Motor torque determination method, device, equipment, medium and program product

Abstract

The invention discloses a motor torque determination method and device, equipment, a medium and a program product, and is applied to the field of vehicle control. The method comprises the following steps: acquiring first motion state data of a vehicle, wherein the first motion state data comprises a first vehicle running speed and a first steering wheel rotation angle; according to the first vehicle running speed, a first torque mapping curved surface corresponding to a first vehicle running speed interval where the first vehicle running speed is located is determined, and the first torque mapping curved surface is used for representing the mapping relation between the motion state data and the motor torque in the first vehicle running speed interval; the motion state data comprises a vehicle driving speed and a steering wheel rotation angle; and determining the motor torque mapped with the first steering wheel rotation angle and the first vehicle running speed in the first torque mapping curved surface as the motor torque of the vehicle. The method can solve the problem that vehicle steering is affected due to inaccurate motor torque.

Description

Technical Field

[0001] The present application belongs to the field of vehicle control technology, and in particular, relates to a method, device, equipment, medium and program product for determining motor torque. Background Art

[0002] When the driver turns the steering wheel, the vehicle's electronic control unit determines the steering wheel torque based on the steering wheel rotation angle and vehicle speed collected by the Electric Power Steering (EPS) system, and converts the steering wheel torque into motor torque to control the vehicle's steering. However, in the process of converting the steering wheel torque into motor torque, conversion errors are prone to occur, resulting in low accuracy of the motor torque, which affects the vehicle's steering. Summary of the invention

[0003] The embodiments of the present application provide a method, device, equipment, medium and program product for determining motor torque, which can solve the problem of inaccurate motor torque affecting vehicle steering.

[0004] In a first aspect, an embodiment of the present application provides a method for determining a motor torque, the method for determining a motor torque comprising:

[0005] Acquire first motion state data of the vehicle, the first motion state data including a first vehicle driving speed and a first steering wheel rotation angle;

[0006] According to the first vehicle driving speed, determining a first torque mapping surface corresponding to a first vehicle driving speed interval in which the first vehicle driving speed is located, the first torque mapping surface being used to characterize a mapping relationship between motion state data and motor torque within the first vehicle driving speed interval, the motion state data including the vehicle driving speed and the steering wheel rotation angle;

[0007] The motor torque mapped to the first steering wheel rotation angle and the first vehicle travel speed in the first torque mapping curve is determined as the motor torque of the vehicle.

[0008] In a second aspect, an embodiment of the present application provides a device for determining motor torque, the device comprising:

[0009] A first acquisition module, used to acquire first motion state data of the vehicle, the first motion state data including a first vehicle driving speed and a first steering wheel rotation angle;

[0010] A first determination module is used to determine, according to a first vehicle driving speed, a first torque mapping surface corresponding to a first vehicle driving speed interval in which the first vehicle driving speed is located, the first torque mapping surface being used to characterize a mapping relationship between motion state data and motor torque within the first vehicle driving speed interval, the motion state data including the vehicle driving speed and a steering wheel rotation angle;

[0011] The second determination module is used to determine the motor torque mapped to the first steering wheel rotation angle and the first vehicle driving speed in the first torque mapping surface as the motor torque of the vehicle.

[0012] In a third aspect, an embodiment of the present application provides a computer device, comprising: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, it implements the method for determining the motor torque as described in any one of the first aspects.

[0013] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having computer program instructions stored thereon. When the computer program instructions are executed by a processor, the method for determining the motor torque as described in any one of the first aspects is implemented.

[0014] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes a computer program or instructions, and when the computer program or instructions are executed by a processor, a method for determining the motor torque as described in any one of the first aspects is implemented.

[0015] The method, device, equipment, medium and program product for determining the motor torque of the embodiment of the present application can determine the first vehicle speed interval in which the first vehicle speed in the first motion state data is located through the first motion state data of the vehicle, and the first torque mapping surface determined according to the first vehicle speed interval can accurately reflect the mapping relationship between the motion state data, i.e., the vehicle speed and the steering wheel rotation angle, and the motor torque in the first vehicle speed interval. The motor torque determined by this first torque mapping surface takes into account the driving characteristics of the vehicle in the first vehicle speed interval, and can directly determine the motor torque of the vehicle based on the first vehicle speed and the first steering wheel rotation angle of the vehicle, thus reducing the conversion error generated in the process of first determining the steering wheel torque and then converting the steering wheel torque into the motor torque, effectively improving the accuracy of the motor torque, and thus enhancing the steering accuracy of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0017] Figure 1 A schematic flow chart of a method for determining motor torque provided in some embodiments of the present application is shown;

[0018] Figure 2 A flowchart showing a specific implementation of step 120 provided in some embodiments of the present application is shown;

[0019] Figure 3 A flowchart showing a specific implementation of step 130 provided in some embodiments of the present application is shown;

[0020] Figure 4 A schematic diagram of a process of determining a torque mapping surface of a method for determining motor torque provided in some embodiments of the present application is shown;

[0021] Figure 5 A schematic flow chart showing a method for updating M vehicle driving speed intervals in a method for determining motor torque provided in some embodiments of the present application;

[0022] Figure 6 A schematic diagram showing a flow chart of determining a division coefficient of a method for determining motor torque provided in some embodiments of the present application;

[0023] Figure 7 A schematic diagram showing a flow chart of constructing a data set in a method for determining motor torque provided in some embodiments of the present application;

[0024] Figure 8 A flowchart showing a specific implementation of step 230 provided in some embodiments of the present application is shown;

[0025] Fig. 9 A schematic diagram showing the structure of a device for determining motor torque provided in some embodiments of the present application is shown;

[0026] Fig.10 A schematic diagram of the structure of a computer device provided in some embodiments of the present application is shown. DETAILED DESCRIPTION

[0027] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0028] 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 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 device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0029] It should be noted that the acquisition, storage, use and processing of data in the embodiments of the present application are in compliance with the relevant provisions of national laws and regulations.

[0030] It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned, and they should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0031] In order to solve the problems in the above-mentioned related technologies, the embodiments of the present application provide a method, device, equipment, medium and program product for determining the torque of a motor. Figure 1 To Attachment Figure 8 , the method for determining the motor torque provided in the embodiment of the present application is described in detail through specific embodiments and application scenarios.

[0032] Figure 1 FIG. 1 is a flow chart of a method for determining the motor torque provided in some embodiments of the present application. Figure 1 As shown, the method for determining the motor torque may include steps 110 to 130 .

[0033] Step 110, obtaining first motion state data of the vehicle, the first motion state data including a first vehicle driving speed and a first steering wheel rotation angle.

[0034] Step 120, determining a first torque mapping surface corresponding to a first vehicle speed interval in which the first vehicle speed is located according to the first vehicle speed, the first torque mapping surface being used to characterize a mapping relationship between motion state data and motor torque within the first vehicle speed interval, the motion state data including the vehicle speed and the steering wheel rotation angle.

[0035] Step 130 : Determine the motor torque mapped to the first steering wheel rotation angle and the first vehicle driving speed in the first torque mapping surface as the motor torque of the vehicle.

[0036] Thus, the first vehicle speed interval in which the first vehicle speed in the first motion state data is located is determined through the first motion state data of the vehicle, and the first torque mapping surface determined based on the first vehicle speed interval can accurately reflect the mapping relationship between the motion state data, i.e., the vehicle speed and the steering wheel rotation angle, and the motor torque within the first vehicle speed interval. The motor torque determined by this first torque mapping surface takes into account the driving characteristics of the vehicle within the first vehicle speed interval, and can directly determine the motor torque of the vehicle based on the first vehicle speed and the first steering wheel rotation angle of the vehicle, thus reducing the conversion error generated in the process of first determining the steering wheel torque and then converting the steering wheel torque into the motor torque, effectively improving the accuracy of the motor torque, and thus enhancing the steering accuracy of the vehicle.

[0037] The above steps are described in detail below, as shown below.

[0038] First, with respect to S110, the motion state data involved in the embodiments of the present application refers to data that can reflect various dynamic conditions of the vehicle during driving, and specifically, may include a first vehicle driving speed and a first steering wheel rotation angle of the vehicle. The first vehicle driving speed is the instantaneous speed of the vehicle during driving or the average speed within a preset time period. The first steering wheel rotation angle refers to the angle value of the steering wheel deviating from the initial center position.

[0039] For example, a first vehicle driving speed of the vehicle may be acquired by a speed sensor on a wheel or a transmission output shaft of the vehicle, and a first steering wheel rotation angle of the vehicle may be acquired by an angle sensor installed on a steering column of a steering wheel of the vehicle.

[0040] Secondly, in step 120, the first vehicle speed interval is a division of the vehicle speed range. The first torque mapping surface is a three-dimensional mathematical model representation, and the first torque mapping surface presents the relationship between the three variables of steering wheel rotation angle, vehicle speed and motor torque in the form of a surface. On this surface, each point represents the corresponding motor torque value under the combination of steering wheel rotation angle and vehicle speed.

[0041] For example, the entire speed range is divided into multiple intervals according to different driving characteristics and working conditions of the vehicle. Specifically, the vehicle speed can be divided into a low speed interval such as 0-30 km / h, a medium speed interval such as 30-60 km / h, a high speed interval such as 60 km / h and above, and the first vehicle driving speed interval here can be one of the multiple intervals.

[0042] In some embodiments of the present application, Figure 2 As shown, the above step 120 may specifically include step 1201 to step 1202.

[0043] Step 1201: Determine a first vehicle driving speed interval in which a first vehicle driving speed is located from a plurality of vehicle driving speed intervals of a preset vehicle driving speed interval.

[0044] Exemplarily, the vehicle electronic control unit stores a data file representing information of a preset vehicle speed interval, and the data file can be stored in a table form, where each row represents a vehicle speed interval, including the lower limit value and the upper limit value of the vehicle speed interval. After obtaining the first vehicle speed, the first vehicle speed can be compared with the lower limit value and the upper limit value of the interval starting from the first vehicle speed interval stored in the data file. If the first vehicle speed is greater than or equal to the lower limit value and less than the upper limit value, then the vehicle speed interval is determined to be the first vehicle speed interval. For example, there are three preset vehicle speed intervals: [0, 30] km / h, (30, 60] km / h, (60, 120] km / h. When the first vehicle speed is 40 km / h, it can be seen by comparison that it is in the interval of (30, 60] km / h, that is, the first vehicle speed interval.

[0045] Step 1202: According to the association information between the preset vehicle speed interval and the preset torque mapping surface, a torque mapping surface associated with the first vehicle speed interval is determined as a first torque mapping surface.

[0046] Among them, the preset torque mapping surface includes multiple pre-established mathematical surfaces, each of which corresponds to a specific vehicle speed range. These surfaces describe the change pattern of the motor torque under different vehicle speed ranges, steering wheel rotation angles and vehicle speed combinations. The associated information clarifies the one-to-one correspondence between the preset vehicle speed range and the preset torque mapping surface. For example, [0, 30] km / h corresponds to a torque mapping surface A, (30, 60] km / h corresponds to a torque mapping surface B, and (60, 120] km / h corresponds to a torque mapping surface C, so that the corresponding torque mapping surface can be quickly found according to the speed range.

[0047] Therefore, the method of determining the first torque mapping surface according to the associated information can quickly and accurately obtain the torque mapping surface suitable for the current vehicle speed range, thereby improving the efficiency and accuracy of the entire motor torque determination process.

[0048] Then, step 130 is involved. The first torque mapping surface is a three-dimensional model. The three dimensions represent the steering wheel rotation angle, the vehicle speed and the motor torque respectively. First, the position of the first vehicle speed on the vehicle speed axis of the first torque mapping surface is clarified. Next, the first steering wheel rotation angle is located on the steering wheel rotation angle axis of the first torque mapping surface. After the positions of the first vehicle speed and the first steering wheel rotation angle are determined respectively in the first torque mapping surface, there will be an intersection on the first torque mapping surface. The value of the third dimension corresponding to this intersection is the motor torque to be determined.

[0049] In some embodiments of the present application, the preset vehicle driving speed interval may include: [0, 30] km / h, [30, 60] km / h and [60, 120] km / h. Based on this, when the first vehicle driving speed is the critical value of two preset vehicle driving speed intervals, the above-mentioned first vehicle driving speed interval includes a first vehicle driving speed sub-interval and a second vehicle driving speed sub-interval, and the first vehicle driving speed sub-interval and the second vehicle driving speed sub-interval are two adjacent vehicle driving speed intervals in multiple vehicle driving speed intervals of the preset vehicle driving speed interval. Correspondingly, the multiple first torque mapping surfaces include a first torque mapping sub-surface corresponding to the first vehicle driving speed sub-interval and a second torque mapping sub-surface corresponding to the second vehicle driving speed sub-interval, and the first torque mapping sub-surface and the second torque mapping sub-surface are two torque mapping surfaces in the above-mentioned preset torque mapping surfaces; the motor torque mapped to the first steering wheel rotation angle and the first vehicle driving speed includes a first motor torque and a second motor torque. Based on this, if Figure 3 As shown, the above step 130 may specifically include steps 1301 to 1303.

[0050] Step 1301: determine the motor torque mapped to the first steering wheel rotation angle and the first vehicle driving speed in the first torque mapping sub-surface as the first motor torque.

[0051] Step 1302: Determine the motor torque mapped to the first steering wheel rotation angle and the first vehicle driving speed in the second torque mapping sub-surface as the second motor torque.

[0052] Step 1303 , performing weighted sum processing on the first motor torque and the second motor torque according to the first weight of the first motor torque and the second weight of the second motor torque to obtain the motor torque of the vehicle.

[0053] The first weight and the second weight are importance coefficients of the first motor torque and the second motor torque in the weighted sum calculation.

[0054] Exemplarily, the first weight and the second weight are determined according to factors such as the driving characteristics of the vehicle in the first vehicle speed sub-interval and the second vehicle speed sub-interval, the proportion of contribution to the overall motor torque, etc. The weight values ​​of the first weight and the second weight are between 0 and 1, and the sum of the two is 1.

[0055] The motor torque of the vehicle can be calculated by the following formula (1):

[0056] T(v,θ)=α(v)T i (v,θ)+(1-α(v))T i+1 (v, θ) (1)

[0057] In formula (1), α(v) is the first weight corresponding to the torque of the first motor, T i (v, θ) is the first motor torque, (1-α(v)) is the second weight corresponding to the second motor torque, T i+1 (v, θ) is the second motor torque.

[0058] Therefore, the vehicle's motor torque is determined by weighted summation, which comprehensively considers the characteristics of the two sub-intervals within the first vehicle speed sub-interval and the second vehicle speed sub-interval, and can more smoothly transition the motor torque requirements of different sub-intervals, avoiding the control abruptness caused by simply selecting the motor torque corresponding to a certain sub-interval.

[0059] In some embodiments of the present application, the preset vehicle speed interval includes M vehicle speed intervals, and the preset torque mapping surface includes M torque mapping surfaces, wherein the M vehicle speed intervals and the M torque mapping surfaces are in a one-to-one correspondence. Figure 4As shown, the above method for determining the motor torque may further include steps 210 to 240 .

[0060] Step 210, obtaining a data set of a sample vehicle, the data set including motion state sample data and sample motor torque corresponding to the motion state sample data, the motion state sample data including sample vehicle driving speed and sample steering wheel rotation angle corresponding to the sample vehicle driving speed.

[0061] Among them, the data set of sample vehicles is a set of data for model training, including motion state sample data and sample motor torque of sample vehicles in various driving states. The motion state sample data is used to reflect the dynamic situation of the sample vehicle during driving, including the driving speed of the sample vehicle and the sample steering wheel rotation angle. The motion state sample data can reflect the actual motion state of the vehicle in different driving scenarios. The sample motor torque is the motor torque value actually measured when the sample vehicle is in a specific motion state, corresponding to the motion state sample data.

[0062] Step 220, divide the data set according to M vehicle driving speed intervals to obtain a sub-data set corresponding to the m-th vehicle driving speed interval among the M vehicle driving speed intervals, m∈[1,2,3,...,M], the sub-data set includes first motion state sample data and a first sample motor torque corresponding to the first motion state sample data, the first motion state sample data includes a first sample vehicle driving speed and a first sample steering wheel rotation angle corresponding to the first sample vehicle driving speed, and the first sample vehicle driving speed is within the m-th vehicle driving speed interval.

[0063] Among them, the M vehicle speed intervals are M different speed ranges divided from the preset vehicle speed interval. The sub-dataset is a subset obtained by dividing the data set according to the vehicle speed interval. Each sub-dataset corresponds to a specific vehicle speed interval, and includes motion state sample data and corresponding sample motor torque within the vehicle speed interval, which is used to specifically train the initial torque determination model corresponding to the vehicle speed interval.

[0064] Exemplarily, the data set of sample vehicles is traversed. For each motion state sample data in the data set, the sample vehicle driving speed is obtained. The speed is compared with the boundary values ​​of M vehicle driving speed intervals to determine which vehicle driving speed interval the motion state sample data and the corresponding sample motor torque belong to.

[0065] Step 230, training the initial torque determination model corresponding to the mth vehicle speed interval through the sub-data set corresponding to the mth vehicle speed interval until the initial torque determination model meets the preset training stop condition, and obtaining the reference torque determination model corresponding to the mth vehicle speed interval.

[0066] Among them, the preset training stop conditions may include that the loss function value is less than a certain threshold, the number of training rounds reaches a set value, etc.

[0067] Exemplarily, the initial torque determination model may adopt a multi-layer perceptron (MLP) model based on a deep structure. Next, the neural network model architecture corresponding to the initial torque determination model will be specifically described.

[0068] The neural network model architecture corresponding to the initial torque determination model includes an input layer, a hidden layer and an output layer. The input layer includes two nodes, and the two nodes receive the sample vehicle speed and the sample steering wheel rotation angle corresponding to the sample vehicle speed as inputs, respectively, expressed as x=[v,θ], and in the initial torque determination model training, the sample vehicle speed of the sample vehicle and the sample steering wheel rotation angle corresponding to the sample vehicle speed are input into the neural network each time.

[0069] The hidden layer includes several fully connected layers. The number of hidden layers and the number of neurons in each layer are determined according to the complexity of the problem, that is, predicting the motor torque based on the vehicle speed and the steering wheel rotation angle. In addition, in order to enhance the nonlinear expression ability of the model, a nonlinear activation function is applied to each neuron in the hidden layer. Specifically, a rectified linear unit (ReLU) activation function can be used. The activation function can be defined as ReLU(z) = max(0, z). Among them, the output h of the lth hidden layer is l It can be expressed by the following formula (2):

[0070] h l =ReLU(W l h l-1 +b l ) (2)

[0071] In formula (2), W l is the weight matrix of the lth layer, b l is the bias vector of the lth layer, h l-1 is the output of the previous layer. For the first hidden layer, h0=x.

[0072] The output layer includes a node whose output is the predicted motor torque T, which can be expressed by the following formula (3):

[0073] T=WL h L +b L (3)

[0074] In formula (3), W L is the weight of the last layer, i.e., the Lth layer, b L is the bias of the last layer, i.e. the Lth layer.

[0075] Step 240 , determining a torque mapping surface corresponding to the m th vehicle speed interval according to a reference torque determination model corresponding to the m th vehicle speed interval, wherein the torque mapping surface includes a torque mapping surface associated with the first vehicle speed interval.

[0076] Exemplarily, by using the reference torque determination model corresponding to the m-th vehicle speed interval, the sub-data set corresponding to the m-th vehicle speed interval is processed to generate a torque mapping surface corresponding to the m-th vehicle speed interval. Specifically, it can include using the reference torque determination model corresponding to the m-th vehicle speed interval, selecting a plurality of different combinations of sample vehicle speeds and sample steering wheel rotation angles in the m-th vehicle speed interval as inputs, and inputting them into the reference torque determination model corresponding to the m-th vehicle speed interval to obtain the corresponding motor torque output value. Through these input and output data points, the torque mapping surface corresponding to the m-th vehicle speed interval is constructed. Specifically, mathematical fitting methods, such as polynomial fitting, interpolation, etc., can be used to fit these discrete data points into a continuous surface. This surface is the torque mapping surface corresponding to the m-th vehicle speed interval, which contains the change information of the motor torque at different speeds and steering wheel rotation angles in the interval.

[0077] Thus, the torque mapping surface is determined according to the reference torque determination model, so that in practical applications, the motor torque can be quickly and accurately determined according to the vehicle speed and steering wheel rotation angle of the vehicle. This torque mapping surface constructed based on the model can fully consider the dynamic characteristics of the vehicle in a specific speed range and effectively improve the efficiency and accuracy of the motor torque determination.

[0078] In some embodiments of the present application, before the above step 240, as Figure 5 As shown, the above method for determining the motor torque may further include steps 310 to 340 .

[0079] Step 310 , a reference torque determination model corresponding to the m-th vehicle speed interval is used to process a first sample vehicle speed and a first sample steering wheel rotation angle to obtain a first reference motor torque.

[0080] Step 320 : determining a deviation value according to the first reference motor torque and the first sample motor torque, where the deviation value is used to represent the degree of deviation of the first reference motor torque relative to the first sample motor torque.

[0081] Among them, the deviation value is a quantitative indicator used to measure the difference or deviation between the first reference motor torque, i.e., the motor torque calculated by the reference torque determination model, and the first sample motor torque, i.e., the actual motor torque actually measured. The size of the deviation value can reflect the accuracy and reliability of the prediction of the reference torque determination model.

[0082] Step 330 : When the deviation value is greater than the first preset threshold, the mth vehicle driving speed interval is divided according to the deviation value to obtain L vehicle driving speed sub-intervals.

[0083] The first preset threshold is a pre-set critical value for comparison with the deviation value. When the deviation value is greater than the first preset threshold, further division of the mth vehicle speed interval is triggered. The vehicle speed sub-interval is a finer speed interval further divided on the basis of the original vehicle speed interval. In some embodiments of the present application, L can be a preset value, such as 2 or 3.

[0084] Step 340, update the L vehicle speed sub-intervals to M vehicle speed intervals, and update the lth vehicle speed sub-interval in the L vehicle speed sub-intervals to the mth vehicle speed interval in the M vehicle speed intervals, l∈[1,2,3,…,L].

[0085] Exemplarily, after the vehicle speed interval is divided, the divided vehicle speed sub-interval is updated to the vehicle speed interval in step 220, and the above steps 220 to 240 are returned to be executed to train the torque determination model corresponding to the divided vehicle speed interval.

[0086] Therefore, when the prediction accuracy of the reference torque determination model is low, the vehicle speed interval is divided more finely, the speed range of each vehicle speed interval is narrowed, and the reference torque determination model trained based on the divided vehicle speed interval can be used to learn the vehicle motion state sample data within a smaller vehicle speed interval to improve the accuracy of the reference torque determination model in predicting the motor torque within this speed range.

[0087] In some embodiments of the present application, the mth vehicle speed interval includes a second vehicle speed and a third vehicle speed, the second vehicle speed is the maximum vehicle speed of the mth vehicle speed interval, and the third vehicle speed is the minimum vehicle speed of the mth vehicle speed interval. Based on this, the above step 330 may specifically include, when the deviation value is greater than the first preset threshold, dividing the mth vehicle speed interval according to the second vehicle speed, the third vehicle speed and the division coefficient to obtain L vehicle speed sub-intervals, the division coefficient is L, and L is a positive integer greater than 1.

[0088] The value of the division coefficient indicates how many vehicle speed sub-intervals the mth vehicle speed interval is divided into, and the value is L, which reflects the degree of subdivision of the vehicle speed interval.

[0089] For example, if the interval of the mth vehicle speed interval is [v min , v max ], the vehicle speed interval is divided into L vehicle speed sub-intervals. Specifically, the sub-interval range of each vehicle speed sub-interval can be calculated by the following formula (4):

[0090]

[0091] In the formula, i=1, 2,…,L.

[0092] In specific applications, starting from the third vehicle speed, the range of each vehicle speed sub-interval is determined in turn by the above formula (4). For example, the range of the first vehicle speed sub-interval is [the third vehicle speed, the third vehicle speed + the sub-interval range], the range of the second sub-interval is [the third vehicle speed + the sub-interval range, the third vehicle speed + 2× the sub-interval range], and so on, until L vehicle speed sub-intervals are divided.

[0093] Therefore, within the smaller vehicle speed sub-intervals obtained by more finely dividing the vehicle speed interval by the division coefficient, within each smaller vehicle speed sub-interval, the reference torque determination model corresponding to the vehicle speed sub-interval can more accurately learn the relationship between the vehicle speed, the steering wheel rotation angle and the motor torque, so as to improve the accuracy of the motor torque prediction.

[0094] In some embodiments of the present application, Figure 6 As shown, the above method for determining the motor torque may further include steps 410 to 420 .

[0095] Step 410: Determine a target deviation value interval in which the deviation value is located from a plurality of deviation value intervals in a preset deviation value interval.

[0096] The multiple deviation value intervals are a set of preset deviation value ranges, and the division of the preset deviation value intervals is to adopt different division strategies according to different deviation degrees. The target deviation value interval is determined from the multiple deviation value intervals and is a deviation value interval that matches the currently calculated deviation value.

[0097] Step 420: According to the association information between the preset deviation value interval and the preset division coefficient, the division coefficient associated with the target deviation value interval is determined as the division coefficient.

[0098] The preset division coefficient includes a plurality of division coefficients, which are preset values ​​used to determine how many vehicle speed sub-intervals the vehicle speed interval is divided into. It is understandable that different division coefficients correspond to different division fineness, and the division coefficient is associated with the preset deviation value interval and is used to adjust the division degree of the vehicle speed interval.

[0099] For example, in an associated information table, a smaller deviation value interval indicates that the reference torque determination model prediction is more accurate and there is no need to over-subdivide the vehicle speed range, and therefore, it corresponds to a smaller division coefficient, while a larger deviation value interval indicates that the reference torque determination model prediction is less accurate and there is a need to perform fine speed range division on the vehicle speed range, and therefore, it corresponds to a larger division coefficient.

[0100] Thus, the division coefficient is determined according to the association information of the preset deviation value interval and the preset division coefficient, and the adaptive adjustment of the fineness of the vehicle speed interval division can be achieved. In this way, the division of the vehicle speed interval can be reasonably changed according to the accuracy of the prediction of the reference torque determination model, so that the reference torque determination model can better adapt to the characteristics of the vehicle in different vehicle speed intervals.

[0101] In some embodiments of the present application, the dynamic characteristics of the vehicle under different driving conditions vary greatly, such as air resistance, tire friction, steering resistance, etc. These factors will affect the demand for motor torque. Based on this, before the above step 210, if Figure 7 As shown, the above method for determining the motor torque may further include steps 510 to 520 .

[0102] Step 510, obtaining an initial data set of the sample vehicle, the initial data set including initial motion state sample data of the sample vehicle in each of a plurality of driving conditions and an initial sample motor torque corresponding to the initial motion state sample data, the initial motion state sample data including an initial sample vehicle driving speed and an initial sample steering wheel rotation angle corresponding to the initial sample vehicle driving speed.

[0103] Among them, driving conditions refer to the combination of different working states and environmental conditions in which the vehicle is in the process of driving. For example, multiple driving conditions may include low-speed large turns, medium-speed turns, high-speed straight turns, etc. Under multiple driving conditions, the speed, steering wheel angle and motor torque of the sample vehicle are collected to obtain initial motion state sample data and the initial sample motor torque corresponding to the initial motion state sample data.

[0104] Step 520, performing data preprocessing operations on the initial data set to obtain a data set, wherein the data preprocessing operations include at least one of the following: deleting abnormal sample motor torques in the initial sample motor torques and initial motion state sample data corresponding to the abnormal sample motor torques, and normalizing processing.

[0105] Among them, data preprocessing operations are a series of processing steps performed on the original data before the initial data set is used for model training, in order to improve the data quality of the data set. During the data acquisition process, due to sensor failure, signal interference and other reasons, some data that obviously deviate from the normal range, namely abnormal sample motor torque, may appear. The corresponding initial motion state sample data also needs to be deleted to ensure data consistency and accuracy.

[0106] And, normalization processing refers to the operation of scaling the initial sample vehicle speed, the initial sample steering wheel rotation angle, and the initial sample motor torque according to a certain ratio so that they fall into a specific interval such as [0, 1] or [-1, 1]. In this way, by normalizing the data such as the initial sample vehicle speed, the initial sample steering wheel rotation angle, and the initial sample motor torque, data of different magnitudes can be on the same scale, which helps to improve the efficiency and stability of torque determination model training.

[0107] Exemplarily, the abnormal sample motor torque in the initial sample motor torque and the initial motion state sample data corresponding to the abnormal sample motor torque can be deleted by using a standard score (Z-score) algorithm, wherein the Z-score algorithm is used to detect whether the initial sample motor torque in the initial data set is an abnormal value. Its basic assumption is that each initial sample motor torque in the initial data set D is collected independently and conforms to a normal distribution. The specific steps are as follows:

[0108] First, the mean μ and standard deviation of the initial sample motor torque in the initial data set D are calculated by the following formulas (5) and (6), respectively.

[0109]

[0110] Where n is the total number of initial sample motor torques, x i is the i-th initial sample motor torque in the data set D.

[0111] Then, the standard score z of each initial sample motor torque is calculated by the following formula (7): i :

[0112]

[0113] Finally, according to the standard fraction z of the initial sample motor torque i Determine whether the initial sample motor torque is an abnormal value. For example, set a threshold γ to a value greater than or equal to 3. If the initial sample motor torque |z i If the initial sample motor torque exceeds the threshold value γ, the initial sample motor torque is considered to be an abnormal sample motor torque, and the abnormal sample motor torque and the initial motion state sample data corresponding to the abnormal sample motor torque are deleted.

[0114] The standard fraction z of each initial sample motor torque is calculated by the above steps. i , and then identify and remove the abnormal sample motor torque and the initial motion state sample data corresponding to the abnormal sample motor torque according to the set threshold. In this way, the noise and outliers in the initial data set can be removed to ensure the data quality, thereby improving the accuracy of subsequent torque determination model training.

[0115] Since the physical quantities in the initial data set include the initial sample vehicle speed, the initial sample steering wheel rotation angle, and the initial sample motor torque, and the units and magnitudes of these physical quantities are different, such as the initial sample vehicle speed may be in km / h, the initial sample steering wheel rotation angle is in degrees, and the initial sample motor torque is in N·m, therefore, before using the initial data set to train the torque determination model, the data of the initial data set needs to be normalized to eliminate the dimensional differences between different physical quantities, which can be as follows:

[0116] For the initial sample vehicle speed, the initial sample steering wheel rotation angle and the initial sample motor torque, the minimum and maximum values ​​of the three in the data set are determined, and then the minimum-maximum normalization formula is applied to map the initial sample vehicle speed, the initial sample steering wheel rotation angle and the initial sample motor torque, wherein the normalization formulas involved are formula (8) to formula (10):

[0117]

[0118]

[0119] In the formula, v represents the initial sample vehicle speed for normalization processing, v min Indicates the minimum value of the initial sample vehicle speed, v max represents the maximum value of the initial sample vehicle speed, v' represents the normalized initial sample vehicle speed; θ represents the normalized initial sample steering wheel angle, θ min Represents the minimum value of the initial sample steering wheel rotation angle, θ max represents the maximum value of the initial sample steering wheel rotation angle, θ' represents the normalized initial sample steering wheel rotation angle, T represents the normalized initial sample motor torque, T min represents the minimum value of the initial sample motor torque, T max represents the maximum value of the initial sample motor torque, and T' represents the normalized initial sample motor torque.

[0120] Through the above steps, the data of different physical quantities can be normalized to facilitate the training of the neural network and make the training process more accurate and efficient.

[0121] In some embodiments of the present application, Figure 8 As shown, the above step 230 may specifically include steps 2301 to 2306.

[0122] Step 2301: Process a first sample vehicle driving speed and a first sample steering wheel rotation angle through an initial torque determination model corresponding to the mth vehicle driving speed interval to obtain a second reference motor torque.

[0123] Referring to the neural network architecture example of the initial torque determination model mentioned above, the initial torque determination model performs neuron activation calculations, weight multiplication and other operations on the input data, i.e., the first sample vehicle speed and the first sample steering wheel rotation angle, in each layer of the neural network according to its internal algorithm structure and current parameter settings. After multiple layers of processing, the second reference motor torque is finally obtained in the output layer.

[0124] Step 2302: determine a loss function value based on the second reference motor torque and the first sample motor torque, where the loss function value is used to characterize the degree of difference between the second reference motor torque and the first sample motor torque.

[0125] Among them, the loss function value is a value used to quantify the degree of difference between the second reference motor torque and the first sample motor torque. The smaller the loss function value, the closer the second reference motor torque predicted by the model is to the actual first sample motor torque, which means that the accuracy of the model is higher.

[0126] In order to minimize the difference between the second reference motor torque and the first sample motor torque, a standardized mean square error can be used as a loss function. Exemplarily, the loss function value can be calculated by the following formula (11):

[0127]

[0128] In formula (11), N is the total number of sample data of the first motion state in the sub-dataset, T i is the first sample motor torque, Determine the reference motor torque output by the model for the initial torque.

[0129] Step 2303, determine whether the loss function value is greater than or equal to a second preset threshold value. If the judgment result is yes, execute step 2304; if the judgment result is no, execute step 2305.

[0130] Step 2304 , adjusting the model parameters of the initial torque determination model according to the loss function value to obtain the adjusted initial torque determination model, and then executing step 2306 .

[0131] The second preset threshold is a pre-set critical value for comparison with the calculated loss function value. The value of the second preset threshold is determined comprehensively based on the requirements for model accuracy and the actual application scenario of the vehicle.

[0132] Exemplarily, when the loss function value is greater than or equal to the second preset threshold, it means that the prediction accuracy of the initial torque determination model has not reached the expected standard, and the initial torque determination model needs to be further adjusted and optimized; when the loss function value is less than the second preset threshold, it means that the prediction result of the initial torque determination model has met certain accuracy requirements, and it can be considered that the training of the initial torque determination model is basically completed.

[0133] Wherein, adjusting the model parameters of the initial torque determination model may include at least one of the following:

[0134] Increase the number of hidden layer nodes to improve the initial torque determination model's ability to fit complex nonlinear relationships;

[0135] Changing the activation function, such as replacing the ReLU activation function with the Leaky ReLU activation function or the Sigmoid function, can improve the fitting effect of the initial torque determination model within a small data range;

[0136] The network learning rate of the initial torque determination model is adjusted to better adapt to different vehicle speed conditions.

[0137] Step 2305, obtaining a target torque determination model.

[0138] Exemplarily, when the loss function value is greater than or equal to the second preset threshold, the back propagation method can be used to calculate the gradient of each parameter in the network of the initial torque determination model, and Adam (Adaptive Moment Estimation) or Stochastic Gradient Descent (SGD) can be used to update the network parameters of the initial torque determination model, such as weights and biases, until the loss function value of the initial torque determination model converges, the network parameters are saved, and the training process of the initial torque determination model is terminated. The weights and biases can be updated by the following formulas (12) and (13):

[0139]

[0140] In formula (12), represents the weight parameter of the lth layer when the number of iterations is t+1, represents the weight parameter of the lth layer when the number of iterations is t, η is the learning rate, which is used to control the step size of the network parameter update, Represents the loss function The partial derivative of the weight parameters of the lth layer when the number of iterations is t represents the rate of change of the loss function relative to the weight parameters, which is used to guide how the weight parameters are updated to reduce the value of the loss function.

[0141] In formula (13), represents the bias parameter of the lth layer when the number of iterations is t+1, represents the bias parameter of the lth layer when the number of iterations is t, η is the learning rate, is the loss function The partial derivative of the bias parameter of the lth layer at the iteration number t represents the rate of change of the loss function relative to the bias parameter, which is used to guide how to update the bias parameter to reduce the value of the loss function.

[0142] Step 2306, the adjusted initial torque determination model is trained by the sub-data set corresponding to the m-th vehicle speed interval, until the loss function value determined by the second reference motor torque and the first sample motor torque is less than the second preset threshold, so as to obtain the reference torque determination model corresponding to the m-th vehicle speed interval.

[0143] Thus, by calculating the loss function value, the difference between the model prediction value and the actual sample value can be accurately quantified, and when the loss function value is greater than or equal to the second preset threshold, the model parameters of the initial torque determination model are adjusted to reduce the prediction error of the initial torque determination model. When the loss function value is less than the second preset threshold, it means that the reference torque determination model has reached a certain accuracy requirement, and in practical applications, the motor torque can be determined more accurately based on the vehicle's motion state data, which improves the accuracy of constructing the torque determination surface based on the reference torque determination model, thereby improving the accuracy of the motor torque determination.

[0144] In some embodiments of the present application, before the reference torque determination model corresponding to the m-th vehicle speed interval is determined, the sub-data set corresponding to the m-th vehicle speed interval is divided into two parts, one part is used for training the initial torque determination model, and the other part is used for verifying the reference torque determination model. When verifying the reference torque determination model, the mean square error can be calculated by the above formula (11) as an evaluation index. The smaller the mean square error, the better the fitting effect of the reference torque determination model. Further, when verifying that the fitting effect of the reference torque determination model reaches the preset standard, the reference torque determination model is used to perform actual road tests, and the vehicle speed, steering wheel rotation angle and motor torque are collected and compared with the output results of the reference torque determination model to further verify the validity of the reference torque determination model.

[0145] The above verification steps and test steps show that the reference torque determination model has an overfitting phenomenon, that is, the training set in the sub-dataset performs well, that is, the error is small, but the verification set in the sub-dataset and the actual road test perform poorly, that is, the error is large. Regularization terms such as L2 regularization can be introduced to limit the complexity of the reference torque determination model, and the training set in the sub-dataset can be used to retrain the reference torque determination model after the regularization is introduced to prevent overfitting training of the model.

[0146] Among them, the regularization loss function can be expressed by the following formula (14):

[0147]

[0148] In formula (14), λ is the regularization parameter, w j is the weight of the neural network.

[0149] Based on the method for determining the motor torque provided in the above embodiment, the present application also provides a specific implementation of a device for determining the motor torque. Please refer to the following embodiment.

[0150] See also Fig. 9, the motor torque determination device 600 provided in the embodiment of the present application includes:

[0151] A first acquisition module 610 is used to acquire first motion state data of the vehicle, where the first motion state data includes a first vehicle driving speed and a first steering wheel rotation angle;

[0152] A first determination module 620 is used to determine, according to the first vehicle driving speed, a first torque mapping surface corresponding to a first vehicle driving speed interval in which the first vehicle driving speed is located, the first torque mapping surface being used to characterize a mapping relationship between motion state data and motor torque within the first vehicle driving speed interval, the motion state data including the vehicle driving speed and the steering wheel rotation angle;

[0153] The second determination module 630 is configured to determine the motor torque mapped to the first steering wheel rotation angle and the first vehicle driving speed in the first torque mapping surface as the motor torque of the vehicle.

[0154] Thus, by processing the first vehicle speed acquired by the first acquisition module 610 using the first determination module 620, the first vehicle speed interval in which the first vehicle speed is located can be determined, and the first torque mapping surface determined based on the first vehicle speed interval can accurately reflect the mapping relationship between the motion state data and the motor torque in the first vehicle speed interval. The motor torque determined by the first torque mapping surface and the first motion state data takes into account the driving characteristics of the vehicle in the first vehicle speed interval, and the second determination module 630 can directly determine the motor torque of the vehicle based on the first vehicle speed and the first steering wheel rotation angle of the vehicle, thus reducing the conversion error generated in the process of first determining the steering wheel torque and then converting the steering wheel torque into the motor torque, effectively improving the accuracy of the motor torque, and thus enhancing the steering accuracy of the vehicle.

[0155] In some embodiments of the present application, the first determining module 620 may specifically include:

[0156] A first determination submodule, configured to determine a first vehicle driving speed interval in which the first vehicle driving speed is located from a plurality of vehicle driving speed intervals of a preset vehicle driving speed interval;

[0157] The second determining submodule is used to determine the torque mapping surface associated with the first vehicle driving speed interval as the first torque mapping surface according to the association information between the preset vehicle driving speed interval and the preset torque mapping surface.

[0158] In some embodiments of the present application, the second determining module 630 may specifically include:

[0159] a third determining submodule, configured to determine the motor torque mapped to the first steering wheel rotation angle and the first vehicle driving speed in the first torque mapping subsurface as the first motor torque, when the first vehicle driving speed interval includes the first vehicle driving speed subinterval and the second vehicle driving speed subinterval, the first torque mapping surface includes the first torque mapping subsurface corresponding to the first vehicle driving speed subinterval and the second torque mapping subsurface corresponding to the second vehicle driving speed subinterval, and the motor torque mapped to the first steering wheel rotation angle and the first vehicle driving speed includes the first motor torque and the second motor torque;

[0160] a fourth determination submodule, configured to determine the motor torque mapped to the first steering wheel rotation angle and the first vehicle driving speed in the second torque mapping subsurface as the second motor torque;

[0161] The fifth determination submodule is used to perform weighted sum processing on the first motor torque and the second motor torque according to the first weight of the first motor torque and the second weight of the second motor torque to obtain the motor torque of the vehicle.

[0162] In some embodiments of the present application, the motor torque determination device 600 may further include:

[0163] A second acquisition module is used to acquire a data set of a sample vehicle, the data set including motion state sample data and a sample motor torque corresponding to the motion state sample data, the motion state sample data including a sample vehicle driving speed and a sample steering wheel rotation angle corresponding to the sample vehicle driving speed;

[0164] a first division module, for dividing the data set according to M vehicle driving speed intervals, to obtain a sub-data set corresponding to an m-th vehicle driving speed interval among the M vehicle driving speed intervals, the sub-data set comprising first motion state sample data and a first sample motor torque corresponding to the first motion state sample data, the first motion state sample data comprising a first sample vehicle driving speed and a first sample steering wheel rotation angle corresponding to the first sample vehicle driving speed, the first sample vehicle driving speed being within the m-th vehicle driving speed interval;

[0165] a training module, configured to train an initial torque determination model corresponding to the mth vehicle speed interval by using a sub-data set corresponding to the mth vehicle speed interval, until the initial torque determination model satisfies a preset training stop condition, thereby obtaining a reference torque determination model corresponding to the mth vehicle speed interval;

[0166] The third determination module is used to determine the torque mapping surface corresponding to the mth vehicle speed interval according to the reference torque determination model corresponding to the mth vehicle speed interval, and the torque mapping surface includes the torque mapping surface associated with the first vehicle speed interval.

[0167] In some embodiments of the present application, the motor torque determination device 600 may further include:

[0168] a processing module, configured to process a first sample vehicle driving speed and a first sample steering wheel rotation angle by using the reference torque determination model corresponding to the m-th vehicle driving speed interval to obtain a first reference motor torque before executing the step of determining the torque mapping surface corresponding to the m-th vehicle driving speed interval according to the reference torque determination model corresponding to the m-th vehicle driving speed interval;

[0169] a fourth determination module, configured to determine a deviation value according to the first reference motor torque and the first sample motor torque, wherein the deviation value is used to characterize a degree of deviation of the first reference motor torque relative to the first sample motor torque;

[0170] A second division module is used to divide the mth vehicle speed interval according to the deviation value to obtain L vehicle speed sub-intervals when the deviation value is greater than a first preset threshold value;

[0171] The updating module is used to update the L vehicle driving speed sub-intervals to M vehicle driving speed intervals, and update the lth vehicle driving speed sub-interval in the L vehicle driving speed sub-intervals to the mth vehicle driving speed interval in the M vehicle driving speed intervals.

[0172] In some embodiments of the present application, the above-mentioned second division module can be specifically used to, when the mth vehicle driving speed interval includes the second vehicle driving speed and the third vehicle driving speed, the second vehicle driving speed is the maximum vehicle driving speed of the mth vehicle driving speed interval, the third vehicle driving speed is the minimum vehicle driving speed of the mth vehicle driving speed interval, and the deviation value is greater than the first preset threshold, divide the mth vehicle driving speed interval according to the second vehicle driving speed, the third vehicle driving speed and the division coefficient to obtain L vehicle driving speed sub-intervals, the value of the division coefficient is L, and L is a positive integer greater than 1.

[0173] In some embodiments of the present application, the motor torque determination device 600 may further include:

[0174] A fifth determination module, used to determine a target deviation value interval in which the deviation value is located from a plurality of deviation value intervals in the preset deviation value interval;

[0175] The sixth determination module is used to determine the division coefficient associated with the target deviation value interval as the division coefficient according to the association information between the preset deviation value interval and the preset division coefficient.

[0176] In some embodiments of the present application, the motor torque determination device 600 may further include:

[0177] a third acquisition module, configured to acquire an initial data set of the sample vehicle before executing the step of acquiring the data set of the sample vehicle, the initial data set comprising initial motion state sample data of the sample vehicle in each driving condition in a plurality of driving conditions and an initial sample motor torque corresponding to the initial motion state sample data, the initial motion state sample data comprising an initial sample vehicle driving speed and an initial sample steering wheel rotation angle corresponding to the initial sample vehicle driving speed;

[0178] The seventh determination module is used to perform data preprocessing operations on the initial data set to obtain a data set; wherein the data preprocessing operation includes at least one of the following: deleting the abnormal sample motor torque in the initial sample motor torque and the initial motion state sample data corresponding to the abnormal sample motor torque, and normalizing processing.

[0179] In some embodiments of the present application, the above training module may specifically include:

[0180] a processing submodule, configured to process the first sample vehicle driving speed and the first sample steering wheel rotation angle through an initial torque determination model corresponding to the mth vehicle driving speed interval to obtain a second reference motor torque;

[0181] a sixth determination submodule, configured to determine a loss function value according to the second reference motor torque and the first sample motor torque, wherein the loss function value is used to characterize a degree of difference between the second reference motor torque and the first sample motor torque;

[0182] an adjustment submodule, configured to adjust the model parameters of the initial torque determination model according to the loss function value when the loss function value is greater than or equal to a second preset threshold value, so as to obtain an adjusted initial torque determination model;

[0183] A training submodule is used to train the adjusted initial torque determination model through the sub-data set corresponding to the m-th vehicle speed interval, until the loss function value determined by the second reference motor torque and the first sample motor torque is less than a second preset threshold, thereby obtaining a reference torque determination model corresponding to the m-th vehicle speed interval.

[0184] The various modules of the motor torque determination device 600 provided in the embodiment of the present application can be implemented Figures 1 to 8The functions of the various steps of the provided method for determining the motor torque and the corresponding technical effects achieved are not described in detail here for the sake of brevity.

[0185] Fig.10 A schematic diagram of the hardware structure of a computer device provided in some embodiments of the present application is shown.

[0186] Each module in the above-mentioned motor torque determination device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0187] In an exemplary embodiment, a computer device is provided, which may include a processor 701 and a memory 702 storing computer program instructions. The memory stores a computer program, and when the processor executes the computer program, the steps in any one of the above-mentioned motor torque determination method embodiments are implemented.

[0188] Exemplarily, the computer device may be a terminal, and specifically may include but is not limited to vehicles, ships, and other transportation vehicles. The processor 701 may include a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0189] The memory 702 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 702 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 702 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 702 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 702 is a non-volatile solid-state memory.

[0190] In a particular embodiment, the memory 702 may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Therefore, generally, the memory 702 includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the data processing method according to the first aspect of the present application.

[0191] The processor 701 reads and executes computer program instructions stored in the memory 702 to implement any one of the methods for determining the motor torque in the above embodiments.

[0192] In one example, the computer device may further include a communication interface 703 and a bus 710. Fig.10 As shown, the processor 701, the memory 702, and the communication interface 703 are connected via a bus 710 and communicate with each other.

[0193] The communication interface 703 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0194] Bus 710 includes hardware, software or both, and the parts of computer equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 710 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the application considers any suitable bus or interconnection.

[0195] The computer device can execute the method for determining the motor torque in the embodiment of the present application, thereby realizing the combination Figures 1 to 9 A method and apparatus for determining motor torque is described.

[0196] In addition, in combination with the method for determining the motor torque in the above-mentioned embodiment, the embodiment of the present application may provide a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any one of the methods for determining the motor torque in the above-mentioned embodiments is implemented. Examples of computer-readable storage media include non-transitory computer-readable storage media, such as portable disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, etc.

[0197] In addition, in combination with the method for determining the motor torque in the above embodiment, the embodiment of the present application may provide a computer program product for implementation. The program product is stored in a storage medium, and may specifically include a computer program or instruction, which is executed by a processor to implement any one of the methods for determining the motor torque in the above embodiment. The program product is executed by at least one processor to implement the various processes of the above data processing method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0198] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0199] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0200] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0201] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box 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, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0202] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A method for determining motor torque, characterized in that: include: Acquire first motion state data of the vehicle, the first motion state data comprising a first vehicle travel speed and a first steering wheel rotation angle; Determine, according to the first vehicle speed, a first torque mapping surface corresponding to a first vehicle speed interval in which the first vehicle speed is located, wherein the first torque mapping surface is used to characterize a mapping relationship between motion state data and motor torque within the first vehicle speed interval, wherein the motion state data includes a vehicle speed and a steering wheel rotation angle; The motor torque mapped to the first steering wheel rotation angle and the first vehicle travel speed in the first torque mapping curve is determined as the motor torque of the vehicle.

2. The determination method according to claim 1, characterized in that: The determining, according to the first vehicle driving speed, a first torque mapping surface corresponding to a first vehicle driving speed interval in which the first vehicle driving speed is located comprises: determining, from a plurality of vehicle driving speed intervals of preset vehicle driving speed intervals, a first vehicle driving speed interval in which the first vehicle driving speed is located; According to the association information between the preset vehicle driving speed interval and the preset torque mapping curved surface, the torque mapping curved surface associated with the first vehicle driving speed interval is determined as the first torque mapping curved surface.

3. The method according to claim 2, characterized in that The preset vehicle speed interval includes M vehicle speed intervals, and the preset torque mapping surface includes M torque mapping surfaces; the method further includes: Acquire a data set of a sample vehicle, the data set comprising motion state sample data and a sample motor torque corresponding to the motion state sample data, the motion state sample data comprising a sample vehicle driving speed and a sample steering wheel rotation angle corresponding to the sample vehicle driving speed; According to the M vehicle driving speed intervals, the data set is divided to obtain a sub-data set corresponding to the m-th vehicle driving speed interval in the M vehicle driving speed intervals, m∈[1,2,3,...,M], the sub-data set includes first motion state sample data and a first sample motor torque corresponding to the first motion state sample data, the first motion state sample data includes a first sample vehicle driving speed and a first sample steering wheel rotation angle corresponding to the first sample vehicle driving speed, the first sample vehicle driving speed is within the m-th vehicle driving speed interval; Training an initial torque determination model corresponding to the m-th vehicle speed interval by using the sub-data set corresponding to the m-th vehicle speed interval until the initial torque determination model meets a preset training stop condition, thereby obtaining a reference torque determination model corresponding to the m-th vehicle speed interval; A torque mapping surface corresponding to the mth vehicle speed interval is determined according to a reference torque determination model corresponding to the mth vehicle speed interval, wherein the torque mapping surface includes a torque mapping surface associated with the first vehicle speed interval.

4. The method according to claim 3, characterized in that Before determining the torque mapping surface corresponding to the m-th vehicle speed interval according to the reference torque determination model corresponding to the m-th vehicle speed interval, the method further includes: The first sample vehicle speed and the first sample steering wheel rotation angle are processed by a reference torque determination model corresponding to the m-th vehicle speed interval to obtain a first reference motor torque; determining a deviation value according to the first reference motor torque and the first sample motor torque, wherein the deviation value is used to represent a degree of deviation of the first reference motor torque relative to the first sample motor torque; In the case where the deviation value is greater than a first preset threshold, dividing the mth vehicle speed interval according to the deviation value to obtain L vehicle speed sub-intervals, where L is a positive integer greater than 1; Update the L vehicle driving speed sub-intervals to the M vehicle driving speed intervals, and update the lth vehicle driving speed sub-interval in the L vehicle driving speed sub-intervals to the mth vehicle driving speed interval in the M vehicle driving speed intervals, l∈[1,2,3,……,L].

5. The method according to claim 4, characterized in that The m-th vehicle driving speed interval includes a second vehicle driving speed and a third vehicle driving speed, the second vehicle driving speed is the maximum vehicle driving speed of the m-th vehicle driving speed interval, and the third vehicle driving speed is the minimum vehicle driving speed of the m-th vehicle driving speed interval; When the deviation value is greater than a first preset threshold, the mth vehicle speed interval is divided according to the deviation value to obtain L vehicle speed sub-intervals, including: When the deviation value is greater than a first preset threshold, the mth vehicle driving speed interval is divided according to the second vehicle driving speed, the third vehicle driving speed and a division coefficient to obtain L vehicle driving speed sub-intervals, and the division coefficient is taken as L.

6. The method according to claim 5, characterized in that The method further comprises: Determining a target deviation value interval in which the deviation value is located from a plurality of deviation value intervals in a preset deviation value interval; According to the association information between the preset deviation value interval and the preset division coefficient, the division coefficient associated with the target deviation value interval is determined as the division coefficient.

7. The method according to claim 3, characterized in that Before obtaining the data set of sample vehicles, the method further includes: Acquire an initial data set of the sample vehicle, the initial data set comprising initial motion state sample data of each driving condition of the sample vehicle in a plurality of driving conditions and an initial sample motor torque corresponding to the initial motion state sample data, the initial motion state sample data comprising an initial sample vehicle driving speed and an initial sample steering wheel rotation angle corresponding to the initial sample vehicle driving speed; Performing a data preprocessing operation on the initial data set to obtain the data set; The data preprocessing operation includes at least one of the following: deleting abnormal sample motor torques in the initial sample motor torques and initial motion state sample data corresponding to the abnormal sample motor torques, and normalization processing.

8. The method according to any one of claims 3 to 7, characterized in that: The initial torque determination model corresponding to the m-th vehicle speed interval is trained by using the sub-data set corresponding to the m-th vehicle speed interval until the initial torque determination model meets a preset training stop condition, thereby obtaining a reference torque determination model corresponding to the m-th vehicle speed interval, including: The first sample vehicle driving speed and the first sample steering wheel rotation angle are processed by the initial torque determination model corresponding to the m-th vehicle driving speed interval to obtain a second reference motor torque; determining a loss function value according to the second reference motor torque and the first sample motor torque, the loss function value being used to characterize the degree of difference between the second reference motor torque and the first sample motor torque; When the loss function value is greater than or equal to a second preset threshold, adjusting the model parameters of the initial torque determination model according to the loss function value to obtain an adjusted initial torque determination model; The adjusted initial torque determination model is trained by using the sub-data set corresponding to the m-th vehicle speed interval until the loss function value determined by the second reference motor torque and the first sample motor torque is less than the second preset threshold, thereby obtaining a reference torque determination model corresponding to the m-th vehicle speed interval.

9. The determination method according to claim 1 or 2, characterized in that: The first vehicle speed interval includes a first vehicle speed sub-interval and a second vehicle speed sub-interval, the first torque mapping surface includes a first torque mapping sub-surface corresponding to the first vehicle speed sub-interval and a second torque mapping sub-surface corresponding to the second vehicle speed sub-interval, and the motor torque mapped to the first steering wheel rotation angle and the first vehicle speed includes a first motor torque and a second motor torque; The step of determining the motor torque mapped to the first steering wheel rotation angle and the first vehicle driving speed in the first torque mapping curve as the motor torque of the vehicle comprises: Determine the motor torque mapped to the first steering wheel rotation angle and the first vehicle driving speed in the first torque mapping sub-surface as the first motor torque; determining the motor torque mapped to the first steering wheel rotation angle and the first vehicle driving speed in the second torque mapping sub-surface as the second motor torque; The first motor torque and the second motor torque are weighted-summed according to a first weight of the first motor torque and a second weight of the second motor torque to obtain the motor torque of the vehicle.

10. A device for determining motor torque, characterized in that: The device comprises: A first acquisition module, configured to acquire first motion state data of a vehicle, wherein the first motion state data includes a first vehicle driving speed and a first steering wheel rotation angle; a first determining module, configured to determine, according to the first vehicle driving speed, a first torque mapping surface corresponding to a first vehicle driving speed interval in which the first vehicle driving speed is located, wherein the first torque mapping surface is used to characterize a mapping relationship between motion state data and motor torque within the first vehicle driving speed interval, wherein the motion state data includes a vehicle driving speed and a steering wheel rotation angle; The second determination module is used to determine the motor torque mapped to the first steering wheel rotation angle and the first vehicle driving speed in the first torque mapping surface as the motor torque of the vehicle.

11. A computer device, characterized in that: The device comprises: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the method for determining the motor torque according to any one of claims 1 to 9 is implemented.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the method for determining the motor torque according to any one of claims 1 to 9 is implemented.

13. A computer program product, characterized in that The invention comprises a computer program, which, when being processed and executed, implements the method for determining the motor torque according to any one of claims 1 to 9.

Images