Brake process optimization method based on hub motor and EMB

Abstract

The invention provides a braking process optimization method based on a hub motor and an EMB, and relates to the technical field of vehicle braking, and the method comprises the steps: building a vehicle dynamics model comprising a hub motor model, an EMB model, a battery model, a tire model and a whole vehicle longitudinal dynamics model; establishing a braking control strategy including required braking force calculation, braking force front-back distribution, braking force left-right distribution and distribution of the braking force of the hub motor and the EMB by using a feedback factor; a parameter optimization strategy based on reinforcement learning is designed, the braking strength and the rotating speed serve as state variables, the rotating speed threshold value, the quit coefficient and the adding coefficient when the hub motor starts to quit braking serve as action variables, and the weighted sum of the braking energy recovery function and the braking comfort function serves as a reward function; and operating the vehicle dynamics model, training the intelligent agent by using a reinforcement learning algorithm until the reward function converges, and obtaining the optimal value of the action variable.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle braking, in particular to a brake process optimization method based on in-wheel motor and EMB. BACKGROUND

[0002] With the acceleration of the electrification and intelligentization of automobiles, the composite brake system with deep integration of in-wheel motors and electronic mechanical brakes (EMB) gradually becomes a new development focus. The in-wheel motor has the advantages of fast response and energy recovery, and the EMB has the advantages of fast response and reliability. How to coordinate the two to achieve high energy efficiency, high comfort and high safety of the brake process control is a difficult problem to be solved. Some scholars have carried out some brake force distribution optimization and compensation control research on the composite brake system of in-wheel motor and EMB, but they do not consider the particularity of the brake mode switching process in detail, and form a brake control scheme with high energy recovery and high comfort. There are the following problems: (1) The boundary of the in-wheel motor exiting and entering the feedback braking is too rough, and the maximization of the energy recovery rate cannot be realized.

[0003] (2) The control of the in-wheel motor exiting and entering the feedback braking process is ignored, and the smoothness and comfort of the brake mode switching in all working conditions cannot be guaranteed. SUMMARY

[0004] The present application aims at at least one of the problems in the related art.

[0005] To this end, the first object of the present application is to provide a brake process optimization method based on in-wheel motor and EMB.

[0006] The second object of the present application is to provide a brake process optimization system based on in-wheel motor and EMB.

[0007] The third object of the present application is to provide an electronic device.

[0008] The fourth object of the present application is to provide a computer readable storage medium.

[0009] The fifth object of the present application is to provide a computer program product.

[0010] To achieve the above objects, the first aspect of the present application provides a brake process optimization method based on in-wheel motor and EMB, comprising: Building a vehicle dynamics model.

[0011] Establishing a brake control strategy.

[0012] The design employs a parameter optimization strategy based on reinforcement learning, with braking intensity and speed as state variables, the speed threshold at which the hub motor begins to exit braking, the exit coefficient, and the entry coefficient as action variables, and the weighted sum of the braking energy recovery and braking comfort functions as the reward function.

[0013] Run the vehicle dynamics model, and train the agent using a reinforcement learning algorithm based on the braking control strategy until the reward function converges, thus obtaining the trained agent.

[0014] In one embodiment of the present invention, the vehicle dynamics model includes a hub motor model, an electromechanical brake model, a battery model, a tire model, and a vehicle longitudinal dynamics model.

[0015] The braking control strategy includes braking demand calculation, front-to-rear distribution of braking force, left-to-right distribution of braking force, and distribution of braking force between the hub motor and EMB using feedback factors.

[0016] In one embodiment of the present invention, the construction of the vehicle dynamics model includes: The in-wheel motor (IWM) model is simplified into a first-order inertial system to dynamically reflect the motor's torque response characteristics, expressed as:

[0017] In the formula, T I_act This represents the actual braking torque of the hub motor. T I The target braking torque for the hub motor; t I is the dynamic response constant of the IWM.

[0018] The electromechanical brake model EMB is simplified to a first-order system, and considering the hysteresis effect of EMB, its response process is considered equivalent to a first-order inertia plus a hysteresis element, expressed as:

[0019] In the formula, T E_act This represents the actual response torque of the EMB. T E The target braking torque for EMB; t E The dynamic response constant of the EMB; tau E This is the pure time delay of the EMB system.

[0020] The battery model is simplified to a circuit structure consisting of a voltage source and a battery internal resistance connected in series. When the vehicle is running, the battery power... P b With current Ib for:

[0021] In the formula, U b The voltage of the external load; U oc This is the open-circuit voltage of the battery; I b This refers to the internal current of the battery. R b This represents the internal resistance of the battery.

[0022] Battery SOC is expressed as:

[0023] In the formula, soc 0 represents the initial remaining battery power; Q nom This is the standard battery capacity; t f This is the battery's operational end point.

[0024] The longitudinal force characteristics of the tire model are described using the magic formula, expressed as:

[0025] In the formula, F x This refers to the longitudinal force of the tire; lambda denoted as wheel slip ratio; B, C, D, and E are the tire stiffness factor, shape factor, peak factor, and curvature factor, respectively.

[0026] Considering only longitudinal motion, the longitudinal dynamics of the vehicle are defined as follows:

[0027] In the formula, m For car quality; v This refers to the longitudinal speed of the vehicle. i =[1,2,3,4] represent the left front wheel, right front wheel, left rear wheel, and right rear wheel respectively; F w For air resistance; F f This refers to the rolling resistance of the tire. F s This is the slope resistance.

[0028] The dynamic model of a wheel is defined as follows:

[0029] In the formula, J The moment of inertia of the wheel; omega The wheel speed;R The radius of the wheel's rolling radius; F z The vertical force acting on the wheel is expressed as:

[0030] In the formula, a , b These are the distances from the front axle and rear axle to the center of mass, respectively. L Wheelbase; h g This is the distance from the center of mass to the ground.

[0031] By coupling the hub motor model, electromechanical brake model, battery model, tire model, and vehicle longitudinal dynamics model with signals and energy flow, the interaction relationship between the subsystems is established, forming a complete vehicle dynamics model.

[0032] In one embodiment of the present invention, establishing the braking control strategy includes: The required braking intensity and the total target braking force of the vehicle are calculated based on the brake pedal opening, and expressed as follows:

[0033] In the formula, S This refers to the brake pedal opening. z Braking strength; k s This is the conversion factor between braking intensity and brake pedal opening. F b As the overall driving force for the goal; G This refers to the total weight of the vehicle. r This is the effective radius of the wheel.

[0034] The target braking force is distributed to the front and rear axles according to the ideal front and rear wheel braking force distribution curve, and converted into the target braking torque of the front and rear axles, as expressed as:

[0035] In the formula, F R For the target braking force of the rear axle; F F For the front axle target braking force; h g The height of the center of mass; b This is the distance between the center of mass and the rear axle; T F The target braking torque for the front axle; T R The target braking torque for the rear axle.

[0036] The target braking torque is distributed to all four wheels according to the principle of equal distribution to the left and right wheels, as follows:

[0037] In the formula, T 1 represents the target braking torque for the left front wheel; T 2 represents the target braking torque for the right front wheel; T 3 represents the target braking torque for the left rear wheel; T 4 represents the target braking torque for the right rear wheel.

[0038] Calculate the feedback factor and use it to divide the target braking torque of each wheel into the hub motor target braking torque and the EMB target braking torque.

[0039] In one embodiment of the present invention, the calculation of the feedback factor, which uses the feedback factor to divide the target braking torque of each wheel into the hub motor target braking torque and the EMB target braking torque, includes: The maximum torque of the hub motor is related to the external characteristics of the hub motor and the battery charging power limit, expressed as:

[0040] In the formula, T Imax This represents the maximum torque of the hub motor; T cha The maximum braking torque, as shown by the external characteristics of the hub motor at different speeds, is obtained by looking up a table using the speed information. P max The maximum charging power of the battery is related to the battery temperature and the battery SOC. It can be obtained by looking up a table using the battery temperature and battery SOC information.

[0041] When the target braking torque of the hub motor does not exceed the maximum torque of the hub motor, it is expressed as:

[0042] In the formula, k This is a feedback factor.

[0043] When the target braking torque of the hub motor exceeds the maximum braking torque of the hub motor, it is supplemented by the EMB, as shown below:

[0044] In the formula, k As a feedback factor, i =[1,2,3,4] represent the left front wheel, right front wheel, left rear wheel, and right rear wheel, respectively.

[0045] In one embodiment of the present invention, the design is based on a parameter optimization strategy of reinforcement learning, using braking intensity and rotational speed as state variables, the rotational speed threshold at which the hub motor begins to exit braking, the exit coefficient, and the entry coefficient as action variables, and the weighted sum of the braking energy recovery and braking comfort functions as the reward function, including: Choosing braking intensity and rotational speed as state variables, it can be represented as follows:

[0046] Select the speed threshold at which the hub motor begins to disengage braking. n d1 Exit coefficient k Dec With the addition coefficient k Inc As an action variable, it is represented as:

[0047] In the formula, k Inc ∈[0,1]; k Dec ∈[0,1]; n d1 ∈[ n d2 , n max ], n d2 This is the speed threshold at which the hub motor stops and exits braking. n max This is the maximum speed of the hub motor.

[0048] Construct the reward function, expressed as:

[0049] In the formula, w 1. w 2 are the weighting functions for regenerative braking and braking comfort, respectively; j Impact level; eta reg Energy recovery rate, expressed as:

[0050] In the formula, n This refers to the rotational speed of the hub motor; eta To improve the efficiency of hub motor regenerative braking; v For vehicle speed; v 0 represents the initial braking speed; m For the overall vehicle weight; F w For air resistance; F fThis refers to the rolling resistance of the tire. F s This is the slope resistance.

[0051] The selected reinforcement learning algorithm includes a deep deterministic policy gradient algorithm, a flexible action-evaluation algorithm, and a dual-delay deep deterministic policy gradient algorithm.

[0052] To achieve the above objectives, a second aspect of the present invention provides a braking process optimization system based on a hub motor and an EMB, comprising: The vehicle dynamics model is used to receive and track the target braking torque from the hub motor and EMB issued by the braking control module, and transmits sensor data including brake pedal opening, wheel speed, battery SOC, and battery temperature to the perception module.

[0053] The sensing module processes the sensor data to obtain the brake pedal opening, wheel speed, battery SOC, and battery temperature, and transmits them to the brake control module and parameter optimization module.

[0054] The braking control module receives information from the sensing module regarding brake pedal opening, wheel speed, battery SOC, and battery temperature, and receives optimized motion variables from the parameter optimization module. It then calculates the total target braking force and distributes it to the hub motors and EMBs of each wheel.

[0055] The parameter optimization module receives information on brake pedal opening, wheel speed, battery SOC, and battery temperature from the perception module, trains the agent using a reinforcement learning algorithm until the reward function converges, obtains the optimal value of the action variables, and then transmits the action variables to the braking control module.

[0056] To achieve the above objectives, a third aspect of the present invention provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of the first aspects.

[0057] To achieve the above objectives, a fourth aspect of the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of the first aspects.

[0058] To achieve the above objectives, a fifth aspect of the present invention provides a computer program product that, when executed by a processor, implements the method described in any one of the first aspects.

[0059] The technical solutions provided by the embodiments of the present invention bring at least the following beneficial effects: By dynamically optimizing the speed threshold and adjustment coefficient for in-wheel motor braking engagement / disengagement using reinforcement learning algorithms, energy recovery efficiency is significantly improved (estimated to increase by 10%-20%) while ensuring braking safety. Simultaneously, a weighted reward function smooths the torque switching process, effectively reducing impact and improving ride comfort. Through closed-loop interaction between a high-precision vehicle dynamics model and real-time sensor data, the torque coordination challenge between the in-wheel motor and EMB during mode switching is resolved. This fully leverages the efficiency of regenerative braking from the in-wheel motor while ensuring braking reliability through the EMB, adapting to all operating conditions from gentle urban braking to high-intensity braking. The system possesses adaptive optimization capabilities and can integrate future EMB mass production technologies, providing core technical support for precise control and energy management of chassis systems in intelligent driving scenarios, and driving the iteration of new energy vehicles towards energy conservation and intelligence.

[0060] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0061] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: figure 1 This is a flowchart illustrating a braking process optimization method based on a hub motor and EMB provided in an embodiment of the present invention. figure 2 This is a flowchart illustrating a feedback factor calculation method based on a hub motor and EMB, provided in an embodiment of the present invention.

[0062] figure 3 A schematic diagram of a braking process optimization system based on a hub motor and EMB provided in an embodiment of the present invention; Detailed Implementation Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0063] This invention develops a braking process optimization method based on hub motor and EMB, enabling the two to work in coordination, reducing the impact of braking mode switching and improving braking smoothness while ensuring high energy recovery rate, so as to give full play to the unique advantages of hub motor and EMB.

[0064] The hybrid braking system based on in-wheel motors and EMB (Electronic Braking System) has broad application prospects in the field of new energy vehicles. Its braking process control scheme can significantly improve braking performance, energy recovery efficiency, and driving smoothness. The in-wheel motor provides fast-response regenerative braking, while the EMB system ensures reliable braking. Their coordinated control can optimize energy recovery under urban driving conditions while meeting high-intensity braking requirements. The braking process control method based on in-wheel motors and EMB can effectively solve the impact problem during the switching process between in-wheel motors and EMB, based on high energy recovery. With the accelerated mass production of EMB, the hybrid braking system based on in-wheel motors and EMB will play a core role in intelligent driving and integrated chassis control, and is expected to improve braking energy recovery rate by 10%-20%, providing important technical support for the energy-saving, environmentally friendly, and intelligent development of new energy vehicles.

[0065] figure 1 This is a schematic flowchart illustrating a braking process optimization method based on a hub motor and EMB, provided in an embodiment of the present invention. figure 1 As shown, the method includes the following steps: S1, Build the vehicle dynamics model.

[0066] The vehicle dynamics model includes the hub motor model, electromechanical brake model, battery model, tire model, and overall vehicle longitudinal dynamics model.

[0067] Specifically, step S1 is performed through the following steps: In this embodiment of the invention, the in-wheel motor model IWM is simplified into a first-order inertial system to dynamically reflect the torque response characteristics of the motor, as follows:

[0068] In the formula, T I_act This represents the actual braking torque of the hub motor. T I The target braking torque for the hub motor; t I is the dynamic response constant of the IWM.

[0069] The electromechanical brake model EMB is simplified to a first-order system, and considering the hysteresis effect of EMB, its response process is considered equivalent to a first-order inertia plus a hysteresis element, expressed as:

[0070] In the formula, T E_act This represents the actual response torque of the EMB. T E The target braking torque for EMB; t EThe dynamic response constant of the EMB; tau E This is the pure time delay of the EMB system.

[0071] The battery model was then simplified into a circuit structure consisting of a voltage source and a battery internal resistance connected in series. When the vehicle is running, the battery power... P b With current I b for:

[0072] In the formula, U b The voltage of the external load; U oc This is the open-circuit voltage of the battery; I b This refers to the internal current of the battery. R b This represents the internal resistance of the battery.

[0073] Battery SOC is expressed as:

[0074] In the formula, soc 0 represents the initial remaining battery power; Q nom This is the standard battery capacity; t f This is the battery's operational end point.

[0075] In this embodiment of the invention, the longitudinal force characteristics of the tire model are described using the magic formula, expressed as:

[0076] In the formula, F x This refers to the longitudinal force of the tire; lambda denoted as wheel slip ratio; B, C, D, and E are the tire stiffness factor, shape factor, peak factor, and curvature factor, respectively.

[0077] Considering only longitudinal motion, the longitudinal dynamics of the vehicle are defined as follows:

[0078] In the formula, m For car quality; v This refers to the longitudinal speed of the vehicle. i =[1,2,3,4] represent the left front wheel, right front wheel, left rear wheel, and right rear wheel respectively; F w For air resistance; F fThis refers to the rolling resistance of the tire. F s This is the slope resistance.

[0079] The dynamic model of a wheel is defined as follows:

[0080] In the formula, J The moment of inertia of the wheel; omega The wheel speed; R The radius of the wheel's rolling radius; F z The vertical force acting on the wheel is expressed as:

[0081] In the formula, a , b These are the distances from the front axle and rear axle to the center of mass, respectively. L Wheelbase; h g This is the distance from the center of mass to the ground.

[0082] By coupling the hub motor model, electromechanical brake model, battery model, tire model, and vehicle longitudinal dynamics model with signals and energy flow, the interaction relationship between the subsystems is established, forming a complete vehicle dynamics model.

[0083] S2, Establish braking control strategy.

[0084] The braking control strategy includes braking demand calculation, front-to-rear distribution of braking force, left-to-right distribution of braking force, and distribution of in-wheel motor and EMB braking force using feedback factors.

[0085] Specifically, step S2 is performed through the following steps: In this embodiment of the invention, the required braking intensity and the total target braking force of the vehicle are calculated based on the brake pedal opening, as expressed as:

[0086] In the formula, S This refers to the brake pedal opening. z Braking strength; k s This is the conversion factor between braking intensity and brake pedal opening. F b As the overall driving force for the goal; G This refers to the total weight of the vehicle. r This is the effective radius of the wheel.

[0087] Next, the target braking force is distributed to the front and rear axles according to the ideal front and rear wheel braking force distribution curve, and converted into target braking torque for the front and rear axles, as follows:

[0088] In the formula, F R For the target braking force of the rear axle; F F For the front axle target braking force; h g The height of the center of mass; b This is the distance between the center of mass and the rear axle; T F The target braking torque for the front axle; T R The target braking torque for the rear axle.

[0089] Then, the target braking torque is distributed to all four wheels according to the principle of equal distribution to the left and right wheels, as shown below:

[0090] In the formula, T 1 represents the target braking torque for the left front wheel; T 2 represents the target braking torque for the right front wheel; T 3 represents the target braking torque for the left rear wheel; T 4 represents the target braking torque for the right rear wheel.

[0091] In this embodiment of the invention, a feedback factor is calculated, and the target braking torque of each wheel is divided into the target braking torque of the hub motor and the target braking torque of the EMB using the feedback factor.

[0092] It should be understood that the feedback factor is a parameter used in reinforcement learning to adjust the weight of the reward signal. Its core function is to balance the agent's immediate and long-term gains. By weighting the rewards at different times, it prevents the agent from pursuing only short-term interests and ignoring the global optimum. At the same time, it affects the learning speed and policy stability. It is commonly used in reinforcement learning applications such as autonomous driving and robot control.

[0093] The calculation of the feedback factor includes the following steps: (1) The maximum torque of the hub motor is related to the external characteristics of the hub motor and the battery charging power limit, and is expressed as:

[0094] In the formula, T Imax This represents the maximum torque of the hub motor; T cha The maximum braking torque, as shown by the external characteristics of the hub motor at different speeds, is obtained by looking up a table using the speed information. P max The maximum charging power of the battery is related to the battery temperature and the battery SOC. It can be obtained by looking up a table using the battery temperature and battery SOC information.

[0095] (2) When the target braking torque of the hub motor does not exceed the maximum torque of the hub motor, it is expressed as:

[0096] In the formula, k This is a feedback factor.

[0097] (3) When the target braking torque of the hub motor exceeds the maximum braking torque of the hub motor, it is supplemented by the EMB, as shown below:

[0098] In the formula, k As a feedback factor, i =[1,2,3,4] represent the left front wheel, right front wheel, left rear wheel, and right rear wheel, respectively.

[0099] S3. A parameter optimization strategy based on reinforcement learning is designed, with braking intensity and speed as state variables, the speed threshold at which the hub motor begins to exit braking, the exit coefficient, and the entry coefficient as action variables, and the weighted sum of the braking energy recovery and braking comfort functions as the reward function.

[0100] It's important to note that the reward function is the core mechanism of reinforcement learning. Its main function is to guide the agent's learning by quantifying reward and punishment signals. Positive rewards are given for behaviors that align with the task objectives, while penalties are imposed for violations or invalid behaviors. This allows the agent to autonomously explore and optimize its decisions through continuous interaction, ultimately learning the optimal behavioral strategy. This approach is widely used in scenarios such as autonomous driving and robot control.

[0101] Specifically, step S3 is performed through the following steps: First, braking intensity and rotational speed are selected as state variables, represented as follows:

[0102] Select the speed threshold at which the hub motor begins to disengage braking. n d1 Exit coefficient k Dec With the addition coefficient k Inc As an action variable, it is represented as:

[0103] In the formula, k Inc ∈[0,1]; k Dec ∈[0,1]; n d1 ∈[ n d2, n max ], n d2 This is the speed threshold at which the hub motor stops and exits braking. n max This is the maximum speed of the hub motor.

[0104] Next, the reward function is constructed, expressed as:

[0105] In the formula, w 1. w 2 are the weighting functions for regenerative braking and braking comfort, respectively; j Impact level; eta reg Energy recovery rate, expressed as:

[0106] In the formula, n This refers to the rotational speed of the hub motor; eta To improve the efficiency of hub motor regenerative braking; v For vehicle speed; v 0 represents the initial braking speed; m For the overall vehicle weight; F w For air resistance; F f This refers to the rolling resistance of the tire. F s This is the slope resistance.

[0107] The selected reinforcement learning algorithm includes a deep deterministic policy gradient algorithm, a flexible action-evaluation algorithm, and a dual-delay deep deterministic policy gradient algorithm.

[0108] S4. Run the vehicle dynamics model and train the agent using a reinforcement learning algorithm based on the braking control strategy until the reward function converges, thus obtaining the trained agent.

[0109] To achieve the above embodiments, the present invention also proposes a method for calculating the feedback factor based on the hub motor and EMB. figure 2 This is a flowchart illustrating a feedback factor calculation method based on a hub motor and EMB, provided as an embodiment of the present invention. The method includes: (1) In step S1, the speed threshold for the hub motor to stop braking is selected according to the required braking intensity. n d2 and the speed threshold at which braking begins n u1 For efficient feedback, the rotational speed corresponding to the contour line of 50% feedback efficiency of the wheel hub motor was selected as the [reform rate].n d2 ,Will n d2 A positive offset of 20 r / min is used as the speed threshold for the hub motor to begin disengaging from braking. n d1 The initial value. To avoid frequent opening and closing of the regenerative braking, the initial value will be... n d1 Positive offset of 30 r / min as n u1 .

[0110] (2) In step S2, initialize the feedback factor. k The value is 1. When the speed is lower than n d1 At that time, the hub motor gradually disengages from the braking process until... k A value of 0 indicates:

[0111] In the formula, k As a feedback factor; k Dec This is the exit coefficient.

[0112] When the speed is higher n u1 At that time, the hub motor gradually engages in the braking process until... k A value of 1 is represented as:

[0113] In the formula, k Inc This is the coefficient to be added.

[0114] To achieve the above embodiments, the present invention also proposes a braking process optimization system based on hub motor and EMB. figure 3 This is a schematic diagram of a braking process optimization system based on a hub motor and EMB, provided as an embodiment of the present invention. figure 3 As shown, the system includes: The vehicle dynamics model is used to receive and track the target braking torque from the hub motor and EMB issued by the braking control module, and transmits sensor data including brake pedal opening, wheel speed, battery SOC, and battery temperature to the perception module.

[0115] The sensing module processes the sensor data to obtain the brake pedal opening, wheel speed, battery SOC, and battery temperature, and transmits them to the brake control module and parameter optimization module.

[0116] The braking control module receives information from the sensing module regarding brake pedal opening, wheel speed, battery SOC, and battery temperature, and receives optimized motion variables from the parameter optimization module. It then calculates the total target braking force and distributes it to the hub motors and EMBs of each wheel.

[0117] The parameter optimization module receives information on brake pedal opening, wheel speed, battery SOC, and battery temperature from the perception module, trains the agent using a reinforcement learning algorithm until the reward function converges, obtains the optimal value of the action variables, and then transmits the action variables to the braking control module.

[0118] Regarding the system in the above embodiments, the specific ways in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0119] To implement the above embodiments, the present invention also proposes an electronic device, comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory to implement the method provided in the foregoing embodiments.

[0120] To implement the above embodiments, the present invention also proposes a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the methods provided in the foregoing embodiments.

[0121] To implement the above embodiments, the present invention also proposes a computer program product, including a computer program that, when executed by a processor, implements the methods provided in the foregoing embodiments.

[0122] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in this invention all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0123] It should be noted that personal information collected from users should be used for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. Furthermore, such collection / sharing should only be conducted after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign an agreement / authorization that includes authorization of relevant user information before the user uses the function. In addition, any necessary steps must be taken to protect and safeguard access to such personal information data and ensure that others with access to personal information data comply with their privacy policies and procedures.

[0124] This invention is intended to provide implementation schemes for users to selectively prevent the use or access to personal information data. That is, this disclosure is intended to provide hardware and / or software to prevent or block access to such personal information data. Once personal information data is no longer needed, risks can be minimized by restricting data collection and deleting data. Furthermore, where applicable, such personal information can be de-identified to protect user privacy.

[0125] In the foregoing descriptions of the embodiments, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0126] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0127] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of the invention pertain.

[0128] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0129] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any of the following techniques known in the art, or a combination thereof: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0130] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0131] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0132] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

[0133] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0134] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A braking process optimization method based on hub motor and EMB, characterized in that, include: Build a vehicle dynamics model; Establish a braking control strategy; The design employs a parameter optimization strategy based on reinforcement learning, with braking intensity and speed as state variables, the speed threshold at which the hub motor begins to exit braking, the exit coefficient, and the entry coefficient as action variables, and the weighted sum of the braking energy recovery and braking comfort functions as the reward function. Run the vehicle dynamics model, and train the agent using a reinforcement learning algorithm based on the braking control strategy until the reward function converges, thus obtaining the trained agent.

2. The method according to claim 1, characterized in that, The vehicle dynamics model includes a hub motor model, an electromechanical brake model, a battery model, a tire model, and a longitudinal dynamics model of the entire vehicle. The braking control strategy includes braking demand calculation, front-to-rear distribution of braking force, left-to-right distribution of braking force, and distribution of braking force between the hub motor and EMB using feedback factors.

3. The method according to claim 2, characterized in that, The construction of the vehicle dynamics model includes: The in-wheel motor (IWM) model is simplified into a first-order inertial system to dynamically reflect the motor's torque response characteristics, expressed as: In the formula, T I_act This represents the actual braking torque of the hub motor. T I The target braking torque for the hub motor; t I is the dynamic response constant of the IWM; The electromechanical brake model EMB is simplified to a first-order system, and considering the hysteresis effect of EMB, its response process is considered equivalent to a first-order inertia plus a hysteresis element, expressed as: In the formula, T E_act This represents the actual response torque of the EMB. T E The target braking torque for EMB; t E The dynamic response constant of the EMB; τ E This refers to the pure time delay of the EMB system. The battery model is simplified to a circuit structure consisting of a voltage source and a battery internal resistance connected in series. When the vehicle is running, the battery power... P b With current I b for: In the formula, U b The voltage of the external load; U oc This is the open-circuit voltage of the battery; I b This refers to the internal current of the battery. R b This is the internal resistance of the battery; Battery SOC is expressed as: In the formula, SOC 0 represents the initial remaining battery power; Q nom This is the standard battery capacity; t f This is the battery's operational end point; The longitudinal force characteristics of the tire model are described using the magic formula, expressed as: In the formula, F x This refers to the longitudinal force of the tire; λ denoted as wheel slip ratio; B, C, D, and E are the tire stiffness factor, shape factor, peak factor, and curvature factor, respectively. Considering only longitudinal motion, the longitudinal dynamics of the vehicle are defined as follows: In the formula, m For car quality; v This refers to the longitudinal speed of the vehicle. i =[1,2,3,4] represent the left front wheel, right front wheel, left rear wheel, and right rear wheel respectively; F w For air resistance; F f This refers to the rolling resistance of the tire. F s For slope resistance; The dynamic model of a wheel is defined as follows: In the formula, J The moment of inertia of the wheel; ω The wheel speed; R The radius of the wheel's rolling radius; F z The vertical force acting on the wheel is expressed as: In the formula, a , b These are the distances from the front axle and rear axle to the center of mass, respectively. L Wheelbase; h g This is the distance from the center of mass to the ground. By coupling the hub motor model, electromechanical brake model, battery model, tire model, and vehicle longitudinal dynamics model with signals and energy flow, the interaction relationship between the subsystems is established, forming a complete vehicle dynamics model.

4. The method according to claim 3, characterized in that, The established braking control strategy includes: The required braking intensity and the total target braking force of the vehicle are calculated based on the brake pedal opening, and expressed as follows: In the formula, S This refers to the brake pedal opening. z Braking strength; k s This is the conversion factor between braking intensity and brake pedal opening. F b As the overall driving force for the goal; G This refers to the total weight of the vehicle. r The effective radius of the wheel; The target braking force is distributed to the front and rear axles according to the ideal front and rear wheel braking force distribution curve, and converted into the target braking torque of the front and rear axles, as expressed as: In the formula, F R For the target braking force of the rear axle; F F For the front axle target braking force; h g The height of the center of mass; b This is the distance between the center of mass and the rear axle; T F The target braking torque for the front axle; T R The target braking torque for the rear axle; The target braking torque is distributed to all four wheels according to the principle of equal distribution to the left and right wheels, as follows: In the formula, T 1 represents the target braking torque for the left front wheel; T 2 represents the target braking torque for the right front wheel; T 3 represents the target braking torque for the left rear wheel; T 4 represents the target braking torque for the right rear wheel; Calculate the feedback factor and use it to divide the target braking torque of each wheel into the hub motor target braking torque and the EMB target braking torque.

5. The method according to claim 4, characterized in that, The calculated feedback factor is used to divide the target braking torque of each wheel into the hub motor target braking torque and the EMB target braking torque, including: The maximum torque of the hub motor is related to the external characteristics of the hub motor and the battery charging power limit, expressed as: In the formula, T Imax This represents the maximum torque of the hub motor; T cha The maximum braking torque, as shown by the external characteristics of the hub motor at different speeds, is obtained by looking up a table using the speed information. P max The maximum charging power of the battery is related to the battery temperature and the battery SOC. It can be obtained by looking up a table using the battery temperature and battery SOC information. When the target braking torque of the hub motor does not exceed the maximum torque of the hub motor, it is expressed as: In the formula, k As a feedback factor; When the target braking torque of the hub motor exceeds the maximum braking torque of the hub motor, it is supplemented by the EMB, as shown below: In the formula, k As a feedback factor, i =[1,2,3,4] represent the left front wheel, right front wheel, left rear wheel, and right rear wheel, respectively.

6. The method according to claim 5, characterized in that, The design is based on a parameter optimization strategy using reinforcement learning. Braking intensity and rotational speed are used as state variables; the rotational speed threshold at which the hub motor begins to disengage braking, the disengagement coefficient, and the entry coefficient are used as action variables; and the weighted sum of the regenerative braking and braking comfort functions is used as the reward function. This includes: Choosing braking intensity and rotational speed as state variables, it can be represented as follows: Select the speed threshold at which the hub motor begins to disengage braking. n d1 Exit coefficient k Dec With the addition coefficient k Inc As an action variable, it is represented as: In the formula, k Inc ∈[0,1]; k Dec ∈[0,1]; n d1 ∈[ n d2 , n max ], n d2 This is the speed threshold at which the hub motor stops and exits braking. n max This is the maximum speed of the hub motor; Construct the reward function, expressed as: In the formula, w 1. w 2 are the weighting functions for regenerative braking and braking comfort, respectively; j Impact level; η reg Energy recovery rate, expressed as: In the formula, n This refers to the rotational speed of the hub motor; η To improve the efficiency of hub motor regenerative braking; v For vehicle speed; v 0 represents the initial braking speed; m For the overall vehicle weight; F w For air resistance; F f This refers to the rolling resistance of the tire. F s For slope resistance; The selected reinforcement learning algorithm includes a deep deterministic policy gradient algorithm, a flexible action-evaluation algorithm, and a dual-delay deep deterministic policy gradient algorithm.

7. A braking process optimization system based on hub motor and EMB, characterized in that, include: The vehicle dynamics model is used to receive and track the target braking torque from the hub motor and EMB sent by the braking control module, and to transmit sensor data including brake pedal opening, wheel speed, battery SOC, and battery temperature to the perception module. The sensing module is used to process the sensor data to obtain the brake pedal opening, wheel speed, battery SOC, and battery temperature, and transmit them to the brake control module and parameter optimization module. The braking control module is used to receive information on brake pedal opening, wheel speed, battery SOC, and battery temperature from the sensing module, and to receive optimized action variables from the parameter optimization module, calculate the total target braking force, and distribute it to the hub motors and EMBs of each wheel. The parameter optimization module receives information on brake pedal opening, wheel speed, battery SOC, and battery temperature from the perception module, trains the agent using a reinforcement learning algorithm until the reward function converges, obtains the optimal value of the action variables, and then transmits the action variables to the braking control module.

8. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1-6.

Images