An automobile bumper parameter determination method and system based on AI modeling

Abstract

The application discloses a kind of automobile bumper parameter determination method and system based on AI modeling, it is related to AI modeling technical field, for solving the problem that automobile bumper parameter determination exists deviation, by calling the bumper parameter data package and confirmation mechanism of AI modeling, according to the collision angle selection impact point and the distance calculation side angle impact score with door, carry out simulation impact experiment, obtain the diagonal deformation difference and extrusion pressure difference of front and rear bumpers and generate diagonal response score, and combined with side angle impact score, obtain the collision angle impact coefficient, mark as side or frontal impact, call side impact label and count quantity, judge whether parameter supplement rule is introduced;Maximum deformation and residual deformation are collected to calculate deformation recovery rate, combined with the number of side impact labels to obtain fatigue supplement coefficient, according to fatigue supplement coefficient to judge whether deformation recovery rate is introduced, and after screening, import parameter confirmation mechanism, realize the intelligent distinction of impact mode under different collision angles.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of AI modeling, more specifically, the present application relates to a kind of automobile bumper parameter determination method and system based on AI modeling. BACKGROUND

[0002] With the development of automobile industry, the safety problem that vehicle faces in the running process is increasingly prominent.As an important part of energy-absorbing structure, automobile bumper needs to play the role of reducing impact and reducing damage in different working conditions such as front collision, side collision and oblique angle collision. The existing bumper parameter determination method mainly depends on finite element simulation or real vehicle test, and the performance of bumper is evaluated through front collision data. When facing complex collisions such as side impact and oblique impact, it is often difficult to accurately classify.

[0003] The prior art has the following shortcomings:

[0004] At present, due to different collision angles, when the current bumper is subjected to left side collision, the rear bumper often shows right side extrusion, that is, the four corners of the front and rear bumpers form diagonal extrusion on the other bumper during the collision process, it is difficult to clearly distinguish between front collision and side collision, and the front or side impact mode of the front and rear bumpers cannot be clearly marked during the collision process. In the AI modeling scene, the introduction of metal fatigue parameters lacks dynamic adjustment, which leads to deviation in subsequent parameter determination, and is prone to parameter lag or overcorrection, further reducing the accuracy of automobile bumper parameter determination. Therefore, a kind of automobile bumper parameter determination method and system based on AI modeling is proposed.

[0005] The above information disclosed in the background section is only used to strengthen the understanding of the background of the present disclosure, and therefore it can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0006] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present application provide a kind of automobile bumper parameter determination method and system based on AI modeling, which solves the problems proposed in the above-mentioned background technology by using multi-angle collision score calculation, diagonal response coefficient marking and fatigue supplementary parameter dynamic introduction mechanism.

[0007] To achieve the above-mentioned purpose, the present application provides the following technical scheme, a kind of automobile bumper parameter determination method based on AI modeling, comprising the following steps:

[0008] Step S1: call the automobile bumper parameter data package of AI modeling and bumper parameter confirmation mechanism, set the distance between each impact point and the door at the collision angle to calculate the side impact score;

[0009] Step S2: According to the collision angle, the simulation impact experiment is carried out, the deformation difference of the front and rear bumpers is obtained, the diagonal response score is obtained, the collision angle is marked as side impact or frontal impact, and the collision coefficient of the collision angle is obtained;

[0010] Step S3: The side impact label is called, the number is counted, whether the parameter supplement rule is input, the maximum deformation of the bumper after each simulation is collected, the residual deformation of the collision object after unloading is calculated, the deformation recovery rate of the bumper is calculated, the fatigue supplement coefficient is obtained combined with the number of side impact labels;

[0011] Step S4: According to the fatigue supplement coefficient, whether the deformation recovery rate is introduced as a parameter is analyzed, the deformation recovery rate is processed and screened, and the bumper parameter confirmation mechanism is introduced.

[0012] In a preferred embodiment, in step S1, the AI modeling automobile bumper parameter data package and the bumper parameter confirmation mechanism are called through the control instruction interface;

[0013] The AI modeling automobile bumper parameter data package refers to a multi-dimensional parameter set generated based on finite element simulation data, collision experiment data and vehicle geometric structure data in the training stage;

[0014] The bumper parameter confirmation mechanism refers to a calculation rule set for retrieving, calling and dynamically correcting the parameters in the data package under different collision conditions.

[0015] In a preferred embodiment, in step S1, the corresponding impact points are determined through the collision angles pre-set in the AI modeling automobile bumper parameter data package;

[0016] The spatial coordinates of the impact points and the spatial coordinates of the door reference points are obtained in the automobile coordinate system, and the distances between the impact points and the door are calculated through the Euclidean distance formula;

[0017] The side impact score is obtained by subtracting the distance between the impact points and the door after standardization from 1, and the specific calculation formula is as follows:

[0018] ;

[0019] In the formula, is the distance between the impact points and the door after standardization, is the side impact score corresponding to the i-th collision angle, i=1, 2, …, n, wherein n is the total number of collision angles, and i is the i-th collision angle.

[0020] In a preferred embodiment, in step S2, based on the preset multiple sets of collision angles in the AI modeled automobile bumper parameter data package, the front end or side front end area of the automobile is subjected to controlled simulation test, and the corresponding front and rear bumper diagonal deformation difference and extrusion force difference are generated;

[0021] The normalized front and rear bumper diagonal deformation difference and extrusion force difference are multiplied to obtain the diagonal response score.

[0022] In a preferred embodiment, in step S2, the diagonal response score and the side angle impact score are substituted into the polynomial regression calculation to obtain the collision angle impact coefficient;

[0023] If the collision angle impact coefficient exceeds the side threshold value, the current collision angle is marked as a side impact;

[0024] If the collision angle impact coefficient is lower than the side threshold value, the current collision angle is marked as a frontal impact and introduced into the bumper parameter confirmation mechanism.

[0025] In a preferred embodiment, in step S3, the number of collisions marked as side impact in the simulation experiment is counted, which is denoted as the side impact label number;

[0026] If the side impact label number exceeds the preset number threshold value, it is determined that the parameter supplement rule is introduced;

[0027] If the side impact label number is lower than the preset number threshold value, it is determined that the parameter supplement rule is not introduced.

[0028] In a preferred embodiment, in step S3, when the parameter supplement rule is introduced, the maximum deformation and the residual deformation after the collision object is unloaded are collected according to the simulation impact experiment;

[0029] The maximum deformation represents the maximum instantaneous displacement value of the bumper at each vertex under the action of collision;

[0030] The residual deformation after the collision object is unloaded represents the deformation value retained by the bumper after the collision object is unloaded;

[0031] Based on the maximum deformation and the residual deformation after the collision object is unloaded, the deformation recovery rate of the bumper is calculated;

[0032] The fatigue supplement coefficient is calculated by combining the side impact label number and the deformation recovery rate.

[0033] In a preferred embodiment, in step S4, when the fatigue supplement coefficient exceeds the fatigue determination threshold value, it is determined that the deformation recovery rate is introduced as a parameter to be introduced;

[0034] When the fatigue supplement coefficient is lower than the fatigue determination threshold, it is determined that the deformation recovery rate is not a parameter to be introduced;

[0035] When it is determined that the deformation recovery rate is a parameter to be introduced, the deformation recovery rate is processed and screened.

[0036] In a preferred embodiment, in step S4, the median absolute deviation algorithm is used to calculate the abnormality determination value of each deformation recovery rate;

[0037] The deformation recovery rates with abnormality determination values lower than or equal to the preset deviation coefficient threshold are screened out and are arithmetically averaged to obtain the screened deformation recovery rate;

[0038] The screened deformation recovery rate is introduced into the bumper parameter confirmation mechanism;

[0039] The bumper parameter confirmation mechanism increases the deformation recovery rate as an additional parameter input on the basis of the original parameter system.

[0040] An automobile bumper parameter determination system based on AI modeling includes a collision scoring module, an angle evaluation module, a coefficient calculation module, and a screening and introduction module, and the functions of each module are as follows:

[0041] The collision scoring module is used to call the AI modeling automobile bumper parameter data package and the bumper parameter confirmation mechanism, set the collision angle, select the distance between each impact point and the door, and calculate the side angle impact score.

[0042] The angle evaluation module is used to simulate the impact experiment according to the collision angle, obtain the deformation difference and extrusion force difference of the front and rear bumpers, obtain the diagonal response score, combine the side angle impact score to obtain the collision angle coefficient, and mark each collision angle as a side impact or a frontal impact.

[0043] The coefficient calculation module is used to call the side impact label, count the number, select whether to pass in the parameter supplement rule, collect the maximum deformation of the bumper after each simulation and the residual deformation after the collision object is unloaded according to the simulation impact experiment, calculate the deformation recovery rate of the bumper, and combine the number of side impact labels to obtain the fatigue supplement coefficient.

[0044] The screening and introduction module is used to analyze whether the deformation recovery rate is a parameter to be introduced according to the fatigue supplement coefficient, and introduce the deformation recovery rate into the bumper parameter confirmation mechanism after processing and screening.

[0045] The technical effects and advantages of the present application are as follows:

[0046] The application calls AI modeling automobile bumper parameter data package and bumper parameter confirmation mechanism, sets the distance between each impact point and the door to calculate the side angle impact score according to the collision angle, carries out simulation impact experiment according to the collision angle, obtains the diagonal deformation difference and extrusion force difference of the front and rear bumpers to obtain the diagonal response score, combines the side angle impact score to obtain the collision angle impact coefficient and marks each collision angle as side impact or frontal impact, calls the side impact label and counts the number to select whether to input parameter supplement rules, calculates the deformation recovery rate of the bumper according to the maximum deformation of the bumper after each simulation and the residual deformation after the collision object is unloaded, combines the number of side impact labels to obtain the fatigue supplement coefficient, analyzes whether the deformation recovery rate is introduced as a parameter according to the fatigue supplement coefficient, imports the deformation recovery rate into the bumper parameter confirmation mechanism after processing and screening, realizes the intelligent differentiation of the impact mode under different collision angles, and improves the flexibility of the introduction of the bumper metal fatigue factor. BRIEF DESCRIPTION OF DRAWINGS

[0047] Figure 1 The method flowchart of the application is a kind of automobile bumper parameter determination method based on AI modeling.

[0048] Figure 2 The module schematic diagram of the application is a kind of automobile bumper parameter determination system based on AI modeling. DETAILED DESCRIPTION

[0049] The technical solutions in the embodiments of the application will be described clearly and completely below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, not all. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the application.

[0050] The application calls an AI modeling automobile bumper parameter data package and a bumper parameter confirmation mechanism, sets a collision angle, selects the distance between each impact point and the door to calculate a side angle impact score, carries out a simulation impact experiment according to the collision angle, obtains a diagonal deformation difference and an extrusion force difference of front and rear bumpers to obtain a diagonal response score, combines the side angle impact score to obtain a collision angle impact coefficient, and marks each collision angle as a side impact or a frontal impact, calls a side impact label and counts the number to select whether to input a parameter supplement rule, calculates a bumper deformation recovery rate according to the maximum deformation of the bumper after each simulation and the residual deformation after unloading the collision object according to the simulation impact experiment, combines the number of side impact labels to obtain a fatigue supplement coefficient, analyzes whether to take the deformation recovery rate as a parameter to be introduced according to the fatigue supplement coefficient, imports the deformation recovery rate into the bumper parameter confirmation mechanism after processing and screening, and realizes intelligent differentiation of impact modes under different collision angles.

[0051] Embodiment 1

[0052] Please refer to Figure 1 An AI modeling automobile bumper parameter determination method, and the specific operation process is as follows:

[0053] Step S1: calling an AI modeling automobile bumper parameter data package and a bumper parameter confirmation mechanism, setting a collision angle, selecting the distance between each impact point and the door to calculate a side angle impact score;

[0054] Step S2: according to the collision angle, carrying out a simulation impact experiment, obtaining a diagonal deformation difference and an extrusion force difference of front and rear bumpers to obtain a diagonal response score, combining the side angle impact score to obtain a collision angle impact coefficient, and marking each collision angle as a side impact or a frontal impact;

[0055] Step S3: calling a side impact label and counting the number to select whether to input a parameter supplement rule, calculating a bumper deformation recovery rate according to the maximum deformation of the bumper after each simulation and the residual deformation after unloading the collision object according to the simulation impact experiment, combining the number of side impact labels to obtain a fatigue supplement coefficient;

[0056] Step S4: according to the fatigue supplement coefficient, analyzing whether to take the deformation recovery rate as a parameter to be introduced, and importing the deformation recovery rate into the bumper parameter confirmation mechanism after processing and screening.

[0057] The specific implementation process is as follows:

[0058] In step S1, the AI modeling automobile bumper parameter data package and the bumper parameter confirmation mechanism are called through a control instruction interface;

[0059] The control instruction interface refers to a data interaction channel provided by the AI modeling to the outside, used for parameter input, result output and label calling between the modeling environment and the parameter confirmation mechanism.

[0060] Further, the AI modeling automobile bumper parameter data package refers to a multi-dimensional parameter set generated based on finite element simulation data, collision experiment data and vehicle geometric structure data in the training stage, which includes but is not limited to the multi-dimensional mapping relationship of bumper material density, elastic modulus, yield strength, ultimate tensile strength, Poisson's ratio, thickness, deformation threshold and collision angle.

[0061] Further, the bumper parameter confirmation mechanism refers to a calculation rule set for retrieving, calling and dynamically correcting the parameters in the data package under different collision conditions, used for determining the parameter changes of the AI modeling automobile bumper.

[0062] The collision angle in the AI modeling automobile bumper parameter data package is determined to determine the corresponding impact points.

[0063] The distance between each impact point and the door is obtained based on the geometric center of the automobile, establishing an automobile coordinate system and setting a door reference point, obtaining the spatial coordinates of the impact points and the spatial coordinates of the door reference point in the automobile coordinate system, and calculating the distance between each impact point and the door by the Euclidean distance formula.

[0064] Optionally, the specific implementation is as follows: based on the geometric center of the automobile, the automobile is equally divided according to the number of doors, for example, for a two-door automobile, the geometric center of the automobile is equally divided to obtain a right half automobile part and a left half automobile part, wherein the right half automobile part and the left half automobile part correspond to the right door and the left door respectively, further, for a four-door automobile, the geometric center of the automobile and the number of doors are equally divided to obtain a right front quarter automobile part, a left front quarter automobile part, a right rear quarter automobile part and a left rear quarter automobile part, and each quarter automobile part corresponds to a right front door, a left front door, a right rear door and a left rear door, etc. Therefore, it can be seen that the distance between each impact point and the door refers to the distance between the spatial coordinates of the door corresponding to each part after equal division, and each impact point is also divided according to the equal division result, for example, if the equal division result is a right front quarter automobile part, a left front quarter automobile part and a right rear quarter automobile part, the impact point is in the left front quarter automobile part, then the impact point is divided into the left front quarter automobile part and its spatial coordinates are calculated, the spatial coordinates of the impact point and the spatial coordinates of the reference point of the left front door are calculated by the Euclidean distance, and the distance between each impact point and the door is obtained, etc. The specific implementation or division method is not limited, and in this example, only this example is used as an implementation means, which is not described here.

[0065] Specifically, the door reference point is determined by the present inventors according to the door area and the door hinge installation coordinates in the AI modeled automobile bumper parameter data package, and the door geometric boundary parameters are used to limit the boundary range of the door in the vehicle coordinate system, wherein the hinge installation coordinates are used to locate the reference point of the door at the geometric center, and the spatial coordinates of the door reference point are obtained in combination with the door area;

[0066] Further, the Euclidean distance formula is well known to those skilled in the art, and the specific implementation method is not limited, and will not be described here;

[0067] The distance between each impact point and the door is standardized, so that the numerical value of the distance between each impact point and the door is expressed between 0 and 1;

[0068] It should be noted that the standardization processing method includes but is not limited to standard linear transformation based on interval scaling, Z-Score standardization method based on statistics, or normalization method based on nonlinear mapping function, and the application method of standardization processing will not be described here;

[0069] The distance between each impact point and the door after standardization is substituted into the side impact score calculation formula, specifically as follows: subtracting the distance between each impact point and the door after standardization from 1 to obtain the side impact score, and the specific calculation formula is as follows:

[0070] ;

[0071] In the formula, is the distance between each impact point and the door after standardization, is the side impact score corresponding to the i-th impact angle, i = 1, 2, …, n, wherein n is the total number of impact angles, and i is the i-th impact angle;

[0072] Wherein, the side impact score corresponds to each impact angle, so the number of impact angles is consistent with the number of side impact scores.

[0073] In step S2, the simulation impact experiment according to the impact angle is a controlled simulation test on the front end or side front end region of the automobile based on the multiple impact angles preset in the AI modeled automobile bumper parameter data package;

[0074] Wherein, the simulation impact experiment is performed by a virtual impact body (such as a standardized rigid barrier or a deformable moving barrier) at a fixed speed and a fixed mass, only changing the included angle (i.e. impact angle) with the geometric center line of the vehicle to perform multiple impact experiments, thereby generating the difference value of the deformation amount and the extrusion force of the front and rear bumpers at different angle conditions.

[0075] It should be noted that simulated impact experiments were conducted for each collision angle, focusing on the four corner vertices of the front and rear bumpers, namely the left front vertex, right front vertex, left rear vertex, and right rear vertex. The four corner vertices were defined as two pairs of opposite corners, namely the left front and right rear vertex as one pair of opposite corners, and the right front and left rear vertex as the other pair of opposite corners. For the two pairs of opposite corners, the difference in deformation and the difference in compressive force of the front and rear bumper opposite corners at each collision angle were analyzed.

[0076] The logic for obtaining the difference in deformation between the front and rear bumpers at the diagonal is as follows: under the collision angle, two preset diagonal combinations are selected respectively. For each diagonal combination, the maximum deformation of the corresponding corner point under the collision angle is obtained. The absolute difference of each diagonal combination is calculated to obtain the difference in deformation of each diagonal combination and then accumulated to obtain the difference in deformation between the front and rear bumpers at the diagonal.

[0077] Specifically, the two sets of opposite corners have been described above and will not be repeated here;

[0078] Furthermore, if the left front and right rear vertices and the diagonal points opposite the right front and left rear vertices are selected as diagonal combinations, then the formula for calculating the deformation difference of each diagonal combination is:

[0079] ;

[0080] In the formula, Let A be the difference in deformation between the diagonal combinations. Let B be the difference in deformation between the two diagonal combinations. In the collision angle The maximum deformation of the lower left front vertex In the collision angle The maximum deformation of the bottom right rear vertex In the collision angle The maximum deformation of the lower right front vertex. In the collision angle The maximum deformation of the bottom left rear vertex;

[0081] The maximum deformation refers to the maximum value of the displacement vector magnitude of the vertex in the three-dimensional coordinate system during the entire collision process. That is, the initial coordinates of the vertex are recorded at the beginning of the collision simulation time and the deformed coordinates of the vertex are recorded after the collision simulation time ends. The maximum deformation is obtained by calculating the Euclidean distance between the deformed coordinates and the initial coordinates.

[0082] Furthermore, the deformation difference between the diagonal combinations of A and B is accumulated to calculate the deformation difference between the front and rear bumpers.

[0083] The obtaining logic of the extrusion force difference of the front and rear bumper diagonals is that, under the collision angle, two preset diagonal groups are selected as diagonal combinations respectively, the peak extrusion force of the corresponding corner point under the collision angle is obtained for each diagonal combination, the peak extrusion force of each diagonal combination is subjected to absolute difference calculation to obtain the extrusion force difference of each diagonal combination, and the extrusion force difference of the front and rear bumper diagonals is obtained through accumulation calculation;

[0084] Specifically, the peak extrusion force refers to the maximum value of the contact force transmitted along the normal direction at the vertex during the entire collision process; in the AI modeling scene, the inner product of the contact force vector at each time and the unit normal vector of the vertex is calculated by sampling the normal contact force sequence at each time during the collision simulation process, and the maximum value of the inner product is selected within the entire collision simulation time, which is taken as the peak extrusion force;

[0085] The deformation difference and the extrusion force difference of the front and rear bumper diagonals are subjected to standardization processing, so that the deformation difference and the extrusion force difference of the front and rear bumper diagonals are kept in the same dimension and the numerical expression is between 0 and 1;

[0086] Specifically, the standardization processing has been described above and will not be repeated here;

[0087] The deformation difference and the extrusion force difference of the front and rear bumper diagonals after standardization processing are subjected to product calculation to obtain the diagonal response score;

[0088] It should be noted that since the deformation difference and the extrusion force difference of the front and rear bumper diagonals are subjected to standardization processing, the numerical expression is between 0 and 1, so it can be determined that the diagonal response score is dimensionless and the numerical expression is between 0 and 1, and the maximum numerical expression is 1, for example, even if the deformation difference and the extrusion force difference of the front and rear bumper diagonals are both the maximum value 1, the product calculation result is still 1, which will not be repeated here;

[0089] The diagonal response score and the side angle impact score are substituted into the polynomial regression calculation to obtain the collision angle impact coefficient, and the specific formula expression is as follows:

[0090] ;

[0091] In the formula, is the i th collision angle impact coefficient, is the diagonal response score corresponding to the i th collision angle, is the side angle impact score corresponding to the i th collision angle, is an adjustment parameter, and The weight coefficient corresponding to the diagonal response score and the side angle impact score is a=ai, i=1, 2, …, n, wherein n is the total number of impact angles, and i is the i th impact angle;

[0092] It should be noted that the order and form of the polynomial regression calculation formula in the present application can be selected according to actual application requirements, and the specific order and function form are not limited herein, and a person skilled in the art can determine them according to the characteristics of the AI modeling scene, which will not be repeated here.

[0093] It should be noted that the weight coefficient mentioned in the polynomial regression calculation formula is obtained by the present experimenters according to the loss function minimization principle and the corresponding optimization algorithm (such as ordinary least squares method, gradient descent method, etc.), which is the common knowledge of a person skilled in the art, and will not be repeated here.

[0094] It should be noted that when the diagonal response score and the side angle impact score are larger, the deformation and stress characteristics of the collision are more significant, the collision risk degree is higher, and the collision coefficient of the impact angle is larger, which is more inclined to be marked as a side impact. On the contrary, when the diagonal response score and the side angle impact score are smaller, the vehicle mainly shows the axial front stress characteristics, the collision coefficient is smaller, and it is more inclined to be marked as a frontal impact.

[0095] The collision coefficient of each impact angle is compared with the preset side threshold value.

[0096] If the collision coefficient of the impact angle exceeds the side threshold value, the current impact angle is marked as a side impact.

[0097] If the collision coefficient of the impact angle is lower than the side threshold value, the current impact angle is marked as a frontal impact and introduced into the bumper parameter confirmation mechanism.

[0098] It should be noted that the side threshold value is set by the present experimenters according to the geometric characteristics of the vehicle structure and the historical collision experiment data, which will not be repeated here.

[0099] Further, introducing the collision angle marked as a frontal impact into the bumper parameter confirmation mechanism is used for dynamically correcting and confirming the performance parameters of the bumper under the condition of facing a frontal impact, which will not be repeated here.

[0100] In step S3, the side impact label is called and the number is counted, and whether the parameter supplement rule is passed is selected according to the side impact label:

[0101] After the simulation impact experiment of each impact angle, the stress conditions of the front and rear bumpers in each simulation impact process are recorded according to the comparison result of the collision coefficient of the impact angle and the preset side threshold value, and the corresponding side impact label is generated, which is used to identify whether the impact angle belongs to a side impact.

[0102] After the side impact label is acquired, the number of collisions marked as side impact in the simulation experiment is counted, denoted as the side impact label number, which is used to reflect the frequency of side force of the bumper under different collision angles.

[0103] The side impact label number is compared with a preset number threshold value:

[0104] If the side impact label number exceeds the preset number threshold value, it is determined that the parameter supplement rule is introduced;

[0105] If the side impact label number is lower than the preset number threshold value, it is determined that the parameter supplement rule is not introduced;

[0106] It should be noted that the preset number threshold value is a critical standard for determining whether the parameter supplement rule needs to be introduced. By collecting a large amount of simulation data of vehicle collision tests and counting the data distribution of different vehicle side collision times, the number of side collisions at which the recovery ability of the vehicle bumper begins to show a decreasing trend is determined as the number threshold value. For example, when the number of side collisions reaches 5 times, the average decrease of the recovery ability of the bumper is more than 10%, and the number threshold value is preset to 5. That is, when the side impact label number in the simulation experiment exceeds 5, it is determined that the parameter supplement rule is introduced.

[0107] When the parameter supplement rule is introduced, the maximum deformation amount generated by the bumper during the collision process before and after the simulation impact experiment is collected, as well as the residual deformation amount after the collision object is unloaded;

[0108] Among them, the maximum deformation amount represents the maximum instantaneous displacement value of the bumper at each vertex under the action of collision, reflecting the instantaneous deformation ability of the bumper; the residual deformation amount after the collision object is unloaded represents the deformation value still retained by the bumper after the collision object is unloaded, which is used to evaluate the shape recovery ability of the bumper;

[0109] Based on the maximum deformation amount and the residual deformation amount after the collision object is unloaded, the deformation recovery rate of the bumper is calculated, and the calculation formula is:

[0110] ;

[0111] Among them, is the deformation recovery rate, is the maximum deformation amount, is the residual deformation amount after the collision object is unloaded.

[0112] Specifically, the maximum instantaneous displacement value of each vertex is recorded at each collision, and after the simulation impact experiment is completed, the maximum value of the maximum instantaneous displacement value of each vertex is selected as the maximum deformation amount;

[0113] Further, when the maximum deformation is selected, the deformation value of the vertex corresponding to the maximum deformation that is still retained by the bumper after the collision object is unloaded is taken as the residual deformation after the collision object is unloaded;

[0114] The deformation recovery rate reflects the fatigue characteristics of the bumper material and structure, and the value range is 0 to 1. The closer the value is to 1, the stronger the recovery ability of the bumper after the collision is unloaded. The closer the value is to 0, the greater the residual deformation of the bumper, and the weaker the recovery ability.

[0115] The fatigue supplement coefficient is further calculated in combination with the side impact label quantity and the deformation recovery rate, and the specific calculation formula is as follows:

[0116] ;

[0117] wherein, is the fatigue supplement coefficient, is the side impact label quantity, is a quantity threshold value for normalizing the side impact label quantity, is the deformation recovery rate, and is a weight coefficient for adjusting the influence degree of the side impact label quantity and the deformation recovery rate on the fatigue supplement coefficient.

[0118] Specifically, the fatigue supplement coefficient has only one numerical expression quantity. Since the deformation recovery rate obtained by selecting each vertex in the deformation recovery rate calculation process (i.e., selecting the maximum value as the maximum deformation according to the maximum instantaneous displacement value of each vertex) has only one vertex, the numerical expression quantity of the fatigue supplement coefficient is consistent with the numerical expression quantity of the deformation recovery rate, which will not be described here.

[0119] It should be noted that the weight coefficient is set by regression analysis on historical collision experiment data. The contribution degree of the side impact label quantity and the deformation recovery rate to the residual deformation accumulation and material fatigue performance of the bumper is compared, and then the value range of the weight coefficient is determined. For example, in a group of experimental data, when the number of side impact increases, the increase rate of the residual deformation of the bumper accounts for 60% of the overall fatigue performance, and the influence caused by the decrease of the deformation recovery rate accounts for 40%. Therefore, the is set to 0.6, and the is set to 0.4.

[0120] The fatigue supplement coefficient reflects the fatigue influence that the bumper may have due to repeated stress under multiple side impact conditions. The greater the side impact label quantity, the lower the deformation recovery rate, and the greater the fatigue supplement coefficient, thereby prompting the bumper parameter confirmation mechanism to introduce a fatigue factor in subsequent parameter optimization. When the side impact label quantity is smaller, the deformation recovery rate is higher, and the fatigue supplement coefficient is smaller, it means that no additional parameters need to be introduced.

[0121] In step S4, it is determined whether the deformation recovery rate is introduced as a parameter according to the fatigue supplement coefficient, and the deformation recovery rate is processed and screened before being introduced into the bumper parameter confirmation mechanism;

[0122] The fatigue supplement coefficient is determined according to a preset fatigue determination threshold value:

[0123] When the fatigue supplement coefficient exceeds the fatigue determination threshold value, it indicates that the bumper has fatigue accumulation effect under multiple collision conditions, and it is determined that the deformation recovery rate is introduced as a parameter;

[0124] When the fatigue supplement coefficient is lower than the fatigue determination threshold value, it indicates that the fatigue accumulation effect of the bumper is not significant, and it is determined that the deformation recovery rate is not introduced as a parameter.

[0125] It should be noted that the fatigue determination threshold value is used as a reference to determine whether the fatigue supplement coefficient reaches a significant level, and its value is set by collecting a large number of experimental data of bumpers under different collision times and deformation recovery rates. By comparing the residual deformation accumulation of the bumper structure in different coefficient intervals, the critical point at which the performance of the bumper begins to significantly degrade is determined as the fatigue determination threshold value. For example, in a set of statistical experiments, when the fatigue supplement coefficient reaches 0.8, the residual deformation of the bumper exceeds 25% of the maximum deformation on average. Therefore, the fatigue determination threshold value is preset to 0.8, that is, when the fatigue supplement coefficient exceeds 0.8, the deformation recovery rate is determined as a parameter to be introduced.

[0126] When it is determined that the deformation recovery rate is introduced as a parameter, the deformation recovery rate is processed and screened:

[0127] The deformation recovery rates of multiple simulation impact experiments are constructed into a deformation recovery rate data set;

[0128] The median of the deformation recovery rate data set is obtained, and the deformation recovery rate median is obtained;

[0129] The absolute value of the deviation of each deformation recovery rate from the median is calculated, and a deviation set is constructed;

[0130] The median of the deviation set is obtained, and the deviation median is obtained;

[0131] The difference between each deformation recovery rate and the deformation recovery rate median is divided by the deviation median to obtain the abnormality determination value of each deformation recovery rate;

[0132] The abnormality determination value is compared with a preset deviation coefficient threshold value:

[0133] When the abnormality determination value is greater than the preset deviation coefficient threshold value, it is determined that the deformation recovery rate is an abnormal value and is removed;

[0134] If not, it is determined that the deformation recovery rate is not an abnormal value and is retained.

[0135] It should be noted that the deviation coefficient threshold is a reference for determining whether the deformation recovery rate is an abnormal value. According to statistical standards, the deviation coefficient threshold can be 2.5 or 3. For example, in a set of experimental data, the abnormal determination value of the deformation recovery rate is calculated to be 3.2, and when the deviation coefficient threshold is preset to 3, the deformation recovery rate is determined to be an abnormal value and is rejected. If the abnormal determination value is 2.1, it is retained.

[0136] After the abnormal value is removed, the retained deformation recovery rate is calculated by arithmetic mean, and the screened deformation recovery rate is obtained.

[0137] The screened deformation recovery rate is introduced into the bumper parameter confirmation mechanism. The bumper parameter confirmation mechanism increases the deformation recovery rate as an additional parameter input on the basis of the original parameter system, and is used to correct and optimize the performance parameter feedback of the bumper under low-speed and side collision conditions.

[0138] By introducing the deformation recovery rate into the confirmation mechanism, the accuracy of the bumper parameter under complex collision scenarios is improved, and the final parameter determination result is more consistent with the actual use conditions.

[0139] Example 2

[0140] Please refer to Figure 2 An AI modeling-based automobile bumper parameter determination system, comprising a collision scoring module, an angle evaluation module, a coefficient calculation module and a screening import module, and each module has the following functions:

[0141] The collision scoring module is used to call the AI modeling automobile bumper parameter data package and the bumper parameter confirmation mechanism, set the distance between each collision point and the door, calculate the side angle collision score, and set the collision angle.

[0142] The angle evaluation module is used to simulate the collision experiment according to the collision angle, obtain the difference between the deformation amounts of the front and rear bumpers, and obtain the diagonal response score by obtaining the difference between the extrusion forces. The collision angle coefficient is obtained by combining the side angle collision score, and each collision angle is marked as a side collision or a frontal collision.

[0143] The coefficient calculation module is used to call the side collision label and count the number to select whether to input the parameter supplement rule. According to the simulation collision experiment, the maximum deformation of the bumper after each simulation and the residual deformation after the collision object is unloaded are collected to calculate the deformation recovery rate of the bumper. The fatigue supplement coefficient is obtained by combining the number of side collision labels.

[0144] The screening introduction module is used for analyzing whether the deformation recovery rate is taken as a parameter to be introduced according to the fatigue supplement coefficient, and introducing the bumper parameter confirmation mechanism after the deformation recovery rate is processed and screened.

[0145] The above formulas are dimensionless values calculated, the formulas are obtained by collecting a large amount of data to simulate a formula of the most recent real situation, and preset parameters in the formulas are set by a person skilled in the art according to actual conditions.

[0146] Finally, it should be noted that in this document, the terms "first", "second", and the like, merely mean one entity or action distinguished from another, and do not necessarily require or imply any actual such relationship or order between such entities or actions.

[0147] Moreover, the terms "comprising", "including", or any other variant thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements recited, but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element preceded by "comprises... " does not, without more constraints, foreclose additional identical elements of the process, method, article, or apparatus that includes the recited element.

[0148] In this document, the singular forms "a", "an", and "the" can also include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "comprise / comprising" or "have / having" and the like specifies the presence of stated features, integers, steps, operations, components, parts, or combinations thereof, but does not exclude the presence or addition of one or more other features, integers, steps, operations, components, parts, or combinations thereof, the possibility of which should be considered, and the term "and / or" used in this specification includes any and all combinations of the associated listed items.

[0149] The various embodiments in the specification are described in a progressive manner, each embodiment focuses on the difference from other embodiments, and each embodiment can be combined as needed, and the same and similar parts refer to each other.

[0150] The above description of the disclosed embodiments enables those skilled in the art to implement or use the various modifications of the embodiments of the present application, and it will be apparent to those skilled in the art that various modifications can be made to the embodiments of the present application without departing from the spirit or scope of the present application. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An AI modeling-based automobile bumper parameter determination method, characterized by: Comprising the following steps: Step S1: calling the AI modeling automobile bumper parameter data package and the bumper parameter confirmation mechanism, setting the collision angle, selecting the distance between each impact point and the door to calculate the side angle impact score; In step S1, the corresponding impact points are determined by the collision angle preset in the AI modeling automobile bumper parameter data package; The spatial coordinates of the impact points and the spatial coordinates of the door reference points are obtained in the automobile coordinate system, and the distances between each impact point and the door are calculated by the Euclidean distance formula; The side angle impact score is obtained by subtracting the distance between each impact point and the door after standardization processing, and the specific calculation formula is as follows: ； In the formula, is the distance between each impact point and the door after standardization processing, is the side impact score corresponding to the i th impact angle, i=1, 2, …, n, wherein n is the total number of impact angles, and i is the i th impact angle. Step S2: according to the collision angle, the difference between the deformation and the extrusion force of the front and rear bumpers is obtained, and the diagonal response score is obtained, and the side impact or frontal impact is marked according to the collision angle impact coefficient and the side impact score; In step S2, based on the multiple collision angles preset in the AI modeling automobile bumper parameter data package, the front or side front area of the automobile is controlled and simulated, and the difference between the deformation and the extrusion force of the front and rear bumpers is generated; The product of the deformation difference and the extrusion force difference of the front and rear bumpers after standardization processing is calculated to obtain the diagonal response score; In step S2, the diagonal response score and the side angle impact score are substituted into the polynomial regression calculation to obtain the collision angle impact coefficient; If the collision angle impact coefficient exceeds the side threshold, the current collision angle is marked as side impact; If the collision angle impact coefficient is lower than the side threshold, the current collision angle is marked as frontal impact and introduced into the bumper parameter confirmation mechanism; Step S3: calling the side impact label and counting the number to select whether to pass in the parameter supplement rule, calculating the deformation recovery rate of the bumper according to the maximum deformation of the bumper after each simulation and the residual deformation after the collision object is unloaded, and obtaining the fatigue supplement coefficient combined with the number of side impact labels; In step S3, the fatigue supplement coefficient is further calculated combined with the number of side impact labels and the deformation recovery rate, and the specific calculation formula is as follows: ； wherein, is a fatigue replenishment coefficient, is a side impact label number, is a number threshold for normalizing the side impact label number, is a deformation recovery rate, and is a weight coefficient for adjusting the influence degree of the side impact label number and the deformation recovery rate on the fatigue replenishment coefficient; Step S4: according to the fatigue supplement coefficient, analyze whether the deformation recovery rate is introduced as a parameter, process and select the deformation recovery rate, and then introduce it into the bumper parameter confirmation mechanism.

2. The automobile bumper parameter determination method based on AI modeling according to claim 1, characterized in that: In step S1, the AI modeling automobile bumper parameter data package and the bumper parameter confirmation mechanism are called through the control instruction interface; The AI modeling automobile bumper parameter data package refers to a multi-dimensional parameter set generated based on finite element simulation data, collision experiment data and vehicle geometric structure data in the training stage; The bumper parameter confirmation mechanism refers to a calculation rule set for retrieving, calling and dynamically correcting the parameters in the data package under different collision conditions.

3. The automobile bumper parameter determination method based on AI modeling according to claim 1, characterized in that: In step S3, the number of collisions labeled as side impact in the simulation experiment is counted, denoted as the side impact label number; If the side impact label number exceeds a preset number threshold, it is determined to introduce the parameter supplement rule; If the side impact label number is lower than the preset number threshold, it is determined not to introduce the parameter supplement rule.

4. The AI modeling-based automobile bumper parameter determination method according to claim 1, characterized in that: In step S3, when the parameter supplement rule is introduced, the maximum deformation and the residual deformation after the collision object is unloaded of the bumper before and after the simulation impact experiment are collected; The maximum deformation represents the maximum instantaneous displacement value of the bumper at each vertex under the action of the collision; The residual deformation after the collision object is unloaded represents the deformation value retained by the bumper after the collision object is unloaded; Based on the maximum deformation and the residual deformation after the collision object is unloaded, the deformation recovery rate of the bumper is calculated; The fatigue supplement coefficient is calculated by combining the side impact label number and the deformation recovery rate.

5. The AI modeling-based automobile bumper parameter determination method according to claim 4, characterized in that: In step S4, when the fatigue supplement coefficient exceeds the fatigue determination threshold, the deformation recovery rate is determined to be introduced as a parameter; When the fatigue supplement coefficient is lower than the fatigue determination threshold, the deformation recovery rate is determined not to be introduced as a parameter; When the deformation recovery rate is determined to be introduced as a parameter, the deformation recovery rate is processed and screened.

6. The AI modeling-based automobile bumper parameter determination method according to claim 5, characterized in that: In step S4, the median absolute deviation algorithm is used to calculate the abnormality determination value of each deformation recovery rate; The deformation recovery rates with abnormality determination values lower than or equal to the preset deviation coefficient threshold are screened out and arithmetically averaged to obtain the screened deformation recovery rate; The screened deformation recovery rate is introduced into the bumper parameter confirmation mechanism; The bumper parameter confirmation mechanism increases the deformation recovery rate as an additional parameter input on the basis of the original parameter system.

7. An AI modeling-based automobile bumper parameter determination system for implementing the AI modeling-based automobile bumper parameter determination method of any one of claims 1-6. The impact scoring module, the angle evaluation module, the coefficient calculation module, and the screening and introduction module are included, and the functions of each module are as follows: The impact scoring module is used to call the AI modeling automobile bumper parameter data package and the bumper parameter confirmation mechanism, set the distance between each impact point and the door to calculate the side angle impact score; The angle evaluation module is used to perform a simulation impact experiment according to the collision angle, obtain the deformation difference and the extrusion force difference of the front and rear bumpers to obtain the diagonal response score, combine the side angle impact score to obtain the collision angle coefficient, and label each collision angle as side impact or frontal impact; The coefficient calculation module is used to call the side impact label and count the number to select whether to introduce the parameter supplement rule, collect the maximum deformation and the residual deformation after the collision object is unloaded of the bumper after each simulation according to the simulation impact experiment to calculate the deformation recovery rate of the bumper, and combine the side impact label number to obtain the fatigue supplement coefficient; The screening import module is used for analyzing whether the deformation recovery rate is taken as a parameter to be introduced according to the fatigue supplement coefficient, and the bumper parameter confirmation mechanism is imported after the deformation recovery rate is processed and screened.

Images