Finite element simulation optimization method and system for anti-collision performance of guardrail plate

Abstract

The invention belongs to the technical field of computer aided design in structures or civil engineering, and particularly provides a finite element simulation optimization method and system for the anti-collision performance of a guardrail plate, and the method mainly comprises the steps: obtaining the collision finite element simulation data of the guardrail plate, dividing the guardrail plate collision finite element simulation data into a stress distribution feature set and a collision condition feature set; performing multi-dimensional feature fusion on the stress distribution feature set to generate a dynamic parameter feature set; generating an anti-collision parameter optimization scheme according to the dynamic parameter feature set; anti-collision effect pre-verification is executed on the anti-collision parameter optimization scheme, and a simulation verification feature set is generated; and according to the collision condition feature set and the simulation verification feature set, generating a final optimization scoring result. According to the method, dynamic adaptation of the parameter optimization direction and the actual collision condition can be achieved, the protection performance deviation risk is effectively reduced, the optimization iteration period is shortened, and a more universal optimization basis is provided for guardrail structure design and safety verification.

Description

Technical Field

[0001] The present invention belongs to the technical field of computer-aided design in structures or civil engineering, and particularly relates to a finite element simulation optimization method and system for the anti-collision performance of guardrail plates. Background Art

[0002] The optimization analysis of the anti-collision performance of guardrail structures is usually realized based on finite element simulation technology. Currently, the mainstream method is to establish a three-dimensional numerical model of the guardrail, simulate the structural deformation and energy absorption characteristics during the vehicle collision process, and then evaluate its protection ability.

[0003] Currently, the optimization direction of the anti-collision performance of guardrail structures is generally found by independently adjusting single variables such as material properties and cross-sectional shapes. This processing method ignores the dynamic coupling effect between different mechanical parameters during the collision process, lacks a systematic evaluation of the synergistic effect of multiple variables, and may lead to a deviation in the protection performance of the optimization scheme in actual complex collision scenarios, affecting the reliability of the safety assessment results. Summary of the Invention

[0004] This application effectively solves the problem in the prior art that the optimization direction of the anti-collision performance of guardrail structures is found by independently adjusting single variables such as material properties and cross-sectional shapes, lacks a systematic evaluation of the synergistic effect of multiple variables, may lead to a deviation in the protection performance of the optimization scheme in actual complex collision scenarios, and affects the reliability of the safety assessment results, realizes the dynamic adaptation of the parameter optimization direction to the actual collision conditions, effectively reduces the risk of protection performance deviation, shortens the optimization iteration cycle, and at the same time ensures the stability and consistency of the safety performance under different collision conditions, providing a more general optimization basis for the design and safety verification of guardrail structures.

[0005] To achieve the above object, the present invention adopts the following technical solutions:

[0006] In a first aspect, this application provides a finite element simulation optimization method for the anti-collision performance of guardrail plates, including:

[0007] Obtain finite element simulation data of guardrail plate collisions, and divide the finite element simulation data of guardrail plate collisions into a stress distribution feature set and a collision condition feature set.

[0008] Perform multi-dimensional feature fusion on the stress distribution feature set to generate a dynamic parameter feature set.

[0009] Generate an anti-collision parameter optimization scheme according to the dynamic parameter feature set.

[0010] Perform pre-verification of the anti-collision effect on the anti-collision parameter optimization scheme to generate a simulation verification feature set.

[0011] Generate the final optimized scoring result according to the collision condition feature set and the simulation verification feature set.

[0012] Further, perform multi-dimensional feature fusion on the stress distribution feature set to generate a dynamic parameter feature set, including:

[0013] Set a specified number of stress zones, divide all stress zones according to the maximum stress value of each stress zone, and extract the independent features of each stress zone.

[0014] Perform time-series correlation analysis on the stress fluctuation frequency and the independent features of each stress zone to generate a zone-frequency correlation matrix.

[0015] Based on the correlation matrix, screen out the abnormal fluctuation zones to generate a dynamic parameter feature set.

[0016] Further, set a specified number of stress zones, divide all stress zones according to the maximum stress value of each stress zone, and extract the independent features of each stress zone, including:

[0017] Divide the guardrail plates into high-stress zones, medium-stress zones, and low-stress zones according to the numerical distribution of the maximum stress value sequence and the preset stress critical value.

[0018] For the high-stress zone: Extract the stress peak interval and the fluctuation frequency as independent features.

[0019] For the medium-stress zone: Extract the stress attenuation rate and the thickness distribution correlation parameter as independent features.

[0020] For the low-stress zone: Extract the stress stability mark as an independent feature.

[0021] Further, generate an anti-collision parameter optimization scheme according to the dynamic parameter feature set, including:

[0022] Use an anti-collision optimization model to process the anti-collision parameter optimization scheme. The anti-collision optimization model adds a multi-modal input layer on the basis of the gradient tree and generates the anti-collision parameter optimization scheme through the joint splitting rule.

[0023] Further, the anti-collision optimization model adds a multi-modal input layer on the basis of the gradient tree and generates the anti-collision parameter optimization scheme through the joint splitting rule, including:

[0024] The multi-modal input layer includes a first channel and a second channel; the first channel is used to receive the independent features of the high-stress zone and calculate the compressive strength matching degree of the material replacement type, and the second channel is used to receive the independent features of the medium-stress zone and the low-stress zone and calculate the deformation inhibition rate of the thickness compensation gradient.

[0025] Compare the compressive strength matching degree with a preset compressive strength threshold. If the compressive strength matching degree exceeds the compressive strength threshold, generate a matching plan for the material replacement type in the high stress area; compare the deformation inhibition rate with a preset deformation threshold. If the deformation inhibition rate is lower than the deformation threshold, generate an incremental plan for the thickness compensation gradient based on the associated features of the medium stress area and the associated features of the low stress area.

[0026] According to the fluctuation abnormal area, perform spatial superposition on the material replacement plan and the incremental plan for thickness compensation.

[0027] According to the result of the superposition, output an anti-collision parameter optimization plan including the material thickness adjustment value and the stress concentration area correction parameter.

[0028] Further, perform a pre-verification of the anti-collision effect on the anti-collision parameter optimization plan to generate a simulation verification feature set, including:

[0029] Generate multiple groups of candidate parameter combinations according to the material thickness adjustment value and the stress concentration area correction parameter.

[0030] Perform two-way correlation analysis and screening according to multiple groups of candidate parameter combinations and the collision condition feature set.

[0031] Verify the effectiveness of the screened candidate parameter combinations to obtain a verification result.

[0032] Use the screened candidate parameter combinations as rows, the stress area-frequency correlation matrix as columns, and the verification result as the matrix element values to generate a simulation verification feature set.

[0033] Further, perform two-way correlation analysis and screening according to multiple groups of candidate parameter combinations and the collision condition feature set, including:

[0034] Input the candidate parameter combination into the anti-collision optimization model to obtain the calculation result of the compressive strength matching degree under the collision speed time series data; input the candidate parameter combination into the anti-collision optimization model to obtain the calculation result of the deformation inhibition rate under the collision contact angle sequence.

[0035] Retain the candidate parameter combinations whose compressive strength matching degree calculation results exceed the preset first ratio value and whose deformation inhibition rate calculation results exceed the preset second ratio value.

[0036] Further, generate a final optimization score result according to the collision condition feature set and the simulation verification feature set, including:

[0037] Align the collision speed time series data with the candidate parameter combination in time series to generate a speed-parameter time series correlation matrix; perform spatial dimension cross-correlation on the collision angle time series data and the stress area-frequency correlation matrix to generate an angle-matrix spatial correlation matrix.

[0038] An anti-collision parameter optimization model is used to process the velocity-parameter time series correlation matrix and the angle-matrix spatial correlation matrix. After the anti-collision parameter optimization model extracts the time correlation features and spatial correlation features, feature merging and conflict resolution are performed to generate the final optimized scoring result.

[0039] Further, performing feature merging and conflict resolution includes:

[0040] Merge the time correlation features and spatial correlation features according to the time step and spatial position to generate comprehensive features.

[0041] The verification results in the simulation verification feature set include invalid candidate parameter combinations and stress stability markers in unstable low-stress areas; according to the verification results in the simulation verification feature set, conflict resolution is performed on the comprehensive features, including:

[0042] If the verification result is marked as an invalid candidate parameter combination, the corresponding time correlation feature is excluded.

[0043] If the verification result is marked as a stress stability marker in an unstable low-stress area, the influence range of the spatial correlation feature is restricted.

[0044] In a second aspect, the present application provides a finite element simulation optimization system for the anti-collision performance of guardrail plates, which includes:

[0045] Data partitioning module: Obtain the finite element simulation data of guardrail plate collision, and partition the finite element simulation data of guardrail plate collision into a stress distribution feature set and a collision condition feature set;

[0046] Feature fusion module: Perform multi-dimensional feature fusion on the stress distribution feature set to generate a dynamic parameter feature set;

[0047] Scheme generation module: Generate an anti-collision parameter optimization scheme according to the dynamic parameter feature set;

[0048] Effect verification module: Perform pre-verification of the anti-collision effect on the anti-collision parameter optimization scheme to generate a simulation verification feature set;

[0049] Scoring output module: Generate the final optimized scoring result according to the collision condition feature set and the simulation verification feature set.

[0050] In a third aspect, the present application provides a finite element simulation optimization device for the anti-collision performance of guardrail plates, which includes a memory and a processor; the memory is used to store a computer program; the processor is used to implement the steps of the finite element simulation optimization method for the anti-collision performance of guardrail plates as described in the first aspect when executing the computer program.

[0051] Fourthly, the present application provides a storage medium storing computer program instructions, which, when read and executed by a processor, perform the steps of the finite element simulation optimization method for the anti-collision performance of guardrail plates as described in the first aspect.

[0052] Advantages of the present invention:

[0053] By systematically analyzing the influence mechanism of the synergistic effect of multiple variables on the protection performance, the present application effectively solves the problem in the prior art that by independently adjusting single variables such as material properties and cross-sectional shapes to find the optimization direction of the anti-collision performance of guardrail structures, lacking a systematic evaluation of the synergistic effect of multiple variables, which may lead to a deviation in the protection performance in actual complex collision scenarios and affect the reliability of safety assessment results. It realizes the dynamic adaptation of the parameter optimization direction to the actual collision conditions, effectively reduces the risk of protection performance deviation, shortens the optimization iteration cycle, and at the same time ensures the stability and consistency of safety performance under different collision conditions, providing a more general optimization basis for guardrail structure design and safety verification.

[0054] Other features and advantages of the present invention will be described in the following specification, and, in part, will be obvious from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention can be achieved and obtained through the structures pointed out in the specification and the drawings. Brief Description of the Drawings

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0056] Figure 1 Shows a flow schematic diagram of the finite element simulation optimization method for the anti-collision performance of guardrail plates of the present invention;

[0057] Figure 2 Shows a module schematic diagram of the finite element simulation optimization system for the anti-collision performance of guardrail plates of the present invention. Detailed Embodiments

[0058] To solve the problems raised in the background art, the present application integrates the stress distribution and collision condition characteristics of guardrail plate collision simulation data, establishes a multi-dimensional dynamic parameter correlation model, generates an anti-collision parameter optimization scheme based on this, combines a pre-verification mechanism with collision condition matching verification, and finally outputs a comprehensive optimization score, providing a more general optimization basis for guardrail structure design and safety verification.

[0059] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0060] In some embodiments, as Figure 1 shown, the present application provides a finite element simulation optimization method for the anti-collision performance of guardrail plates, including:

[0061] S100. Obtain finite element simulation data of guardrail plate collision, and divide the finite element simulation data of guardrail plate collision into a stress distribution feature set and a collision condition feature set.

[0062] Simulate the dynamic process of a vehicle colliding with a guardrail plate through finite element simulation software, and output the key data during the collision process as finite element simulation data.

[0063] The input conditions may include the collision speed V(t) at time t, the collision angle θ(t) at time t, and the vehicle mass m.

[0064] The output data may include stress data and deformation data; among them, the stress data is the VonMises stress value of each node of the guardrail plate, which can be recorded as a matrix S(x, y, t) according to the time step, where x and y represent spatial coordinates, and t represents time; the deformation data is the displacement matrix D(x, y, t) of each node of the guardrail plate.

[0065] The stress distribution feature set includes the maximum stress value sequence and the stress fluctuation frequency.

[0066] Divide the guardrail plate into multiple regions, such as dividing it into a 10×10 grid, and extract the maximum stress value of each region in the time dimension from the matrix S(x, y, t) to form the maximum stress value sequence S max (x, y) = [max(S(x, y, t1)), max(S(x, y, t2)), …, max(S(x, y, t n ))], where max(S(x, y, t n )) represents the maximum stress value of region (x, y) in the time dimension t n above.

[0067] Calculate the frequency principal components of the stress changes in each stress region through Fourier transform to obtain the stress fluctuation frequency of each stress region.

[0068] The collision condition feature set includes the collision velocity time series data V(t), the collision angle time series data θ(t), the vehicle mass m, and the collision energy E(t), and the collision energy E(t) can be calculated according to the functional formula.

[0069] Directly mixing the velocity time series data with the stress data will cause the model to misattribute the stress fluctuations caused by velocity changes to material property problems. After separating the velocity time series data from the stress data, the optimization scheme can specifically correct the material parameters or structural parameters to avoid the coupling interference between the two types of data.

[0070] S200. Perform multi-dimensional feature fusion on the stress distribution feature set to generate a dynamic parameter feature set.

[0071] S300. Generate an anti-collision parameter optimization scheme based on the dynamic parameter feature set.

[0072] S400. Perform pre-verification of the anti-collision effect on the anti-collision parameter optimization scheme to generate a simulation verification feature set.

[0073] S500. Generate a final optimization score result based on the collision condition feature set and the simulation verification feature set.

[0074] In some embodiments, performing multi-dimensional feature fusion on the stress distribution feature set in S200 to generate a dynamic parameter feature set includes:

[0075] S210. Set a specified number of stress zones, divide all stress zones according to the maximum stress value of each stress zone, and extract the independent features of each stress zone.

[0076] S220. Perform time series correlation analysis on the stress fluctuation frequency and the independent features of each stress zone to generate a zone-frequency correlation matrix.

[0077] S230. Screen out the abnormal fluctuation zones based on the correlation matrix to generate a dynamic parameter feature set.

[0078] In some embodiments, setting a specified number of stress zones in S210, dividing all stress zones according to the maximum stress value of each stress zone, and extracting the independent features of each stress zone includes:

[0079] Divide the guardrail plate into a high stress zone, a medium stress zone, and a low stress zone according to the numerical distribution of the maximum stress value sequence and the preset stress critical value.

[0080] For the high stress zone: Extract the stress peak interval and the fluctuation frequency as independent features.

[0081] For the medium stress zone: Extract the stress decay rate and the thickness distribution correlation parameter as independent features.

[0082] For the low stress area: Extract the stress stability marker as an independent feature.

[0083] The stress area can be delimited by setting a threshold according to the material yield strength. For example, the critical value for the high stress area is 250 MPa, and the critical value for the medium stress area is 150 MPa. The delimited stress areas can be the high stress area, the medium stress area, and the low stress area.

[0084] When clustering the areas, taking the critical value of 250 MPa for the high stress area and 150 MPa for the medium stress area as examples, the areas with the maximum stress value sequence exceeding 250 MPa are classified as the high stress area, the areas with the value between 150 MPa and 250 MPa, and the areas with the value lower than 150 MPa are classified as the low stress area, so as to obtain three stress areas.

[0085] For the high stress area, the independent features can be the stress peak interval and the fluctuation frequency. The stress peak interval can be obtained by calculating the time difference between adjacent peaks, and the fluctuation frequency represents the number of peaks per unit time.

[0086] For the medium stress area, the independent features can be the stress attenuation rate and the thickness distribution correlation parameter. The formula for the stress attenuation rate is: where, Ar represents the stress attenuation rate, σ max represents the maximum stress value in the medium stress area within the time range, σ min represents the minimum stress value in the medium stress area within the range time, and Δt represents the time when the stress drops from the maximum value to the minimum value; calculate the correlation coefficient between the stress and the thickness to obtain the thickness distribution correlation parameter.

[0087] For the low stress area, the independent feature can be the stress stability marker. Specifically, the stability can be calculated by variance, and a stability threshold is set. If the stability is less than the stability threshold, it is marked as "stable". The stability threshold can be determined based on the statistical analysis of the historical data of the stress fluctuation of the guardrail under normal working conditions, industry standards, and actual engineering experience.

[0088] In S220, the correlation degree Cov(X,Y) between the stress fluctuation frequency and the independent feature of each stress area can be calculated by the covariance calculation formula, where X represents the fluctuation frequency sequence, and Y represents a certain independent feature sequence (such as the peak interval).

[0089] In S230, taking the high stress area, the medium stress area, and the low stress area as rows, and the covariance values of the fluctuation frequency and each independent feature as columns, a stress area - frequency correlation matrix is generated.

[0090] Example matrix:

[0091] An abnormal threshold can be set. If the absolute value of the covariance of a certain area exceeds the abnormal threshold, it is determined as a fluctuating abnormal area. The abnormal threshold is determined based on the historical simulation data and actual collision test data of the guardrail, or by combining multiple test debuggings and industry experience.

[0092] Combine the independent features of the abnormal area with the covariance value to generate a dynamic parameter feature set that includes the combination of the independent features and covariance value of the abnormal area.

[0093] In some embodiments, S300 generates an anti-collision parameter optimization scheme based on the dynamic parameter feature set, including: using an anti-collision optimization model to process the anti-collision parameter optimization scheme. The anti-collision optimization model adds a multi-modal input layer on the basis of the gradient tree and generates the anti-collision parameter optimization scheme through the joint splitting rule.

[0094] In some embodiments, the anti-collision optimization model adds a multi-modal input layer on the basis of the gradient tree and generates the anti-collision parameter optimization scheme through the joint splitting rule, including:

[0095] The multi-modal input layer includes a first channel and a second channel; the first channel is used to receive the independent features of the high-stress area and calculate the compressive strength matching degree of the material replacement type, and the second channel is used to receive the independent features of the medium-stress area and the independent features of the low-stress area and calculate the deformation suppression rate of the thickness compensation gradient.

[0096] The input features of the first channel include the stress peak interval and fluctuation frequency of the high-stress area, and the value obtained by comparing the compressive strength of the candidate material with the average value of the historical peak stress in the high-stress area is marked as the compressive strength matching degree R.

[0097] The input features of the second channel are the attenuation rate of the medium-stress area, the thickness distribution correlation parameter, and the stability mark of the low-stress area.

[0098] Adjust the thickness parameter of the stress area of the guardrail, input the adjusted thickness parameter into the finite element simulation model, re-simulate the collision process, and output the compensated deformation amount. Take the reduction ratio of the deformation amount after thickness compensation as the deformation suppression rate. The reference formula is: where D r represents the deformation suppression rate, δ o represents the original deformation amount, and δ c represents the compensated deformation amount.

[0099] Discretize the compressive strength matching degree R and the deformation suppression rate D r

[0100] ​S320. Compare the compressive strength matching degree with a preset compressive strength threshold. If the compressive strength matching degree exceeds the compressive strength threshold, generate a matching plan for the material replacement type in the high stress area; compare the deformation inhibition rate with a preset deformation threshold. If the deformation inhibition rate is lower than the deformation threshold, generate an incremental plan for the thickness compensation gradient based on the correlation characteristics of the medium stress area and the low stress area.

[0101] The combined splitting rules include Rule 1 and Rule 2:

[0102] Rule 1: Compare the compressive strength matching degree with a preset compressive strength threshold. If the compressive strength matching degree exceeds the compressive strength threshold, generate a matching plan for the material replacement type in the high stress area. Exemplarily, if the compressive strength matching degree is less than the preset compressive strength threshold, trigger the replacement of the high stress area material from Q235 steel to S355 steel.

[0103] Rule 2: Compare the deformation inhibition rate with a preset deformation threshold. If the deformation inhibition rate is lower than the deformation threshold, generate an incremental plan for the thickness compensation gradient based on the correlation characteristics of the medium stress area and the low stress area. Exemplarily, if the deformation inhibition rate in the medium stress area is less than the deformation threshold, trigger the thickness to increase from 8 mm to 8.8 mm; for the low stress area, it can be determined whether to limit the compensation range according to the stability mark. If it is stable, the thickness of the low stress area remains unchanged, otherwise the thickness of the low stress area is adjusted by a certain proportion.

[0104] S330. According to the fluctuation abnormal area, perform spatial superposition on the material replacement plan and the incremental plan for thickness compensation.

[0105] According to the position of the fluctuation abnormal area, superpose the material replacement plan and the incremental plan for thickness compensation in space to avoid conflicts.

[0106] S340. According to the superposed result, output an anti-collision parameter optimization plan including the material thickness adjustment value and the stress concentration area correction parameter.

[0107] Exemplarily, the material thickness adjustment value is such that the original thickness of the S355 steel is adjusted from 6 mm to 8 mm, and the stress concentration area correction parameter is such that the chamfer radius at the edge of the high stress area increases from 3 mm to 5 mm.

[0108] When training the anti-collision optimization model, a combined loss function can be designed to comprehensively consider the errors of the compressive strength matching degree and the deformation inhibition rate. Different weight combinations can be tried for the errors of the compressive strength matching degree and the deformation inhibition rate. Compare the compressive strength matching and deformation inhibition effects of the model on the test set, select the optimal combination, and finally adjust the weight coefficients through backpropagation iteration to minimize the loss value.

[0109] In some embodiments, in S400, perform pre-verification of the anti-collision effect on the anti-collision parameter optimization plan to generate a simulation verification feature set, including:

[0110] S410. Adjust the numerical value according to the material thickness and the correction parameter of the stress concentration area to generate multiple groups of candidate parameter combinations.

[0111] S420. Perform two-way correlation analysis screening based on multiple groups of candidate parameter combinations and the collision condition feature set.

[0112] S430. Verify the effectiveness of the screened candidate parameter combinations to obtain the verification result.

[0113] S440. Take the screened candidate parameter combinations as rows, the stress area-frequency correlation matrix as columns, and the verification result as the matrix element value to generate the simulation verification feature set.

[0114] In some embodiments, S420. Perform two-way correlation analysis screening based on multiple groups of candidate parameter combinations and the collision condition feature set, including:

[0115] S421. Input the candidate parameter combination into the anti-collision optimization model to obtain the calculation result of the compressive strength matching degree under the collision speed time series data; input the candidate parameter combination into the anti-collision optimization model to obtain the calculation result of the deformation suppression rate under the collision contact angle sequence.

[0116] S422. Retain the candidate parameter combinations whose compressive strength matching degree calculation results exceed the preset first ratio value and whose deformation suppression rate calculation results exceed the preset second ratio value.

[0117] In S410, for the numerical value of material thickness adjustment, multiple groups of candidate parameters can be generated according to a fixed step (such as ±1 mm); for the correction parameter of the stress concentration area, multiple groups of candidate parameters can be generated according to a fixed step (such as ±1 mm).

[0118] Exemplarily, candidate parameter combination 1: the thickness is adjusted from the original thickness of 6 mm to 8 mm, and the edge chamfer radius is increased from 3 mm to 5 mm; candidate parameter combination 2: the thickness is adjusted from the original thickness of 6 mm to 7 mm, and the edge chamfer radius is increased from 3 mm to 4 mm; candidate parameter combination 3: the thickness is adjusted from the original thickness of 6 mm to 10 mm, and the edge chamfer radius is increased from 3 mm to 6 mm.

[0119] In S421, calculate the matching degree of the compressive capacity of the candidate parameter combination under the collision speed to obtain the compressive strength matching degree R v , the formula is: where csofcm represents the compressive strength of the material, the maximum value in the collision speed time series data, and k v represents the velocity stress coefficient, which is used to normalize the influence of velocity on the compressive strength of the material.

[0120] Calculate the deformation suppression ratio of the candidate parameter combination under the collision angle to obtain the deformation suppression rate D θ , the formula is: Among them, D θ represents the deformation suppression rate at the collision angle, and δ o represents the original deformation amount, and δ c represents the deformation amount after compensation.

[0121] The compressive strength of the material needs to reserve a safety margin of 1.5 times, and the first proportional value can be 1.5; the second proportional value calculates the safe deformation amount through the elastic limit of the material, and is then determined through finite element simulation verification and industry standard calibration.

[0122] Screen for candidate parameter combinations that satisfy the compressive matching degree R v greater than the first proportional value and the deformation suppression rate D θ greater than the second proportional value.

[0123] When performing effectiveness verification, input the screened candidate parameter combinations into the finite element simulation model and re-simulate the collision process to verify whether the following indicators are simultaneously satisfied:

[0124] 1. Whether the maximum stress in the high stress area is lower than the compressive strength of the material.

[0125] 2. Whether the deformation amount in the medium stress area is lower than the safety threshold.

[0126] The verification results include valid and invalid.

[0127] In some embodiments, in S500, according to the collision condition feature set and the simulation verification feature set, a final optimization score result is generated, including:

[0128] S510. Align the collision speed time series data with the candidate parameter combinations in time series to generate a speed-parameter time series correlation matrix; cross-correlate the collision angle time series data with the stress area-frequency correlation matrix in the spatial dimension to generate an angle-matrix spatial correlation matrix.

[0129] To generate the speed-parameter time series correlation matrix, the candidate parameter combinations can be used as columns and the speed time series data as rows to generate the speed-parameter time series correlation matrix as follows:

[0130] [[ID=4�]]

[0131] The sliding window covariance formula can be used to calculate the correlation value between the speed and the candidate parameter combinations at each time step as the speed-parameter correlation value T ij .

[0132] If the speed-parameter time series correlation matrix is: It represents that the correlation value of the valid candidate parameter combination 1 is the highest at V(t2), and the compressive performance is the best.

[0133] Construct an angular-matrix spatial correlation matrix with the angular time-series data as rows and the covariance values of the stress area-frequency correlation matrix as columns as follows:

[0134]

[0135] Reference formula for the covariance correlation value between angle and stress area: S ik = θ(t i ) × Cov k ; where, S ik represents the spatial correlation value of the k-th stress area at the i-th time step, marked as the angular-matrix correlation value, Cov k represents the covariance value of the k-th stress area in the stress area-frequency correlation matrix, and θ(t i ) represents the normalized collision angle.

[0136] If the collision angles at time points t i are: θ(t1) = 30°, θ(t2) = 45°, θ(t2) = 60°, and the covariance values of the high, medium, and low stress areas and the fluctuation frequency are 0.85, 0.60, and 0.10 respectively, then the angular-matrix spatial correlation matrix is: It represents that the correlation value of the high stress area is the highest at θ(t3) = 60°, indicating that large-angle collisions require priority optimization of the high stress area.

[0137] S520. Use the anti-collision parameter optimization model to process the velocity-parameter time-series correlation matrix and the angular-matrix spatial correlation matrix. After the anti-collision parameter optimization model extracts the time correlation features and spatial correlation features, it performs feature merging and conflict resolution to generate the final optimized score result.

[0138] The anti-collision parameter optimization model can add a multi-modal input layer based on the gradient tree model, and the multi-modal input layer includes a time correlation branch and a spatial correlation branch.

[0139] The time correlation branch is used to receive the velocity-parameter time-series correlation matrix and extract time correlation features, such as the velocity-parameter correlation value; the spatial correlation branch is used to receive the angular-matrix spatial correlation matrix and extract spatial correlation features, such as the angular-matrix correlation value.

[0140] In some embodiments, the feature merging and conflict resolution in S520 include:

[0141] S521. Merge the time correlation features and the spatial correlation features according to the time step and the spatial position to generate a comprehensive feature.

[0142] Align the time correlation features and the spatial correlation features according to the time step and the stress area to generate a comprehensive feature matrix: F ijk = α × T ij + β × Sik ; among them, F ijk represents the element value in the comprehensive feature matrix, T ij represents the speed-parameter correlation value, S ik represents the angle-matrix correlation value, and α and β respectively represent T ij and S ik 's weight coefficients, which can be obtained through training.

[0143] S522. The verification results in the simulation verification feature set include invalid candidate parameter combinations and stress stability markers in unstable low-stress areas; according to the verification results in the simulation verification feature set, conflict resolution is performed on the comprehensive features, including:

[0144] If the verification result is marked as an invalid candidate parameter combination, the corresponding time-correlated feature is removed.

[0145] Exemplarily, if combination 2 is marked as invalid, the second column in the time-correlation matrix is deleted:

[0146]

[0147] After removing the invalid combinations, the computational amount can be effectively reduced.

[0148] If the verification result is marked as a stress stability marker in an unstable low-stress area, the influence range of the spatial correlation feature is restricted.

[0149] Exemplarily, when the low-stress area is unstable, only the time-correlated part in the low-stress area of the comprehensive feature matrix is retained: F ijk = 0.6×T ij + 0×S ik = 0.6×T ij .

[0150] After restricting the influence of the low-stress area, the noise interference in the unstable area can be reduced.

[0151] In S520, the comprehensive feature matrix is summed by row (candidate combination) and normalized to a percentage system:

[0152]

[0153] Among them, Score j represents the final optimized scoring result of the jth candidate parameter combination, which is used to quantify the comprehensive anti-collision performance of this combination, represents the sum of all time and stress zone characteristic values of the j-th combination to obtain the total score of the combination, N represents the total number of time steps, that is, the number of discrete time points in the collision process, j represents the number of the candidate parameter combination, i represents the time step index, stress zone index, 1 = high stress zone, 2 = medium stress zone, 3 = low stress zone, max(∑F) represents the maximum value of the total score of all combinations, which is used to normalize the scoring benchmark.

[0154] For example, if the total score of combination 1 is ∑F=2.30 and the total score of combination 2 is ∑F=1.80, then

[0155] The comprehensive crashworthiness of different candidate parameter combinations is directly quantified through percentage scoring, with higher values representing better solutions.

[0156] For example, the crash resistance of combination 1 is significantly better than that of combination 2, and it can be put into production or further verification first. Combination 2 scores lower, and its deficiencies in high-stress areas or high-speed collision scenarios need to be checked and targeted improvements should be made.

[0157] In some embodiments, as Figure 2 As shown, the present application provides a finite element simulation optimization system for the anti-collision performance of guardrails, which includes:

[0158] Data partitioning module: obtains guardrail collision finite element simulation data and divides the guardrail collision finite element simulation data into stress distribution feature set and collision condition feature set;

[0159] Feature fusion module: performs multi-dimensional feature fusion on the stress distribution feature set to generate a dynamic parameter feature set;

[0160] Solution generation module: generates anti-collision parameter optimization solutions based on dynamic parameter feature sets;

[0161] Effect verification module: performs anti-collision effect pre-verification on the anti-collision parameter optimization scheme and generates a simulation verification feature set;

[0162] Scoring output module: Generates the final optimization scoring results based on the collision condition feature set and simulation verification feature set.

[0163] In some embodiments, the present application provides a finite element simulation optimization device for the anti-collision performance of a guardrail, which includes a memory and a processor; the memory is used to store a computer program; and the processor is used to implement the steps of a finite element simulation optimization method for the anti-collision performance of a guardrail when executing the computer program.

[0164] In some embodiments, the present application provides a storage medium storing computer program instructions. When the computer program instructions are read and executed by a processor, the steps of a finite element simulation optimization method for the anti-collision performance of a guardrail are executed.

[0165] Any reference to memory, storage, database, or other media used in the embodiments provided by the present invention may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory.

[0166] It should be noted that, in this document, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including", or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the presence of additional identical elements in the process, method, article, or device comprising the element.

[0167] Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A finite element simulation optimization method for the anti-collision performance of guardrail plates, characterized in that, Including: Obtain finite element simulation data of guardrail plate collision, and divide the finite element simulation data of guardrail plate collision into a stress distribution feature set and a collision condition feature set; Perform multi-dimensional feature fusion on the stress distribution feature set to generate a dynamic parameter feature set; Generate an anti-collision parameter optimization scheme according to the dynamic parameter feature set; Perform pre-verification of anti-collision effect on the anti-collision parameter optimization scheme to generate a simulation verification feature set; Generate a final optimization score result according to the collision condition feature set and the simulation verification feature set.

2. The method according to claim 1, wherein Performing multi-dimensional feature fusion on the stress distribution feature set to generate a dynamic parameter feature set includes: Set a specified number of stress zones, divide all stress zones according to the maximum stress value of each stress zone, and extract independent features of each stress zone; Perform time-series correlation analysis on the stress fluctuation frequency and the independent features of each stress zone to generate a zone-frequency correlation matrix; Based on the correlation matrix, screen out abnormal fluctuation zones to generate a dynamic parameter feature set.

3. The method according to claim 2, characterized in that, Set a specified number of stress zones, divide all stress zones according to the maximum stress value of each stress zone, and extract independent features of each stress zone, including: Divide the guardrail plate into high stress zones, medium stress zones, and low stress zones according to the numerical distribution of the maximum stress value sequence and the preset stress critical value; For high stress zones: Extract the stress peak interval and fluctuation frequency as independent features; For medium stress zones: Extract the stress attenuation rate and thickness distribution correlation parameters as independent features; For low stress zones: Extract the stress stability mark as an independent feature.

4. The method according to claim 3, wherein Generating an anti-collision parameter optimization scheme according to the dynamic parameter feature set includes: Use an anti-collision optimization model to process the anti-collision parameter optimization scheme. The anti-collision optimization model adds a multi-modal input layer on the basis of a gradient tree and generates an anti-collision parameter optimization scheme through a joint splitting rule.

5. The method according to claim 4, wherein The anti-collision optimization model adds a multi-modal input layer on the basis of a gradient tree and generates an anti-collision parameter optimization scheme through a joint splitting rule, including: The multi-modal input layer includes a first channel and a second channel; the first channel is used to receive the independent features of high stress zones and calculate the compressive strength matching degree of material replacement types, and the second channel is used to receive the independent features of medium stress zones and low stress zones and calculate the deformation inhibition rate of the thickness compensation gradient; Compare the compressive strength matching degree with a preset compressive strength threshold. If the compressive strength matching degree exceeds the compressive strength threshold, generate a matching scheme for the material replacement type in the high stress zone; compare the deformation inhibition rate with a preset deformation threshold. If the deformation inhibition rate is lower than the deformation threshold, generate an increment scheme for the thickness compensation gradient based on the correlation features of the medium stress zone and the correlation features of the low stress zone; According to the abnormal fluctuation zones, perform spatial superposition on the material replacement scheme and the increment scheme of thickness compensation; According to the superimposed result, output an anti-collision parameter optimization scheme including the material thickness adjustment value and the stress concentration zone correction parameter.

6. The method according to claim 5, wherein Performing pre-verification of anti-collision effect on the anti-collision parameter optimization scheme to generate a simulation verification feature set includes: Generate multiple groups of candidate parameter combinations according to the material thickness adjustment value and the stress concentration zone correction parameter; Perform two-way correlation degree analysis and screening according to multiple groups of candidate parameter combinations and the collision condition feature set; Perform validity verification on the screened candidate parameter combinations to obtain verification results; The simulation verification feature set is generated with the screened candidate parameter combinations as rows, the stress area-frequency correlation matrix as columns, and the verification results as matrix element values.

7. The method according to claim 6, characterized in that, Based on multiple sets of candidate parameter combinations and collision condition feature sets, two-way correlation analysis and screening are performed, including: The candidate parameter combinations are input into the anti-collision optimization model to obtain the calculation results of the compression matching degree under the collision velocity time series data; the candidate parameter combinations are input into the anti-collision optimization model to obtain the calculation results of the deformation suppression rate under the collision contact angle sequence; Candidate parameter combinations are retained, for which the calculated results of the compression resistance matching degree exceed a preset first proportional value and the calculated results of the deformation suppression rate exceed a preset second proportional value.

8. The method according to claim 6, wherein Based on the collision condition feature set and the simulation verification feature set, the final optimization scoring results are generated, including: The collision velocity time series data is aligned with the candidate parameter combination to generate a velocity-parameter time series correlation matrix; the collision angle time series data is cross-correlated with the stress area-frequency correlation matrix in the spatial dimension to generate an angle-matrix spatial correlation matrix; The anti-collision parameter optimization model is used to process the speed-parameter temporal correlation matrix and the angle-matrix spatial correlation matrix. The anti-collision parameter optimization model extracts the temporal correlation features and spatial correlation features, then performs feature merging and conflict resolution to generate the final optimization score result.

9. The method according to claim 8, wherein Perform feature merging and conflict resolution, including: Combine temporal correlation features and spatial correlation features according to time steps and spatial positions to generate comprehensive features; The verification results in the simulation verification feature set include invalid candidate parameter combinations and unstable low-stress area stress stability marks; based on the verification results in the simulation verification feature set, conflict resolution is performed on the comprehensive features, including: If the verification result marks the candidate parameter combination as invalid, the corresponding time-related features are eliminated; If the verification result marks the stress stability mark of the unstable low stress area, the influence range of the spatial correlation feature is limited.

10. The finite element simulation and optimization system for the anti-collision performance of guardrail plates, characterized in that, It includes: Data partitioning module: obtaining guardrail collision finite element simulation data, and dividing the guardrail collision finite element simulation data into a stress distribution feature set and a collision condition feature set; Feature fusion module: performing multi-dimensional feature fusion on the stress distribution feature set to generate a dynamic parameter feature set; Solution generation module: generates anti-collision parameter optimization solutions based on dynamic parameter feature sets; Effect verification module: performs anti-collision effect pre-verification on the anti-collision parameter optimization scheme and generates a simulation verification feature set; Scoring output module: Generates the final optimization scoring results based on the collision condition feature set and simulation verification feature set.

Images