Vehicle ABS parameter optimization system and method oriented to multiple working conditions

Abstract

The invention discloses a multi-working-condition-oriented vehicle ABS parameter optimization system and method. The method comprises the steps that vehicle and road condition information is obtained through a fusion algorithm and information of all sensors; aBS parameters and a double-agent strategy network are initialized; identifying a road surface type according to the vehicle and road condition information; the double intelligent agents output influence factors of a wheel target slip rate and parameters of the slip rate tracking controller, the slip rate tracking controller calculates and issues target braking force, and the actuator executes a control instruction; calculating a reward of the action of the double agents; and optimizing the double-agent strategy network according to the rewards and the acquired real-time data. The ABS control parameters can be adjusted in a self-adaptive mode according to various working conditions, the braking performance is improved, the braking distance is shortened, and the phenomenon that a vehicle is out of control or wheels are locked is effectively avoided.

Description

Technical Field

[0001] The present invention relates to the field of vehicle braking technology, and in particular to a vehicle ABS parameter optimization system and method for multiple working conditions. Background Art

[0002] The vehicle anti-lock braking system prevents wheel lock by controlling the slip rate, ensuring braking stability and control of the driving direction. However, the parameters of the existing anti-lock braking system controller are no longer adjusted after manual calibration, and the impact of different road types and braking conditions on system performance is not fully considered. This method has the following defects:

[0003] (1) The target slip rate cannot change with the road surface type: The road adhesion coefficient and wheel state change significantly under different road surface types (such as dry road surface, wet road surface, icy road surface). The optimal target slip rate should change dynamically with the change of road surface type.

[0004] (2) Controller parameters cannot adapt to changes in operating conditions: Under different operating conditions, the response speed of the controller with fixed parameters to the slip rate varies. The response lag under certain conditions may lead to increased braking distance or vehicle loss of control.

[0005] (3) Manual calibration is time-consuming: Traditional ABS controller parameters require the use of a large amount of experimental data for parameter calibration, which has a long debugging cycle and poor adaptability.

[0006] Therefore, it is urgent to develop a technology that can dynamically optimize ABS parameters according to different working conditions, so that the ABS system has adaptive capabilities and performs well under different working conditions. Summary of the invention

[0007] The present invention aims to solve one of the technical problems in the related art at least to a certain extent.

[0008] To this end, the present invention proposes a vehicle ABS parameter optimization system for multiple working conditions, which can dynamically optimize system parameters according to the working conditions and improve the braking performance of the vehicle under different road conditions.

[0009] Another object of the present invention is to provide a vehicle ABS parameter optimization method for multiple working conditions.

[0010] To achieve the above-mentioned purpose, the present invention proposes a vehicle ABS parameter optimization system for multiple working conditions, including an information collection module, a road type recognition module, a slip rate tracking module, a parameter optimization module and an execution module; wherein,

[0011] The information acquisition module is used to process the measured signal and send it to the road type identification module, the slip rate tracking module and the parameter optimization module;

[0012] The road surface type identification module is used to identify the road surface type information based on the combined sensing information sent by the information acquisition module, and send it to the parameter optimization module;

[0013] The parameter optimization module is used to calculate the braking distance and slip rate tracking error based on the road type information sent by the road type identification module and the combined sensor information sent by the information acquisition module, and use them as feedback on the vehicle braking performance, and calculate the target slip rate influencing factor and controller parameters;

[0014] The slip rate tracking module is used to calculate the actual slip rate according to the combined sensing information sent by the information acquisition module, and calculate the required target braking force according to the target slip rate influencing factor and controller parameters sent by the parameter optimization module, and send it to the execution module;

[0015] The execution module is used to receive and execute the target braking force command sent by the slip rate tracking module;

[0016] The parameter optimization module is also used to obtain the optimal values ​​of the target slip rate influencing factor and the controller parameters through iterative training.

[0017] The vehicle ABS parameter optimization system for multiple working conditions according to the embodiment of the present invention may also have the following additional technical features:

[0018] In one embodiment of the present invention, the information acquisition module includes multiple types of cameras, radars, inertial measurement units, wheel speed sensors, wheel steering angle sensors, tire noise sensors, and tire pressure sensors.

[0019] To achieve the above object, the present invention further provides a vehicle ABS parameter optimization method for multiple working conditions, comprising:

[0020] The combined sensing information is filtered and fused to obtain vehicle dynamic parameters, and the actual longitudinal speed, slip rate and utilized adhesion coefficient of each wheel are calculated based on the vehicle dynamic parameters;

[0021] Use fusion algorithms and information from various sensors to obtain vehicle and road condition information;

[0022] Initialize ABS parameters and dual-agent strategy network;

[0023] Identify road surface type based on vehicle and road condition information;

[0024] Based on the road surface type, the dual agent outputs the influencing factor of the wheel target slip rate and the parameters of the slip rate tracking controller, the slip rate tracking controller calculates and sends the target braking force, and the actuator executes the control instruction;

[0025] Calculate rewards for dual-agent actions;

[0026] Optimize the two-agent policy network based on rewards and acquired real-time data.

[0027] The vehicle ABS parameter optimization system and method for multiple working conditions of the embodiment of the present invention utilizes working condition identification and artificial intelligence algorithms to adjust the target slip rate and optimize the ABS controller parameters.

[0028] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0030] Figure 1 is a structural schematic diagram of a vehicle ABS parameter optimization system for multiple working conditions according to an embodiment of the present invention;

[0031] Figure 2 It is a flow chart of a vehicle ABS parameter optimization method for multiple working conditions according to an embodiment of the present invention. DETAILED DESCRIPTION

[0032] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0033] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme 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 only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0034] A vehicle ABS parameter optimization system and method for multiple working conditions proposed according to an embodiment of the present invention will be described below with reference to the accompanying drawings.

[0035] Figure 1 A vehicle ABS parameter optimization system for multiple working conditions according to an embodiment of the present invention is provided. Figure 1 As shown, it includes an information collection module, a road type identification module, a slip rate tracking module, a parameter optimization module and an execution module; wherein,

[0036] The information collection module includes a camera, a radar, an inertial measurement unit, a wheel speed sensor, a wheel steering angle sensor, a tire noise sensor, a tire pressure sensor, etc. The measured signal is processed and transmitted to the road type recognition module, the slip rate tracking module and the parameter optimization module.

[0037] The road surface type identification module receives the combined sensing information transmitted by the information acquisition module, identifies the road surface type, and transmits it to the parameter optimization module.

[0038] The parameter optimization module receives the road type information transmitted by the road type identification module, receives the combined sensor information transmitted by the information acquisition module, calculates the braking distance and slip rate tracking error, and uses them as feedback on the vehicle braking performance, obtains the optimal values ​​of the target slip rate influencing factor and the controller parameters through iterative training, and transmits them to the slip rate tracking module.

[0039] The slip rate tracking module receives the combined sensing information transmitted by the information acquisition module, calculates the actual slip rate, receives the target slip rate influencing factor and controller parameters transmitted by the parameter optimization module, calculates the required target braking force, and transmits it to the execution module.

[0040] The execution module is a braking system that receives and executes the target braking force command issued by the slip rate tracking module.

[0041] According to the vehicle ABS parameter optimization system for multiple working conditions of the embodiment of the present invention, the working condition recognition and artificial intelligence algorithm are used to adjust the target slip rate and optimize the ABS controller parameters. The method can adaptively adjust the ABS control parameters according to multiple working conditions, improve the braking performance, shorten the braking distance, and effectively avoid vehicle loss of control or wheel locking.

[0042] In order to implement the above embodiment, Figure 2 As shown, this embodiment also provides a vehicle ABS parameter optimization method for multiple working conditions, including:

[0043] S1, using fusion algorithm and information from various sensors to obtain vehicle and road condition information;

[0044] S2, initialize ABS parameters and dual-agent strategy network;

[0045] S3, identifying the road type according to the vehicle and road condition information;

[0046] S4, based on the road type, the dual agent outputs the influencing factor of the wheel target slip rate and the parameters of the slip rate tracking controller, the slip rate tracking controller calculates and sends the target braking force, and the actuator executes the control instruction;

[0047] S5, calculates the rewards of the dual-agent actions;

[0048] S6, optimizes the dual-agent policy network based on rewards and acquired real-time data.

[0049] In one embodiment of the present invention, the fusion algorithm and the information from each sensor are used to obtain vehicle and road condition information, including vehicle speed v, wheel speed n, wheel steering angle δ, vehicle tire noise characteristic Δ, tire pressure p, wheel-road adhesion coefficient Etc. And calculate the wheel slip rate s.

[0050] s=(v-nr) / v

[0051] Where r is the wheel radius.

[0052] In one embodiment of the present invention, initial values ​​of the factors affecting the target wheel slip rate, such as the wheel longitudinal speed, steering angle, road adhesion coefficient and road type, are randomly given, and the initial value of the target wheel slip rate is calculated according to the following formula and is limited to between 0.1 and 0.3.

[0053]

[0054] Where o is the target wheel slip rate; λ, ε, η are the factors affecting the target wheel slip rate, respectively, by the longitudinal speed of the wheel, the steering angle, and the road adhesion coefficient; ξ j is the influence factor of road surface type on the target wheel slip rate, and j is the code of the road surface type.

[0055] The PID algorithm is used as the slip tracking controller, and the controller parameter k is randomly given. P , k I , k D The initial value of .

[0056] Randomly initialize the policy networks of the first agent and the second agent.

[0057] Among them, the first intelligent agent is used to optimize the influencing factors of the target slip rate.

[0058] The second agent is used to optimize the parameters of the slip tracking controller.

[0059] Among them, the state space of the first agent is defined as The action space is defined as {λ,ε,η,ξ j}, the reward function is designed as {-a1L-a2[(o>0.5)|(o<0)]}. Among them, v0 is the initial braking speed; L is the braking distance; a1 is the braking distance penalty function; a2 is the penalty function for the target slip rate exceeding the normal range.

[0060] The state space of the second agent is defined as The action space is defined as {k P ,k I ,k D}, the reward function is designed as {-b1|Δd|-b2ΔF b}. Where d is the slip tracking error; Δd is the rate of change of the slip tracking error; F b is the wheel braking force; ΔF b is the rate of change of wheel braking force; b1 is the tracking error penalty function; b2 is the frequent adjustment penalty coefficient.

[0061] Among them, the first agent and the second agent both include but are not limited to the Deep Deterministic Policy Gradient (DDPG) algorithm, the Twin Delayed DDPG (TD3) algorithm, and the Soft Actor-Critic (SAC) algorithm.

[0062] In one embodiment of the present invention, when the vehicle speed and tire pressure are constant, the tire noise characteristics of the vehicle when driving on different roads are different. The road type is identified according to the vehicle speed, tire pressure and the tire noise characteristics of the vehicle.

[0063] Among them, the vehicle tire noise characteristics include but are not limited to the main sound frequency and decibel.

[0064] Among them, road surface types include but are not limited to dry road surface, wet road surface, icy and snowy road surface, and gravel road surface.

[0065] In one embodiment of the present invention, the dual agent selects an action (i.e., outputs the influencing factor of the target wheel slip rate and the parameter of the slip rate tracking controller), the slip rate tracking controller calculates and sends the target braking force, and the actuator executes the control instruction, including:

[0066] Real-time acquisition of the road type, initial braking speed, braking distance, slip tracking error d, slip tracking error change rate Δd, wheel braking force change rate ΔF of the current braking process b And other data.

[0067] The first agent based on the current state Select an action {λ,ε,η,ξ j}(i.e. adjust and output λ, ε, η, ξ j ), and then calculate the target wheel slip rate.

[0068] The second agent is based on the current state Select action {k P ,k I ,k D}(i.e. adjust and output k P, k I , k D ).

[0069] The slip rate tracking controller calculates and sends the target braking force based on the target wheel slip rate, controller parameters and the current actual slip rate. The actuator executes the control command and the vehicle enters the braking process.

[0070] In one embodiment of the present invention, the reward of an action is calculated:

[0071] Calculate the reward for the first agent’s action {-a1L-a2[(o>0.5)|(o<0)]}.

[0072] Calculate the reward for the second agent's action {-b1|Δd|-b2ΔF b}.

[0073] In one embodiment of the present invention, the policy network is updated based on the rewards and the acquired real-time data to optimize the action selection strategy.

[0074] In one embodiment of the present invention, S3 to S6 are repeated until the reward function gradually converges, the training is terminated, and the optimal values ​​of the wheel target slip rate influencing factor and the slip rate tracking controller parameters are obtained. When the vehicle enters a new operating condition, or the braking performance is unstable, or the ABS parameters are not updated for a certain period of time, retraining is carried out, and S3 to S6 are repeated until the braking performance is stable, and the optimal values ​​of the wheel target slip rate influencing factor and the slip rate tracking controller parameters are updated.

[0075] In summary, in recent years, vehicles are developing rapidly towards electrification, intelligence, and unmanned operation. With the rapid advancement of chassis-by-wire technology and autonomous driving technology, the uncertainty of vehicle driving conditions has greatly increased. As the carrier of upper-level technologies such as autonomous driving, the adaptability of the vehicle chassis to dynamic environments is becoming increasingly important, especially in terms of braking safety under complex road conditions. The implementation of this multi-condition ABS parameter optimization method can significantly improve the braking performance of the vehicle under various conditions, especially providing important safety guarantees for vehicle occupants and the vehicle body under extreme conditions such as emergency braking, slippery or icy roads.

[0076] The vehicle ABS parameter optimization method for multiple working conditions according to the embodiment of the present invention is a method for optimizing the parameters of the intelligent vehicle anti-lock braking system for multiple road types such as ice and snow, wet and slippery, and dry roads and multiple driving conditions such as forward, reverse, and steering. The working condition identification and artificial intelligence algorithm are used to adjust the target slip rate and optimize the ABS controller parameters. The method can adaptively adjust the ABS control parameters according to multiple working conditions, improve the braking performance, shorten the braking distance, and effectively avoid vehicle loss of control or wheel locking.

[0077] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0078] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

Claims

1. A vehicle ABS parameter optimization system for multiple working conditions, characterized in that: It includes information collection module, road type identification module, slip rate tracking module, parameter optimization module and execution module; among which, The information acquisition module is used to process the measured signal and send it to the road type identification module, the slip rate tracking module and the parameter optimization module; The road surface type identification module is used to identify the road surface type information based on the combined sensing information sent by the information acquisition module, and send it to the parameter optimization module; The parameter optimization module is used to calculate the braking distance and slip rate tracking error based on the road type information sent by the road type identification module and the combined sensor information sent by the information acquisition module, and use them as feedback on the vehicle braking performance, and calculate the target slip rate influencing factor and controller parameters; The slip rate tracking module is used to calculate the actual slip rate according to the combined sensing information sent by the information acquisition module, and calculate the required target braking force according to the target slip rate influencing factor and controller parameters sent by the parameter optimization module, and send it to the execution module; The execution module is used to receive and execute the target braking force command sent by the slip rate tracking module; The parameter optimization module is also used to obtain the optimal values ​​of the target slip rate influencing factor and the controller parameters through iterative training.

2. The method according to claim 1, characterized in that The information collection module includes multiple types of cameras, radars, inertial measurement units, wheel speed sensors, wheel steering angle sensors, tire noise sensors, and tire pressure sensors.

3. A vehicle ABS parameter optimization method for multiple working conditions, characterized in that: include: Use fusion algorithms and information from various sensors to obtain vehicle and road condition information; Initialize ABS parameters and dual-agent strategy network; Identify road surface type based on vehicle and road condition information; Based on the road surface type, the dual agent outputs the influencing factor of the wheel target slip rate and the parameters of the slip rate tracking controller, the slip rate tracking controller calculates and sends the target braking force, and the actuator executes the control instruction; Calculate rewards for dual-agent actions; Optimize the two-agent policy network based on rewards and acquired real-time data.

4. The method according to claim 3, characterized in that Vehicle and road condition information, including: vehicle speed v, wheel speed n, wheel steering angle δ, vehicle tire noise characteristics Δ, tire pressure p, wheel-road adhesion coefficient And calculate the wheel slip rate s: s=(v-nr) / v Where r is the wheel radius.

5. The method according to claim 4, characterized in that Initialize ABS parameters and dual-agent policy network, including: The initial values ​​of the factors affecting the wheel target slip rate, such as the wheel longitudinal speed, steering angle, road adhesion coefficient, and road type, are randomly given, and the initial value of the wheel target slip rate is calculated according to the following formula: Where o is the target wheel slip rate; λ, ε, η are the factors affecting the target wheel slip rate, respectively, of the wheel longitudinal velocity, steering angle, and road adhesion coefficient; ξ j is the influence factor of the road surface type on the target wheel slip rate, j is the code of the road surface type; The PID algorithm is used as the slip tracking controller, and the controller parameter k is randomly given. P , k I , k D The initial value of The policy networks of the first agent and the second agent are randomly initialized; wherein the first agent is used to optimize the influencing factor of the target slip rate; and the second agent is used to optimize the parameters of the slip rate tracking controller.

6. The method according to claim 5, characterized in that The state space of the first agent is defined as The action space is defined as {λ,ε,η,ξ j }, the reward function is designed as {-a1L-a2[(o>0.5)|(o<0)]}; Among them, v0 is the initial braking speed; L is the braking distance; a1 is the braking distance penalty function; a2 is the penalty function when the target slip rate exceeds the normal range.

7. The method according to claim 5, characterized in that The state space of the second agent is defined as The action space is defined as {k P ,k I ,k D }, the reward function is designed as {-b1|Δd|-b2ΔF b }; where d is the slip tracking error; Δd is the rate of change of the slip tracking error; F b is the wheel braking force; ΔF b is the rate of change of wheel braking force; b1 is the tracking error penalty function; b2 is the frequent adjustment penalty coefficient.

8. The method according to claim 7, characterized in that The dual agents output the influencing factors of the wheel target slip rate and the parameters of the slip rate tracking controller. The slip rate tracking controller calculates and sends the target braking force, and the actuator executes the control instructions, including: Real-time acquisition of the road type, initial braking speed, braking distance, slip tracking error d, slip tracking error change rate Δd, wheel braking force change rate ΔF of the current braking process b ; The first agent based on the current state Select an action {λ,ε,η,ξ j }, and calculate the target wheel slip rate; The second agent is based on the current state Select action {k P ,k I ,k D }; The slip rate tracking controller calculates and sends the target braking force based on the target wheel slip rate, controller parameters and the current actual slip rate. The actuator executes the control command and the vehicle enters the braking process.

9. The method according to claim 8, characterized in that Calculate the rewards for the dual-agent actions, including: Calculate the reward of the first agent’s action {-a1L-a2[(o>0.5)|(o<0)]}; Calculate the reward for the second agent's action {-b1|Δd|-b2ΔF b }.

Images