Suspension connecting rod axial rigidity prediction method and related equipment thereof

Abstract

The invention provides a suspension connecting rod axial rigidity prediction method and related equipment thereof, and the method comprises the steps: obtaining an input set of a target suspension connecting rod, the input set comprising a cross section set, a hard point spacing and a material elastic modulus, and the cross section set comprising a cross section area and a cross section inertia moment; the input set is input into a suspension connecting rod axial rigidity prediction model obtained through training, so that the axial rigidity of the target suspension connecting rod is obtained, and the suspension connecting rod axial rigidity prediction model is used for predicting the axial rigidity of the suspension connecting rod according to the input set. The problem that in the prior art, obtaining of the axial rigidity of the suspension connecting rod is time-consuming, tedious and complex is solved.

Description

Technical Field

[0001] The present application relates to the field of vehicle suspension links, and in particular to a method for predicting the axial stiffness of a suspension link and related equipment. Background Art

[0002] The suspension link is a link structure with two-force characteristics in the vehicle's suspension system. The main load is along the line connecting the ball joints or the center points of the bushings at both ends, and it bears tensile or compressive loads. Its cross-sectional shape can be circular, rectangular, or open thin-walled structure. Common suspension links are front suspension steering rods, upper control arms and toe control arms of multi-link rear suspensions, etc. As the suspension link is an important component of the vehicle chassis suspension, its axial stiffness, buckling force and other properties are directly related to the stability of the vehicle, and thus to driving safety.

[0003] In order to obtain the axial stiffness of the suspension link, the finite element method is usually used to simulate and calculate the axial stiffness of the suspension link, and the process is time-consuming, tedious and complicated. Summary of the invention

[0004] The present application provides a method for predicting the axial stiffness of a suspension link and related equipment thereof, which solves the problem of time-consuming, tedious and complicated problem of obtaining the axial stiffness of a suspension link in the prior art.

[0005] A first aspect of the present application provides a method for predicting the axial stiffness of a suspension link, comprising:

[0006] Obtaining an input set of a target suspension link, wherein the input set includes a cross-section set, a hard point spacing, and a material elastic modulus, and the cross-section set includes a cross-sectional area and a cross-sectional moment of inertia;

[0007] The input set is input into the trained suspension link axial stiffness prediction model to obtain the axial stiffness of the target suspension link, wherein the suspension link axial stiffness prediction model is used to predict the axial stiffness of the suspension link based on the input set.

[0008] In some implementations, the suspension link axial stiffness prediction method further includes:

[0009] Acquire training samples of each of a plurality of suspension links, wherein the training samples include a training parameter set and a sample axial stiffness, wherein the training parameter set includes a sample cross-section set, a sample hard point spacing, and a sample material elastic modulus, and the sample cross-section set includes a sample cross-sectional area and a sample cross-sectional moment of inertia;

[0010] The suspension link axial stiffness prediction model that meets preset conditions is obtained by training based on the plurality of training samples.

[0011] In some implementations, the sample cross-sectional area is the area of ​​a cross section of the suspension link, the sample cross-sectional moment of inertia is the moment of inertia of a cross section of the suspension link, and the sample axial stiffness is the axial stiffness of the suspension link.

[0012] In some implementations, the sample cross-section set includes the cross-sectional areas and the cross-sectional moments of inertia of respective cross-sections of a plurality of the slices, wherein the respective cross-sections are different.

[0013] In some implementations, the suspension link axial stiffness prediction method further includes:

[0014] Acquire the initial parameter set of the suspension link according to the script to obtain the initial parameter set of each of the plurality of suspension links, wherein the initial parameter set includes the content category and axial stiffness of the training parameter set;

[0015] The initial parameter set is analyzed according to a correlation analysis method to obtain a target parameter set, and then the target parameter set is determined as the training sample to obtain training samples of each of the plurality of suspension links.

[0016] In some implementations, during the training process, the loss function of the suspension link axial stiffness prediction model is optimized according to a stochastic gradient descent optimizer to train the suspension link axial stiffness prediction model, and the training samples are increased according to the DOE method to improve the training accuracy of the suspension link axial stiffness prediction model.

[0017] A second aspect of the present application provides a suspension link axial stiffness prediction device, comprising:

[0018] A first acquisition module is used to acquire an input set of a target suspension link, wherein the input set includes a cross-section set, a hard point spacing, and a material elastic modulus, and the cross-section set includes a cross-sectional area and a cross-sectional moment of inertia;

[0019] A prediction module is used to input the input set into the trained suspension link axial stiffness prediction model to obtain the axial stiffness of the target suspension link, wherein the suspension link axial stiffness prediction model is used to predict the axial stiffness of the suspension link based on the input set.

[0020] In some implementations, a suspension link axial stiffness prediction device further includes:

[0021] A second acquisition module is used to acquire training samples of each of the plurality of suspension links, wherein the training samples include a training parameter set and a sample axial stiffness, wherein the training parameter set includes a sample cross-section set, a sample hard point spacing, and a sample material elastic modulus, and the sample cross-section set includes a sample cross-sectional area and a sample cross-sectional moment of inertia;

[0022] A training module is used to obtain the suspension link axial stiffness prediction model that meets preset conditions based on a plurality of the training samples.

[0023] A third aspect of the present application provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the suspension link axial stiffness prediction method in any implementation of the first aspect.

[0024] A fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method for predicting the axial stiffness of a suspension link in any implementation of the first aspect is implemented.

[0025] The technical solution of the present application obtains an input set of a target suspension link, wherein the input set includes a cross-section set, hard point spacing, and material elastic modulus, and the cross-section set includes a cross-section area and a cross-section moment of inertia, and then inputs the input set into a trained suspension link axial stiffness prediction model to obtain the axial stiffness of the target suspension link, wherein the suspension link axial stiffness prediction model is used to predict the axial stiffness of the suspension link according to the input set. Compared with the prior art that uses the time-consuming, labor-intensive, and cumbersome finite element method to simulate and calculate the axial stiffness of the suspension link, the suspension link axial stiffness prediction model obtained by training in the present application can efficiently and accurately obtain the axial stiffness. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0027] Figure 1 is a schematic diagram of obtaining the axial stiffness of a suspension link in the prior art;

[0028] Figure 2 It is a schematic diagram of a training process of a suspension link axial stiffness prediction model in an embodiment of the present application;

[0029] Figure 3 It is a schematic diagram of an axial stiffness prediction process based on a suspension link axial stiffness prediction model according to an embodiment of the present application;

[0030] Figure 4 This is a schematic diagram of a training sample creation process in an embodiment of the present application;

[0031] Figure 5a is a schematic diagram of a suspension link axial stiffness prediction device according to an embodiment of the present application;

[0032] Figure 5b is a schematic diagram of another suspension link axial stiffness prediction device according to an embodiment of the present application;

[0033] Figure 6 It is a schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0034] The scheme of the embodiment of the present application is described in detail below in conjunction with the drawings of the specification.

[0035] In the following description, for the purpose of explanation rather than limitation, specific details such as specific system structures, interfaces, and technologies are provided to facilitate a thorough understanding of the present application.

[0036] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0037] The terms "first", "second", "third" in this application are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Thus, the features defined as "first", "second", "third" can expressly or implicitly include at least one of the features. In the description of this application, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. In the embodiments of this application, all directional indications (such as up, down, left, right, front, back...) are only used to explain the relative position relationship, movement, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication also changes accordingly. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the steps or units listed, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices.

[0038] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0039] See also Figure 1 Currently, the industry usually uses the finite element method to obtain the axial stiffness of the suspension link. The specific process usually includes geometric modeling, geometric cleaning, meshing, material property definition, boundary conditions and load definition, calculation and solution, and result post-processing. During this period, it also involves a lot of repetitive work with multiple iterations due to solution optimization.

[0040] See also Figure 2 , Figure 2 The process of training the suspension link axial stiffness prediction model is shown. The training device can be a server or a user terminal, which is not limited here. The server is used as the training device for exemplary description, and this application is not limited to this. Specifically, it includes:

[0041] 201: Acquire training samples of each of a plurality of suspension links, wherein the training samples include a training parameter set and a sample axial stiffness, wherein the training parameter set includes a sample cross-section set, a sample hard point spacing, and a sample material elastic modulus, and the sample cross-section set includes a sample cross-sectional area and a sample cross-sectional moment of inertia;

[0042] The server obtains a training sample set of the suspension link, where the training sample set includes a training parameter set and a sample axial stiffness.

[0043] The training parameter set includes a sample cross-section set, a sample hard point spacing, and a sample material elastic modulus. The sample cross-section set includes a sample cross-section area and a sample cross-section moment of inertia.

[0044] The material elastic modulus refers to the material elastic modulus of the suspension link. The hard point spacing refers to the length of the line between the hard points of the suspension link. The cross-sectional area is the entire area of ​​the cross section of each slice after the suspension link is sliced. The cross-sectional moment of inertia refers to the moment of inertia of the cross section of each slice after the suspension link is sliced. Among them, the slicing process refers to obtaining multiple cutting points based on the hard point spacing and the number of slices preset in the suspension link, and then cutting the suspension link according to the multiple cutting points to obtain multiple slices of the suspension link. It can be understood that there are identical sections between adjacent slices. The number of cross-sectional areas is the same as the number of sample cross-sectional moments of inertia, and the cross-sectional area, cross-sectional moment of inertia and cross section are interrelated. The sample cross-sectional set uses cross-sectional areas and cross-sectional moments of inertia of multiple different cross sections.

[0045] Each slice has a plane reference point, which is located on the hard point line. The normal of the slice is parallel to the hard point line. The cross-sectional area and cross-sectional inertia moment correspond to the cross section where the slice plane intersects the suspension link. The cross-sectional inertia moment corresponds to the coordinate system with the slice plane reference point as the coordinate origin.

[0046] Preferably, the sample cross-section set uses 20 different cross-sections, thereby obtaining 20 cross-sectional areas and 20 cross-sectional moments of inertia, each cross-section belonging to a different slice of the suspension link.

[0047] It should be pointed out that the hard point spacing of different suspension links is different.

[0048] It is understandable that in order to obtain a high-precision prediction model for the axial stiffness of the suspension link, the number of slices can be adjusted to obtain more slices corresponding to each suspension link for training, thereby obtaining a more accurate prediction model for the axial stiffness of the suspension link.

[0049] It can be understood that a training sample includes a sample hard point spacing, a sample material elastic modulus, multiple sample cross-sectional areas, and multiple sample cross-sectional moments of inertia.

[0050] 202: Obtain the suspension link axial stiffness prediction model that meets preset conditions through training based on the plurality of training samples.

[0051] The server uses the acquired multiple training samples to train an initial model of the suspension link axial stiffness prediction model to obtain a suspension link axial stiffness prediction model that meets preset conditions.

[0052] See also Figure 3 , Figure 3 It shows that the axial stiffness of the target suspension link is predicted by the server as the execution subject based on the suspension link axial stiffness prediction model obtained by training. In some embodiments, the axial stiffness of the target suspension link may also be output by the user terminal. The specific details are not limited here. Figure 3 Specifically include:

[0053] 301: Obtain an input set of a target suspension link, wherein the input set includes a cross-section set, a hard point spacing, and a material elastic modulus, and the cross-section set includes a cross-sectional area and a cross-sectional moment of inertia;

[0054] Understandably, according to Figure 2 In an embodiment, the cross-section set includes a plurality of cross-section areas and cross-section moments of inertia. Preferably, the cross-section set uses 20 different cross-sections, thereby obtaining 20 cross-section areas and 20 cross-section moments of inertia, each cross-section belonging to a different slice of the suspension link.

[0055] 302: Inputting the input set into the trained suspension link axial stiffness prediction model to obtain the axial stiffness of the target suspension link, wherein the suspension link axial stiffness prediction model is used to predict the axial stiffness of the suspension link according to the input set.

[0056] In some implementations, the server obtains an input set of a target suspension link sent by a user terminal, and then inputs the input set into a trained suspension link axial stiffness prediction model to obtain the axial stiffness of the target suspension link.

[0057] In some embodiments, the user terminal obtains an input set of the target suspension link input by the user, and then sends it to the server, so that the server executes steps 301-302 to obtain the axial stiffness of the target suspension link, and then returns it to the user terminal.

[0058] In some implementations, the user terminal locally obtains the suspension link axial stiffness prediction model trained by the server, and thus the user terminal executes steps 301-302 to obtain the axial stiffness of the target suspension link.

[0059] The user terminal may be a portable device, such as a mobile phone, a smart phone or a laptop, or a factory equipment, such as a lathe, a milling machine, a grinder or a planer, etc., which is not limited here.

[0060] See also Figure 4 , Figure 4 The creation of training samples is shown, and an exemplary description is given by taking a server as the execution subject, but the present application is not limited thereto, and specifically includes:

[0061] 401: Acquire the initial parameter set of the suspension link according to the script to obtain the initial parameter set of each of the plurality of suspension links, wherein the initial parameter set includes the content category and axial stiffness of the training parameter set;

[0062] In some embodiments, the server can obtain a historical database of the suspension link, which includes parameter information of the suspension link, including at least hard point spacing, material elastic modulus, cross-sectional area and cross-sectional moment of inertia, and then obtain an initial parameter set including the hard point spacing and material elastic modulus of the suspension link, the cross-sectional area and cross-sectional moment of inertia of the suspension link, and the axial stiffness from the database based on a script.

[0063] In some embodiments, for a given suspension link, the server extracts an initial parameter set from software including such suspension link information based on a script. Specifically, the server creates several sections between the hard point lines of the suspension link through a script to form corresponding slices, that is, creates several shear surfaces (sections) in the middle of the two end bushings or ball joint lines of the suspension link, wherein the two end bushings or ball joints are used as two hard points to form hard point indirection, the distance between adjacent shear surfaces is determined by the hard point spacing and the number of slices, and the intersection of the shear surface and the suspension link forms a slice section, and then extracts the hard point spacing, cross-sectional area and cross-sectional moment of inertia based on the hard point lines, and extracts the material elastic modulus and axial stiffness to obtain the initial parameter set. For example, a Python script is used in HyperMesh or Ansa software to obtain an initial parameter set from a finite element model of a suspension link.

[0064] 402: Analyze the initial parameter set according to a correlation analysis method to obtain a target parameter set, and then determine the target parameter set as the training sample to obtain training samples for each of the plurality of suspension links.

[0065] After obtaining the initial parameter set, the server analyzes the initial parameter set according to the correlation analysis method, obtains the hard point spacing, material elastic modulus, cross-sectional area and cross-sectional moment of inertia, and axial stiffness from the initial parameter set, and then forms a target parameter set, and determines it as the training sample parameter set, wherein the target parameter set is the hard point spacing, material elastic modulus, cross-sectional area and cross-sectional moment of inertia, and axial stiffness that are correlated and determined from the initial parameter set based on the correlation analysis method.

[0066] In some embodiments, the script includes a parameter reduction algorithm to reduce the order of the target parameter set to speed up the training of the suspension link axial stiffness prediction model. The parameter reduction algorithm includes a principal component analysis method.

[0067] In some embodiments, the target parameter set is divided into training samples and test samples according to a preset ratio to obtain a suspension link axial stiffness prediction model through training and testing. Optionally, 80% of the target parameter set is used as training samples and 20% is used as test samples.

[0068] In some embodiments, when the training samples are insufficient to achieve the preset conditions of the suspension link axial stiffness prediction model, the DOE method is used to increase the training samples to achieve the suspension link axial stiffness prediction model with training accuracy. Specifically, based on the feedback information during the test process, the test sample with the maximum error is determined, so as to obtain the corresponding suspension link for training, and then obtain its initial parameter set, and the DOE method is used to generate new training samples to expand the original training samples and then use them for training to obtain the suspension link axial stiffness prediction model with training accuracy. Optionally, the training accuracy is less than 5%.

[0069] In some embodiments, during the training process of the suspension link axial stiffness prediction model, a stochastic gradient descent optimizer may be used to automatically optimize the mean squared error loss function (MSE) so as to efficiently train the suspension link axial stiffness prediction model.

[0070] In some implementations, the original suspension link axial stiffness prediction model is updated by acquiring new training samples.

[0071] See also Figure 5a , Figure 5a A schematic diagram of a suspension link axial stiffness prediction device is shown, comprising:

[0072] A first acquisition module 501 is used to acquire an input set of a target suspension link, wherein the input set includes a cross-section set, a hard point spacing, and a material elastic modulus, and the cross-section set includes a cross-sectional area and a cross-sectional moment of inertia;

[0073] The prediction module 502 is used to input the input set into the trained suspension link axial stiffness prediction model to obtain the axial stiffness of the target suspension link, wherein the suspension link axial stiffness prediction model is used to predict the axial stiffness of the suspension link according to the input set.

[0074] See also Figure 5b , Figure 5b A schematic diagram of another suspension link axial stiffness prediction device is shown, which includes, in addition to the first acquisition module 501 and the prediction module 502, also includes:

[0075] A second acquisition module 503 is used to acquire training samples of each of the plurality of suspension links, wherein the training samples include a training parameter set and a sample axial stiffness, wherein the training parameter set includes a sample cross-section set, a sample hard point spacing, and a sample material elastic modulus, and the sample cross-section set includes a sample cross-sectional area and a sample cross-sectional moment of inertia;

[0076] The training module 504 is used to train the suspension link axial stiffness prediction model that meets preset conditions according to the plurality of training samples.

[0077] This application also includes an electronic device, see Figure 6 The processor 602 includes a memory 601 and a processor 602; wherein the memory 601 is used to store programs; the processor 602 is used to execute the programs in the memory 601, including executing the aforementioned Figures 2 to 4 Methods;

[0078] In some embodiments, the electronic device further includes a bus system, which is used to connect the memory and the processor so that the memory and the processor can communicate with each other.

[0079] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0080] In some embodiments, the memory may be an internal storage unit of the cloud device, for example, a hard disk or memory of the cloud device. In other embodiments, the memory may also be an external storage device of the cloud device, for example, a plug-in hard disk equipped on the cloud device, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Further, the memory may also include both an internal storage unit of the cloud device and an external storage device. The memory is used to store an operating system, an application, a boot loader (BootLoader), data, and other programs, such as program code of a computer program, etc. The memory may also be used to temporarily store data that has been output or is to be output.

[0081] The present application also includes a computer-readable storage medium including instructions that, when executed on a computer, cause the computer to execute Figures 2 to 4 Any of the methods.

[0082] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of each of the above-mentioned method embodiments can be implemented.

[0083] The computer program includes computer program code, which may be in source code form, object code form, executable file or some intermediate form. Computer readable media may include at least: any entity or device capable of carrying computer program code to a camera / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electric carrier signal, a telecommunication signal and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer readable media cannot be electric carrier signals and telecommunication signals.

[0084] The above are only implementation methods of the present application, and are not intended to limit the patent protection scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for predicting the axial stiffness of a suspension link, characterized in that: include: Obtaining an input set of a target suspension link, wherein the input set includes a cross-section set, a hard point spacing, and a material elastic modulus, and the cross-section set includes a cross-sectional area and a cross-sectional moment of inertia; The input set is input into the trained suspension link axial stiffness prediction model to obtain the axial stiffness of the target suspension link, wherein the suspension link axial stiffness prediction model is used to predict the axial stiffness of the suspension link based on the input set.

2. The method for predicting the axial stiffness of a suspension link according to claim 1, characterized in that: Also includes: Acquire training samples of each of a plurality of suspension links, wherein the training samples include a training parameter set and a sample axial stiffness, wherein the training parameter set includes a sample cross-section set, a sample hard point spacing, and a sample material elastic modulus, and the sample cross-section set includes a sample cross-sectional area and a sample cross-sectional moment of inertia; The suspension link axial stiffness prediction model that meets preset conditions is obtained by training based on the plurality of training samples.

3. The method for predicting the axial stiffness of a suspension link according to claim 2, characterized in that: The sample cross-sectional area is the area of ​​the cross section of the suspension link, the sample cross-sectional moment of inertia is the moment of inertia of the cross section of the suspension link, and the sample axial stiffness is the axial stiffness of the suspension link.

4. The method for predicting the axial stiffness of a suspension link according to claim 3, characterized in that: The sample cross-section set includes the cross-sectional areas and the cross-sectional moments of inertia of respective cross-sections of a plurality of the slices, wherein the respective cross-sections are different.

5. The method for predicting the axial stiffness of a suspension link according to any one of claims 1 to 4, characterized in that: Before obtaining the training sample, the method further includes: Acquire the initial parameter set of the suspension link according to the script to obtain the initial parameter set of each of the plurality of suspension links, wherein the initial parameter set includes the content category and axial stiffness of the training parameter set; The initial parameter set is analyzed according to a correlation analysis method to obtain a target parameter set, and then the target parameter set is determined as the training sample to obtain training samples for each of the plurality of suspension links.

6. The method for predicting the axial stiffness of a suspension link according to any one of claims 1 to 4, characterized in that: During the training process, the loss function of the suspension link axial stiffness prediction model is optimized according to the stochastic gradient descent optimizer to train the suspension link axial stiffness prediction model, and the training samples are increased according to the DOE method to improve the training accuracy of the suspension link axial stiffness prediction model.

7. A suspension link axial stiffness prediction device, characterized in that: include: A first acquisition module is used to acquire an input set of a target suspension link, wherein the input set includes a cross-section set, a hard point spacing, and a material elastic modulus, and the cross-section set includes a cross-sectional area and a cross-sectional moment of inertia; A prediction module is used to input the input set into the trained suspension link axial stiffness prediction model to obtain the axial stiffness of the target suspension link, wherein the suspension link axial stiffness prediction model is used to predict the axial stiffness of the suspension link based on the input set.

8. A suspension link axial stiffness prediction device, characterized in that: Also includes A second acquisition module is used to acquire training samples of each of the plurality of suspension links, wherein the training samples include a training parameter set and a sample axial stiffness, wherein the training parameter set includes a sample cross-section set, a sample hard point spacing, and a sample material elastic modulus, and the sample cross-section set includes a sample cross-sectional area and a sample cross-sectional moment of inertia; A training module is used to obtain the suspension link axial stiffness prediction model that meets preset conditions based on a plurality of the training samples.

9. An electronic device, comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to execute the suspension link axial stiffness prediction method according to any one of claims 1 to 6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for predicting the axial stiffness of a suspension link as claimed in any one of claims 1 to 6 is implemented.

Images