to the output layer, e k is the kth group of damage evaluation indicators in the validation set, s k is the injury assessment index learned through the kth group of physical sign parameters in the validation set, and t is the number of groups of physical sign parameters in the validation set;

[0041] ;

[0042] Among them, ckhou is the updated bias from hidden layer to output layer, c kqian is the bias from the hidden layer to the output layer before updating, η is the learning rate, e k is the kth group of damage evaluation indicators in the validation set, s k is the injury assessment index learned through the kth group of vital sign parameters in the validation set.

[0043] In a second aspect, the present invention provides an electronic device, comprising:

[0044] at least one processor, and a memory communicatively coupled to at least one of the processors;

[0045] The memory stores instructions that can be executed by at least one of the processors, and the instructions are executed by at least one of the processors so that at least one of the processors can perform the above method.

[0046] In a third aspect, the present invention provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to enable a computer to execute the above method.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] The prediction method of the damage evaluation index of the automobile collision dummy provided by the present invention inputs multiple groups of collision dummy physical sign parameters into the simulation system to obtain the damage evaluation index corresponding to each group of collision dummy physical sign parameters; the damage evaluation index includes damage evaluation indicators of multiple target parts and comprehensive damage evaluation indicators; the physical sign parameters and the damage evaluation indicators are used to train the neural network to construct a damage evaluation index prediction model; the physical sign parameters of the collision dummy to be tested are input into the prediction model to obtain the predicted value of the damage evaluation index. The method is based on simulation and neural network, and can obtain the correlation between the physical sign parameters of the collision dummy and the damage evaluation index, and then can quickly predict the damage of dummies with different physical sign parameters, which is of great significance for guiding the optimization design of the occupant restraint system and improving the comprehensive protection ability of the vehicle for various groups of people. At the same time, it can also reduce manpower and material resources and reduce the time engineers spend on simulation experiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1It is a flow chart of a method for predicting damage evaluation indexes of a car collision dummy provided by the present invention;

[0051] Figure 2 It is a structural schematic diagram of a device for predicting damage evaluation indexes of a collision dummy provided by the present invention;

[0052] Figure 3 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0053] The following is a description of exemplary embodiments of the present application in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0054] Example 1

[0055] Figure 1 This is a flow chart of a method for predicting a damage evaluation index of a car collision dummy provided in this embodiment. The method can be executed by a prediction device for a damage evaluation index of a collision dummy. The device can be composed of software and / or hardware and is generally integrated in an electronic device. The electronic device can be a computer or other mobile terminal (such as a smart phone, a tablet computer, etc.). For ease of understanding, each step in the control method of this embodiment is executed by a computer.

[0056] like Figure 1 As shown, this embodiment provides a method for predicting damage evaluation indicators of a car collision dummy, comprising the following steps:

[0057] S110, inputting multiple groups of collision dummy body sign parameters into a simulation system to obtain damage evaluation indicators corresponding to each group of collision dummy body sign parameters; the damage evaluation indicators include damage evaluation indicators of multiple target parts and a comprehensive damage evaluation indicator.

[0058] Furthermore, the inputting of multiple groups of collision dummy body sign parameters into the simulation system to obtain the damage assessment index corresponding to each group of collision dummy body sign parameters includes:

[0059] Input multiple groups of collision dummy body sign parameters into the simulation system to obtain the change curves of target indicators of multiple groups of collision dummies during the collision process;

[0060] According to the change curve of the target index, the damage evaluation index and the comprehensive damage evaluation index of the target part are determined respectively.

[0061] Furthermore, the multiple groups of collision dummy physical sign parameters are input into the simulation system to obtain the change curves of the target indicators of the multiple groups of collision dummies during the collision process, including:

[0062] Inputting multiple groups of collision dummy physical sign parameters into the simulation system;

[0063] According to the physical sign parameters, key nodes corresponding to the physical sign parameters are driven to change positions, thereby completing the construction of multiple groups of finite element dummies;

[0064] Primer is called to perform H-point alignment, sitting posture adjustment, seat foam compression, and seat belt setting; Lsdyna is called to perform simulation calculations to obtain the change curves of target indicators of multiple groups of collision dummies during the collision process.

[0065] Optionally, in the simulation system: the model of the simulation system is a frontal collision simulation model, which is given the same basic parameters as the corresponding parts of the vehicle, such as materials and properties, and constructs constraints, contacts and other information, and applies gravity acceleration to the model. The vehicle acceleration curve during the collision is established and loaded onto the trolley model.

[0066] Specifically, after multiple sets of collision dummy physical sign parameters are input into the simulation system, multiple finite element dummies will be constructed, and a change curve of the target indicator can be obtained for each finite element dummy.

[0067] Optionally, after inputting multiple groups of collision dummy physical sign parameters into the simulation system, first determine whether the parameters are reasonable, and if not, feedback unreasonable results; if reasonable, proceed with subsequent finite element dummy construction and other processes.

[0068] Furthermore, the comprehensive damage evaluation index is calculated using the following formula:

[0069] ;

[0070] Among them, WIC is the comprehensive damage evaluation index, HIC 15 is the head injury index, a 3ms N is the head's accumulated 3ms synthetic acceleration value. ij is the neck injury index, s1 is the chest compression deformation, VC is the chest viscosity index, F1 is the thigh compression force, s2 is the knee sliding displacement, TI is the tibia index, and F2 is the calf compression force; α1, α2, α3, α4, α5, α6, α7, α8, and α9 represent the weights of each evaluation index, satisfying α1+α2+α3+α4+α5+α6+α7+α8+α9=1, 0≤α1,α2,α3,α4,α5,α6,α7,α8,α9≤1.

[0071] It should be noted that the injury evaluation index of the target part adopts the change curve of the target index and is scored according to the front dummy scoring method in the 2024 version of the "C-NCAP Management Rules". It should also be noted that the above target indicators include: head injury index, cumulative 3ms synthetic acceleration value of the head, neck injury index, chest compression deformation, chest viscosity index, thigh compression force, knee sliding displacement, tibia index, calf compression force. The above target parts include: head, neck, chest, thigh, calf. The above physical sign parameters include: head parameters, neck parameters, chest parameters, lower trunk parameters, upper limb parameters and lower limb parameters. The head parameters include head length, head height, and head circumference; the neck parameters include neck length and neck circumference; the chest parameters include chest thickness, chest height, and chest width; the lower torso parameters include hip width, hip circumference, and height from the top of the abdomen to the bottom of the hips; the upper limb parameters include upper arm length, upper arm circumference, forearm length, forearm circumference, hand length, and hand width; the lower limb parameters include thigh length, mid-thigh circumference, calf length, calf circumference, foot length, and foot width.

[0072] S120, using the physical sign parameters and the injury assessment index to train a neural network and construct an injury assessment index prediction model.

[0073] It should be understood that the “damage assessment index” herein refers to the damage assessment index corresponding to each group of collision dummy body sign parameters.

[0074] Furthermore, the use of the physical sign parameters and the damage assessment index to train a neural network and construct a damage assessment index prediction model includes:

[0075] Divide the multiple groups of physical sign parameters and the injury assessment indicators into three parts: a training set, a validation set and a test set; the training set accounts for 60%, the validation set accounts for 20%, and the test set accounts for 20%;

[0076] Inputting the physical sign parameters and the damage assessment index in the training set to train the BP neural network;

[0077] The physical sign parameters and the injury assessment indexes in the validation set are used to test whether the prediction model meets the accuracy requirements; if the accuracy requirements are met, the prediction model is confirmed to be successfully constructed; if the accuracy requirements are not met, back propagation is performed until a prediction model that meets the accuracy requirements is obtained.

[0078] Furthermore, when training the BP neural network, forward propagation is first performed, and the function of the output layer is:

[0079] ;

[0080] Among them, s k is the predicted output value of the damage index of each target part, ψ is the activation function, and w kyis the weight from the hidden layer to the output layer, q k is the output value of the hidden layer, c k is the bias from the hidden layer to the output layer, t is the number of groups of vital sign parameters in the validation set;

[0081] The function of the hidden layer is:

[0082] ;

[0083] Among them, q k is the output value of the hidden layer, ψ is the activation function, w ik is the weight from the input layer to the hidden layer, a i is the value of the ith neuron, h j is the bias from the input layer to the hidden layer, and t is the number of groups of vital sign parameters in the validation set.

[0084] Furthermore, the expected error E is used to determine whether the prediction model is successfully constructed:

[0085] ;

[0086] Among them, e k is the kth group of damage evaluation indicators in the validation set, s k is the injury assessment index learned through the kth group of physical sign parameters in the validation set, and t is the number of groups of physical sign parameters in the validation set;

[0087] If E<δ, it is confirmed that the prediction model is successfully constructed, and δ is the accuracy.

[0088] Furthermore, during the back-propagation process, the error is reduced by updating the weights and biases. The weights are updated as follows:

[0089] ;

[0090] Among them, w ijhou is the updated weight from the input layer to the hidden layer, w ijqian is the weight from the input layer to the hidden layer before updating, w jk is the weight from the hidden layer to the input layer, q k is the output value of the hidden layer, e k is the kth group of damage evaluation indicators in the validation set, s k is the injury assessment index learned through the kth group of physical sign parameters in the validation set, a i is the value of the ith neuron, η is the learning rate, and t is the number of groups of sign parameters in the validation set;

[0091] The bias update method is:

[0092] ;

[0093] Among them, h jhou is the updated bias from the input layer to the hidden layer, h jqian is the bias from the input layer to the hidden layer before updating, η is the learning rate, q k is the output value of the hidden layer, w ky is the weight from the hidden layer to the output layer, e k is the kth group of damage evaluation indicators in the validation set, s k is the injury assessment index learned through the kth group of physical sign parameters in the validation set, and t is the number of groups of physical sign parameters in the validation set;

[0094] ;

[0095] Among them, c khou is the updated bias from hidden layer to output layer, c kqian is the bias from the hidden layer to the output layer before updating, η is the learning rate, e k is the kth group of damage evaluation indicators in the validation set, s k is the injury assessment index learned through the kth group of vital sign parameters in the validation set.

[0096] S130, inputting the physical sign parameters of the collision dummy to be tested into the prediction model to obtain a predicted value of the damage assessment index.

[0097] The method provided in this embodiment is based on simulation and neural network, and can obtain the correlation between the physical parameters of the collision dummy and the damage evaluation index, and then can quickly predict the damage conditions of dummies with different physical parameters. This is of great significance for guiding the optimal design of the occupant restraint system and improving the comprehensive protection ability of the vehicle for various groups of people. At the same time, it can also reduce manpower and material resources and reduce the time engineers spend on simulation experiments.

[0098] Example 2

[0099] like Figure 2 As shown, this embodiment provides a prediction device for a collision dummy damage evaluation index, comprising:

[0100] The damage evaluation index determination module 201 is used to input multiple groups of collision dummy body sign parameters into the simulation system to obtain damage evaluation indicators corresponding to each group of collision dummy body sign parameters; the damage evaluation indicators include damage evaluation indicators of multiple target parts and comprehensive damage evaluation indicators;

[0101] A model building module 202, used to train a neural network using the physical sign parameters and the damage assessment index to build a damage assessment index prediction model;

[0102] The prediction module 203 is used to input the body sign parameters of the collision dummy to be tested into the prediction model to obtain the predicted value of the damage assessment index.

[0103] The device is used to execute the above method, and thus has at least functional modules and beneficial effects corresponding to the above method.

[0104] Example 3

[0105] like Figure 3 As shown, this embodiment provides an electronic device, including:

[0106] at least one processor; and

[0107] a memory communicatively connected to at least one of the processors; wherein,

[0108] The memory stores instructions executable by at least one of the processors, and the instructions are executed by at least one of the processors to enable at least one of the processors to perform the above method. At least one processor in the electronic device can perform the above method, and thus has at least the same advantages as the above method.

[0109] Optionally, the electronic device also includes interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the electronic device, including instructions stored in or on a memory to display graphical information of a GUI (Graphical User Interface) on an external input / output device (such as a display device coupled to an interface). In other embodiments, if necessary, multiple processors can be used together with multiple memories, and / or multiple buses can be used together with multiple memories. Similarly, multiple electronic devices can be connected (for example, as a server array, a group of blade servers, or a multi-processor system), and each device provides some necessary operations. Figure 3 A processor 301 is taken as an example.

[0110] The memory 302, as a computer-readable storage medium, can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the method for predicting the damage evaluation index of a car collision dummy in the embodiment of the present invention (for example, the damage evaluation index determination module, model building module, and prediction module in the device for predicting the damage evaluation index of a collision dummy). The processor 301 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 302, that is, realizes the above-mentioned method for predicting the damage evaluation index of a car collision dummy.

[0111] The memory 302 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 302 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 302 may further include a memory remotely arranged relative to the processor 301, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0112] The electronic device may further include: an input device 303 and an output device 304. The processor 301, the memory 302, the input device 303 and the output device 304 may be connected via a bus or other means. Figure 3 The example of connecting through bus is taken in the following.

[0113] The input device 303 can receive input digital or character information, and the output device 304 can include a display device, an auxiliary lighting device (e.g., LED), and a tactile feedback device (e.g., a vibration motor), etc. The display device can include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display, and a plasma display. In some embodiments, the display device can be a touch screen.

[0114] Example 4

[0115] This embodiment provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to enable a computer to execute the above method. The computer instructions on the computer-readable storage medium are used to enable a computer to execute the above method, and thus have at least the same advantages as the above method.

[0116] The medium in the present invention may adopt any combination of one or more computer-readable media. The medium may be a computer-readable signal medium or a computer-readable storage medium. The medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples of the medium (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, the medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device, or device.

[0117] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0118] The program code contained on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to wireless, wire, optical cable, RF (Radio Frequency), etc., or any suitable combination of the above.

[0119] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0120] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution disclosed in this application can be achieved, and this document is not limited here.

[0121] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A method for predicting damage evaluation index of a car collision dummy, characterized in that: include: Multiple groups of collision dummy body sign parameters are input into the simulation system to obtain damage evaluation indicators corresponding to each group of collision dummy body sign parameters; the damage evaluation indicators include damage evaluation indicators of multiple target parts and comprehensive damage evaluation indicators; the comprehensive damage evaluation indicators are calculated using the following formula: ; Among them, WIC is the comprehensive damage evaluation index, HIC 15 is the head injury index, a 3ms N is the head's accumulated 3ms synthetic acceleration value. ij is the neck injury index, s1 is the chest compression deformation, VC is the chest viscosity index, F1 is the thigh compression force, s2 is the knee sliding displacement, TI is the tibia index, and F2 is the calf compression force; α1, α2, α3, α4, α5, α6, α7, α8, α9 represent the weights of each evaluation index, satisfying α1+α2+α3+α4+α5+α6+α7+α8+α9=1, 0≤α1,α2,α3,α4,α5,α6,α7,α8,α9≤1; The physical sign parameters and the damage evaluation index are used to train a neural network and construct a damage evaluation index prediction model, including: dividing multiple groups of physical sign parameters and the damage evaluation index into three parts: a training set, a validation set and a test set; wherein the training set accounts for 60%, the validation set accounts for 20%, and the test set accounts for 20%; inputting the physical sign parameters and the damage evaluation index in the training set to train the BP neural network; using the physical sign parameters and the damage evaluation index in the validation set to check whether the prediction model meets the accuracy requirements; if the accuracy requirements are met, confirming that the prediction model is successfully constructed, if not, performing back propagation until a prediction model that meets the accuracy requirements is obtained; in the back propagation process, reducing the error by updating the weights and biases, and the weight update method is as follows: ; Among them, w ijhou is the updated weight from the input layer to the hidden layer, w ijqian is the weight from the input layer to the hidden layer before updating, w jk is the weight from the hidden layer to the input layer, q k is the output value of the hidden layer, e k is the kth group of damage evaluation indicators in the validation set, s k is the injury assessment index learned through the kth group of physical sign parameters in the validation set, a i is the value of the i-th neuron, η is the learning rate, and t is the number of groups of sign parameters in the validation set; the bias update method is: ; Among them, h jhou is the updated bias from the input layer to the hidden layer, h jqian is the bias from the input layer to the hidden layer before updating, η is the learning rate, q k is the output value of the hidden layer, w ky is the weight from the hidden layer to the output layer, e k is the kth group of damage evaluation indicators in the validation set, s k is the injury assessment index learned through the kth group of physical sign parameters in the validation set, and t is the number of groups of physical sign parameters in the validation set; ; Among them, c khou is the updated bias from hidden layer to output layer, c kqian is the bias from the hidden layer to the output layer before updating, η is the learning rate, e k is the kth group of damage evaluation indicators in the validation set, s k is the injury assessment index learned through the kth group of physical sign parameters in the validation set; The body sign parameters of the collision dummy to be tested are input into the prediction model to obtain the predicted value of the damage evaluation index.

2. The method for predicting damage evaluation index of a vehicle collision dummy according to claim 1, characterized in that: The multiple groups of collision dummy body sign parameters are input into the simulation system to obtain the damage evaluation index corresponding to each group of collision dummy body sign parameters, including: Input multiple groups of collision dummy body sign parameters into the simulation system to obtain the change curves of target indicators of multiple groups of collision dummies during the collision process; According to the change curve of the target index, the damage evaluation index and the comprehensive damage evaluation index of the target part are determined respectively.

3. The method for predicting damage evaluation index of a vehicle collision dummy according to claim 2, characterized in that: The multiple groups of collision dummy body sign parameters are input into the simulation system to obtain the change curves of the target indicators of the multiple groups of collision dummies during the collision process, including: Inputting multiple groups of collision dummy physical sign parameters into the simulation system; According to the physical sign parameters, key nodes corresponding to the physical sign parameters are driven to change positions, thereby completing the construction of multiple groups of finite element dummies; Primer is called to perform H-point alignment, sitting posture adjustment, seat foam compression, and seat belt setting; Lsdyna is called to perform simulation calculations to obtain the change curves of target indicators of multiple groups of collision dummies during the collision process.

4. The method for predicting damage evaluation index of a vehicle collision dummy according to claim 1, characterized in that: When training the BP neural network, forward propagation is performed first, and the function of the output layer is: ; Among them, s k is the predicted output value of the damage index of each target part, ψ is the activation function, and w ky is the weight from the hidden layer to the output layer, q k is the output value of the hidden layer, c k is the bias from the hidden layer to the output layer, t is the number of groups of vital sign parameters in the validation set; The function of the hidden layer is: ; Among them, q k is the output value of the hidden layer, ψ is the activation function, w ik is the weight from the input layer to the hidden layer, a i is the value of the ith neuron, h j is the bias from the input layer to the hidden layer, and t is the number of groups of vital sign parameters in the validation set.

5. The method for predicting damage evaluation index of a vehicle collision dummy according to claim 1, characterized in that: The expected error E is used to determine whether the prediction model is successfully constructed: ; Among them, e k is the kth group of damage evaluation indicators in the validation set, s k is the injury assessment index learned through the kth group of physical sign parameters in the validation set, and t is the number of groups of physical sign parameters in the validation set; If E<δ, it is confirmed that the prediction model is successfully constructed, and δ is the accuracy.

6. An electronic device, characterized in that: include: at least one processor, and a memory communicatively coupled to at least one of the processors; The memory stores instructions executable by at least one of the processors, and the instructions are executed by at least one of the processors so that the at least one processor can execute the method according to any one of claims 1 to 5.

7. A computer-readable storage medium, characterized in that: The medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 5.