Method and device for controlling torque distribution of a vehicle

Abstract

The present invention provides a method and device for controlling the torque distribution of a vehicle, and relates to the field of automotive technology. In this application, the current state of the vehicle (braking or accelerating) is accurately identified based on the vehicle state information, such as vehicle speed, acceleration, battery parameters and other multivariate data, so that the control center can enter the corresponding control mode, which speeds up the response rate of the vehicle driving controller to accelerate or brake, so as to coordinate and control the torque distribution between motors and improve the overall working efficiency of the motors. Then, the inter-axle torque is optimized and distributed according to the vehicle state information and road condition information. The system performance is improved based on the trial-and-error interaction with the environment through reinforcement learning, based on the observation value and the analysis of the system behavior. The optimal control strategy is usually obtained with the goal of maximizing the cumulative reward function. It can not only improve the vehicle's handling stability and safety, but also has great potential in improving economy and the energy utilization rate of the vehicle.

Description

Technical Field

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

[0002] Currently, driven by the government, the current vehicle control system has a relatively mature R&D system. However, with the development of hybrid and pure electric vehicle technologies, the dual-motor equal torque distribution strategy has certain problems. It cannot meet the requirements of reducing system energy consumption and improving driving comfort, which is not conducive to the economy and comfort of the overall operation of the vehicle.

[0003] Moreover, the vehicle driving torque control strategy of the existing related technology is usually to distribute the torque after obtaining the target torque according to the accelerator pedal and speed table under different driving modes. The torque distribution strategy is single and is not conducive to reducing energy consumption. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and device for controlling torque distribution of a vehicle to improve the above-mentioned problem. To achieve the above-mentioned purpose, the technical solution adopted by the present invention is as follows:

[0005] In a first aspect, the present application provides a method for controlling torque distribution of a vehicle, comprising:

[0006] Acquiring vehicle status information and road condition information, wherein the vehicle status information includes at least an accelerator pedal opening value, a brake pedal opening value, vehicle speed, motor parameters, and battery parameters; and the road condition information includes at least driving weather information and road information;

[0007] determining whether the accelerator pedal opening value is greater than or equal to a first threshold, the first threshold being the accelerator pedal threshold for the vehicle to enter a driving mode; if the accelerator pedal opening value is greater than or equal to the first threshold, determining whether the brake pedal opening value is greater than or equal to a second threshold, the second threshold being the brake pedal threshold for the vehicle to enter a braking mode; if the brake pedal opening value is greater than or equal to the second threshold, calculating the vehicle braking demand torque based on the vehicle state information and the road condition information; and if the brake pedal opening value is less than the second threshold, calculating the vehicle driving demand torque based on the vehicle state information;

[0008] Building a torque distribution model based on the vehicle braking demand torque or the vehicle driving demand torque;

[0009] A torque distribution plan for the vehicle is obtained based on the torque distribution model using a reinforcement learning algorithm, and distribution control is performed based on the torque distribution plan for the vehicle.

[0010] In a second aspect, the present application further provides a vehicle torque distribution control device, comprising an acquisition module, a judgment module, a construction module, and a distribution module, wherein:

[0011] Acquisition module: used to acquire vehicle status information and road condition information, wherein the vehicle status information includes at least accelerator pedal opening value, brake pedal opening value, vehicle speed, motor parameters and battery parameters; the road condition information includes at least driving weather information and road information;

[0012] a judgment module configured to judge whether the accelerator pedal opening value is greater than or equal to a first threshold value, the first threshold value being the accelerator pedal threshold value for the vehicle to enter a driving mode; if the accelerator pedal opening value is greater than or equal to the first threshold value, then judge whether the brake pedal opening value is greater than or equal to a second threshold value, the second threshold value being the brake pedal threshold value for the vehicle to enter a braking mode; if the brake pedal opening value is greater than or equal to the second threshold value, then calculate the vehicle braking demand torque based on the vehicle state information and the road condition information; if the brake pedal opening value is less than the second threshold value, then calculate the vehicle driving demand torque based on the vehicle state information;

[0013] A construction module is configured to construct a torque distribution model based on the vehicle braking requirement torque or the vehicle driving requirement torque;

[0014] Distribution module: used to use the reinforcement learning algorithm to solve the vehicle's torque distribution plan based on the torque distribution model, and perform distribution control based on the vehicle's torque distribution plan.

[0015] The beneficial effects of the present invention are:

[0016] In this application, the current state of the vehicle (braking or acceleration) is accurately identified based on vehicle status information, such as vehicle speed, battery parameters and other multivariate data, so that the control center can enter the corresponding control mode, which speeds up the response rate of the vehicle driving controller to accelerate or brake, so as to coordinate and control the torque distribution between motors and improve the overall working efficiency of the motors. Then, under the corresponding driving state, the inter-axle torque is optimized according to the vehicle status information and road condition information, and the optimal control strategy is obtained by using reinforcement learning. Moreover, this application can improve the sensitivity and speed of the vehicle driving controller in identifying driving conditions and braking conditions, so that the torque change rate of the torque filter can be quickly determined to achieve slow engagement between gears and reduce zero-crossing shock.

[0017] Furthermore, in the present invention, the braking torque coefficient is set to three levels (large, medium, and small) (corresponding to different braking modes) based on the magnitude of the braking deceleration corresponding to the brake pedal opening value, and is assigned corresponding weights. The calculated required torque is then compared with a preset torque table (which lists the coordinated control modes between different motors and their corresponding required torques) to roughly determine whether a single motor or multiple motors are operating in combination. Furthermore, considering the impact of wind speed, road roughness, and uphill and downhill slopes on vehicle deceleration during actual driving, the mechanical braking torque is dynamically tracked in real time based on actual driving conditions, facilitating the subsequent determination of the precise required vehicle braking torque. The braking torque generated during motor energy recovery is also adjusted within a certain range to compensate for the negative acceleration generated during braking, ensuring that the negative acceleration generated during vehicle braking remains consistent with the required value.

[0018] This application utilizes reinforcement learning through trial-and-error interaction with the environment, using vehicle state information and road condition information as inputs to a torque distribution model. This model is then solved using a reinforcement learning algorithm to obtain an optimal torque control strategy. Compared to traditional reinforcement learning algorithms that maximize the cumulative reward function to solve for optimal control strategies, the optimization goal of this application is to minimize instantaneous energy consumption. Therefore, this application defines instantaneous reward as the inverse of the system's instantaneous energy consumption. This approach not only improves vehicle handling stability and safety, but also has great potential for improving economy and overall vehicle energy efficiency.

[0019] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or understood by practicing the embodiments of the present invention. The purposes and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 A flowchart of a method for controlling torque distribution of a vehicle in an embodiment of the present invention;

[0022] Figure 2 A block diagram of a control device for torque distribution of a vehicle in an embodiment of the present invention;

[0023] Figure 3This is a block diagram of a control device for torque distribution of a vehicle in an embodiment of the present invention.

[0024] Markings in the figure: 710-acquisition module; 720-judgment module; 721-braking coefficient unit; 722-first acquisition unit; 723-first calculation unit; 7231-second acquisition unit; 7232-third acquisition unit; 7233-second calculation unit; 724-processing unit; 725-judgment subunit; 726-fourth acquisition unit; 727-third calculation unit; 730-construction module; 731-first mapping unit; 732-second mapping unit; 733-fourth calculation unit; 740-distribution module; 800-vehicle torque distribution control device; 801-processor; 802-memory; 803-multimedia component; 804-I / O interface; 805-communication component. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0026] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are used only to distinguish the description and should not be understood as indicating or implying relative importance.

[0027] Example 1:

[0028] See also Figure 1 , Figure 1 FIG2 is a flowchart of a method for controlling torque distribution of a vehicle in accordance with an embodiment of the present invention. The present embodiment provides a method for controlling torque distribution of a vehicle, and the method includes steps S1, S2, S3, and S4.

[0029] Step S1, obtaining vehicle status information and road condition information, wherein the vehicle status information includes at least accelerator pedal opening value, brake pedal opening value, vehicle speed, motor parameters and battery parameters; the road condition information includes at least driving weather information and road information.

[0030] It can be understood that in this step, the vehicle driving controller obtains information data such as the vehicle's position, speed, ambient wind speed, rolling friction coefficient of the wheels corresponding to the driving road surface, slope angle, etc. through on-board sensors (camera, lidar, millimeter-wave radar, ultrasonic radar, GPS, etc.); at the same time, the vehicle driving controller also retrieves relevant parameter information of equipment such as batteries and motors.

[0031] Step S2, determine whether the accelerator pedal opening value is greater than or equal to a first threshold value, the first threshold value is the accelerator pedal threshold for the vehicle to enter the driving mode; if the accelerator pedal opening value is greater than or equal to the first threshold value, determine whether the brake pedal opening value is greater than or equal to a second threshold value, the second threshold value is the brake pedal threshold for the vehicle to enter the braking mode; if the brake pedal opening value is greater than or equal to the second threshold value, calculate the vehicle braking demand torque based on the vehicle status information and the road condition information; if the brake pedal opening value is less than the second threshold value, calculate the vehicle driving demand torque based on the vehicle status information.

[0032] It is understandable that in this step, the continuous judgment of the first threshold and the second threshold can distinguish whether the driver's current driving operation is acceleration or braking, and thus the vehicle driving controller can directly enter the driving mode after the accelerator pedal is stepped on, and optimize the torque distribution between the axles according to the vehicle status information; and after the brake pedal is stepped on, the driving controller directly enters the braking mode, and optimizes the torque distribution between the axles according to the vehicle status information and the road condition information. This step speeds up the response rate of the vehicle driving controller to accelerate or brake, and when the driving operations of acceleration and braking are converted to each other, in order to reduce the torque zero-crossing impact and improve driving comfort, the torque needs to be filtered. This application can improve the sensitivity and speed of the vehicle driving controller in identifying driving conditions and braking conditions, so that the torque change rate of the torque filter can be quickly determined to achieve slow engagement between gears and reduce zero-crossing impact.

[0033] In detail, the method for calculating the vehicle braking required torque includes step S21, step S22 and step S23.

[0034] Step S21: Determine a braking torque coefficient based on the brake pedal opening value.

[0035] It will be appreciated that in this step, the braking torque coefficient is set to three levels (large, medium, and small) (corresponding to different braking modes) based on the magnitude of the braking deceleration corresponding to the brake pedal opening value, and is assigned corresponding weights. In this embodiment, when the braking torque coefficient is small, the vehicle performs regenerative braking; when the braking torque coefficient is medium, hybrid braking is performed; and when the braking torque coefficient is large, mechanical braking is performed. Regenerative braking is performed jointly by the ISG motor and the rear-drive motor, with the ratio of the regenerative braking torques from the ISG motor and the rear-drive motor satisfying a fixed front and rear wheel braking torque ratio.

[0036] Step S22: Obtain corresponding first characteristic parameters based on the motor parameters, where the first characteristic parameters include the maximum torque that the ISG motor can provide at the current speed, the maximum torque that the rear-drive motor can provide, the CVT speed ratio, the front axle main reduction ratio, and the rear axle main reduction ratio.

[0037] It can be understood that in this step, each different type of motor in the vehicle is calculated using existing direct calculation methods, estimation methods based on inductance changes, or estimation methods based on observers, and the parameters are stored to establish a database, and the first characteristic parameters of the corresponding motor are retrieved from the database.

[0038] Step S23: Calculate the maximum torque that can be provided by the mechanical brake based on the vehicle state information and the road condition information.

[0039] In detail, the method for calculating the maximum torque that can be provided by the mechanical brake includes step S231 , step S232 and step S233 .

[0040] Step S231: obtaining second characteristic parameters based on the vehicle status information, where the second characteristic parameters include vehicle load, vehicle speed, required deceleration, wheel rolling resistance coefficient, rotational mass conversion coefficient, rear axle speed ratio, and transmission efficiency.

[0041] It can be understood that in this step, the second characteristic parameter is obtained through various corresponding sensors, for example, the vehicle load information is obtained through a pressure sensor, and the vehicle speed is obtained through an ultrasonic radar.

[0042] Step S232: Acquire a third characteristic parameter based on the road condition information, where the third characteristic parameter includes a ramp angle, a drag coefficient, and a frontal area.

[0043] It can be understood that in this step, the road conditions are captured in real time by a camera and the ramp angle is calculated using a ramp scene recognition algorithm, the drag coefficient is measured using an air resistance coefficient tester, and the front projection area of the vehicle is taken as the windward area.

[0044] Step S233: Calculate based on the second characteristic parameter and the third characteristic parameter to obtain the maximum torque that can be provided by the mechanical brake.

[0045] It can be understood that in this step, the maximum torque that can be provided by the mechanical brake is calculated according to formula (1):

[0046] (1)

[0047] Where: N T is the maximum torque that the mechanical brake can provide; λ is the rotation mass conversion coefficient; m is the vehicle load; a j is the required deceleration; g is the acceleration due to gravity; f is the wheel rolling resistance coefficient; α is the slope angle (positive for uphill and negative for downhill); F d is the drag coefficient; A is the frontal area; V is the vehicle speed; S0 is the rear axle speed ratio; μ i is the transmission efficiency; r is the wheel radius. In actual driving, factors such as wind speed, road roughness, and uphill and downhill slopes all affect vehicle deceleration. This step dynamically tracks the mechanical braking torque in real time based on actual driving conditions, facilitating accurate determination of the vehicle's required braking torque. It also adjusts the braking torque generated during motor energy recovery within a certain range to compensate for the negative acceleration generated during braking, ensuring that the negative acceleration generated during braking is consistent with the required value.

[0048] Step S24: Calculate the vehicle braking requirement torque based on the brake pedal opening value, the braking torque coefficient, the first characteristic parameter, and the maximum torque that can be provided by the mechanical brake.

[0049] It can be understood that in this step, the vehicle braking requirement torque is calculated according to formula (2):

[0050] (2)

[0051] Where: N Z is the braking torque required for the vehicle; β is the brake pedal opening value; N imax The maximum torque that the ISG motor can provide; I h is the CVT speed ratio; I q is the front axle main reduction ratio; I e is the rear axle main reduction ratio; N emax The maximum torque that the rear drive motor can provide; N T The maximum torque that the mechanical brake can provide; K z The above steps can better reflect the driver's driving intention and make the calculation of the required torque more accurate.

[0052] The above-mentioned method for calculating the required vehicle driving torque includes step S25, step S26 and step S27.

[0053] Step S25: The battery parameters include a current SOC value, and whether the current SOC value is greater than or equal to a third threshold is determined. The third threshold is the SOC threshold for allowing vehicle driving; if so, the driving torque coefficient is determined based on the accelerator pedal opening value.

[0054] It will be appreciated that in this step, when the vehicle driving controller enters the driving mode, it first determines whether the vehicle is experiencing an uninterrupted high voltage and irreversible zero torque fault. This ensures that the vehicle control center can switch between different driving modes based on real-time driving conditions. Furthermore, the driving torque coefficient is set to three levels (large, medium, and small) (corresponding to different driving modes) based on the acceleration and deceleration corresponding to the accelerator pedal opening value, and is assigned corresponding weights. In this embodiment, when the driving torque coefficient is small, the rear axle is driven; when the driving torque coefficient is medium, the front axle is driven; and when the driving torque coefficient is large, both axles are driven.

[0055] Step S26: Obtain corresponding second characteristic parameters based on the vehicle status information, wherein the second characteristic parameters include the maximum torque that the generator can provide at the current speed, the maximum torque that the ISG motor can provide, the maximum torque that the rear-drive motor can provide, the CVT speed ratio, the front axle main reduction ratio, and the rear axle main reduction ratio.

[0056] Step S27: Calculate the required driving torque based on the accelerator pedal opening value, the driving torque coefficient, and the second characteristic parameter.

[0057] It can be understood that in this step, the driving demand torque is calculated according to formula (3):

[0058] (3)

[0059] Where: Nx is the driving torque requirement; α is the accelerator pedal opening value; N fmax The maximum torque that the generator can provide; N imax The maximum torque that the ISG motor can provide; I h is the CVT speed ratio; I q is the front axle main reduction ratio; I e is the rear axle main reduction ratio; N emax The maximum torque that the rear drive motor can provide; K X The above steps can better reflect the driver's driving intention and make the calculation of the required torque more accurate.

[0060] Step S3: constructing a torque distribution model based on the vehicle braking demand torque or the vehicle driving demand torque.

[0061] It can be understood that in this step, the maximum system efficiency is used as the objective function, and the torque distribution coefficient of each axle is used as a variable to establish a mathematical model for torque optimization distribution. The torque distribution coefficients of the front, middle, and rear axles of the vehicle are determined by multi-objective genetic algorithms and quadratic programming torque distribution algorithms to optimize the model. This is used as online lookup table data for the vehicle's torque optimization distribution strategy, reducing the complexity of control and improving the speed of real-time calculation.

[0062] In detail, step S3 includes step S31, step S32 and step S33.

[0063] Step S31: forming a first matrix based on the vehicle braking requirement torque and its corresponding motor speed.

[0064] It can be understood that in this step, the allocation model is constructed according to formula (4):

[0065] (4)

[0066] Where: N11, N12, N21 and N22 are the torques of the left front wheel, right front wheel, left rear wheel and right rear wheel respectively; N Q and N H are the torques of the front and rear axles respectively; p is the proportion of the front axle torque in the total driving torque; T i is the required torque, i=1, 2 represents braking mode and driving mode respectively; V C is the wheel motor speed, c=1,2,3,4 represent the left front wheel, right front wheel, left rear wheel, right rear wheel respectively; V M is the motor speed corresponding to the vehicle's braking torque requirement; β R is the speed ratio of the wheel reducer (or accelerator); r is the wheel radius; and V is the vehicle speed. Each set of corresponding braking demand torque and motor speed is then combined to form a two-dimensional vector.

[0067] Step S32: forming a second matrix based on the vehicle drive required torque and its corresponding motor speed.

[0068] It can be understood that, in this step, the second matrix is constructed according to the method of step S31.

[0069] Step S33: Based on a deep reinforcement learning algorithm, the first matrix or the second matrix is used as an input value, and minimizing instantaneous energy consumption is used as an objective function to obtain a torque distribution model.

[0070] It can be understood that in this step, the objective function is constructed according to formula (5):

[0071] (5)

[0073] Where: ƞ is the instantaneous energy consumption; V M is the motor speed corresponding to the vehicle's braking torque requirement; p is the proportion of the front axle torque in the total driving torque; T n is the required torque, n=1 and 2 represent braking mode and driving mode respectively; λ is the motor efficiency; G is the indicator function, G=-1 and 1 represent driving mode and braking mode respectively.

[0074] Step S4: using a reinforcement learning algorithm to solve a torque distribution plan for the vehicle based on the torque distribution model, and performing distribution control based on the torque distribution plan for the vehicle.

[0075] It is understandable that in this step, the purpose of torque distribution is to ultimately achieve the reliable realization of the vehicle's braking and driving functions on the basis of maximizing the recovery of braking energy through reasonable distribution. The present application utilizes reinforcement learning through trial-and-error interaction with the environment, takes the vehicle state information and road condition information as input values of the torque distribution model and uses the reinforcement learning algorithm to solve it, thereby obtaining the torque optimal control strategy. Compared with the traditional reinforcement learning algorithm that solves the optimal control strategy with the goal of maximizing the cumulative reward function, the optimization goal of the present invention is to minimize instantaneous energy consumption. Therefore, the instantaneous reward is defined in this application as the opposite of the instantaneous energy consumption of the system, which can not only improve the vehicle's handling stability and safety, but also has great potential in improving economy and the energy utilization rate of the vehicle.

[0076] Example 2:

[0077] See also Figure 2 , Figure 2 7 is a block diagram of a vehicle torque distribution control device according to an exemplary embodiment, including an acquisition module 710, a judgment module 720, a construction module 730 and a distribution module 740, wherein:

[0078] Acquisition module 710: for acquiring vehicle status information and road condition information, wherein the vehicle status information includes at least accelerator pedal opening value, brake pedal opening value, vehicle speed, motor parameters, and battery parameters; the road condition information includes at least driving weather information and road information;

[0079] Determination module 720: used to determine whether the accelerator pedal opening value is greater than or equal to a first threshold value, the first threshold value being the accelerator pedal threshold for the vehicle to enter the driving mode; if the accelerator pedal opening value is greater than or equal to the first threshold value, then determine whether the brake pedal opening value is greater than or equal to a second threshold value, the second threshold value being the brake pedal threshold for the vehicle to enter the braking mode; if the brake pedal opening value is greater than or equal to the second threshold value, then calculate the vehicle braking demand torque based on the vehicle state information and the road condition information; if the brake pedal opening value is less than the second threshold value, then calculate the vehicle driving demand torque based on the vehicle state information;

[0080] Preferably, the judgment module 720 includes a braking coefficient unit 721, a first acquisition unit 722, a first calculation unit 723, and a processing unit 724, wherein:

[0081] Braking coefficient unit 721: used to determine a braking torque coefficient based on the brake pedal opening value;

[0082] A first acquiring unit 722 is configured to acquire corresponding first characteristic parameters based on the motor parameters, the first characteristic parameters including a maximum torque that can be provided by the ISG motor at a current speed, a maximum torque that can be provided by the rear-drive motor, a CVT speed ratio, a front axle main reduction ratio, and a rear axle main reduction ratio;

[0083] The first calculation unit 723 calculates the maximum torque that can be provided by the mechanical brake based on the vehicle state information and the road condition information.

[0084] Furthermore, the first acquiring unit 723 includes a second acquiring unit 7231, a third acquiring unit 7232, and a second calculating unit 7233, wherein:

[0085] A second acquiring unit 7231 is configured to acquire second characteristic parameters based on the vehicle state information, the second characteristic parameters including vehicle load, vehicle speed, required deceleration, wheel rolling resistance coefficient, rotational mass conversion coefficient, rear axle speed ratio, and transmission efficiency;

[0086] A third acquiring unit 7232 is configured to acquire a third characteristic parameter based on the road condition information, wherein the third characteristic parameter includes a slope angle, a drag coefficient, and a frontal area;

[0087] The second calculation unit 7233 is configured to calculate, based on the second characteristic parameter and the third characteristic parameter, a maximum torque that can be provided by the mechanical brake.

[0088] The processing unit 724 is configured to calculate and obtain the vehicle braking requirement torque based on the brake pedal opening value, the braking torque coefficient and the first characteristic parameter.

[0089] The judgment module 720 further includes a judgment subunit 725, a fourth acquisition unit 726, and a third calculation unit 727, wherein:

[0090] Determining subunit 725 : for determining whether the battery parameter includes a current SOC value, the current SOC value is greater than or equal to a third threshold, the third threshold being the SOC threshold for allowing vehicle driving; and if so, determining a driving torque coefficient based on the accelerator pedal opening value;

[0091] A fourth acquiring unit 726 is configured to acquire corresponding second characteristic parameters based on the vehicle state information, the second characteristic parameters including a maximum torque that can be provided by the generator at a current speed, a maximum torque that can be provided by the ISG motor, a maximum torque that can be provided by the rear-drive motor, a CVT speed ratio, a front axle final reduction ratio, and a rear axle final reduction ratio;

[0092] The third calculation unit 727 is configured to calculate and obtain the required driving torque based on the accelerator pedal opening value, the driving torque coefficient and the second characteristic parameter.

[0093] A construction module 730 is configured to construct a torque distribution model based on the vehicle braking requirement torque or the vehicle driving requirement torque;

[0094] Preferably, the construction module 730 includes a first mapping unit 731, a second mapping unit 732 and a fourth calculation unit 733, wherein:

[0095] A first mapping unit 731 is configured to form a first matrix based on the vehicle braking requirement torque and its corresponding motor speed;

[0096] The second mapping unit 732 is configured to form a second matrix based on the vehicle driving demand torque and the corresponding motor speed;

[0097] The fourth calculation unit 733 is used to obtain a torque distribution model based on a deep reinforcement learning algorithm, using the first matrix or the second matrix as an input value and minimizing instantaneous energy consumption as an objective function.

[0098] The distribution module 740 is configured to obtain a torque distribution plan for the vehicle based on the torque distribution model using a reinforcement learning algorithm, and perform distribution control based on the torque distribution plan for the vehicle.

[0099] It should be noted that, regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated on here.

[0100] Example 3:

[0101] Corresponding to the above method embodiment, this embodiment also provides a vehicle torque distribution control device 800. The vehicle torque distribution control device 800 described below and the vehicle torque distribution control method described above can be referenced to each other.

[0102] Figure 3 FIG. 8 is a block diagram of a vehicle torque distribution control device 800 according to an exemplary embodiment. Figure 3 As shown, the vehicle torque distribution control device 800 may include: a processor 801 and a memory 802. The vehicle torque distribution control device 800 may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0103] The processor 801 is used to control the overall operation of the vehicle torque distribution control device 800 to complete all or part of the steps in the above-mentioned vehicle torque distribution control method. The memory 802 is used to store various types of data to support the operation of the vehicle torque distribution control device 800. This data may include, for example, instructions for any application or method operating on the vehicle torque distribution control device 800, as well as application-related data such as contact information, sent and received messages, pictures, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 802 or transmitted via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, which may be a keyboard, a mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the vehicle's torque distribution control device 800 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more thereof, may include: a Wi-Fi module, a Bluetooth module, and an NFC module.

[0104] In an exemplary embodiment, the vehicle torque distribution control device 800 can be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned vehicle torque distribution control method.

[0105] In another exemplary embodiment, a computer storage medium including program instructions is also provided. When executed by a processor, the program instructions implement the steps of the above-described method for controlling vehicle torque distribution. For example, the computer storage medium may be the aforementioned memory 802 including the program instructions. The program instructions may be executed by the processor 801 of the vehicle torque distribution control device 800 to implement the above-described method for controlling vehicle torque distribution.

[0106] Example 4:

[0107] Corresponding to the above method embodiment, a storage medium is further provided in this embodiment. The storage medium described below and the vehicle torque distribution control method described above can refer to each other.

[0108] A storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for controlling torque distribution of a vehicle in the above-mentioned method embodiment.

[0109] The storage medium may specifically be any storage medium capable of storing program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0110] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

[0111] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A method for controlling torque distribution of a vehicle, characterized in that: include: Acquiring vehicle status information and road condition information, wherein the vehicle status information includes at least an accelerator pedal opening value, a brake pedal opening value, a vehicle speed, motor parameters, and battery parameters; The road condition information includes at least driving weather information and road information; determining whether the accelerator pedal opening value is greater than or equal to a first threshold, where the first threshold is an accelerator pedal threshold for the vehicle to enter a driving mode; If the accelerator pedal opening value is greater than or equal to the first threshold, then determining whether the brake pedal opening value is greater than or equal to a second threshold, where the second threshold is a brake pedal threshold for the vehicle to enter a braking mode; If the brake pedal opening value is greater than or equal to a second threshold, calculating the vehicle braking required torque based on the vehicle state information and the road condition information; If the brake pedal opening value is less than a second threshold, calculating the vehicle driving required torque based on the vehicle state information; Building a torque distribution model based on the vehicle braking demand torque or the vehicle driving demand torque; Obtaining a torque distribution plan for the vehicle based on the torque distribution model using a reinforcement learning algorithm, and performing distribution control based on the torque distribution plan for the vehicle; Establishing a torque distribution model based on the vehicle braking demand torque or the vehicle driving demand torque includes: A first matrix is formed based on the vehicle braking demand torque and its corresponding motor speed; A second matrix is formed based on the vehicle drive demand torque and its corresponding motor speed; Based on a deep reinforcement learning algorithm, the first matrix or the second matrix is used as an input value, and minimizing instantaneous energy consumption is used as an objective function to obtain a torque distribution model.

2. The method for controlling torque distribution of a vehicle according to claim 1, wherein: If the brake pedal opening value is greater than or equal to a second threshold, calculating the vehicle braking requirement torque based on the vehicle state information and the road condition information includes: determining a braking torque coefficient based on the brake pedal opening value; Acquire corresponding first characteristic parameters based on the motor parameters, the first characteristic parameters including the maximum torque that the ISG motor can provide at the current speed, the maximum torque that the rear drive motor can provide, the CVT speed ratio, the front axle final reduction ratio, and the rear axle final reduction ratio; Calculating the maximum torque that can be provided by the mechanical brake based on the vehicle state information and the road condition information; The vehicle braking requirement torque is calculated based on the brake pedal opening value, the braking torque coefficient, the first characteristic parameter, and the maximum torque that can be provided by the mechanical brake.

3. The method for controlling torque distribution of a vehicle according to claim 2, wherein: The calculation formula of the vehicle braking required torque is: ； Where: N Z is the braking torque required for the vehicle; β is the brake pedal opening value; N imax The maximum torque that the ISG motor can provide; I h is the CVT speed ratio; I q is the front axle main reduction ratio; I e is the rear axle main reduction ratio; N emax The maximum torque that the rear drive motor can provide; N T The maximum torque that the mechanical brake can provide; K z is the braking torque coefficient.

4. The method for controlling torque distribution of a vehicle according to claim 2, wherein: The calculating the maximum torque that can be provided by the mechanical brake based on the vehicle state information and the road condition information includes: obtaining second characteristic parameters based on the vehicle state information, the second characteristic parameters including vehicle load, vehicle speed, required deceleration, wheel rolling resistance coefficient, rotational mass conversion coefficient, rear axle speed ratio, and transmission efficiency; acquiring a third characteristic parameter based on the road condition information, the third characteristic parameter including a ramp angle, a drag coefficient, and a frontal area; The maximum torque that can be provided by the mechanical brake is obtained by calculation based on the second characteristic parameter and the third characteristic parameter.

5. The method for controlling torque distribution of a vehicle according to claim 4, characterized in that: The calculation formula of the maximum torque that the mechanical brake can provide is: ； Where: N T is the maximum torque that the mechanical brake can provide; λ is the rotation mass conversion coefficient; m is the vehicle load; a j is the required deceleration; g is the acceleration due to gravity; f is the wheel rolling resistance coefficient; α is the slope angle (positive for uphill and negative for downhill); F d is the drag coefficient; A is the frontal area; V is the vehicle speed; S0 is the rear axle speed ratio; μ i is the transmission efficiency; r is the wheel radius.

6. The method for controlling torque distribution of a vehicle according to claim 1, wherein: If the brake pedal opening value is less than a second threshold, calculating the vehicle driving required torque based on the vehicle state information includes: The battery parameter includes a current SOC value, determining whether the current SOC value is greater than or equal to a third threshold, the third threshold being an SOC threshold for allowing vehicle driving; if so, determining a driving torque coefficient based on the accelerator pedal opening value; Acquire corresponding second characteristic parameters based on the vehicle state information, the second characteristic parameters including the maximum torque that the generator can provide at the current speed, the maximum torque that the ISG motor can provide, the maximum torque that the rear drive motor can provide, the CVT speed ratio, the front axle final reduction ratio, and the rear axle final reduction ratio; The driving demand torque is obtained based on the accelerator pedal opening value, the driving torque coefficient and the second characteristic parameter.

7. The method for controlling torque distribution of a vehicle according to claim 6, wherein: The calculation formula of the driving demand torque is: ； Where: Nx is the driving torque requirement; α is the accelerator pedal opening value; N fmax The maximum torque that the generator can provide; N imax The maximum torque that the ISG motor can provide; I h is the CVT speed ratio; I q is the front axle main reduction ratio; I e is the rear axle main reduction ratio; N emax The maximum torque that the rear drive motor can provide; K X is the driving torque coefficient.

8. The method for controlling torque distribution of a vehicle according to claim 1, wherein: The calculation formula of the torque distribution model is: Where: ƞ is the instantaneous energy consumption; V M is the motor speed corresponding to the vehicle's braking torque requirement; p is the proportion of the front axle torque in the total driving torque; T n is the required torque, n=1 and 2 represent braking mode and driving mode respectively; λ is the motor efficiency; G is the indicator function, G=-1 and 1 represent driving mode and braking mode respectively.

9. A vehicle torque distribution control device, characterized in that: The method comprises modules for executing the method for controlling torque distribution of a vehicle according to any one of claims 1 to 8, wherein the modules include an acquisition module, a judgment module, a construction module and a distribution module, wherein: Acquisition module: used to acquire vehicle status information and road condition information, wherein the vehicle status information includes at least accelerator pedal opening value, brake pedal opening value, vehicle speed, motor parameters and battery parameters; the road condition information includes at least driving weather information and road information; a judgment module configured to judge whether the accelerator pedal opening value is greater than or equal to a first threshold value, the first threshold value being the accelerator pedal threshold value for the vehicle to enter a driving mode; if the accelerator pedal opening value is greater than or equal to the first threshold value, then judge whether the brake pedal opening value is greater than or equal to a second threshold value, the second threshold value being the brake pedal threshold value for the vehicle to enter a braking mode; if the brake pedal opening value is greater than or equal to the second threshold value, then calculate the vehicle braking demand torque based on the vehicle state information and the road condition information; if the brake pedal opening value is less than the second threshold value, then calculate the vehicle driving demand torque based on the vehicle state information; A construction module is configured to construct a torque distribution model based on the vehicle braking requirement torque or the vehicle driving requirement torque; A distribution module is configured to obtain a vehicle torque distribution scheme based on the torque distribution model using a reinforcement learning algorithm, and to perform distribution control based on the vehicle torque distribution scheme; a torque distribution model is constructed based on the vehicle braking demand torque or the vehicle driving demand torque, including: A first matrix is formed based on the vehicle braking demand torque and its corresponding motor speed; A second matrix is formed based on the vehicle drive demand torque and its corresponding motor speed; Based on a deep reinforcement learning algorithm, the first matrix or the second matrix is used as an input value, and minimizing instantaneous energy consumption is used as an objective function to obtain a torque distribution model.

Images