Method for computing coordinated control weights in distributed drive electric vehicle

Abstract

The present application relates to a method for computing coordinated control weights in a distributed drive electric vehicle. In the present application, vehicle motion states are classified into three categories, which are respectively a stable state category, a transitional state category, and an unstable state category; weight factors are determined on the basis of Euclidean distances between clustering centers of different categories; an AFS / DYC coordination controller objective function is constructed on the basis of the weight factors; finally, optimal weight coefficients for the AFS system and the DYC system are obtained by means of solving, thereby meeting vehicle stability control requirements and improving the lateral stability of vehicles.

Description

A coordination control weight calculation method for a distributed drive electric vehicle

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] The present application claims priority to the Chinese patent application No. 202411081966.2 filed on August 08, 2024, and entitled "A coordination control weight calculation method for a distributed drive electric vehicle", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0003] The present application relates to the field of automobile control, in particular, to a coordination control weight calculation method for a distributed drive electric vehicle. BACKGROUND

[0004] As advanced active safety control systems, both active front steering (AFS) and direct yaw moment control (DYC) systems can be used to improve the handling stability of vehicles. When the vehicle is in the stability region, the DYC system is prone to cause fluctuations in the longitudinal speed of the vehicle, which deteriorates the ride comfort of the vehicle, while the AFS system has faster response speed and control effect. In order to improve the handling performance of the vehicle, the control weight of the AFS system needs to be increased; when the vehicle is in the instability region, the tire lateral force tends to be saturated, and the control accuracy of the AFS system decreases, which cannot meet the vehicle stability control demand in this working condition. In order to improve the lateral stability of the vehicle, the control weight of the DYC system needs to be increased. Therefore, the coordination control weight calculation method of the high-speed and accurate AFS and DYC system determines the intervention and exit time of the active safety control system, which is of great significance to improve the driving safety performance of the vehicle.

[0005] Currently, the research on the coordination control weight of the vehicle stability system mainly determines the stability state of the vehicle through the phase plane theory, and calculates the coordination control weight size according to the phase plane instability error. Its stability region is mainly divided by regular shapes such as straight lines, circles or diamonds, which is a simplified form of the stability region and cannot fully reflect the actual stability boundary. In addition, in the phase plane, the judgment criteria related to the lateral stability are mainly represented by some characteristic values, such as the yaw angular velocity or the mass center side slip angle, which has the problems of weak data basis and single characteristic parameter. SUMMARY

[0006] In order to overcome at least one deficiency in the prior art, the present application provides a coordination control weight calculation method for a distributed drive electric vehicle.

[0007] In a first aspect, a coordination control weight calculation method for a distributed drive electric vehicle is provided, comprising:

[0008] construct a vehicle motion state dataset; the vehicle motion state data in the vehicle motion state dataset are characteristic parameters related to the lateral stability state;

[0009] perform clustering analysis on the vehicle motion state data in the vehicle motion state dataset, divide the vehicle motion state data into three categories, namely a stable state category, a transition state category and an unstable state category, and determine clustering centers of the three categories;

[0010] determine a midpoint of a line connecting the clustering center of the stable state category and the clustering center of the transition state category, and calculate an Euclidean distance between the midpoint and the clustering center of the stable state category, denoted as a first distance; calculate an Euclidean distance between the clustering center of the stable state category and the clustering center of the transition state category, denoted as a second distance; calculate an Euclidean distance between the clustering center of the stable state category and the clustering center of the unstable state category, denoted as a third distance; calculate an Euclidean distance between the vehicle motion state data at the current moment and the clustering center of the stable state category, denoted as a fourth distance;

[0011] determine a weight factor in an AFS / DYC coordinated controller target function according to a relationship among the first distance, the second distance, the third distance and the fourth distance;

[0012] construct the AFS / DYC coordinated controller target function according to the weight factor;

[0013] solve the AFS / DYC coordinated controller target function to obtain optimal weight coefficients of the AFS system and the DYC system.

[0014] In one embodiment, the characteristic parameters related to the lateral stability state include a longitudinal speed, a steering wheel angle, a lateral speed, a sideslip angle, a roll angle, a yaw rate, a roll rate, a lateral acceleration, a front axle load transfer rate and a rear axle load transfer rate.

[0015] In one embodiment, the weight factor in the AFS / DYC coordinated controller target function is determined according to a relationship among the first distance, the second distance, the third distance and the fourth distance, and the following formula is adopted: λ3=1-λ1-λ2

[0016] wherein λ1 is a weight factor related to the lateral displacement, λ2 is a weight factor related to the yaw rate, and λ3 is a weight factor related to the centroid sideslip angle; xx1 is the fourth distance, L1 is the first distance, L2 is the second distance, and L3 is the third distance.

[0017] In one embodiment, the AFS / DYC coordinated controller target function is expressed by the following formula:

[0018] wherein, J is a target function value, λ1 is a weight factor related to lateral displacement, λ2 is a weight factor related to yaw rate, λ3 is a weight factor related to centroid side slip angle; N is a number of sampling time points, e di is a lateral displacement deviation at the sampling time point i; e dmax is a maximum value of the lateral displacement deviation, β i is a centroid side slip angle at the sampling time point i, β ref is a reference centroid side slip angle, β max is a maximum value of the centroid side slip angle, w i is a yaw rate at the sampling time point i, w ref is a reference yaw rate, w max is a maximum value of the yaw rate;

[0019] e di , β i , w i According to a discrete vehicle motion differential equation, the discrete vehicle motion differential equation is related to a weight coefficient of the AFS system.

[0020] In an embodiment, a KDPC algorithm is used to perform clustering analysis on vehicle motion state data in a vehicle motion state data set.

[0021] In an embodiment, a particle swarm optimization algorithm is used to solve a target function of an AFS / DYC coordinated controller.

[0022] In a second aspect, a distributed drive electric vehicle coordinated control weight calculation device is provided, comprising:

[0023] A data set construction module is configured to construct a vehicle motion state data set; vehicle motion state data in the vehicle motion state data set is a feature parameter related to lateral stability state;

[0024] A category division module is configured to perform clustering analysis on vehicle motion state data in the vehicle motion state data set, divide the vehicle motion state data into three categories, i.e., a stable state category, a transition state category and an unstable state category, and determine clustering centers of the three categories;

[0025] A distance calculation module is configured to determine a midpoint of a line connecting the clustering center of the stable state category and the clustering center of the transition state category, calculate an Euclidean distance between the midpoint and the clustering center of the stable state category, denoted as a first distance; calculate an Euclidean distance between the clustering center of the stable state category and the clustering center of the transition state category, denoted as a second distance; calculate an Euclidean distance between the clustering center of the stable state category and the clustering center of the unstable state category, denoted as a third distance; calculate an Euclidean distance between the vehicle motion state data at a current time point and the clustering center of the stable state category, denoted as a fourth distance;

[0026] a weight factor determination module configured to determine a weight factor in the AFS / DYC coordinated controller target function according to a relationship among the first distance, the second distance, the third distance and the fourth distance;

[0027] a target function construction module configured to construct the AFS / DYC coordinated controller target function according to the weight factor;

[0028] a solution module configured to solve the AFS / DYC coordinated controller target function to obtain optimal weight coefficients of the AFS system and the DYC system.

[0029] In a third aspect, a computer readable storage medium is provided, which stores a computer program. The computer program is executed by a processor to implement the distributed drive electric vehicle coordinated control weight calculation method.

[0030] In a fourth aspect, a computer program product is provided, which includes computer programs / instructions. The computer programs / instructions are executed by a processor to implement the distributed drive electric vehicle coordinated control weight calculation method.

[0031] Compared with the prior art, the present application has the following beneficial effects: the present application divides the vehicle motion state into three categories, namely, a stable state category, a transition state category and an unstable state category, and determines the weight factor according to the Euclidean distance of the clustering centers among different categories, and constructs the AFS / DYC coordinated controller target function based on the weight factor. Finally, the optimal weight coefficients of the AFS system and the DYC system are obtained by solving, so as to meet the vehicle stability control demand and improve the lateral stability of the vehicle. BRIEF DESCRIPTION OF DRAWINGS

[0032] The present application can be better understood by referring to the following description in conjunction with the accompanying drawings, which form a part of this specification. In the drawings:

[0033] FIG. 1 shows a flow chart of a distributed drive electric vehicle coordinated control weight calculation method according to an embodiment of the present application;

[0034] FIG. 2 shows a schematic diagram of a steering wheel angle;

[0035] FIG. 3 shows a data point clustering result distribution diagram;

[0036] FIG. 4 shows a simulation result diagram of the distributed drive electric vehicle coordinated control weight;

[0037] FIG. 5 shows a structural block diagram of a distributed drive electric vehicle coordinated control weight calculation device according to an embodiment of the present application. DETAILED DESCRIPTION

[0038] In the following, exemplary embodiments of the present application will be described with reference to the accompanying drawings. In the description, not all of the features of a practical embodiment are described in order to make the description clear and concise. It should be appreciated, however, that many embodiment-specific decisions can be made in the development of any such practical embodiment in order to achieve the specific goals of the developer, and these decisions can vary from embodiment to embodiment.

[0039] It should also be noted that, in order not to obscure the application with unnecessary details, only the structures closely related to the scheme according to the present application are shown in the drawings, and other details not closely related to the present application are omitted.

[0040] It should be understood that the present application is not limited to the described embodiments by virtue of the following description with reference to the drawings. In this context, embodiments can be combined with each other, features can be replaced or borrowed between different embodiments, and one or more features can be omitted in an embodiment.

[0041] Many attribute parameters of the vehicle can be used to reflect lateral stability, such as longitudinal speed, front wheel steering angle, lateral acceleration, etc. Therefore, the present application provides a distributed drive electric vehicle coordinated control weight calculation method, which aims to comprehensively analyze multiple attribute parameters related to handling stability by K-means-density peak clustering (KDPC) algorithm, divide stability types, and calculate the optimal weight coefficients of AFS system and DYC system in real time based on PSO algorithm.

[0042] FIG. 1 shows a flow chart of a distributed drive electric vehicle coordinated control weight calculation method according to an embodiment of the present application, referring to FIG. 1, the method comprises:

[0043] Step S1, constructing a vehicle motion state data set; the vehicle motion state data in the vehicle motion state data set is a feature parameter related to the lateral stability state.

[0044] Based on a ten-degree-of-freedom vehicle driving simulator, a steering wheel angle step input test is performed, and vehicle longitudinal-lateral-vertical motion state information under different front wheel angles and different driving speeds is collected to construct a vehicle motion state data set.

[0045] Driving simulators offer high safety and allow for the design of arbitrary experimental scenarios to meet experimental needs, unaffected by weather conditions. Compared to real-vehicle experiments, they offer greater flexibility, and the driver behavior trends show good consistency between the two data acquisition methods. Therefore, vehicle motion state datasets were collected using PreScan, MATLAB / Simulink, and the Logitech G29 driving simulator. PreScan was used to provide a virtual driving environment and establish standardized vehicle test simulation scenarios; MATLAB / Simulink was used to build the vehicle dynamics model, including 10 degrees of freedom such as longitudinal, lateral, vertical, yaw, roll, pitch, and tire movement; the Logitech G29 driving simulator was mainly used to collect the driver's steering wheel angle, acceleration, and brake pedal opening signals to simulate real-vehicle driving behavior. Furthermore, this embodiment considered the operating behaviors of drivers with different driving styles, selecting 27 drivers (23 male drivers and 4 female drivers) to conduct simulator experiments at different driving speeds. The test conditions were set as a standard handling stability test scenario. After a lot of debugging, Figure 2 shows a schematic diagram of the steering wheel angle, starting from zero and gradually changing to 180 degrees after 1 second. The longitudinal speed was set from 30km / h to 120km / h, and the speed interval was 10km / h.

[0046] To comprehensively consider the vehicle's motion state, the following characteristic parameters related to lateral stability are collected, including: longitudinal velocity, steering wheel angle, lateral velocity, sideslip angle, roll angle, yaw rate, roll ratio, lateral acceleration, front axle load transfer rate, and rear axle load transfer rate.

[0047] The sampling frequency was set to 0.05s, and the simulation time was set to 10s. A vehicle motion state dataset was ultimately established under different vehicle speeds and steering angles, comprising 3825 data sets. The vehicle motion state dataset is defined as X, and represented as:

[0048] X i Let y represent the i-th data set, m be the number of data sets, and y be the number of data sets. ij X represents i The data in the j-th dimension is represented by D, where D represents the number of dimensions. In this embodiment, D = 10.

[0049] Considering the different unit dimensions of various vehicle state parameters, in order to summarize the distribution range of the samples, a normalization method is used to limit the sample data to the range [0,1] for X. i Normalization is performed to obtain the normalized vehicle motion state data x. i For: x i =(x i1 ,x i2 ,…x ij …,x iD )

[0050] Where, x ij For x i The data in the j-th dimension, y j_min Let y be the minimum value of the data in the j-th dimension of dataset X. j_max It represents the maximum value of the data in the j-th dimension of dataset X.

[0051] Step S2: Perform cluster analysis on the vehicle motion state data in the vehicle motion state dataset, divide the vehicle motion state data into three categories: stable state category, transitional state category, and unstable state category, and determine the cluster centers of the three categories.

[0052] Specifically, the KDPC algorithm is used to perform cluster analysis on the vehicle motion state data in the vehicle motion state dataset.

[0053] In the KDPC algorithm, DPC (Density Peak Clustering Algorithm) is a novel clustering method based on density peaks. It aims to obtain initial cluster centers and the number of clusters, and then uses the K-means algorithm to update the positions of the cluster centers, avoiding local convergence. The specific implementation process of the KDPC algorithm is well-known in the field and will not be elaborated here.

[0054] Figure 3 shows the distribution of data point clustering results. As can be seen from the figure, the data points are divided into three clusters and distributed in various locations in the image. The green data points in the leftmost area indicate that the vehicle is in a "stable state". As the vehicle speed and steering wheel angle increase, the vehicle successively enters the red "transitional state" and the blue "unstable state".

[0055] Step S3: Determine the midpoint of the line connecting the cluster centers of the stable state category and the cluster centers of the transitional state category, and calculate the Euclidean distance between the midpoint and the cluster centers of the stable state category, denoted as the first distance; calculate the Euclidean distance between the cluster centers of the stable state category and the cluster centers of the transitional state category, denoted as the second distance; calculate the Euclidean distance between the cluster centers of the stable state category and the cluster centers of the unstable state category, denoted as the third distance; calculate the Euclidean distance between the vehicle motion state data at the current moment and the cluster centers of the stable state category, denoted as the fourth distance.

[0056] Step S4: Determine the weighting factors in the objective function of the AFS / DYC coordinating controller based on the relationship between the first distance, the second distance, the third distance, and the fourth distance.

[0057] Step S5: Construct the objective function of the AFS / DYC coordinating controller based on the weighting factors.

[0058] Step S6, solving the AFS / DYC coordinated controller target function to obtain the optimal weight coefficients of the AFS system and the DYC system.

[0059] Specifically, the particle swarm optimization algorithm (PSO) can be used to solve the AFS / DYC coordinated controller target function to obtain the optimal weight coefficients of the AFS system, and the optimal weight coefficients of the DYC system can be obtained by subtracting the optimal weight coefficients of the AFS system from 1. Here, the position of the particle in the particle swarm optimization algorithm is defined as the weight coefficient of the AFS system, and the particle swarm optimization algorithm is a well-known technology in the art, which will not be described here.

[0060] In this embodiment, the vehicle motion state is divided into three categories, namely, a stable state category, a transition state category, and an unstable state category, and the weight factor is determined according to the Euclidean distance between the clustering centers of different categories, and the AFS / DYC coordinated controller target function is constructed based on the weight factor; finally, the optimal weight coefficients of the AFS system and the DYC system are obtained by solving, thereby meeting the vehicle stability control requirements and improving the lateral stability of the vehicle.

[0061] In one embodiment, when the vehicle is in a stable state, there is a large stability margin, and the main goal of the coordinated controller is to improve the accuracy of vehicle path tracking, so the weight coefficient λ1 related to the lateral displacement is large. Similarly, when the vehicle is in a transition state, compared to the path tracking accuracy and lateral stability performance, the vehicle handling performance dominates, so the weight coefficient λ2 related to the yaw rate is large, and when the vehicle is in an unstable state, the size of the center of mass side slip angle needs to be suppressed to correct the vehicle unstable state, and the weight coefficient λ3 related to the center of mass side slip angle is large. Specifically, in step S4, the weight factor in the AFS / DYC coordinated controller target function is determined according to the relationship between the first distance, the second distance, the third distance, and the fourth distance, and the following formula is used: λ3=1-λ1-λ2

[0062] Wherein, λ2 is the weight factor related to the lateral displacement, λ2 is the weight factor related to the yaw rate, and λ3 is the weight factor related to the center of mass side slip angle; xx1 is the fourth distance, L1 is the first distance, L2 is the second distance, and L3 is the third distance.

[0063] In one embodiment, the AFS / DYC coordinated controller target function is expressed by the following formula:

[0064] wherein, J is the objective function value, λ1 is a weight factor related to lateral displacement, λ2 is a weight factor related to yaw rate, λ3 is a weight factor related to side slip angle; N is the number of sampling time, e di is the lateral displacement deviation at sampling time i; e dmax is the maximum value of lateral displacement deviation, β i is the side slip angle at sampling time i, β ref is the reference side slip angle, β max is the maximum value of side slip angle, w i is the yaw rate at sampling time i, w ref is the reference yaw rate, w max is the maximum value of yaw rate;

[0065] e di , β i , w i According to the discrete vehicle motion differential equation, the discrete vehicle motion differential equation is related to the weight coefficient of the AFS system, and the following formula can be used to determine the weight coefficient of the AFS system: b 11 = k1 / mv x , b 12 = k2 / mv x , b 21 = ak1 / I z , b 22 = -bk2 / I z

[0066] wherein, z * is the vehicle motion state information, i is the sampling time, e d is the lateral displacement deviation, e ψ is the heading angle deviation, β is the side slip angle, w is the yaw rate, E * , D * are all coefficient matrices, b 11 , b 21 , a 11 , a 12 , a 21 , a 22 are all dynamic model parameters; v x is the longitudinal speed of the vehicle, I z is the rotational inertia of the vehicle around the z axis, k1 and k2 are the side stiffness of the front wheel and the rear wheel respectively, m is the mass of the vehicle, a and b are the distances from the vehicle mass center to the front axle and the rear axle respectively, P is the weight coefficient of the AFS system, ΔM is the additional yaw moment, Ψ d is the reference heading angle, δ f is the front wheel steering angle.

[0067] Reference yaw rate w ref For

[0068] Wherein, K is the vehicle stability coefficient, l is the wheelbase, l=a+b, μ is the ground adhesion absorption, g is the gravity acceleration.

[0069] Reference center of mass side slip angle β ref For:

[0070] In order to further verify the effectiveness of the method of the application, the single moving line working condition is used to further illustrate the coordination control weight when the simulation experiment is carried out on the road surface with the road surface adhesion coefficient of 0.3 at the driving speed of 80km / h.

[0071] Figure 4 shows the simulation result graph of the distributed drive electric vehicle coordination control weight, according to figure 4, in the stable region, the AFS system weight is larger, when the vehicle is in the unstable region, the AFS and DYC weight fluctuates sharply, and the vehicle's handling stability is improved.

[0072] Based on the same invention concept as the distributed drive electric vehicle coordination control weight calculation method, the embodiment also provides a distributed drive electric vehicle coordination control weight calculation device corresponding thereto, figure 5 shows the structure block diagram of the distributed drive electric vehicle coordination control weight calculation device according to the embodiment of the application, including:

[0073] The data set construction module 51 is used to construct the vehicle motion state data set; the vehicle motion state data in the vehicle motion state data set is a feature parameter related to the lateral stability state;

[0074] The category division module 52 is used to perform cluster analysis on the vehicle motion state data in the vehicle motion state data set, divide the vehicle motion state data into three categories, which are stable state category, transition state category and unstable state category, and determine the cluster centers of the three categories;

[0075] The distance calculation module 53 is used to calculate the midpoint of the line connecting the cluster center of the stable state category and the cluster center of the transition state category, and the Euclidean distance between the cluster center of the stable state category, recorded as the first distance; calculate the Euclidean distance between the cluster center of the stable state category and the cluster center of the transition state category, recorded as the second distance; calculate the Euclidean distance between the cluster center of the stable state category and the cluster center of the unstable state category, recorded as the third distance; calculate the Euclidean distance between the current time vehicle motion state data and the cluster center of the stable state category, recorded as the fourth distance;

[0076] The weight factor determination module 54 is configured to determine the weight factor in the AFS / DYC coordinated controller target function according to the relationship among the first distance, the second distance, the third distance and the fourth distance.

[0077] The target function construction module 55 is configured to construct the AFS / DYC coordinated controller target function according to the weight factor.

[0078] The solving module 56 is configured to solve the AFS / DYC coordinated controller target function to obtain the optimal weight coefficient of the AFS system and the DYC system.

[0079] The distributed drive electric vehicle coordinated control weight calculation device of the embodiment has the same inventive concept as the distributed drive electric vehicle coordinated control weight calculation method described above, and therefore the specific implementation of the device can be seen from the embodiment part of the distributed drive electric vehicle coordinated control weight calculation method described above, and the technical effects thereof correspond to the technical effects of the method described above, which will not be repeated here.

[0080] The embodiment of the present application provides a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the distributed drive electric vehicle coordinated control weight calculation method.

[0081] The embodiment of the present application provides a computer program product, which includes computer programs / instructions. The computer programs / instructions are executed by a processor to implement the distributed drive electric vehicle coordinated control weight calculation method.

[0082] The above is only various embodiments of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can easily think of changes or replacements within the technical range disclosed in the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A distributed drive electric vehicle coordination control weight calculation method, characterized by, The method comprises the following steps: constructing a vehicle motion state data set; the vehicle motion state data in the vehicle motion state data set is a characteristic parameter related to a lateral stability state; performing cluster analysis on the vehicle motion state data in the vehicle motion state data set, dividing the vehicle motion state data into three categories, namely a stable state category, a transition state category and an unstable state category, and determining cluster centers of the three categories; determining a midpoint of a line connecting the cluster center of the stable state category and the cluster center of the transition state category, and calculating an Euclidean distance between the midpoint and the cluster center of the stable state category, denoted as a first distance; calculating an Euclidean distance between the cluster center of the stable state category and the cluster center of the transition state category, denoted as a second distance; calculating an Euclidean distance between the cluster center of the stable state category and the cluster center of the unstable state category, denoted as a third distance; calculating an Euclidean distance between the vehicle motion state data at a current moment and the cluster center of the stable state category, denoted as a fourth distance; determining a weight factor in an AFS / DYC coordinated controller target function according to a relationship among the first distance, the second distance, the third distance and the fourth distance; constructing an AFS / DYC coordinated controller target function according to the weight factor; solving the AFS / DYC coordinated controller target function to obtain optimal weight coefficients of an AFS system and a DYC system.

2. The method of claim 1, wherein, The characteristic parameter related to the lateral stability state comprises a longitudinal speed, a steering wheel angle, a lateral speed, a sideslip angle, a roll angle, a yaw rate, a roll rate, a lateral acceleration, a front axle load transfer rate and a rear axle load transfer rate.

3. The method of claim 1, wherein, Wherein, According to the relationship among the first distance, the second distance, the third distance and the fourth distance, a weight factor in an AFS / DYC coordination controller target function is determined, using the following formula: λ3 = 1 - λ1 - λ2 Wherein, λ1 is a weight factor related to a lateral displacement, λ2 is a weight factor related to a yaw rate, and λ3 is a weight factor related to a mass center sideslip angle; xx1 is the fourth distance, L1 is the first distance, L2 is the second distance, and L3 is the third distance.

4. The method of claim 1, wherein, The AFS / DYC coordinated controller objective function is expressed by the following formula: wherein J is a target function value, λ1 is a weight factor related to lateral displacement, λ2 is a weight factor related to yaw rate, λ3 is a weight factor related to side slip angle; N is a number of sampling time points, e di is a lateral displacement deviation at sampling time point i; e dmax is a maximum value of lateral displacement deviation, β i is a side slip angle at sampling time point i, β ref is a reference side slip angle, β max is a maximum value of side slip angle, w i is a yaw rate at sampling time point i, w ref is a reference yaw rate, w max is a maximum value of yaw rate; e di 、β i 、w i determined from discrete vehicle motion differential equations related to the weight coefficients of the AFS system.

5. The method of claim 1, wherein, The KDPC algorithm is used to perform cluster analysis on the vehicle motion state data in the vehicle motion state data set.

6. The method of claim 1, wherein, The particle swarm optimization algorithm is used to solve the AFS / DYC coordinated controller target function.

7. A distributed drive electric vehicle coordinated control weight calculation device characterized by comprising: The method comprises the following steps: a data set construction module for constructing a vehicle motion state data set; the vehicle motion state data in the vehicle motion state data set is a characteristic parameter related to a lateral stability state; a category division module for performing cluster analysis on the vehicle motion state data in the vehicle motion state data set, dividing the vehicle motion state data into three categories, namely a stable state category, a transition state category and an unstable state category, and determining cluster centers of the three categories; a distance calculation module, configured to determine a midpoint of a line connecting a cluster center of the stable state category and a cluster center of the transition state category, and calculate a Euclidean distance between the midpoint and the cluster center of the stable state category, denoted as a first distance; calculate a Euclidean distance between the cluster center of the stable state category and the cluster center of the transition state category, denoted as a second distance; calculate a Euclidean distance between the cluster center of the stable state category and the cluster center of the unstable state category, denoted as a third distance; calculate a Euclidean distance between the vehicle motion state data at the current moment and the cluster center of the stable state category, denoted as a fourth distance; a weight factor determination module, configured to determine a weight factor in an AFS / DYC coordinated controller target function according to a relationship among the first distance, the second distance, the third distance and the fourth distance; a target function construction module, configured to construct the AFS / DYC coordinated controller target function according to the weight factor; a solution module, configured to solve the AFS / DYC coordinated controller target function to obtain optimal weight coefficients of the AFS system and the DYC system.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the distributed drive electric vehicle coordinated control weight calculation method in any one of claims 1-6.

9. A computer program product, characterised in that, The computer program / instruction is executed by the processor to implement the distributed drive electric vehicle coordinated control weight calculation method in any one of claims 1-6.

Images