Vehicle braking energy recovery control method and device

Abstract

The embodiment of the invention provides a vehicle braking energy recovery control method and device, and the method comprises the steps: generating an input vector according to a first parameter in a vehicle driving process, obtaining clustering information corresponding to a plurality of driving styles, and obtaining a plurality of driving styles according to the clustering information and the input vector; according to the method, the target driving style is determined from the multiple driving styles, the target feedback torque is determined according to the target driving style, and the braking energy recovery intensity of the vehicle is controlled according to the target feedback torque, so that the driving styles are accurately recognized in a clustering mode, and then braking energy is recovered according to the driving styles. The braking energy recovery efficiency is improved, and the driving experience and the energy utilization rate are improved.

Description

Technical Field

[0001] The present invention relates to the field of automobile technology, and in particular to a method and device for controlling vehicle braking energy recovery. Background Art

[0002] With the development of electric vehicle technology, some vehicles are equipped with a braking energy recovery mechanism for environmental protection and energy saving. Through the braking energy recovery mechanism, kinetic energy can be recovered. However, in the existing technology, the efficiency of braking energy recovery is not high. Summary of the invention

[0003] In view of the above problems, a method and device for controlling vehicle braking energy recovery is proposed to overcome the above problems or at least partially solve the above problems, including:

[0004] A method for controlling vehicle braking energy recovery, the method comprising:

[0005] generating an input vector according to a first parameter during the vehicle driving process;

[0006] Acquire clustering information corresponding to a plurality of driving styles, and determine a target driving style from the plurality of driving styles according to the clustering information and the input vector;

[0007] According to the target driving style, a target feedback torque is determined, and the braking energy recovery intensity of the vehicle is controlled according to the target feedback torque.

[0008] Optionally, determining a target feedback torque according to the target driving style includes:

[0009] determining a basic feedback torque according to the target driving style;

[0010] A rolling resistance correction coefficient is generated according to a second parameter during vehicle driving, and the basic feedback torque is adjusted according to the rolling resistance correction coefficient to obtain a target feedback torque.

[0011] Optionally, generating a rolling resistance correction coefficient according to a second parameter during vehicle driving includes:

[0012] A real-time rolling resistance coefficient is generated according to the second parameter during the vehicle driving process, and a rolling resistance correction coefficient is generated by combining a preset rolling resistance coefficient and the real-time rolling resistance coefficient.

[0013] Optionally, the second parameter includes any one or more of the following: vehicle mass, motor torque, vehicle speed, and vehicle acceleration.

[0014] Optionally, before acquiring clustering information corresponding to a plurality of driving styles, the method further includes:

[0015] Obtain a data set consisting of data objects corresponding to multiple driving styles;

[0016] In the data set, a plurality of cluster centers are determined, and data objects in the data set are divided into a plurality of data clusters according to the plurality of cluster centers, each data cluster corresponding to a driving style;

[0017] The cluster centers of the multiple data clusters are re-determined as the cluster centers corresponding to the multiple driving styles, and cluster information corresponding to the multiple driving styles is obtained.

[0018] Optionally, determining a plurality of cluster centers in the data set includes:

[0019] In the data set, a first cluster center is determined, and a second cluster center is determined according to the distance between the data object in the data set and the first cluster center;

[0020] Determine the Kth cluster center according to the distances between the data objects in the data set and all cluster centers from the first cluster center to the K-1th cluster center;

[0021] Wherein, K is a positive integer greater than 2, and the maximum value of K is the number of driving style types.

[0022] Optionally, in the data set, before determining a plurality of cluster centers, the method further includes:

[0023] determining density values ​​of data objects in the data set;

[0024] In the data set, some data objects whose density values ​​are less than a threshold are removed.

[0025] Optionally, determining the density value of the data object in the data set includes:

[0026] The density value of the current data object is determined according to the distance between the current data object and M other data objects in the data set; wherein the M other data objects are the M data objects closest to the current data object, and M is a positive integer greater than or equal to 1.

[0027] Optionally, determining a first cluster center in the data set includes:

[0028] The data object with the smallest density value in the data set is determined as the first cluster center.

[0029] Optionally, determining the second cluster center according to the distance between the data object in the data set and the first cluster center includes:

[0030] The distance between the data objects in the data set and the first cluster center is determined, and the data object with the largest distance from the first cluster center is selected as the second cluster center.

[0031] Optionally, determining the Kth cluster center according to the distances between the data objects in the data set and all cluster centers from the first cluster center to the K-1th cluster center includes:

[0032] For a data object in the data set, determining the distances from all cluster centers from the first cluster center to the K-1th cluster center, and determining the minimum distance from the distances from all cluster centers;

[0033] The data object with the largest minimum distance is selected as the Kth cluster center.

[0034] Optionally, the re-determining the cluster centers of the multiple data clusters includes:

[0035] Among the data objects in the data cluster, the data object with the smallest sum of square distances to other data objects in the data cluster is selected as a new clustering center in the data cluster.

[0036] Optionally, determining a target driving style from the multiple driving styles according to the clustering information and the input vector includes:

[0037] A target driving style is determined from the plurality of driving styles according to a similarity between a cluster center indicated by the cluster information and the input vector.

[0038] Optionally, determining a target driving style from the multiple driving styles according to the similarity between the cluster center indicated by the cluster information and the input vector includes:

[0039] The Euclidean distance between the cluster center indicated by the cluster information and the input vector is determined, and the driving style corresponding to the cluster center with the smallest Euclidean distance is determined as the target driving style.

[0040] Optionally, controlling the braking energy recovery intensity of the vehicle according to the target feedback torque includes:

[0041] According to the target feedback torque, the actual output torque of the motor during braking is set to control the braking energy recovery intensity of the vehicle.

[0042] Optionally, generating an input vector according to a first parameter during vehicle driving includes:

[0043] The first parameter during the vehicle driving process is averaged in combination with the sampling duration to obtain a parameter average value, and an input vector is generated according to the parameter average value.

[0044] Optionally, the first parameter includes any one or more of the following: vehicle speed, vehicle deceleration, accelerator pedal opening, brake pedal opening.

[0045] A device for controlling vehicle braking energy recovery, the device being used for:

[0046] generating an input vector according to a first parameter during the vehicle driving process;

[0047] Acquire clustering information corresponding to a plurality of driving styles, and determine a target driving style from the plurality of driving styles according to the clustering information and the input vector;

[0048] According to the target driving style, a target feedback torque is determined, and the braking energy recovery intensity of the vehicle is controlled according to the target feedback torque.

[0049] A vehicle comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, wherein the computer program implements the method described above when executed by the processor.

[0050] An electronic device comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, wherein the computer program implements the method described above when executed by the processor.

[0051] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described above is implemented.

[0052] A computer program product comprises a computer program, wherein when the computer program is executed by a processor, the computer program implements the method as described above.

[0053] The embodiments of the present invention have the following advantages:

[0054] In an embodiment of the present invention, an input vector is generated according to a first parameter in a vehicle driving process, clustering information corresponding to a plurality of driving styles is obtained, and a target driving style is determined from the plurality of driving styles according to the clustering information and the input vector, and a target feedback torque is determined according to the target driving style, and the braking energy recovery intensity of the vehicle is controlled according to the target feedback torque, thereby achieving accurate identification of driving styles by clustering, and then performing braking energy recovery according to the driving styles, thereby improving the efficiency of braking energy recovery, and improving driving experience and energy utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solution of the present invention, the accompanying drawings required for use in the description of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0056] Figure 1 is a flowchart of the steps of a method for controlling vehicle braking energy recovery provided by some embodiments of the present invention;

[0057] Figure 2 is a flow chart of steps of a clustering process provided by some embodiments of the present invention;

[0058] Figure 3 It is a flowchart of the steps of another method for controlling vehicle braking energy recovery provided by some embodiments of the present invention. DETAILED DESCRIPTION

[0059] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0060] In the related art, the first reverse torque is calculated according to the accelerator pedal signal, the driver's style information is obtained based on the driver's driving habit data, and then the first reverse torque is corrected using the obtained driving style information to obtain the target reverse torque, and the target reverse torque is used to control the energy recovery intensity of the whole vehicle, thereby solving the problem that when the driver's driving style does not match the preset energy recovery intensity, the driver needs to intervene more in the vehicle's deceleration process. However, in this solution, the accuracy of the driver's driving style recognition is not high, and the rolling resistance coefficient factor is not considered, so that when the rolling resistance coefficient changes significantly, the control of the energy recovery intensity affects the driving experience and reduces the energy utilization efficiency.

[0061] In the embodiment of the present invention, the cluster center corresponding to each driving style is determined based on the improved K-Means (k-means clustering algorithm). The input vector composed of the average vehicle speed, average deceleration, average accelerator pedal opening, average accelerator pedal opening rate of change, average brake pedal opening, and average brake pedal opening rate of change within the vehicle sampling time is calculated, and a similarity comparison is performed with each cluster center to improve the accuracy of driver driving style recognition. Then, according to the recognized driving style, a reasonable braking energy recovery intensity is controlled, thereby improving energy utilization efficiency.

[0062] Moreover, based on the determination of the corresponding energy recovery intensity according to the driver's driving style, the change of the rolling resistance coefficient during vehicle driving is further considered to correct the energy recovery intensity. Compared with the common method of controlling the energy recovery intensity by only considering the driving style, when the rolling resistance coefficient of the vehicle changes, the energy recovery intensity can meet the driver's driving habits and improve energy utilization.

[0063] The present invention is further described below:

[0064] Reference Figure 1 , shows a flowchart of a method for controlling vehicle braking energy recovery provided by some embodiments of the present invention, which may specifically include the following steps:

[0065] Step 101: Generate an input vector according to a first parameter during vehicle driving.

[0066] In some embodiments of the present invention, the first parameter includes any one or more of the following: vehicle speed, vehicle deceleration, accelerator pedal opening, brake pedal opening.

[0067] The brake pedal opening represents the degree to which the driver presses the brake pedal. In some examples, when the brake pedal is not pressed by the driver, the brake pedal opening is 0, and when the brake pedal is fully pressed to the lowest end by the driver, the brake pedal opening is 1.

[0068] In some embodiments of the present invention, generating an input vector based on a first parameter during vehicle driving includes: averaging the first parameter during vehicle driving in combination with a sampling duration to obtain a parameter average value, and generating an input vector based on the parameter average value.

[0069] In practical applications, the real-time vehicle speed, vehicle deceleration, accelerator pedal opening, and brake pedal opening are obtained, and then the average values ​​of the parameters within the sampling time t are calculated, such as the average vehicle speed, average deceleration, average accelerator pedal opening, average accelerator pedal opening rate of change, brake pedal opening, and brake pedal opening rate of change. Then, the input vector can be generated according to the calculated parameter average values, as follows:

[0070] p0=[v0,a0,s a0 ,q a0 ,s d0 ,q d0 ]

[0071] In some examples, the average vehicle speed may be calculated using the following formula:

[0072]

[0073] Among them, v is the vehicle speed, and is the moment when the vehicle speed is not 0.

[0074] In some examples, the average deceleration may be calculated as follows:

[0075]

[0076] Among them, t de The moment when the vehicle slows down.

[0077] In some examples, the average accelerator pedal opening can be calculated using the following formula:

[0078]

[0079] Among them, s a is the accelerator pedal opening, t ac It is the moment when the accelerator pedal opening is not 0.

[0080] In some examples, the average accelerator pedal opening rate can be expressed as follows:

[0081]

[0082] In some examples, the average brake pedal opening can be calculated using the following formula:

[0083]

[0084] Among them, s d is the brake pedal opening, t de It is the moment when the brake pedal opening is not 0.

[0085] In some examples, the average brake pedal opening rate can be calculated using the following formula:

[0086]

[0087] Step 102 : acquiring clustering information corresponding to a plurality of driving styles, and determining a target driving style from the plurality of driving styles according to the clustering information and the input vector.

[0088] In practical applications, multiple driving styles may be set, such as driving styles including conservative, conservative, normal, aggressive, and aggressive. Clustering information corresponding to each driving style may be pre-set, such as clustering information including information of cluster centers. Then, the input vector may be combined with the clustering information of multiple driving styles to obtain a target driving style that matches the input vector.

[0089] In some embodiments of the present invention, determining the target driving style from the multiple driving styles based on the clustering information and the input vector includes: determining the target driving style from the multiple driving styles based on the similarity between the cluster center indicated by the clustering information and the input vector.

[0090] In some embodiments of the present invention, determining a target driving style from the multiple driving styles based on the similarity between the cluster center indicated by the clustering information and the input vector includes: determining the Euclidean distance between the cluster center indicated by the clustering information and the input vector, and determining the driving style corresponding to the cluster center with the smallest Euclidean distance as the target driving style.

[0091] In practical applications, the Euclidean distance between the input vector and the cluster center corresponding to each driving style can be calculated. The Euclidean distance can represent the similarity. Then, the cluster center with the smallest Euclidean distance can be selected, and the driving style corresponding to the cluster center is used as the target driving style.

[0092] In some embodiments of the present invention, before obtaining the clustering information corresponding to the multiple driving styles, the method further includes: obtaining a data set consisting of data objects corresponding to the multiple driving styles; determining a plurality of cluster centers in the data set, and dividing the data objects in the data set into a plurality of data clusters according to the plurality of cluster centers, each data cluster corresponding to a driving style; and re-determining the cluster centers of the plurality of data clusters as the cluster centers corresponding to the plurality of driving styles, thereby obtaining the clustering information corresponding to the plurality of driving styles.

[0093] In practical applications, a data set can be obtained, which may include data objects corresponding to multiple driving styles. For example, a set S consisting of 1000 data objects is inputted, which is S={x1,x2,…,x 1000}.

[0094] Each data object may include data of the same type as the parameter average of the first parameter, such as data object x i =[v i ,a i ,s ai ,q ai ,s di ,q di ], where the average vehicle speed v i , average deceleration a i , Average opening of accelerator pedal s ai , accelerator pedal average opening rate q ai , brake pedal opening s di , Brake pedal opening rate q di .

[0095] After obtaining the data set, the improved K-Means algorithm can be used to determine multiple cluster centers in the data set. Each cluster center can correspond to a driving style, and a data cluster can be set. Then, the distance between the data objects in the data set and each cluster center can be calculated, and the data objects can be divided into the data clusters with the smallest distance to obtain multiple data clusters.

[0096] In some examples, if the minimum distance value corresponds to multiple cluster centers, the density distance of the data objects in each cluster is calculated, and the cluster corresponding to the minimum density distance is selected and classified.

[0097] After obtaining multiple data clusters, the cluster center of each data cluster can be recalculated according to the data objects in the data cluster, and then the re-determined cluster center is used as the cluster center corresponding to the corresponding driving style to obtain cluster information corresponding to multiple driving styles.

[0098] In some embodiments of the present invention, the re-determining of the cluster centers of the multiple data clusters includes: among the data objects in the data cluster, selecting the data object with the smallest sum of squared distances to other data objects in the data cluster as the new cluster center in the data cluster.

[0099] When a new data object is added to a data cluster during data clustering, the cluster center may change. In this case, the data object with the smallest sum of squared distances to other data objects in the data cluster can be selected as the new cluster center, thereby minimizing the sum of squared distances from all data objects in the data cluster to the new cluster center. For example, the following formula can be used:

[0100]

[0101] Where J(C) is the sum of squared distances, C is the data cluster, and C = {c j ,i=1,2,…,K},x i is the data object, u k is the cluster center of the Kth data cluster. If x i ∈c j , then d ki =1, otherwise d ki =0.

[0102] In some embodiments of the present invention, before determining a plurality of cluster centers in the data set, the method further includes: determining density values ​​of data objects in the data set; and removing some data objects in the data set whose density values ​​are less than a threshold.

[0103] In some embodiments of the present invention, determining the density value of the data object in the data set includes: determining the density value of the current data object based on the distance between the current data object and M other data objects in the data set; wherein the M other data objects are the M data objects closest to the current data object, and M is a positive integer greater than or equal to 1.

[0104] In some examples, the M other data objects may be data objects that are centered on the current data object and are closest to the current data object. For example, M may be 10.

[0105] In practical applications, for a data object in a data set, the density value of the current data object can be determined based on the distance between the current data object and M other data objects, and then the data objects with density values ​​less than the threshold can be removed from the data set according to the set threshold.

[0106] Among them, the larger the density value, the larger the distance between sample objects near the data object, and the smaller the density value of the data object, the sparser the data object distribution. By setting a low density threshold, data objects in relatively low density areas are deleted to obtain a high density set D.

[0107] In some embodiments of the present invention, determining multiple cluster centers in the data set includes: determining a first cluster center in the data set, and determining a second cluster center based on the distance between the data object in the data set and the first cluster center; determining the Kth cluster center based on the distance between the data object in the data set and all cluster centers from the first cluster center to the K-1th cluster center. K is a positive integer greater than 2, and the maximum value of K is the number of driving style types.

[0108] In the process of determining the cluster center, the first cluster center may be determined first, and then the second cluster center may be determined based on the distance between the data objects in the data set (the data set may be a data set after removing data objects with density values ​​less than a threshold) and the first cluster center.

[0109] After determining the first cluster center and the second cluster center, the third cluster center and the subsequent K-th cluster center can be selected from the data set according to the distance between the data object and the previously determined cluster center.

[0110] In some embodiments of the present invention, determining the first cluster center in the data set includes: determining a data object with the smallest density value in the data set as the first cluster center.

[0111] For the first cluster, the data object with the smallest density value can be selected from all the data objects in the data set as the first cluster center.

[0112] In some embodiments of the present invention, determining the second cluster center based on the distance between the data object in the data set and the first cluster center includes: determining the distance between the data object in the data set and the first cluster center, and selecting the data object with the largest distance to the first cluster center as the second cluster center.

[0113] After determining the first cluster center, the distance between the data objects in the data set and the first cluster center can be calculated, and then the data object with the largest distance, that is, the data object farthest from the first cluster center, can be selected as the second cluster center. i The Euclidean distance between them can be expressed as follows:

[0114] d(x i ,z1)=||x i -z1||

[0115] In some embodiments of the present invention, determining the Kth cluster center based on the distance between the data object in the data set and all cluster centers from the first cluster center to the K-1th cluster center includes: for the data object in the data set, determining the distance from all cluster centers from the first cluster center to the K-1th cluster center, and determining the minimum distance from the distances to all cluster centers; and selecting the data object with the largest minimum distance as the Kth cluster center.

[0116] After determining the first cluster center and the second cluster center, for the third and subsequent cluster centers, the distance between each data object in the data set and the previously determined cluster center can be calculated, and the minimum distance can be determined therefrom. Each data object has a minimum distance.

[0117] After determining the minimum distance of each data object, the data object with the largest minimum distance can be selected from all data objects as the Kth cluster center.

[0118] For example, for the third cluster center z3, the following formula can be satisfied:

[0119] max(min(d(x i ,z1),d(x i ,z2))),i=1,2,…,n

[0120] Among them, z1 is the first cluster center and z2 is the second cluster center.

[0121] Similarly, the Kth cluster center must satisfy the following formula:

[0122] max(min(d(x i ,z1),d(x i ,z2),…,d(x i ,z k-1 ))),i=1,2,…,n

[0123] In some examples, when the K-Means algorithm is clustered, the division is uncertain due to the existence of special points. By introducing the density minimum, if the data object is close to the cluster center z1, z2, ..., z m-1 The minimum distance is the same, that is: min(d(x i ,z1),d(x i ,z2),…,d(x i ,z m-1 ))=min(d(x j ,z1),d(x j ,z2),…,d(x j ,z m-1 )), the next smallest distance can be used to replace the minimum distance in the clustering formula to determine the Kth cluster center.

[0124] The following combination Figure 2 The clustering process is illustrated as follows:

[0125] Step 201, calculate the density value of the data objects in the data set S according to the input constant M, and select the data object with the smallest density parameter as the first initial center Z1 (ie, the first clustering center).

[0126] Step 202, calculating the Euclidean distance between the cluster center Z1 and all data objects, selecting the data object farthest from Z1, and using it as the second cluster center Z2.

[0127] Step 203, according to the cluster center conditional formula, obtain the Kth initial cluster center in sequence.

[0128] Step 204, calculate the distance from the data object to each cluster center, and divide the data into the data cluster with the closest distance.

[0129] Step 205, recalculate the cluster center of the cluster, and then calculate the sum of squares of all sample data objects in the cluster to the cluster center, that is, the j(C) value.

[0130] Step 206, determine whether the cluster center and J(C) value have changed, if so, execute step 205, if not, end.

[0131] Step 103: determining a target feedback torque according to the target driving style, and controlling the braking energy recovery intensity of the vehicle according to the target feedback torque.

[0132] After determining the target driving style, the target feedback torque can be determined according to the target driving style. The feedback torque can be a reverse torque. Then, the braking energy recovery intensity is controlled by the target feedback torque.

[0133] In some embodiments of the present invention, controlling the braking energy recovery intensity of the vehicle according to the target feedback torque includes: setting the actual output torque of the motor during braking according to the target feedback torque to control the braking energy recovery intensity of the vehicle.

[0134] In practical applications, the target feedback torque can be used as the actual output torque of the motor during braking. By outputting the target feedback torque during braking, the braking energy recovery intensity can be controlled.

[0135] In some embodiments of the present invention, determining the target feedback torque according to the target driving style includes: determining a basic feedback torque according to the target driving style; generating a rolling resistance correction coefficient according to a second parameter during vehicle driving, and adjusting the basic feedback torque according to the rolling resistance correction coefficient to obtain the target feedback torque.

[0136] In some embodiments of the present invention, the second parameter includes any one or more of the following: vehicle mass, motor torque, vehicle speed, and vehicle acceleration.

[0137] In practical applications, the basic feedback torque can be determined according to the target driving style, and the rolling resistance correction coefficient can be generated according to the second parameter during vehicle driving. The basic feedback torque is then adjusted according to the rolling resistance correction coefficient to obtain the target feedback torque.

[0138] In some examples, the following formula may be used:

[0139] T t =λT1

[0140] Among them, T1 is the basic feedback torque, T t is the target feedback torque, and λ is the rolling resistance correction coefficient.

[0141] In some embodiments of the present invention, generating a rolling resistance correction coefficient based on a second parameter during vehicle driving includes: generating a real-time rolling resistance coefficient based on the second parameter during vehicle driving, and generating a rolling resistance correction coefficient by combining a preset rolling resistance coefficient and the real-time rolling resistance coefficient.

[0142] In practical applications, the real-time rolling resistance coefficient can be generated based on the second parameters such as vehicle mass, vehicle speed, acceleration, motor torque, etc. during vehicle driving, and then the preset rolling resistance coefficient and the real-time rolling resistance coefficient can be combined to generate a rolling resistance correction coefficient.

[0143] In some examples, the following formula may be used:

[0144]

[0145] Among them, f0 is the preset rolling resistance coefficient, f t is the real-time rolling resistance coefficient.

[0146] In a specific implementation, the real-time rolling resistance coefficient can be calculated according to the longitudinal dynamics formula of the vehicle. According to the basic formula of longitudinal dynamics of the vehicle:

[0147] F x =F f +F w +F i +F j

[0148] Among them, F x 、F f 、F w 、F i 、F j They correspond to the longitudinal force, rolling resistance, wind resistance, ramp resistance and acceleration resistance of the vehicle respectively, which can be written as:

[0149]

[0150] Among them, T tq is the motor torque, i0 is the gear ratio of the reducer, r is the tire rolling radius, m is the vehicle mass, f is the rolling resistance coefficient, ρ is the air density, C d is the air resistance coefficient, A is the frontal area of ​​the vehicle, θ is the road slope, is the actual acceleration of the vehicle.

[0151] Since the acceleration signal obtained by the vehicle is collected by the longitudinal acceleration sensor, the acceleration a collected by the longitudinal acceleration sensor satisfies:

[0152]

[0153] Based on this, the vehicle longitudinal dynamics formula is simplified to:

[0154]

[0155] Set the system output Observable data vector a k= mg, and μ(k) and μ(k-1) correspond to the estimated values ​​of the rolling resistance coefficient at the kth moment and the k-1th moment respectively. The recursive least squares model is introduced for estimation:

[0156]

[0157] P(0)=aE

[0158] M(0)=ε

[0159] Where a is a sufficiently large positive real number, E is the identity matrix, and ε is the zero vector.

[0160] Therefore, the rolling resistance coefficient f can be calculated in real time based on the vehicle mass, speed, acceleration, and motor torque. t , f t That is, it can be μ(k) mentioned above, that is, the estimated value of the rolling resistance coefficient.

[0161] In an embodiment of the present invention, an input vector is generated according to a first parameter in a vehicle driving process, clustering information corresponding to a plurality of driving styles is obtained, and a target driving style is determined from the plurality of driving styles according to the clustering information and the input vector, and a target feedback torque is determined according to the target driving style, and the braking energy recovery intensity of the vehicle is controlled according to the target feedback torque, thereby achieving accurate identification of driving styles by clustering, and then performing braking energy recovery according to the driving styles, thereby improving the efficiency of braking energy recovery, and improving driving experience and energy utilization.

[0162] The following combination Figure 3 The present invention is exemplified as follows:

[0163] Step 201: construct an input vector according to the average vehicle speed, average deceleration, average accelerator pedal opening, average accelerator pedal opening rate of change, average brake pedal opening, and average brake pedal opening rate of change within the vehicle sampling time.

[0164] Step 202: Calculate the Euclidean distance between the input vector and the cluster center corresponding to each driving style determined according to the improved K-Means algorithm.

[0165] In step 203 , the driving style corresponding to the minimum Euclidean distance is the current driver's driving style (ie, the target driving style), and then the first feedback torque (ie, the basic feedback torque) is determined according to the current driving style.

[0166] Step 204, based on the least squares estimation model of the road slope of longitudinal dynamics, the current rolling resistance coefficient is calculated in real time according to the vehicle mass, speed, motor torque, and acceleration, and the rolling resistance correction coefficient is obtained according to the preset rolling resistance coefficient.

[0167] Step 205 , a target feedback torque may be obtained by using the first feedback torque and the rolling resistance correction coefficient, and the vehicle energy recovery intensity may be controlled by using the target feedback torque.

[0168] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0169] Some embodiments of the present invention also provide a vehicle braking energy recovery control device, which is used for:

[0170] generating an input vector according to a first parameter during the vehicle driving process;

[0171] Acquire clustering information corresponding to a plurality of driving styles, and determine a target driving style from the plurality of driving styles according to the clustering information and the input vector;

[0172] According to the target driving style, a target feedback torque is determined, and the braking energy recovery intensity of the vehicle is controlled according to the target feedback torque.

[0173] In some embodiments of the present invention, determining the target feedback torque according to the target driving style includes:

[0174] determining a basic feedback torque according to the target driving style;

[0175] A rolling resistance correction coefficient is generated according to a second parameter during vehicle driving, and the basic feedback torque is adjusted according to the rolling resistance correction coefficient to obtain a target feedback torque.

[0176] In some embodiments of the present invention, generating a rolling resistance correction coefficient according to a second parameter during vehicle travel includes:

[0177] A real-time rolling resistance coefficient is generated according to the second parameter during the vehicle driving process, and a rolling resistance correction coefficient is generated by combining a preset rolling resistance coefficient and the real-time rolling resistance coefficient.

[0178] In some embodiments of the present invention, the second parameter includes any one or more of the following: vehicle mass, motor torque, vehicle speed, and vehicle acceleration.

[0179] In some embodiments of the present invention, before acquiring the clustering information corresponding to the plurality of driving styles, the method is further configured to:

[0180] Obtain a data set consisting of data objects corresponding to multiple driving styles;

[0181] In the data set, a plurality of cluster centers are determined, and data objects in the data set are divided into a plurality of data clusters according to the plurality of cluster centers, each data cluster corresponding to a driving style;

[0182] The cluster centers of the multiple data clusters are re-determined as the cluster centers corresponding to the multiple driving styles, and cluster information corresponding to the multiple driving styles is obtained.

[0183] In some embodiments of the present invention, determining a plurality of cluster centers in the data set includes:

[0184] In the data set, a first cluster center is determined, and a second cluster center is determined according to the distance between the data object in the data set and the first cluster center;

[0185] Determine the Kth cluster center according to the distances between the data objects in the data set and all cluster centers from the first cluster center to the K-1th cluster center;

[0186] Wherein, K is a positive integer greater than 2, and the maximum value of K is the number of driving style types.

[0187] In some embodiments of the present invention, before determining a plurality of cluster centers in the data set, it is further used to:

[0188] determining density values ​​of data objects in the data set;

[0189] In the data set, some data objects whose density values ​​are less than a threshold are removed.

[0190] In some embodiments of the present invention, determining the density value of the data object in the data set includes:

[0191] The density value of the current data object is determined according to the distance between the current data object and M other data objects in the data set; wherein the M other data objects are the M data objects closest to the current data object, and M is a positive integer greater than or equal to 1.

[0192] In some embodiments of the present invention, determining a first cluster center in the data set includes:

[0193] The data object with the smallest density value in the data set is determined as the first cluster center.

[0194] In some embodiments of the present invention, determining the second cluster center according to the distance between the data object in the data set and the first cluster center includes:

[0195] The distance between the data objects in the data set and the first cluster center is determined, and the data object with the largest distance from the first cluster center is selected as the second cluster center.

[0196] In some embodiments of the present invention, determining the Kth cluster center according to the distances between the data objects in the data set and all cluster centers from the first cluster center to the K-1th cluster center includes:

[0197] For a data object in the data set, determining the distances from all cluster centers from the first cluster center to the K-1th cluster center, and determining the minimum distance from the distances from all cluster centers;

[0198] The data object with the largest minimum distance is selected as the Kth cluster center.

[0199] In some embodiments of the present invention, the re-determining the cluster centers of the plurality of data clusters includes:

[0200] Among the data objects in the data cluster, the data object with the smallest sum of square distances to other data objects in the data cluster is selected as a new clustering center in the data cluster.

[0201] In some embodiments of the present invention, determining a target driving style from the multiple driving styles according to the clustering information and the input vector includes:

[0202] A target driving style is determined from the plurality of driving styles according to a similarity between a cluster center indicated by the cluster information and the input vector.

[0203] In some embodiments of the present invention, determining a target driving style from the multiple driving styles according to the similarity between the cluster center indicated by the cluster information and the input vector includes:

[0204] The Euclidean distance between the cluster center indicated by the cluster information and the input vector is determined, and the driving style corresponding to the cluster center with the smallest Euclidean distance is determined as the target driving style.

[0205] In some embodiments of the present invention, controlling the braking energy recovery intensity of the vehicle according to the target feedback torque includes:

[0206] According to the target feedback torque, the actual output torque of the motor during braking is set to control the braking energy recovery intensity of the vehicle.

[0207] In some embodiments of the present invention, generating an input vector according to a first parameter during vehicle driving includes:

[0208] The first parameter during the vehicle driving process is averaged in combination with the sampling duration to obtain a parameter average value, and an input vector is generated according to the parameter average value.

[0209] In some embodiments of the present invention, the first parameter includes any one or more of the following: vehicle speed, vehicle deceleration, accelerator pedal opening, brake pedal opening.

[0210] In an embodiment of the present invention, an input vector is generated according to a first parameter in a vehicle driving process, clustering information corresponding to a plurality of driving styles is obtained, and a target driving style is determined from the plurality of driving styles according to the clustering information and the input vector, and a target feedback torque is determined according to the target driving style, and the braking energy recovery intensity of the vehicle is controlled according to the target feedback torque, thereby achieving accurate identification of driving styles by clustering, and then performing braking energy recovery according to the driving styles, thereby improving the efficiency of braking energy recovery, and improving driving experience and energy utilization.

[0211] Some embodiments of the present invention further provide a vehicle, comprising a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the above method is implemented when the computer program is executed by the processor.

[0212] Some embodiments of the present invention further provide an electronic device, comprising a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the above method is implemented when the computer program is executed by the processor.

[0213] Some embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, and the computer program implements the above method when executed by a processor.

[0214] Some embodiments of the present invention further provide a computer program product, including a computer program, which implements the above method when executed by a processor.

[0215] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0216] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0217] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0218] Those skilled in the art will appreciate that the embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0219] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0220] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0221] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0222] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0223] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the above elements.

[0224] The above is a detailed introduction to a method and device for controlling vehicle braking energy recovery. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for controlling vehicle braking energy recovery, characterized in that: The method comprises: generating an input vector according to a first parameter during the vehicle driving process; Acquire clustering information corresponding to a plurality of driving styles, and determine a target driving style from the plurality of driving styles according to the clustering information and the input vector; According to the target driving style, a target feedback torque is determined, and the braking energy recovery intensity of the vehicle is controlled according to the target feedback torque.

2. The method according to claim 1, characterized in that The determining the target feedback torque according to the target driving style includes: determining a basic feedback torque according to the target driving style; A rolling resistance correction coefficient is generated according to a second parameter during vehicle driving, and the basic feedback torque is adjusted according to the rolling resistance correction coefficient to obtain a target feedback torque.

3. The method according to claim 2, characterized in that The step of generating a rolling resistance correction coefficient according to the second parameter during the vehicle driving process includes: A real-time rolling resistance coefficient is generated according to the second parameter during the vehicle driving process, and a rolling resistance correction coefficient is generated by combining a preset rolling resistance coefficient and the real-time rolling resistance coefficient.

4. The method according to claim 2, characterized in that: The second parameter includes any one or more of the following: vehicle mass, motor torque, vehicle speed, and vehicle acceleration.

5. The method according to any one of claims 1 to 4, characterized in that: Before acquiring clustering information corresponding to a plurality of driving styles, the method further includes: Obtain a data set consisting of data objects corresponding to multiple driving styles; In the data set, a plurality of cluster centers are determined, and data objects in the data set are divided into a plurality of data clusters according to the plurality of cluster centers, each data cluster corresponding to a driving style; The cluster centers of the multiple data clusters are re-determined as the cluster centers corresponding to the multiple driving styles, and cluster information corresponding to the multiple driving styles is obtained.

6. The method according to claim 5, characterized in that In the data set, a plurality of cluster centers are determined, including: In the data set, a first cluster center is determined, and a second cluster center is determined according to the distance between the data object in the data set and the first cluster center; Determine the Kth cluster center according to the distances between the data objects in the data set and all cluster centers from the first cluster center to the K-1th cluster center; Wherein, K is a positive integer greater than 2, and the maximum value of K is the number of driving style types.

7. The method according to claim 6, characterized in that In the data set, before determining a plurality of cluster centers, the method further includes: determining density values ​​of data objects in the data set; In the data set, some data objects whose density values ​​are less than a threshold are removed.

8. The method according to claim 7, characterized in that Determining the density value of the data object in the data set includes: The density value of the current data object is determined according to the distance between the current data object and M other data objects in the data set; wherein the M other data objects are the M data objects closest to the current data object, and M is a positive integer greater than or equal to 1.

9. The method according to claim 7 or 8, characterized in that: Determining a first cluster center in the data set includes: The data object with the smallest density value in the data set is determined as the first cluster center.

10. The method according to claim 6, characterized in that Determining the second cluster center according to the distance between the data object in the data set and the first cluster center includes: The distance between the data objects in the data set and the first cluster center is determined, and the data object with the largest distance from the first cluster center is selected as the second cluster center.

11. The method according to claim 6, characterized in that The determining the Kth cluster center according to the distances between the data objects in the data set and all cluster centers from the first cluster center to the K-1th cluster center comprises: For a data object in the data set, determining the distances from all cluster centers from the first cluster center to the K-1th cluster center, and determining the minimum distance from the distances from all cluster centers; The data object with the largest minimum distance is selected as the Kth cluster center.

12. The method according to claim 5, characterized in that The re-determining the cluster centers of the plurality of data clusters comprises: Among the data objects in the data cluster, the data object with the smallest sum of square distances to other data objects in the data cluster is selected as a new clustering center in the data cluster.

13. The method according to any one of claims 1 to 4, characterized in that: The determining a target driving style from the plurality of driving styles according to the clustering information and the input vector comprises: A target driving style is determined from the plurality of driving styles according to a similarity between a cluster center indicated by the cluster information and the input vector.

14. The method according to claim 13, characterized in that The determining a target driving style from the plurality of driving styles according to the similarity between the cluster center indicated by the cluster information and the input vector comprises: The Euclidean distance between the cluster center indicated by the cluster information and the input vector is determined, and the driving style corresponding to the cluster center with the smallest Euclidean distance is determined as the target driving style.

15. The method according to any one of claims 1 to 4, characterized in that: The step of controlling the braking energy recovery intensity of the vehicle according to the target feedback torque includes: According to the target feedback torque, the actual output torque of the motor during braking is set to control the braking energy recovery intensity of the vehicle.

16. The method according to any one of claims 1 to 4, characterized in that: The step of generating an input vector according to a first parameter during vehicle driving includes: The first parameter during the vehicle driving process is averaged in combination with the sampling duration to obtain a parameter average value, and an input vector is generated according to the parameter average value.

17. The method according to claim 1, characterized in that The first parameter includes any one or more of the following: vehicle speed, vehicle deceleration, accelerator pedal opening, and brake pedal opening.

18. A vehicle braking energy recovery control device, characterized in that: The device is used for: generating an input vector according to a first parameter during the vehicle driving process; Acquire clustering information corresponding to a plurality of driving styles, and determine a target driving style from the plurality of driving styles according to the clustering information and the input vector; According to the target driving style, a target feedback torque is determined, and the braking energy recovery intensity of the vehicle is controlled according to the target feedback torque.

19. A vehicle, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program implements the method according to any one of claims 1 to 17 when executed by the processor.

20. An electronic device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program implements the method according to any one of claims 1 to 17 when executed by the processor.

21. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 17 is implemented.

22. A computer program product, characterized in that The invention comprises a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 17.

Images