Test methods, devices, and vehicles for vehicle regenerative braking function

Abstract

This invention discloses a method, apparatus, and vehicle for testing the regenerative braking function of a vehicle. The method includes: acquiring various driving state data of the vehicle, wherein the driving state data represents the degree of driving intensity during driving; performing clustering processing on the driving intensity corresponding to the various driving state data to obtain clustering results, wherein the clustering results represent the driving scenarios corresponding to the driving intensity levels; and testing the vehicle's regenerative braking function based on the clustering results to obtain test results, wherein the test results indicate whether the regenerative braking function is in a normal state, and the regenerative braking function is used to recover and utilize additional braking energy in the vehicle under the corresponding driving intensity levels. This invention solves the technical problem of low efficiency in testing the regenerative braking function of vehicles.

Description

Technical Field

[0001] This invention relates to the field of vehicles, and more specifically, to a test method, apparatus, and vehicle for the braking energy recovery function of a vehicle. Background Technology

[0002] In related technologies, the regenerative braking function of a vehicle can be tested through a comprehensive test. However, this requires traversing all driving state data of the vehicle to test the corresponding regenerative braking function. Traversing all driving state data takes a lot of time. Therefore, there is still a technical problem of low efficiency in testing the regenerative braking function of a vehicle.

[0003] There is currently no effective solution to the technical problem of low efficiency in testing the regenerative braking function of vehicles. Summary of the Invention

[0004] This invention provides a method, apparatus, and vehicle for testing the regenerative braking function of a vehicle, thereby addressing at least the technical problem of low efficiency in testing the regenerative braking function of a vehicle.

[0005] According to one aspect of the present invention, a method for testing the regenerative braking function of a vehicle is provided. The method may include: acquiring various driving state data of the vehicle, wherein the driving state data represents the degree of driving intensity during driving; performing clustering processing on the driving intensity corresponding to the various driving state data to obtain clustering results, wherein the clustering results represent the driving scenarios corresponding to the degree of driving intensity; and testing the regenerative braking function of the vehicle based on the clustering results to obtain test results, wherein the test results indicate whether the regenerative braking function is in a normal state, and the regenerative braking function is used to recover and utilize additional braking energy in the vehicle under the corresponding degree of driving intensity.

[0006] Optionally, before performing clustering processing on the driving intensity levels corresponding to various driving state data to obtain the clustering results, the method further includes: determining the cluster center dimension value of the fuzzy clustering model for clustering processing based on the driving state data, and setting the driving intensity level of the vehicle, wherein the driving intensity level is used to represent different intensities during vehicle driving; determining the number of cluster centers of the fuzzy clustering model based on the cluster center dimension value and the driving intensity level, wherein the number of cluster centers is negatively correlated with the driving intensity level.

[0007] Optionally, after determining the number of cluster centers in the fuzzy clustering model based on the cluster center dimension value and the driving intensity level, the method further includes: integrating the cluster center dimension values ​​corresponding to different driving intensity levels to determine the sample set composed of samples of different driving intensity levels; determining the initial cluster centers corresponding to different driving intensity levels based on the sample set, and determining the initial membership matrix corresponding to the cluster center dimension value in the sample set; and determining the initial iteration number and initial value function corresponding to different driving intensity levels.

[0008] Optionally, clustering is performed on the driving intensity corresponding to various driving state data to obtain clustering results, including: updating the initial cluster centers based on the sample set and the initial membership matrix to obtain the updated cluster center group corresponding to the initial cluster centers; updating the initial membership matrix based on the cluster center dimension value to obtain the updated membership matrix corresponding to the initial membership matrix; updating the initial value function based on the membership matrix and each sample in the sample set to obtain the updated value function corresponding to the initial value function; and incrementing the initial iteration number by one in response to the updated cluster center group, membership matrix, and value function to obtain the updated iteration number. The clustering results include at least the cluster center group, membership matrix, and value function.

[0009] Optionally, the method may further include: determining the change in the value function corresponding to the iteration number in response to the iteration number being less than an iteration number threshold; stopping the iteration in response to the change being less than the change amount threshold, and using the cluster center group corresponding to the iteration number as input data for the vehicle's braking control system.

[0010] Optionally, based on the clustering results, the vehicle's regenerative braking function is tested to obtain test results, including: in response to using the cluster center group as input data for the vehicle's braking control system, controlling the braking control system to test the vehicle's regenerative braking function based on the input data, and obtaining test results.

[0011] According to another aspect of the present invention, a testing device for the regenerative braking function of a vehicle is also provided. The device may include: an acquisition unit for acquiring various driving state data of the vehicle, wherein the driving state data represents the degree of driving intensity during vehicle operation; a processing unit for performing clustering processing on the driving intensity corresponding to the various driving state data to obtain clustering results, wherein the clustering results represent the driving scenario corresponding to the degree of driving intensity; and a testing unit for testing the regenerative braking function of the vehicle based on the clustering results to obtain test results, wherein the test results indicate whether the regenerative braking function is in a normal state, and the regenerative braking function is used to recover and utilize additional braking energy in the vehicle under the corresponding degree of driving intensity.

[0012] According to another aspect of the present invention, a computer-readable storage medium is also provided. The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to perform a test method for the regenerative braking function of a vehicle according to the embodiments of the present invention.

[0013] According to another aspect of the present invention, a processor is also provided. The processor is used to run a program, wherein the program, when running, executes a test method for the regenerative braking function of a vehicle according to an embodiment of the present invention.

[0014] According to another aspect of the present invention, a vehicle is also provided. This vehicle is used to perform a test method for the regenerative braking function of a vehicle according to embodiments of the present invention.

[0015] In this embodiment of the invention, various driving state data of the vehicle are acquired, wherein the driving state data is used to represent the driving intensity of the vehicle during driving; the driving intensity corresponding to the various driving state data is clustered to obtain clustering results, wherein the clustering results are used to represent the driving scenario corresponding to the driving intensity; based on the clustering results, the vehicle's regenerative braking function is tested to obtain test results, wherein the test results are used to indicate whether the regenerative braking function is in a normal state, and the regenerative braking function is used to recover and utilize the additional braking energy in the vehicle under the corresponding driving intensity. In other words, the embodiments of the present invention can cluster the collected driving state data according to the driving intensity to obtain clustering results. That is, driving scenarios corresponding to different driving intensities can be obtained. Based on different driving scenarios, the regenerative braking function of the corresponding driving scenario can be tested to determine whether the regenerative braking function can recover and utilize the additional braking energy in the vehicle under the corresponding driving intensity scenario. This can determine whether the vehicle's regenerative braking function is in a normal state. Since the driving state data can be analyzed through clustering to determine different driving scenarios and test each driving scenario, the goal of not having to traverse all driving state data is achieved. This solves the technical problem of low efficiency in testing the vehicle's regenerative braking function and achieves the technical effect of improving the efficiency of testing the vehicle's regenerative braking function. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0017] Figure 1 This is a flowchart of a test method for the regenerative braking function of a vehicle according to an embodiment of the present invention;

[0018] Figure 2 This is a schematic diagram of a test device for the braking energy recovery function of a vehicle according to an embodiment of the present invention. Detailed Implementation

[0019] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0020] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0021] Example 1

[0022] According to an embodiment of the present invention, an embodiment of a test method for the braking energy recovery function of a vehicle is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0023] Figure 1 This is a flowchart of a test method for the regenerative braking function of a vehicle according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0024] Step S102: Obtain various driving status data of the vehicle, wherein the driving status data is used to represent the degree of driving intensity of the vehicle during driving.

[0025] In the technical solution provided by step S102 of the present invention, various driving state data of the vehicle can be acquired. These driving state data can be used to represent the degree of driving intensity during the driving process and may include vehicle speed, steering wheel angle, steering wheel speed, brake pedal travel, and brake pedal rate, among other driving state data. It should be noted that the driving state data mentioned above is only illustrative and is not intended to be specific.

[0026] Optionally, various driving status data of vehicles that have been put into use can be obtained during the driving process, thereby facilitating the testing of the regenerative braking function of the vehicles to be put into use based on the various driving status data.

[0027] Step S104: Cluster the driving intensity corresponding to the various driving state data to obtain clustering results, whereby the clustering results are used to represent the driving scenarios corresponding to the driving intensity.

[0028] In the technical solution provided in step S104 of the present invention, after obtaining multiple driving state data of the vehicle, the driving intensity corresponding to the multiple driving state data can be clustered to obtain clustering results, wherein the clustering results can be used to represent the driving scenario corresponding to the driving intensity.

[0029] Optionally, since different driving state data correspond to different driving intensity levels, the corresponding driving state data can be clustered based on different driving intensity levels to obtain clustering results. In other words, the driving scenarios corresponding to different driving intensity levels can be obtained.

[0030] Optionally, the driving status data can be analyzed and clustered offline to quickly extract the driving scenarios corresponding to different driving intensities, which facilitates hardware-in-the-loop testing of different driving scenarios and helps determine whether the regenerative braking function is in normal working order.

[0031] Testing a vehicle's regenerative braking function through comprehensive testing requires traversing all driving state data to test the corresponding function. However, traversing all driving state data is time-consuming, resulting in low efficiency in testing regenerative braking. In this invention, the collected driving state data can be clustered according to driving intensity to obtain driving scenarios corresponding to different levels of intensity. This facilitates testing regenerative braking in different driving scenarios, avoiding the need to traverse all driving state data and thus improving the efficiency of testing regenerative braking.

[0032] Step S106: Based on the clustering results, test the vehicle's regenerative braking function and obtain the test results. The test results are used to indicate whether the regenerative braking function is in a normal state. The regenerative braking function is used to recover and utilize the additional braking energy in the vehicle under the corresponding driving intensity.

[0033] In the technical solution of step S106 of the present invention, after clustering the driving intensity corresponding to the driving state data to obtain the clustering results, the vehicle's regenerative braking function can be tested based on the clustering results to obtain test results. The test results can be used to indicate whether the regenerative braking function is in a normal state. The regenerative braking function can be used to recover and utilize additional braking energy in the vehicle under corresponding driving intensity conditions.

[0034] Optionally, after obtaining the clustering results, the regenerative braking function can be tested based on the driving scenarios corresponding to different driving intensities in the clustering results. The test results can be used to determine whether the regenerative braking function can recover and utilize the additional braking energy in the vehicle under the corresponding driving intensities, and whether the required amount of braking energy is recovered and utilized. This can help determine whether the regenerative braking function is in a normal state.

[0035] Optionally, if, under a certain level of driving intensity, the regenerative braking function cannot recover or utilize the additional braking energy in the vehicle, or cannot recover the required braking energy, then the regenerative braking function is in an abnormal state. If, under all driving intensity scenarios obtained through clustering, the regenerative braking function can recover the required braking energy in the vehicle, then the regenerative braking function is in a normal state.

[0036] In this embodiment of the invention, multiple driving state data and their corresponding driving intensity can be clustered to determine the driving scenarios corresponding to different driving intensity levels after clustering. This eliminates the need to traverse all driving state data and conduct comprehensive experiments to determine the state of the regenerative braking function, thus avoiding the significant time consumed by traversing all data and conducting comprehensive experiments. Only the regenerative braking function under different driving scenarios obtained from the clustering process needs to be tested, thereby improving the efficiency of testing the vehicle's regenerative braking function.

[0037] In the embodiments of the present invention, steps S102 to S106 above involve acquiring various driving state data of the vehicle, wherein the driving state data is used to represent the degree of driving intensity during the driving process; clustering processing is performed on the driving intensity corresponding to the various driving state data to obtain clustering results, wherein the clustering results are used to represent the driving scenario corresponding to the degree of driving intensity; based on the clustering results, the vehicle's regenerative braking function is tested to obtain test results, wherein the test results are used to indicate whether the regenerative braking function is in a normal state, and the regenerative braking function is used to recover and utilize additional braking energy in the vehicle under the corresponding degree of driving intensity. In other words, the embodiments of the present invention can cluster the collected driving state data according to the driving intensity to obtain clustering results. That is, driving scenarios corresponding to different driving intensities can be obtained. Based on different driving scenarios, the regenerative braking function of the corresponding driving scenario can be tested to determine whether the regenerative braking function can recover and utilize the additional braking energy in the vehicle under the corresponding driving intensity scenario. This can determine whether the vehicle's regenerative braking function is in a normal state. Since the driving state data can be analyzed through clustering to determine different driving scenarios and test each driving scenario, the goal of not having to traverse all driving state data is achieved. This solves the technical problem of low efficiency in testing the vehicle's regenerative braking function and achieves the technical effect of improving the efficiency of testing the vehicle's regenerative braking function.

[0038] The method described in this embodiment will be further described below.

[0039] As an optional embodiment, in step S104, before clustering the driving intensity levels corresponding to various driving state data to obtain the clustering results, the method further includes: determining the cluster center dimension value of the fuzzy clustering model for clustering based on the driving state data, and setting the driving intensity level of the vehicle, wherein the driving intensity level is used to represent different intensities during vehicle driving; determining the number of cluster centers of the fuzzy clustering model based on the cluster center dimension value and the driving intensity level, wherein the number of cluster centers is negatively correlated with the driving intensity level.

[0040] In this embodiment, before clustering the driving intensity data corresponding to various driving states to obtain the clustering results, the cluster center dimension value of the fuzzy clustering model can be determined using the driving state data. Furthermore, the driving intensity level of the vehicle can be set. Based on the driving intensity level and the cluster center dimension value, the number of cluster centers in the fuzzy clustering model can be determined. The driving intensity level can represent different degrees of intensity during vehicle operation. The number of cluster centers and the driving intensity level can be negatively correlated. The fuzzy clustering model can be a fuzzy C-means clustering model.

[0041] Optionally, the five data points in the driving status data—vehicle speed, steering wheel angle, steering wheel speed, brake pedal travel, and brake pedal rate—can be used as input signals for the integrated braking control system in the vehicle, and these five input signals can be used as cluster center dimension values.

[0042] Optionally, a driving intensity level P can be set according to different levels of intensity during vehicle driving. For example, five driving intensity levels can be set, that is, P=5 can be set. The larger the P value, the more intense the driving intensity.

[0043] Optionally, the number of cluster centers m can be set. pmax As the driving intensity level P increases, the number of cluster centers m... pmax The smaller the value, for example, the more likely the number of cluster centers m can be. pmax These are: the number of cluster centers m corresponding to level P=1. 1max =20, corresponding to the number of cluster centers m at level P=2. 2max =18, corresponding to the number of cluster centers m for level P=3. 3max =14, corresponding to the number of cluster centers m at level P=4. 4max =12, corresponding to the number of cluster centers m for level P=5. 5max =8.

[0044] It should be noted that the number of driving intensity levels and the size of the cluster centers mentioned above are merely illustrative examples and are not specifically limited here. Any method or process that involves clustering driving state data to obtain driving scenarios with different levels of driving intensity, and then testing the regenerative braking function under different driving scenarios, falls within the protection scope of this invention.

[0045] As an optional embodiment, in step S104, after determining the number of cluster centers of the fuzzy clustering model based on the cluster center dimension value and the driving intensity level, the method further includes: integrating the cluster center dimension values ​​corresponding to different driving intensity levels to determine a sample set composed of samples of different driving intensity levels; determining the initial cluster centers corresponding to different driving intensity levels based on the sample set, and determining the initial membership matrix corresponding to the cluster center dimension values ​​in the sample set; and determining the initial iteration number and initial value function corresponding to different driving intensity levels.

[0046] In this embodiment, after determining the number of cluster centers in the fuzzy clustering model based on the cluster center dimension value and the driving intensity level, the cluster center dimension values ​​corresponding to different driving intensity levels can be integrated to determine the sample set composed of samples of different driving intensity levels. Alternatively, based on the sample set, the initial cluster centers corresponding to different driving intensity levels and the initial membership matrix corresponding to the cluster center dimension values ​​in the sample set can be determined. Also, the initial iteration number and initial value function corresponding to different driving intensity levels can be determined.

[0047] Optionally, at a certain moment, the cluster center dimension values ​​(vehicle speed s, steering wheel angle θ, steering wheel speed n, brake pedal travel l, and brake pedal speed v) corresponding to the driving intensity level P can be captured as samples for the corresponding P levels, and the number of samples can be i. pmax This corresponds to the driving intensity level P, and the sample set can contain 5×i. pmax The sample set can be represented by the following expression:

[0048]

[0049] Among them, X p (i p ) can be used to represent the sample set of driving severity level P; s(i p ) can be used to represent vehicle speed samples of driving severity level P; θ(i p ) can be used to represent the steering wheel angle sample of the driving severity level P; n(i p ) can be used to represent the steering wheel speed sample for the driving intensity level P; l(i p ) can be used to represent the brake pedal travel sample of the driving severity level P; v(i p This can be used to represent a sample of brake pedal rate for driving severity level P.

[0050] Optionally, for each driving severity level P, initial cluster centers can be determined, which may include 5×m cluster centers. pmaxThe initialization of cluster centers can be represented by the following expression:

[0051]

[0052] Among them, c p (m p k) can be used to represent the initial cluster centers of the driving severity level P; c sp (m p (k) can be used to represent the number of vehicle speed cluster centers for the driving severity level P; c θp (m p (k) can be used to represent the number of cluster centers for the steering wheel angle at the driving severity level P; c np (m p k) can be used to represent the number of cluster centers for the steering wheel rotation speed at the driving intensity level P; c lp (m p k) can be used to represent the number of cluster centers for brake pedal travel at driving severity level P; c vp (m p ,k) can be used to represent the number of cluster centers for brake pedal rate at driving severity level P.

[0053] Optionally, considering expert experience, for any driving intensity level P, the initial membership degrees corresponding to the five cluster center dimensions—vehicle speed s, steering wheel angle θ, steering wheel speed n, brake pedal travel l, and brake pedal rate v—are considered to be the same. The initial membership degree matrix corresponding to any driving intensity level P can include 5×i... pmax The membership matrix can be initialized using the following expression: (The matrix contains n elements.)

[0054]

[0055] (m p =m p1 m p2 , ..., m pmax i p =i p1 i p2 , ..., i pmax (k=0)

[0056] Among them, u p (i p ,m p ,k) can be used to represent the initial membership matrix; u sp (ip, m) p (k) can be used to represent the initial membership degree of the vehicle speed for the driving severity level P; u θp (i p ,m p,k) can be used to represent the initial membership degree of the steering wheel angle for the driving severity level P; u np (i p m p k) can be used to represent the steering wheel speed initialization membership degree for the driving intensity level P; u lp (i p m p ,k) can be used to represent the initial membership degree of the brake pedal travel for the driving severity level P; u vp (i p m p ,k) can be used to represent the initial membership of the brake pedal rate for the driving severity level P.

[0057] Optionally, for each driving intensity level P, the initial iteration number A is set. p =0, or the initial value function J can be set. p In this embodiment of the invention, the initial value function J can be taken. p It can be a maximum value.

[0058] As an optional embodiment, step S104 involves clustering the driving intensity corresponding to various driving state data to obtain clustering results, including: updating the initial cluster centers based on the sample set and the initial membership matrix to obtain the updated cluster center group corresponding to the initial cluster centers; updating the initial membership matrix based on the cluster center dimension value to obtain the updated membership matrix corresponding to the initial membership matrix; updating the initial value function based on the membership matrix and each sample in the sample set to obtain the updated value function corresponding to the initial value function; and incrementing the initial iteration number by one in response to the updated cluster center group, membership matrix, and value function to obtain the updated iteration number. The clustering results include at least the cluster center group, membership matrix, and value function.

[0059] In this embodiment, during the process of clustering the driving intensity corresponding to various driving state data to obtain the clustering results, the initial cluster centers can be updated based on the sample set and the initial membership matrix to obtain the updated cluster center group corresponding to the initial cluster centers. Alternatively, the initial membership matrix can be updated based on the cluster center dimension value to obtain the updated membership matrix corresponding to the initial membership matrix. Or, the initial value function can be updated based on the membership matrix and each sample in the sample set to obtain the updated value function corresponding to the initial value function. After updating the initial cluster centers, the initial membership matrix, and the initial value function to obtain the cluster center group, the membership matrix, and the value function, the initial iteration number can be incremented by one to obtain the updated iteration number. The clustering results include at least the cluster center group, the membership matrix, and the value function.

[0060] Optionally, for each driving intensity level P, the initial cluster centers are updated to obtain a cluster center group c. p (m p ,k+1), where the cluster center group can be divided into five dimensions: vehicle speed dimension, steering wheel angle dimension, steering wheel speed dimension, brake pedal travel dimension, and brake pedal rate dimension.

[0061] For example, taking vehicle speed as an example, updating the initial cluster centers for each vehicle speed dimension can include the following steps: Calculate the sum of the products of the vehicle speed corresponding to each sample in the entire sample set and the initial membership degree of the vehicle speed corresponding to each vehicle speed dimension cluster center in the membership matrix, divided by the sum of the initial membership degrees of the vehicle speed corresponding to each vehicle speed dimension cluster center in the initial membership matrix of the entire sample set. The update method for the initial cluster centers corresponding to the other four cluster center dimension values ​​is similar to the method for initializing the initial cluster centers for the vehicle speed dimension. A total of m cluster center dimension values ​​are updated. p A cluster of cluster centers.

[0062] Optionally, the initial cluster centers can be updated to obtain the cluster center group shown in the following expression:

[0063]

[0064] (m p =m p1 m p2 , ..., m pmax i p =i p1 i p2 , ..., i pmax (k=0)

[0065] Among them, c p (m p (k+1) can be used to represent the updated cluster center group; k can be used to represent the k-th iteration; k+1 can be used to represent the k+1-th iteration.

[0066] Optionally, for each driving severity level P, the initial membership matrix can be updated to obtain the updated membership dimension. This membership dimension can be divided into five dimensions: vehicle speed, steering wheel angle, steering wheel speed, brake pedal travel, and brake pedal rate.

[0067] For example, taking vehicle speed as an example, the method for updating the initial membership matrix of each sample's vehicle speed dimension for each vehicle speed dimension cluster center can include the following steps: Calculate the reciprocal of the squared difference between the vehicle speed value corresponding to each sample in the sample set and the updated cluster center for that vehicle speed dimension, divided by the sum of the reciprocals of the squared differences between the vehicle speed value corresponding to each sample in the entire vehicle speed dimension cluster center group and the updated cluster center for that vehicle speed dimension cluster center group. The update method for the initial membership matrices corresponding to the other four cluster center dimension values ​​is similar to the update method for the initial membership matrix of the vehicle speed dimension. Each cluster center dimension value updates a total of i... p Membership degree.

[0068] Optionally, the initial membership matrix can be updated to obtain the membership matrix shown in the following expression:

[0069]

[0070] (m p =m p1 m p2 , ..., m pmax i p =i p1 i p2 , ..., i pmax (k=0)

[0071] Among them, u p (i p m p (k+1) can be used to represent the updated membership matrix.

[0072] Optionally, for each driving intensity level P, the number of iterations A p Add one more time, update the initial value function, and obtain the value function J. pThe value function can have five dimensions: vehicle speed, steering wheel angle, steering wheel speed, brake pedal travel, and brake pedal rate.

[0073] For example, taking vehicle speed as an example, updating the initial value function for each vehicle speed dimension can include the following steps: Calculate the squared difference between the vehicle speed value corresponding to each sample in the sample set and the updated membership degree corresponding to the vehicle speed of each cluster center in the initial membership matrix. Then, calculate the sum of the squared differences between all samples in the entire sample set and all cluster centers in the entire sample set. The update method for the initial value functions corresponding to the other four cluster center dimensions is similar to that for the vehicle speed dimension. A total of five value functions are obtained by updating each cluster center dimension.

[0074] For another example, the initial value function can be updated to obtain the value function shown in the following expression:

[0075]

[0076] (m p =m p1 m p2 , ..., m pmax i p =i p1 i p2 , ..., i pmax (k=0)

[0077] Among them, J p (k+1) can be used to represent the updated value function; J sp (k+1) can be used to represent the value function of the vehicle speed after the updated driving intensity level P; J θp (k+1) can be used to represent the value function of the steering wheel angle after the updated driving intensity level P; J np (k+1) can be used as a value function to represent the steering wheel speed after the updated driving intensity level P; J lp (k+1) can be used to represent the value function of the brake pedal travel for the updated driving severity level P; J vp (k+1) can be used to represent the value function of the brake pedal rate for the updated driving severity level P.

[0078] Optionally, the initial iteration count can be updated using the following formula:

[0079] A p (k+1)=A p (k)+1

[0080] Among them, A p (k+1) can be used to represent the number of iterations after the update; A p (k) can be used to represent the number of iterations before the update.

[0081] As an optional embodiment, step S104 may further include: in response to the iteration number being less than an iteration number threshold, determining the change in the value function corresponding to the iteration number; in response to the change being less than the change threshold, stopping the iteration, and using the cluster center group corresponding to the iteration number as input data for the vehicle's braking control system.

[0082] In this embodiment, the relationship between the number of iterations and the iteration threshold can be determined. If the number of iterations is greater than or equal to the iteration threshold, the iterative calculation process can be stopped. If the number of iterations is less than the iteration threshold, the change in the value function corresponding to the number of iterations can be determined. The relationship between the change and the change threshold can be determined. If the change is greater than or equal to the change threshold, the iterative calculation can continue. If the change is less than the change threshold, the iteration can be stopped, and the cluster center group corresponding to the number of iterations can be used as input data for the vehicle's braking control system, which can be an integrated braking control system. The change threshold can include the change in the value function of vehicle speed, the change in the value function of steering wheel angle, the change in the value function of steering wheel speed, the change in the value function of brake pedal travel, and the change in the value function of brake pedal rate. The iteration threshold and the change threshold can be preset values ​​or data set according to the actual testing requirements of the braking energy recovery function. For example, the iteration threshold can be set to 100. The change in the value function for vehicle speed can be set to 0.15, the change in the value function for steering wheel angle can be set to 0.2, the change in the value function for steering wheel speed can be set to 1, the change in the value function for brake pedal travel can be set to 0.03, and the change in the value function for brake pedal rate can be set to 0.5. It should be noted that the above-mentioned settings and values ​​for the iteration number threshold and change threshold are for illustrative purposes only and are not subject to specific limitations.

[0083] Optionally, for each driving intensity level P, the iteration number A can be determined. p With the iteration number threshold (maximum number of iterations) A pmax In this embodiment of the invention, the relationship between the two can be determined by setting an iteration threshold A. pmax =100. If the number of iterations is greater than or equal to the iteration threshold, the iteration calculation can be stopped. If the number of iterations is less than the iteration threshold, the change in the value function can be determined.

[0084] Optionally, for each driving severity level P, the change in the value function for each cluster center dimension can be calculated, and it can be determined whether the changes in the value functions for all cluster center dimensions are less than the corresponding change threshold. If yes, the iterative calculation can be stopped. If not, the iterative calculation can continue.

[0085] For example, the relationship between the change amount and the change amount threshold can be expressed by the following formula:

[0086] ΔJ sp =|J sp (k+1)-J sp (k)|<0.15

[0087] ΔJ θp =|J θp (k+1)-J θp (k)|<0.2

[0088] ΔJ np =|J np (k+1)-J np (k)|<1

[0089] ΔJl p =|Jl p (k+1)-Jlp(k)|<0.03

[0090] ΔJ vp =|J vp (k+1)-J vp (k)|<0.5

[0091] Where, ΔJ sp It can be used to represent the change in the value function of the vehicle speed between the (k+1)th iteration and the kth iteration; ΔJ θp It can be used to represent the change in the value function of the steering wheel angle between the (k+1)th iteration and the kth iteration; ΔJ np It can be used to represent the change in the value function of the steering wheel rotation speed between the (k+1)th iteration and the kth iteration; ΔJ lp This can be used to represent the change in the value function of the brake pedal travel between the (k+1)th iteration and the kth iteration; ΔJ vp It can be used to represent the change in the value function of the brake pedal rate between the (k+1)th iteration and the kth iteration.

[0092] Optionally, after stopping the iteration, and having obtained the clustering results for all driving severity levels P, the final version of the cluster center group with the five cluster center dimension values ​​can be used as the input data for the vehicle's braking control system.

[0093] As an optional embodiment, step S106, based on the clustering results, tests the vehicle's regenerative braking function to obtain test results, including: in response to using the cluster center group as input data for the vehicle's braking control system, controlling the braking control system to test the vehicle's regenerative braking function based on the input data to obtain test results.

[0094] In this embodiment, during the process of testing the vehicle's regenerative braking function based on the clustering results and obtaining the test results, after the vehicle's braking control system receives the cluster center group, it can control the braking control system to test the vehicle's regenerative braking function based on the cluster center group and obtain the test results.

[0095] Optionally, the final version of the cluster center group obtained through iteration can be used as input data for an integrated braking control system. Different input data can be used to test the braking energy recovery function under different driving intensity scenarios. The final version of the cluster center group can be represented by the following expression:

[0096] [c sp (m p ), c θp (m p ), c np (m p ), c lp (m p ), c vp (m p )](m p =m p1 m p2 , ..., m pmax )

[0097] Among them, c sp (m p ) can be used to represent the final version of cluster centers for vehicle speed; c θp (m p ) can be used to represent the final version of cluster centers for steering wheel angles; c np (m p ) can be used as the final version of the cluster center to represent steering wheel rotation speed; c lp (m p ) can be used to represent the final version of the brake pedal travel cluster center; c vp (m p () can be used as the final version of the cluster center to represent the brake pedal rate.

[0098] For example, we can obtain m p Each driving scenario uses m pEach driving scenario represents hundreds or thousands of different driving state data points, and the extracted m p Hardware-in-the-loop tests are conducted on each driving scenario to determine whether the regenerative braking function of the integrated braking control system meets the expected performance, that is, to determine whether the regenerative braking function is in a normal state.

[0099] In this embodiment of the invention, various driving state data of the vehicle are acquired, wherein the driving state data is used to represent the driving intensity of the vehicle during driving; the driving intensity corresponding to the various driving state data is clustered to obtain clustering results, wherein the clustering results are used to represent the driving scenario corresponding to the driving intensity; based on the clustering results, the vehicle's regenerative braking function is tested to obtain test results, wherein the test results are used to indicate whether the regenerative braking function is in a normal state, and the regenerative braking function is used to recover and utilize the additional braking energy in the vehicle under the corresponding driving intensity. In other words, the embodiments of the present invention can cluster the collected driving state data according to the driving intensity to obtain clustering results. That is, driving scenarios corresponding to different driving intensities can be obtained. Based on different driving scenarios, the regenerative braking function of the corresponding driving scenario can be tested to determine whether the regenerative braking function can recover and utilize the additional braking energy in the vehicle under the corresponding driving intensity scenario. This can determine whether the vehicle's regenerative braking function is in a normal state. Since the driving state data can be analyzed through clustering to determine different driving scenarios and test each driving scenario, the goal of not having to traverse all driving state data is achieved. This solves the technical problem of low efficiency in testing the vehicle's regenerative braking function and achieves the technical effect of improving the efficiency of testing the vehicle's regenerative braking function.

[0100] Example 2

[0101] The technical solutions of the embodiments of the present invention will be illustrated below with reference to preferred embodiments.

[0102] Currently, with the development of electronic braking control systems, more and more vehicles are using integrated braking control systems. Input data for integrated braking control systems can include vehicle speed, brake pedal travel, brake pedal rate, steering wheel angle, and steering wheel speed. Based on this input data, the integrated braking control system can identify the degree of driving aggression and then calculate the state of the regenerative braking function. However, in related technologies, while comprehensive testing of a vehicle's regenerative braking function can be conducted, this requires traversing all driving state data to test the corresponding regenerative braking function. However, traversing all driving state data is time-consuming, thus the technical problem of low efficiency in testing a vehicle's regenerative braking function remains.

[0103] In a related technology, a braking energy recovery method, system, and vehicle based on an adaptive cruise control system are proposed, relating to the field of automotive control. The method includes: when the vehicle is in adaptive cruise control mode, and the cruise torque is less than a preset threshold, simultaneously acquiring the total braking torque required by the vehicle and the energy recovery torque that the energy recovery system can generate; comparing the total braking torque and the energy recovery torque; and allocating the total braking torque according to the comparison result, wherein if the total braking torque is less than the energy recovery torque, braking is performed using the energy recovery system; if the total braking torque is greater than the energy recovery torque, the excess braking torque is generated by the braking system. This method, even when the vehicle is in adaptive cruise control mode, can effectively recover and store braking energy through the energy recovery system, extending the vehicle's driving range under this condition and improving overall vehicle economy.

[0104] In another related technology, a method, device, electric vehicle, and medium for controlling the motor drive of an electric vehicle are also proposed. The method includes: detecting a brake signal after the vehicle enters normal driving conditions; if a brake signal is detected, determining the current regenerative braking power; if the current regenerative braking power exceeds a set first power limit, controlling the motor drive system to enter a dual-motor operating mode for regenerative braking. This method determines the motor operating mode from multiple dimensions, including the influence of the brake signal, the impact of dual motors on regenerative braking, and the switching between single and dual motors due to motor power limits. This maximizes the system's regenerative braking capacity, improves system efficiency, avoids power waste, and switches the motor operating mode based on the output speed and the actual required power, preventing slow system power response caused by immediately switching to dual-motor mode due to high torque demand during start-up.

[0105] However, the above method still has the technical problem of low efficiency in testing the vehicle's regenerative braking function.

[0106] However, this invention proposes a method for implementing a regenerative braking scenario. This method may include: clustering collected driving state data according to driving intensity to obtain clustering results, i.e., obtaining driving scenarios corresponding to different driving intensities; based on different driving scenarios, testing the regenerative braking function of the corresponding driving scenario to determine whether the regenerative braking function can recover and utilize the additional braking energy in the vehicle under the corresponding driving intensity scenario, thereby determining whether the vehicle's regenerative braking function is in a normal state. Since clustering can be used to analyze driving state data, identify different driving scenarios, and test each driving scenario, the goal of not needing to traverse all driving state data is achieved, thus solving the technical problem of low efficiency in testing the vehicle's regenerative braking function and realizing the technical effect of improving the efficiency of testing the vehicle's regenerative braking function.

[0107] The embodiments of the present invention will be further described below.

[0108] In this embodiment, various driving status data of the vehicle being put into use can be obtained during the driving process, thereby facilitating the testing of the braking energy recovery function of the vehicle to be put into use based on the various driving status data.

[0109] Optionally, the five data points in the driving status data—vehicle speed, steering wheel angle, steering wheel speed, brake pedal travel, and brake pedal rate—can be used as input signals for the integrated braking control system in the vehicle, and these five input signals can be used as cluster center dimension values.

[0110] Optionally, a driving intensity level P can be set according to different levels of intensity during vehicle driving. For example, five driving intensity levels can be set, that is, P=5 can be set. The larger the P value, the more intense the driving intensity.

[0111] Optionally, the number of cluster centers m can be set. pmax As the driving intensity level P increases, the number of cluster centers m... pmax The smaller the value, for example, the more likely the number of cluster centers m can be. pmax These are: the number of cluster centers m corresponding to level P=1. 1max =20, corresponding to the number of cluster centers m at level P=2. 2max =18, corresponding to the number of cluster centers m for level P=3. 3max =14, corresponding to the number of cluster centers m at level P=4. 4max =12, corresponding to the number of cluster centers m for level P=5. 5max =8.

[0112] Optionally, at a certain moment, the cluster center dimension values ​​(vehicle speed s, steering wheel angle θ, steering wheel speed n, brake pedal travel l, and brake pedal speed v) corresponding to the driving intensity level P can be captured as samples for the corresponding P levels, and the number of samples can be i. pmax This corresponds to the driving intensity level P, and the sample set can contain 5×i. pmax The sample set can be represented by the following expression:

[0113]

[0114] Among them, X p (i p ) can be used to represent the sample set of driving severity level P; s(i p ) can be used to represent vehicle speed samples of driving severity level P; θ(i p ) can be used to represent the steering wheel angle sample of the driving severity level P; n(i p ) can be used to represent the steering wheel speed sample for the driving intensity level P; l(i p ) can be used to represent the brake pedal travel sample of the driving severity level P; v(i p This can be used to represent a sample of brake pedal rate for driving severity level P.

[0115] Optionally, for each driving severity level P, initial cluster centers can be determined, which may include 5×m cluster centers. pmax The initialization of cluster centers can be represented by the following expression:

[0116]

[0117] Among them, c p (m p k) can be used to represent the initial cluster centers of the driving severity level P; c sp (m p (k) can be used to represent the number of vehicle speed cluster centers for the driving severity level P; c θp (m p (k) can be used to represent the number of cluster centers for the steering wheel angle at the driving severity level P; c np (m p k) can be used to represent the number of cluster centers for the steering wheel rotation speed at the driving intensity level P; c lp (m p k) can be used to represent the number of cluster centers for brake pedal travel at driving severity level P; c vp (m p ,k) can be used to represent the number of cluster centers for brake pedal rate at driving severity level P.

[0118] Optionally, considering expert experience, for any driving intensity level P, the initial membership degrees corresponding to the five cluster center dimensions—vehicle speed s, steering wheel angle θ, steering wheel speed n, brake pedal travel l, and brake pedal rate v—are considered to be the same. The initial membership degree matrix corresponding to any driving intensity level P can include 5×i... pmax The membership matrix can be initialized using the following expression: (The matrix contains n elements.)

[0119]

[0120] Where, m p =m p1 m p2 , ..., m pmax i p =i p1 i p2 , ..., i pmax k = 0. p (i p m p k) can be used to represent the initial membership matrix; u sp (i p m p ,k) can be used to represent the initial membership degree of the vehicle speed for the driving severity level P; u θp (i p m p k) can be used to represent the initial membership degree of the steering wheel angle for the driving severity level P; u np (i p m p k) can be used to represent the steering wheel speed initialization membership degree for the driving intensity level P; u lp (i p m p ,k) can be used to represent the initial membership degree of the brake pedal travel for the driving severity level P; u vp (i p， m p ,k) can be used to represent the initial membership of the brake pedal rate for the driving severity level P.

[0121] Optionally, for each driving intensity level P, the initial iteration number A is set. p =0, or the initial value function J can be set. p In this embodiment of the invention, the initial value function J can be taken. p It can be a maximum value.

[0122] In this embodiment, various driving state data correspond to different driving intensity levels. Based on different driving intensity levels, the corresponding driving state data can be clustered to obtain clustering results. That is, the driving scenarios corresponding to different driving intensity levels can be obtained.

[0123] Optionally, for each driving intensity level P, the initial cluster centers are updated to obtain a cluster center group c. p (m p ,k+1), where the cluster center group can be divided into five dimensions: vehicle speed dimension, steering wheel angle dimension, steering wheel speed dimension, brake pedal travel dimension, and brake pedal rate dimension.

[0124] For example, taking vehicle speed as an example, updating the initial cluster centers for each vehicle speed dimension can include the following steps: Calculate the sum of the products of the vehicle speed corresponding to each sample in the entire sample set and the initial membership degree of the vehicle speed corresponding to each vehicle speed dimension cluster center in the membership matrix, divided by the sum of the initial membership degrees of the vehicle speed corresponding to each vehicle speed dimension cluster center in the initial membership matrix of the entire sample set. The update method for the initial cluster centers corresponding to the other four cluster center dimension values ​​is similar to the method for initializing the initial cluster centers for the vehicle speed dimension. A total of m cluster center dimension values ​​are updated. p A cluster of cluster centers.

[0125] Optionally, the initial cluster centers can be updated to obtain the cluster center group shown in the following expression:

[0126]

[0127] (m p =m p1 m p2 , ..., m pmax i p =i p1 i p2 , ..., i pmax (k=0)

[0128] Among them, c p (m p (k+1) can be used to represent the updated cluster center group; k can be used to represent the k-th iteration; k+1 can be used to represent the k+1-th iteration.

[0129] Optionally, for each driving severity level P, the initial membership matrix can be updated to obtain the updated membership dimension. This membership dimension can be divided into five dimensions: vehicle speed, steering wheel angle, steering wheel speed, brake pedal travel, and brake pedal rate.

[0130] For example, taking vehicle speed as an example, the method for updating the initial membership matrix of each sample's vehicle speed dimension for each vehicle speed dimension cluster center can include the following steps: Calculate the reciprocal of the squared difference between the vehicle speed value corresponding to each sample in the sample set and the updated cluster center for that vehicle speed dimension, divided by the sum of the reciprocals of the squared differences between the vehicle speed value corresponding to each sample in the entire vehicle speed dimension cluster center group and the updated cluster center for that vehicle speed dimension cluster center group. The update method for the initial membership matrices corresponding to the other four cluster center dimension values ​​is similar to the update method for the initial membership matrix of the vehicle speed dimension. Each cluster center dimension value updates a total of i... p Membership degree.

[0131] Optionally, the initial membership matrix can be updated to obtain the membership matrix shown in the following expression:

[0132]

[0133] (m p =m p1 m p2 , ..., m pmax i p =i p1 ,t p2 , ..., i pmax (k=0)

[0134] Among them, u p (i p ,m p (k+1) can be used to represent the updated membership matrix.

[0135] Optionally, for each driving intensity level P, the number of iterations A p Add one more time, update the initial value function, and obtain the value function J. p The value function can have five dimensions: vehicle speed, steering wheel angle, steering wheel speed, brake pedal travel, and brake pedal rate.

[0136] For example, taking vehicle speed as an example, updating the initial value function for each vehicle speed dimension can include the following steps: Calculate the squared difference between the vehicle speed value corresponding to each sample in the sample set and the updated membership degree corresponding to the vehicle speed of each cluster center in the initial membership matrix. Then, calculate the sum of the squared differences between all samples in the entire sample set and all cluster centers in the entire sample set. The update method for the initial value functions corresponding to the other four cluster center dimensions is similar to that for the vehicle speed dimension. A total of five value functions are obtained by updating each cluster center dimension.

[0137] For another example, the initial value function can be updated to obtain the value function shown in the following expression:

[0138]

[0139] (m p =m p1 m p2 , ..., m pmax i p =i p1 i p2 , ..., i pmax (k=0)

[0140] Among them, J p (k+1) can be used to represent the updated value function; J sp (k+1) can be used to represent the value function of the vehicle speed after the updated driving intensity level P; J θp (k+1) can be used to represent the value function of the steering wheel angle after the updated driving intensity level P; J np (k+1) can be used as a value function to represent the steering wheel speed after the updated driving intensity level P; J lp (k+1) can be used to represent the value function of the brake pedal travel for the updated driving severity level P; J vp (k+1) can be used to represent the value function of the brake pedal rate for the updated driving severity level P.

[0141] Optionally, the initial iteration count can be updated using the following formula:

[0142] A p (k+1)=A p (k)+1

[0143] Among them, A p (k+1) can be used to represent the number of iterations after the update; A p (k) can be used to represent the number of iterations before the update.

[0144] As an optional embodiment, step S104 may further include: in response to the iteration number being less than an iteration number threshold, determining the change in the value function corresponding to the iteration number; in response to the change being less than the change threshold, stopping the iteration, and using the cluster center group corresponding to the iteration number as input data for the vehicle's braking control system.

[0145] In this embodiment, the relationship between the number of iterations and the iteration threshold can be determined. If the number of iterations is greater than or equal to the iteration threshold, the iterative calculation process can be stopped. If the number of iterations is less than the iteration threshold, the change in the value function corresponding to the number of iterations can be determined. The relationship between the change and the change threshold can be determined. If the change is greater than or equal to the change threshold, the iterative calculation can continue. If the change is less than the change threshold, the iteration can be stopped, and the cluster center group corresponding to the number of iterations can be used as input data for the vehicle's braking control system, which can be an integrated braking control system. The change threshold can include the change in the value function of vehicle speed, the change in the value function of steering wheel angle, the change in the value function of steering wheel speed, the change in the value function of brake pedal travel, and the change in the value function of brake pedal rate. The iteration threshold and the change threshold can be preset values ​​or data set according to the actual testing requirements of the braking energy recovery function. For example, the iteration threshold can be set to 100. The change in the value function for vehicle speed can be set to 0.15, the change in the value function for steering wheel angle can be set to 0.2, the change in the value function for steering wheel speed can be set to 1, the change in the value function for brake pedal travel can be set to 0.03, and the change in the value function for brake pedal rate can be set to 0.5. It should be noted that the above-mentioned settings and values ​​for the iteration number threshold and change threshold are for illustrative purposes only and are not subject to specific limitations.

[0146] Optionally, for each driving intensity level P, the iteration number A can be determined. p With the iteration number threshold (maximum number of iterations) A pmax In this embodiment of the invention, the relationship between the two can be determined by setting an iteration threshold A. pmax =100. If the number of iterations is greater than or equal to the iteration threshold, the iteration calculation can be stopped. If the number of iterations is less than the iteration threshold, the change in the value function can be determined.

[0147] Optionally, for each driving severity level P, the change in the value function for each cluster center dimension can be calculated, and it can be determined whether the changes in the value functions for all cluster center dimensions are less than the corresponding change threshold. If yes, the iterative calculation can be stopped. If not, the iterative calculation can continue.

[0148] For example, the relationship between the change amount and the change amount threshold can be expressed by the following formula:

[0149] ΔJ sp =|J sp (k+1)-J sp (k)|<0.15

[0150] ΔJ θp =|J θp (k+1)-J θp (k)|<0.2

[0151] ΔJ np =|J np (k+1)-J np (k)|<1

[0152] ΔJ l p = |J lp (k+1)-Jx p (k)|<0.03

[0153] ΔJ vp =|J vp (k+1)-J vp (k)|<0.5

[0154] Where, ΔJ sp It can be used to represent the change in the value function of the vehicle speed between the (k+1)th iteration and the kth iteration; ΔJ θp It can be used to represent the change in the value function of the steering wheel angle between the (k+1)th iteration and the kth iteration; ΔJ np It can be used to represent the change in the value function of the steering wheel rotation speed between the (k+1)th iteration and the kth iteration; ΔJ lp This can be used to represent the change in the value function of the brake pedal travel between the (k+1)th iteration and the kth iteration; ΔJ vp It can be used to represent the change in the value function of the brake pedal rate between the (k+1)th iteration and the kth iteration.

[0155] Optionally, after stopping the iteration, and having obtained the clustering results for all driving severity levels P, the final version of the cluster center group with the five cluster center dimension values ​​can be used as the input data for the vehicle's braking control system.

[0156] In this embodiment, after obtaining the clustering results, the braking energy recovery function of the corresponding driving scenario can be tested based on the driving scenarios corresponding to different driving intensities in the clustering results. The test results can be used to determine whether the braking energy recovery function can recover and utilize the additional braking energy in the vehicle under the corresponding driving intensities, and whether the required amount of braking energy can be recovered and utilized. Thus, it can be determined whether the braking energy recovery function is in a normal state.

[0157] Optionally, the final version of the cluster center group obtained through iteration can be used as input data for an integrated braking control system. Different input data can be used to test the braking energy recovery function under different driving intensity scenarios. The final version of the cluster center group can be represented by the following expression:

[0158] [c sp (m p ), c θp (m p ), c np (m p ), c lp (m p ), c vp (m p )](m p =m p1 m p2 , ..., m pmax )

[0159] Among them, c sp (m p ) can be used to represent the final version of cluster centers for vehicle speed; c θp (m p ) can be used to represent the final version of cluster centers for steering wheel angles; c np (m p ) can be used as the final version of the cluster center to represent steering wheel rotation speed; c lp (m p ) can be used to represent the final version of the brake pedal travel cluster center; c vp (m p () can be used as the final version of the cluster center to represent the brake pedal rate.

[0160] For example, we can obtain m p Each driving scenario uses m p Each driving scenario represents hundreds or thousands of different driving state data points, and the extracted m pHardware-in-the-loop tests are conducted on each driving scenario to determine whether the regenerative braking function of the integrated braking control system meets the expected performance, that is, to determine whether the regenerative braking function is in a normal state.

[0161] In this embodiment of the invention, multiple driving state data and their corresponding driving intensity can be clustered to determine the driving scenarios corresponding to different driving intensity levels after clustering. This eliminates the need to traverse all driving state data and conduct comprehensive experiments to determine the state of the regenerative braking function, thus avoiding the significant time consumed by traversing all data and conducting comprehensive experiments. Only the regenerative braking function under different driving scenarios obtained from the clustering process needs to be tested, thereby improving the efficiency of testing the vehicle's regenerative braking function.

[0162] This invention can cluster various driving state data collected according to the intensity of driving to obtain clustering results. That is, it can obtain driving scenarios corresponding to different levels of driving intensity. Based on different driving scenarios, the regenerative braking function of the corresponding driving scenario can be tested to determine whether the regenerative braking function can recover and utilize the additional braking energy in the vehicle under the corresponding level of driving intensity. This can determine whether the vehicle's regenerative braking function is in a normal state. Since the driving state data can be analyzed through clustering to determine different driving scenarios and test each driving scenario, the goal of not needing to traverse all driving state data is achieved. This solves the technical problem of low efficiency in testing the vehicle's regenerative braking function and improves the technical effect of testing the vehicle's regenerative braking function.

[0163] Example 3

[0164] According to an embodiment of the present invention, a testing device for the regenerative braking function of a vehicle is also provided. It should be noted that this testing device for the regenerative braking function of a vehicle can be used to perform the testing method for the regenerative braking function of a vehicle in Embodiment 1.

[0165] Figure 2 This is a schematic diagram of a test device for the regenerative braking function of a vehicle according to an embodiment of the present invention. Figure 2 As shown, the test device 200 for the vehicle's regenerative braking function may include: an acquisition unit 202, a processing unit 204, and a test unit 206.

[0166] The acquisition unit 202 is used to acquire various driving state data of the vehicle, wherein the driving state data is used to represent the degree of driving intensity of the vehicle during driving.

[0167] The processing unit 204 is used to perform clustering processing on the driving intensity corresponding to various driving state data to obtain clustering results, wherein the clustering results are used to represent the driving scenario corresponding to the driving intensity.

[0168] Test unit 206 is used to test the vehicle's regenerative braking function based on clustering results and obtain test results. The test results are used to indicate whether the regenerative braking function is in a normal state. The regenerative braking function is used to recover and utilize the additional braking energy in the vehicle under the corresponding driving intensity.

[0169] Optionally, the device may include: a first determining module, configured to determine the cluster center dimension value of the fuzzy clustering model for clustering based on driving state data, and to set the driving intensity level of the vehicle, wherein the driving intensity level is used to represent different degrees of intensity during vehicle driving; and a second determining module, configured to determine the number of cluster centers of the fuzzy clustering model based on the cluster center dimension value and the driving intensity level, wherein the number of cluster centers and the driving intensity level are negatively correlated.

[0170] Optionally, the device may further include: a third determining module, used to integrate the cluster center dimension values ​​corresponding to different driving intensity levels to determine a sample set composed of samples of different driving intensity levels; a fourth determining module, used to determine the initial cluster centers corresponding to different driving intensity levels based on the sample set, and to determine the initial membership matrix corresponding to the cluster center dimension values ​​in the sample set; and a fifth determining module, used to determine the initial iteration number and initial value function corresponding to different driving intensity levels.

[0171] Optionally, the processing unit 204 may include: a first update module, used to update the initial cluster centers based on the sample set and the initial membership matrix, so as to obtain the updated cluster center group corresponding to the initial cluster centers.

[0172] Optionally, the processing unit 204 may include: a second update module, used to update the initial membership matrix based on the cluster center dimension value to obtain the updated membership matrix corresponding to the initial membership matrix; a third update module, used to update the initial value function based on the membership matrix and each sample in the sample set to obtain the updated value function corresponding to the initial value function; and a fourth update module, used to increment the initial iteration number by one in response to the updated cluster center group, membership matrix, and value function to obtain the updated iteration number, wherein the clustering result includes at least the cluster center group, membership matrix, and value function.

[0173] Optionally, the device may further include: a sixth determining module, configured to determine the change in the value function corresponding to the iteration number in response to the iteration number being less than an iteration number threshold; and a processing module, configured to stop the iteration in response to the change being less than a change amount threshold, and to use the cluster center group corresponding to the iteration number as input data for the vehicle's braking control system.

[0174] Optionally, the test unit 206 may include: a test module, configured to, in response to using the cluster center group as input data for the vehicle's braking control system, control the braking control system to test the vehicle's regenerative braking function based on the input data, and obtain test results.

[0175] In this embodiment of the invention, an acquisition unit acquires various driving state data of the vehicle, wherein the driving state data represents the degree of driving intensity during the vehicle's operation; a processing unit performs clustering processing on the driving intensity corresponding to the various driving state data to obtain clustering results, wherein the clustering results represent the driving scenarios corresponding to the degree of driving intensity; a testing unit tests the vehicle's regenerative braking function based on the clustering results to obtain test results, wherein the test results indicate whether the regenerative braking function is in a normal state. The regenerative braking function is used to recover and utilize additional braking energy in the vehicle under the corresponding degree of driving intensity, thereby solving the technical problem of low efficiency in testing the vehicle's regenerative braking function and achieving the technical effect of improving the efficiency of testing the vehicle's regenerative braking function.

[0176] Example 4

[0177] According to an embodiment of the present invention, a computer-readable storage medium is also provided, the storage medium including a stored program, wherein the program executes the test method for the regenerative braking function of a vehicle as described in Embodiment 1.

[0178] Example 5

[0179] According to an embodiment of the present invention, a processor is also provided for running a program, wherein the program executes the test method for the regenerative braking function of a vehicle as described in Embodiment 1.

[0180] Example 6

[0181] According to an embodiment of the present invention, a vehicle is also provided, which is used for testing the braking energy recovery function of the vehicle according to the embodiment of the present invention.

[0182] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0183] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0184] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0185] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0186] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0187] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0188] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method of testing a brake energy recovery function of a vehicle, characterized by, The method comprises the following steps: acquiring a plurality of driving state data of a vehicle, wherein the driving state data is used to represent the driving intensity of the vehicle during driving, and the plurality of driving state data comprises the vehicle speed, steering wheel angle, steering wheel speed, brake pedal stroke and brake pedal rate of the vehicle; respectively clustering the driving intensity corresponding to the plurality of driving state data to obtain a clustering result, wherein the clustering result is used to represent the driving scene corresponding to the driving intensity; based on the clustering result, testing the brake energy recovery function of the vehicle to obtain a test result, wherein the test result is used to represent whether the brake energy recovery function is in a normal state, and the brake energy recovery function is used to recover and utilize the additional brake energy of the vehicle under the corresponding driving intensity.

2. The method of claim 1, wherein, Before the step of respectively clustering the driving intensity corresponding to the plurality of driving state data to obtain a clustering result, the method further comprises the following steps: based on the driving state data, determining the clustering center dimension value of a fuzzy clustering model used for the clustering, and setting the driving intensity level of the vehicle, wherein the driving intensity level is used to represent different driving intensities during driving of the vehicle; based on the clustering center dimension value and the driving intensity level, determining the number of clustering centers of the fuzzy clustering model, wherein the number of clustering centers and the driving intensity level are negatively correlated.

3. The method of claim 2, wherein, After the step of based on the clustering center dimension value and the driving intensity level, determining the number of clustering centers of the fuzzy clustering model, the method further comprises the following steps: integrating the clustering center dimension value corresponding to different driving intensity levels to determine a sample set composed of samples of different driving intensity levels; based on the sample set, determining the initialization clustering center corresponding to different driving intensity levels, and determining the initialization membership matrix corresponding to the clustering center dimension value in the sample set; determining the initialization iteration number and initialization value function corresponding to different driving intensity levels.

4. The method of claim 3, wherein, The step of respectively clustering the driving intensity corresponding to the plurality of driving state data to obtain a clustering result comprises the following steps: based on the sample set and the initialization membership matrix, updating the initialization clustering center to obtain an updated clustering center group corresponding to the initialization clustering center; based on the clustering center dimension value, updating the initialization membership matrix to obtain an updated membership matrix corresponding to the initialization membership matrix; based on the membership matrix, each sample in the sample set, updating the initialization value function to obtain an updated value function corresponding to the initialization value function; in response to the updated clustering center group, membership matrix and value function, adding one to the initialization iteration number to obtain an updated iteration number, wherein the clustering result at least comprises the clustering center group, the membership matrix and the value function.

5. The method of claim 4, wherein, The method further comprises the following steps: in response to the iteration number being less than an iteration number threshold, determining a change of the value function corresponding to the iteration number; in response to the change being less than a change threshold, stopping iteration, and taking the cluster center group corresponding to the iteration number as input data of a brake control system of the vehicle.

6. The method of claim 3, wherein, based on the clustering result, testing a brake energy recovery function of the vehicle to obtain a test result, including: in response to taking the cluster center group as input data of a brake control system of the vehicle, controlling the brake control system to test a brake energy recovery function of the vehicle based on the input data to obtain the test result.

7. A test device for a brake energy recovery function of a vehicle, characterized by including: an acquisition unit configured to acquire a plurality of driving state data of a vehicle, wherein the driving state data is used to represent a driving intensity of the vehicle during driving, and wherein the plurality of driving state data includes a vehicle speed, a steering wheel angle, a steering wheel speed, a brake pedal stroke, and a brake pedal rate of the vehicle; a processing unit configured to respectively cluster the driving intensity corresponding to the plurality of driving state data to obtain a clustering result, wherein the clustering result is used to represent a driving scenario corresponding to the driving intensity. a testing unit configured to test a brake energy recovery function of the vehicle based on the clustering result to obtain a test result, wherein the test result is used to represent whether the brake energy recovery function is in a normal state, and wherein the brake energy recovery function is used to recover and utilize extra brake energy of the vehicle under the corresponding driving intensity.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium includes a stored program, wherein the program controls the device where the computer readable storage medium is located to execute the method of any one of claims 1-6 when the program is running.

9. A processor, comprising: The processor is configured to run a program, wherein the program is executed by the processor when the program is running to execute the method of any one of claims 1-6.

10. A vehicle characterized by comprising: The processor is configured to run a program, wherein the program is executed by the processor when the program is running to execute the method of any one of claims 1-6. The processor is configured to run a program, wherein the program is executed by the processor when the program is running to execute the method of any one of claims 1-6.

Images