Cooperative control method for corner actuator and hand feeling simulator in SBW system

Abstract

The invention discloses a cooperative control method for a corner actuator and a hand feeling simulator in an SBW system. S1, the sensor group collects steering data information; s2, the collected steering data information is processed; s3, transmitting the steering data information to a control system; s4, controlling a corner actuator; s5, feeding back data information; s6, controlling the hand feeling simulator; s7, cooperative control and optimization adjustment are carried out; the steering data information is analyzed and processed through model prediction control, so that the steering actuator performs steering control adjustment, uncertainty items are introduced into the model prediction control, and the precise control of the steering actuator is improved; feedback information is dynamically generated through adaptive control, and the hand feeling of a driver in a traditional steering system is simulated; and the feedback force of the hand feeling simulator is synchronous with the change of the wheel turning angle, so that the driving experience is optimized, and the control habits of a driver are autonomously learned through machine learning, so that the control of the vehicle is more comfortable.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent control, and more specifically, particularly relates to a cooperative control method for a steering angle actuator and a feel simulator in an SBW system. Background Technique

[0002] With the continuous development of automotive electronic technology and the integration of automotive systems, people can drive a car through electronic means instead of using a traditional mechanical mechanism to transmit control signals.

[0003] The by-wire technology is developed from Fly-By-Wire applied to aircraft flight control. This technology uses sensors to transmit the driver's input signal to the central processor, and sends a signal to the corresponding actuator through the control logic of the central processor to complete the driver's related operations. In this way, the traditional mechanical structure can be replaced to achieve electronic by-wire control of various movements of the car.

[0004] The steer-by-wire system (SBW) mainly consists of a steering wheel module, a steering gear module, and an electronic control unit (ECU). In the SBW system, the driver transmits the steering signal to the electronic control unit through the sensor on the steering wheel. After analyzing and processing the collected signal, the electronic control unit transmits the control signal to the steering motor, thereby controlling the torque required for the steering motor to turn and driving the wheels to turn to achieve the driver's steering intention. At the same time, the sensors on the steering wheels feedback the wheel steering angle and steering acceleration to the electronic control unit, and the electronic control unit sends a signal to the steering wheel return torque motor to generate a steering wheel return torque to provide the driver with corresponding sensing information.

[0005] Advantages of the steer-by-wire system: It improves the degree of freedom in the design of the whole vehicle and facilitates the layout of the control system. It has high steering efficiency, fast response, and sensitive control. It eliminates steering interference and provides a prerequisite for the realization of automatic control and the integration of the vehicle dynamic control system and the vehicle ride control system. It can realize arbitrary setting of the transmission ratio, thereby improving the vehicle's maneuverability. Since the mechanical steering column is cancelled, it is beneficial to improve the vehicle collision safety and the active safety of the whole vehicle.

[0006] However, there are some problems in the existing technology: The existing SBW system realizes control operations through a steering angle actuator and a feel simulator, but the cooperation between the steering angle actuator and the feel simulator is particularly important to improve the operation feel of the vehicle. The existing steering angle actuator and feel simulator use a single algorithm for control, resulting in a relatively high operation delay of the feel simulator and being not convenient for realizing synchronous and cooperative operation. Therefore, we propose a cooperative control method for a steering angle actuator and a feel simulator in an SBW system. Summary of the Invention

[0007] Aiming at the problems existing in the prior art, the purpose of the present invention is to provide a cooperative control method for a steering angle actuator and a haptic simulator in an SBW system, which realizes separate calculation and processing of the SBW system through various algorithms, thereby improving the cooperative cooperation between the steering angle actuator and the haptic simulator, and improving the synchronization between the steering angle actuator and the haptic simulator.

[0008] To achieve the above object, the present invention provides the following technical solutions: A cooperative control method for a steering angle actuator and a haptic simulator in an SBW system, comprising the following steps:

[0009] S1. The sensor group collects steering data information: The rotation of the steering wheel generates steering data information, which includes the steering angle of the steering wheel collected in real time by the sensor group, as well as the vehicle speed, driving direction and road conditions collected, and converts the steering data information into a digital signal;

[0010] S2. Process the collected steering data information: Process the steering data information collected by the sensor group, and perform denoising, cleaning and normalization processing on the steering data information;

[0011] S3. Transmit the steering data information to the control system: Transmit the processed steering data information to the control system through the CAN bus. The control system calculates the steering angle based on model predictive control, generates a control signal, and transmits the control signal to the steering angle actuator through the CAN bus;

[0012] S4. Steering angle actuator control: After receiving the control signal generated by the control system, the steering angle actuator adjusts the steering angle of the wheel according to the control signal to ensure that the wheel rotates at the angle of the control signal;

[0013] S5. Feedback data information: The control system receives the steering angle calculated by model predictive control, combines the vehicle state and road surface information, and dynamically generates feedback information of steering force and haptic feedback through adaptive control, and transmits the feedback information to the haptic simulator through the CAN bus;

[0014] S6. Haptic simulator control: According to the feedback information, the haptic simulator imitates the force feedback characteristics in the traditional mechanical steering system. The haptic simulator adjusts the torque of the steering wheel through an electro-hydraulic drive device to simulate the feel that the driver can feel in the traditional steering system;

[0015] S7. Cooperative control and optimization adjustment: The feedback force of the haptic simulator is synchronized with the change of the wheel steering angle, and the steering parameters are adjusted through a feedback loop to optimize the driving experience. The machine learning autonomously learns the driving habits of the driver and gradually optimizes the feedback strategy.

[0016] Specifically, the sensor group in S1 includes an angle sensor, a force sensor, a speed sensor, a gyroscope and a vibration sensor;

[0017] The angle sensor is used to detect the rotation angle of the steering wheel;

[0018] The force sensor is used to detect the force of the steering wheel rotation;

[0019] The speed sensor is used to detect the speed of the vehicle;

[0020] The gyroscope is used to detect the direction and tilt of the vehicle;

[0021] The vibration sensor is used to detect vibration data generated by the vehicle when the vehicle is running and the road conditions.

[0022] Specifically, after calculating the steering angle, the control system in S5 transmits the steering angle to the steering angle actuator, and the control system directly uses the steering angle, vehicle status and road surface information to dynamically generate feedback information of steering force and feel feedback through adaptive control, and transmits the feedback information to the feel simulator through the CAN bus.

[0023] Specifically, the steering data information and steering angle information in S2 and S3 are de-noised, cleaned and normalized in the same manner;

[0024] The denoising is calculated as follows:

[0025]

[0026] Among them, w t is the weight of each data point of the steering data information and steering angle information, x i is the input steering data information and steering angle information, N is the window size, y t is the steering data information and steering angle information after filtering;

[0027] and,

[0028] Among them, σ t It is the standard deviation of the data within a certain time window. The larger the standard deviation, the more drastic the fluctuation of the steering data information and the steering angle information. More weight is given when the data changes drastically, and less weight is given when the changes are stable.

[0029] Specifically, the calculation formula for the cleaning is as follows:

[0030]

[0031] Among them, x is the value of the data point, μ is the mean of the data set, σ is the standard deviation of the data set. Points with a Z value greater than 3 or less than -3 are considered outliers, and the outliers are removed;

[0032] For the removed outliers or missing values, mean filling is performed; and the calculation formula for the mean is as follows:

[0033]

[0034] Among them, x' i is the value of non-missing data, and n is the number of non-missing data;

[0035] The calculation formula for the normalization process is as follows:

[0036]

[0037] Among them, x i is the input steering data information and steering angle information, x min is the minimum value in the data set, x max is the maximum value in the data set, and the steering data information and steering angle information are scaled to the range of [0, 1].

[0038] Specifically, the calculation formula for model predictive control in S3 is as follows:

[0039] x(k + 1) = Ax(k) + Bu(k) + △x(k),

[0040] Among them, x(k) is the state of the system, u(k) is the control input, that is, the steering data information, A and B are the state transition matrix and control input matrix of the system, and △x(k) is the uncertainty term, that is, the influence factor of the road surface condition on the vehicle vibration during the vehicle driving process.

[0041] Specifically, the goal of the model predictive control is to minimize the performance index within a finite prediction horizon:

[0042]

[0043] Among them, x(k|t) is the prediction of the future state at time t, x ref (k|t) is the desired reference trajectory or target state, is the weighted quadratic error term of the state error, Q is the weight matrix, is the weighted quadratic error term of the control input, R is the weight matrix of the control input, u(k|t) is the control input at time t, that is, the steering data information, L is the number of steps in the prediction horizon, that is, when performing optimization, the states and control inputs in the future L steps are considered.

[0044] Specifically, the calculation of the adaptive control in S5 is as follows:

[0045] Assume the reference model is:

[0046]

[0047] where y m is the output of the reference model, u m is the control input of the reference model, A m and B m are the parameters of the reference model, is the derivative of the reference model output, A m y m is the interaction term between the state and its own dynamics in the reference model, B m u m is the influence term of the control input on the model state in the reference model;

[0048] The state equation of the actual system is:

[0049]

[0050] where y is the output of the actual system, is the derivative of the system state, u is the actual control input, and A and B are the parameters of the actual system.

[0051] Specifically, the controller of the adaptive control is:

[0052]

[0053] where K is the controller gain, is the estimated value of the system parameter, θ is the weight of the desired control input, u is the control input or output, that is, the signal acting on the controlled system to adjust the system state, y is the output of the system, is the quadratic term of the adaptive parameter;

[0054] The error is defined as:

[0055] e = y - y m ,

[0056] Based on the error dynamics, the adaptive controller adjusts the control input of the system to make the error e converge. The parameter update rule of the adaptive controller is usually based on the parameter estimator:

[0057]

[0058] where, represents the adaptive controller parameter, and Γ is the adaptive gain matrix used to control the rate of parameter update;

[0059] Adaptive control realizes the control of the haptic simulator through the output y of the system.

[0060] Specifically, the calculation formula of the machine learning is as follows:

[0061]

[0062] where s t is the current state, a t is the current action, r t+1 is the immediate reward obtained after taking the action a t from the state s t ; γ is the discount factor, representing the weight of future rewards, and α is the learning rate, controlling the step size of learning;

[0063] DQN uses a deep neural network to approximate the Q function. The input of the network is the current state s t , and the output is the Q value corresponding to each action a, that is where are the parameters of the neural network, namely the weights and biases;

[0064] Therefore, the approximation of the Q function is:

[0065]

[0066] The target Q value is calculated by the following formula:

[0067]

[0068] where: are the parameters of the target network, which is a copy of the Q network and will be updated only after a certain number of steps to avoid instability during the training process; is the output of the target network, representing the Q values of all future actions in the next state s t+1 ;

[0069] Update of the Q network:

[0070] The training objective of DQN is to make the Q value output by the network close to the target Q value. Usually, the mean square error is used as the loss function:

[0071]

[0072] The loss function represents the gap between the predicted Q value and the target Q value, and then updates the parameters of the Q network through the backpropagation algorithm to optimize the error between the target Q value and the predicted Q value;

[0073] Realize the driving habits of autonomous learning drivers and gradually optimize the feedback strategy.

[0074] Technical effects and advantages of the present invention:

[0075] When the present invention is in use, the steering data information of the steering wheel rotation is collected through the sensor group, and the steering data information is calculated and analyzed through model predictive control, so that the control system calculates the steering angle. The control system generates a control signal according to the steering angle and transmits the control signal to the steering angle actuator through the CAN bus, so that the steering angle actuator can complete the steering control adjustment of the vehicle;

[0076] And the steering angle information is fed back to the control system, combined with the vehicle state and road surface information, and the feedback information of the steering force and feel feedback is dynamically generated through adaptive control, and the feedback information is transmitted to the feel simulator through the CAN bus, so that the feel simulator can adjust the torque of the steering wheel through the electro-hydraulic drive device to simulate the feel that the driver can feel in the traditional steering system;

[0077] And the feedback force of the feel simulator is synchronized with the change of the wheel steering angle. The steering parameters are adjusted through the feedback loop to optimize the driving experience, and the control habits of the driver are autonomously learned through machine learning and the feedback strategy is gradually optimized, so that the control of the vehicle is more comfortable and more in line with the operating feeling of the vehicle;

[0078] And an uncertainty term is introduced in the model predictive control, that is, the influence factor of the road surface condition on the vibration of the vehicle during the vehicle driving process. Through the introduced uncertainty term, the model predictive control can eliminate the influence of the road surface on the vehicle and reduce the influence of the road surface vibration on the vehicle sensor detection, which is convenient for improving the precise control of the steering angle actuator of the vehicle.

[0079] Through the following detailed description of the exemplary embodiments of the present invention with reference to the accompanying drawings, other features and advantages of the present invention will become clear. Description of the drawings

[0080] Figure 1 It is a schematic flow chart of the steps provided by the present invention. Detailed implementation manners

[0081] In order to make the purpose, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0082] Such as Figure 1As shown in the figure, a collaborative control method for a steering angle actuator and a feel simulator in an SBW system provided by an embodiment of the present invention includes the following steps:

[0083] S1. The sensor group collects steering data information: The rotation of the steering wheel generates steering data information, which includes the steering angle of the steering wheel collected in real time by the sensor group, as well as the vehicle speed, driving direction, and road conditions collected, and converts the steering data information into a digital signal;

[0084] S2. Process the collected steering data information: Process the steering data information collected by the sensor group, and perform denoising, cleaning, and normalization processing on the steering data information;

[0085] S3. Transmit the steering data information to the control system: Transmit the processed steering data information to the control system through the CAN bus. The control system calculates the steering angle based on model predictive control, generates a control signal, and transmits the control signal to the steering angle actuator through the CAN bus;

[0086] S4. Control the steering angle actuator: After receiving the control signal generated by the control system, the steering angle actuator adjusts the steering angle of the wheel according to the control signal to ensure that the wheel rotates at the angle of the control signal;

[0087] S5. Feedback data information: The control system receives the steering angle calculated by model predictive control, combines the vehicle state and road surface information, and dynamically generates feedback information of steering force and feel feedback through adaptive control, and transmits the feedback information to the feel simulator through the CAN bus;

[0088] S6. Control the feel simulator: According to the feedback information, the feel simulator imitates the force feedback characteristics in the traditional mechanical steering system. The feel simulator adjusts the torque of the steering wheel through an electro-hydraulic drive device to simulate the feel that the driver can feel in the traditional steering system;

[0089] S7. Collaborative control and optimization adjustment: The feedback force of the feel simulator is synchronized with the change of the wheel steering angle, and adjusts the steering parameters through a feedback loop to optimize the driving experience, autonomously learns the driving habits of the driver through machine learning, and gradually optimizes the feedback strategy.

[0090] In this embodiment, preferably, the sensor group in S1 includes an angle sensor, a force sensor, a speed sensor, a gyroscope, and a vibration sensor;

[0091] The angle sensor is used to detect the rotation angle of the steering wheel;

[0092] The force sensor is used to detect the force of the steering wheel rotation;

[0093] The speed sensor is used to detect the speed of the vehicle;

[0094] The gyroscope is used to detect the direction and tilt of the vehicle;

[0095] The vibration sensor is used to detect the vibration data generated by the vehicle when the vehicle is running and the road conditions;

[0096] It should be noted that the rotation of the steering wheel is detected by using multiple sensors in the sensor group, and various information of the vehicle is detected, so as to control and adjust the steering of the vehicle.

[0097] In this embodiment, preferably, after calculating the steering angle, the control system in S5 transmits the steering angle to the steering angle actuator, and the control system directly uses the steering angle, vehicle state and road surface information to dynamically generate feedback information of steering force and hand feel feedback through adaptive control, and transmits the feedback information to the hand feel simulator through the CAN bus;

[0098] It should be noted that the steering angle of the wheel obtained by calculation and reverse control in conjunction with the vehicle's speed, direction, inclination and vibration data facilitates the simulation of the operating feel of a mechanical vehicle, and after the steering angle is transmitted to the steering angle actuator, feedback information of the steering force and feel feedback is generated through adaptive control at the same time, thereby maintaining the synchronization of steering and feedback.

[0099] In this embodiment, preferably, the steering data information and steering angle information in S2 and S3 are de-noised, cleaned and normalized in the same manner;

[0100] The denoising is calculated as follows:

[0101]

[0102] Among them, w t is the weight of each data point of the steering data information and steering angle information, x i is the input steering data information and steering angle information, N is the window size, y t is the steering data information and steering angle information after filtering;

[0103] and,

[0104] Among them, σ t is the standard deviation of the data within a certain time window. The larger the standard deviation, the more drastic the fluctuation of the steering data information and the steering angle information. More weight is given when the data changes drastically, and less weight is given when the change is stable.

[0105] It should be noted that by denoising the collected steering data information and steering angle information, the accuracy of the steering data information and steering angle information is improved, and according to the allocated weights, more weight allocation is facilitated during steering, and less weight is allocated when the vehicle vibrates, facilitating precise control adjustment.

[0106] In this embodiment, preferably, the calculation formula for cleaning is as follows:

[0107]

[0108] Among them, x is the value of the data point, μ is the mean of the data set, σ is the standard deviation of the data set, and points with a Z value greater than 3 or less than -3 are considered outliers, and the outliers are removed;

[0109] For the removed outliers or missing values, mean filling is performed; and the calculation formula for the mean is as follows:

[0110]

[0111] Among them, x' i is the value of non-missing data, and n is the number of non-missing data;

[0112] The calculation formula for the normalization process is as follows:

[0113]

[0114] Among them, x i is the input steering data information and steering angle information, x min is the minimum value in the data set, x max is the maximum value in the data set, and the steering data information and steering angle information are scaled to the range of [0, 1];

[0115] It should be noted that by using the mean and standard deviation, outliers in the data information are detected and removed, and by using the mean, missing values and removed values are compensated to maintain the integrity of the steering data information and steering angle information, and through the normalization process, the steering data information and steering angle information can be scaled to the range of [0, 1], facilitating the reduction of the calculation pressure of the steering data information and steering angle information.

[0116] In this embodiment, preferably, the calculation formula for model predictive control in S3 is as follows:

[0117] x(k + 1) = Ax(k) + Bu(k) + △x(k),

[0118] Wherein, x(k) is the state of the system, u(k) is the control input, i.e., the steering data information, A and B are the state transition matrix and the control input matrix of the system, and △x(k) is the uncertainty term, i.e., during the vehicle driving process, the influence factor of the road surface condition on the vehicle vibration;

[0119] It should be noted that introducing the uncertainty term in the model predictive control facilitates eliminating the influence factor of the road surface condition on the vehicle vibration and improving the accuracy of the model predictive control.

[0120] In this embodiment, preferably, the objective of the model predictive control is to minimize the performance index within a finite prediction horizon:

[0121]

[0122] Wherein, x(k|t) is the prediction of the future state at time t, x ref (k|t) is the desired reference trajectory or target state, is the weighted quadratic error term of the state error, Q is the weight matrix, is the weighted quadratic error term of the control input, R is the weight matrix of the control input, u(k|t) is the control input at time t, i.e., the steering data information, and L is the number of steps of the prediction horizon, i.e., when performing optimization, the states and control inputs in the future L steps are considered;

[0123] It should be noted that the model predictive control predicts the future trajectory through multiple steps, which facilitates minimizing the performance index within the prediction horizon and calculating and processing the states and control inputs in the future N steps, enabling the model predictive control to calculate the steering angle based on the collected steering data information and realize the steering process by controlling the steering actuator.

[0124] In this embodiment, preferably, the calculation of the adaptive control in S5 is as follows:

[0125] Assume the reference model is:

[0126]

[0127] Wherein, y m is the output of the reference model, u m is the control input of the reference model, A m and B m are the parameters of the reference model, is the derivative of the reference model output, A m y m is the interaction term between the state and its own dynamics in the reference model, B m u m is the influence term of the control input on the model state in the reference model;

[0128] The state equation of the actual system is as follows:

[0129]

[0130] where y is the output of the actual system, is the derivative of the system state, u is the actual control input, and A and B are the parameters of the actual system;

[0131] It should be noted that the goal of adaptive control is to make the output of the system track the output of an ideal reference model as closely as possible by adjusting the parameters of the controller. Its basic idea is to update the parameters of the controller through the error dynamics. The reference model is used to define the desired behavior or performance of the system. The goal of the controller is to make the output of the actual system track the output of the reference model as closely as possible. The state equation of the actual system is usually used to describe the dynamic behavior of the system and reflect the relationship between the input, output, and state variables of the system.

[0132] In this embodiment, preferably, the controller of the adaptive control is:

[0133]

[0134] where K is the controller gain, is the estimated value of the system parameter, θ is the weight of the desired control input, u is the control input or output, that is, the signal acting on the controlled system for adjusting the system state, and y is the output of the system, is the quadratic term of the adaptive parameter;

[0135] The error is defined as:

[0136] e = y - y m ,

[0137] Based on the error dynamics, the adaptive controller adjusts the control input of the system to make the error e converge. The parameter update rule of the adaptive controller is usually based on the parameter estimator:

[0138]

[0139] where, represents the parameters of the adaptive controller, and Γ is the adaptive gain matrix used to control the rate of parameter update;

[0140] The adaptive control controls the haptic simulator through the output y of the system;

[0141] It should be noted that the controller will adjust its control strategy in real time according to the error between the actual output of the system and the output of the reference model. The error is the difference between the actual output of the system and the output of the reference model, and is usually used to evaluate the performance of the control system.

[0142] In this embodiment, preferably, the calculation formula of the machine learning is as follows:

[0143]

[0144] where s t is the current state, a t is the current action, r t+1 is the immediate reward obtained after taking the action a t from the state s t , γ is the discount factor, representing the weight of future rewards, and α is the learning rate, controlling the learning step size;

[0145] DQN uses a deep neural network to approximate the Q function. The input of the network is the current state s t , and the output is the Q value corresponding to each action a, that is where are the parameters of the neural network, namely the weights and biases;

[0146] Therefore, the approximation of the Q function is:

[0147]

[0148] The target Q value is calculated by the following formula:

[0149]

[0150] where: are the parameters of the target network, which is a copy of the Q network and will be updated only after several steps to avoid instability during the training process; is the output of the target network, representing the Q values of all future actions in the next state s t+1 ;

[0151] Update of the Q network:

[0152] The training objective of DQN is to make the Q value output by the network close to the target Q value. Usually, the mean square error is used as the loss function:

[0153]

[0154] The loss function represents the gap between the predicted Q value and the target Q value, and then the parameters of the Q network are updated through the backpropagation algorithm to optimize the error between the target Q value and the predicted Q value;

[0155] Realize the driving habits of autonomous learning drivers and gradually optimize the feedback strategy;

[0156] It should be noted that the Q-value is used to represent the expected cumulative reward for taking a certain action in a certain state. The Q-value is the state-action value function. The goal of Q-learning is to learn an optimal Q-function so that the intelligent agent can select the optimal action to maximize the long-term reward. Through continuous iteration and training, DQN can learn an efficient policy to adapt to complex environments.

[0157] The specific operation process of the present invention:

[0158] Step 1: The sensor group collects steering data information. The rotation of the steering wheel generates steering data information, which includes the steering angle of the steering wheel collected in real time by the sensor group, as well as the vehicle speed, driving direction, and road conditions collected, and converts the steering data information into a digital signal.

[0159] Step 2: Process the collected steering data information. Process the steering data information collected by the sensor group, and perform denoising, cleaning, and normalization processing on the steering data information.

[0160] Step 3: Transmit the steering data information to the control system. Transmit the processed steering data information to the control system through the CAN bus. The control system calculates the steering angle based on model predictive control, generates a control signal, and transmits the control signal to the steering angle actuator through the CAN bus.

[0161] The calculation formula of model predictive control is as follows:

[0162] x(k + 1) = Ax(k) + Bu(k) + △x(k),

[0163] where x(k) is the state of the system, u(k) is the control input, that is, the steering data information, A and B are the state transition matrix and control input matrix of the system, and △x(k) is the uncertainty term, that is, the influence factor of the road conditions on the vibration of the vehicle during the vehicle driving process.

[0164] The goal of model predictive control is to minimize the performance index within a finite prediction time domain:

[0165]

[0166] where x(k|t) is the prediction of the future state at time t, x ref (k|t) is the expected reference trajectory or target state, is the weighted quadratic error term of the state error, Q is the weight matrix, is the weighted quadratic error term of the control input, R is the weight matrix of the control input, u(k|t) is the control input at time t, which is the steering data information, L is the number of steps in the prediction horizon, that is, when performing optimization, the states and control inputs in the next L steps are considered;

[0167] Step Four: Steering actuator control: After receiving the control signal generated by the control system, the steering actuator adjusts the steering angle of the wheel according to the control signal to ensure that the wheel rotates at the angle of the control signal;

[0168] Step Five: Feedback data information: The control system receives the steering angle calculated by the model predictive control. The control system combines the vehicle state and road surface information, and dynamically generates the feedback information of the steering force and feel feedback through adaptive control, and transmits the feedback information to the feel simulator through the CAN bus;

[0169] The calculation of the adaptive control is as follows:

[0170] Assume the reference model is:

[0171]

[0172] where y m is the output of the reference model, u m is the control input of the reference model, A m and B m are the parameters of the reference model, is the derivative of the reference model output, A m y m is the interaction term between the state and its own dynamics in the reference model, B m u m is the influence term of the control input on the model state in the reference model;

[0173] The state equation of the actual system is:

[0174]

[0175] where y is the output of the actual system, is the derivative of the system state, u is the actual control input, A and B are the parameters of the actual system;

[0176] The controller of the adaptive control is:

[0177]

[0178] where K is the controller gain, is the estimated value of the system parameter, θ is the weight of the desired control input, u is the control input or output, that is, the signal acting on the controlled system, used to adjust the system state, y is the output of the system, is the quadratic term of the adaptive parameter;

[0179] The error is defined as:

[0180] e = y - y m ,

[0181] Based on the error dynamics, the adaptive controller adjusts the control input of the system to make the error e converge. The parameter update rule of the adaptive controller is usually based on the parameter estimator:

[0182]

[0183] where, represents the parameters of the adaptive controller, and Γ is the adaptive gain matrix, which is used to control the rate of parameter update;

[0184] The adaptive control realizes the control of the haptic simulator through the output y of the system;

[0185] Step 6: Haptic simulator control: The haptic simulator imitates the force feedback characteristics in the traditional mechanical steering system according to the feedback information. The haptic simulator adjusts the torque of the steering wheel through the electro-hydraulic drive device to simulate the feel that the driver can feel in the traditional steering system;

[0186] Step 7: Cooperative control and optimization adjustment: The feedback force of the haptic simulator is synchronized with the change of the wheel angle, and the steering parameters are adjusted through the feedback loop to optimize the driving experience. The haptic simulator autonomously learns the driving habits of the driver through machine learning and gradually optimizes the feedback strategy;

[0187] The calculation formula of machine learning is as follows:

[0188]

[0189] where s t is the current state, a t is the current action, r t+1 is the immediate reward obtained after taking the action a t from the state s t , γ is the discount factor, which represents the weight of future rewards, and α is the learning rate, which controls the step size of learning;

[0190] The DQN uses a deep neural network to approximate the Q function. The input of the network is the current state s t , and the output is the Q value corresponding to each action a, that is where are the parameters of the neural network, that is, the weights and biases;

[0191] Therefore, the approximation of the Q function is:

[0192]

[0193] The target Q value is calculated by the following formula:

[0194]

[0195] Where: are the parameters of the target network, which is a copy of the Q network and will only be updated every several steps to avoid instability during the training process; is the output of the target network, representing the Q values of all future actions in the next state s t+1 under, the Q values of all future actions;

[0196] Update of the Q network:

[0197] The training objective of DQN is to make the Q value output by the network close to the target Q value. Usually, the mean square error is used as the loss function:

[0198]

[0199] The loss function represents the gap between the predicted Q value and the target Q value, and then the parameters of the Q network are updated through the backpropagation algorithm Optimize the error between the target Q value and the predicted Q value;

[0200] Realize the driving habits of autonomous learning drivers and gradually optimize the feedback strategy.

[0201] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for cooperatively controlling a rotation angle actuator and a hand feeling simulator in an SBW system, characterized in that: The steps include: S1. The sensor group collects steering data information: the rotation of the steering wheel generates steering data information, which includes the steering angle of the steering wheel collected in real time by the sensor group, as well as the collected vehicle speed, driving direction and road conditions, and converts the steering data information into a digital signal; S2. Processing the collected steering data information: Processing the steering data information collected by the sensor group, and performing denoising, cleaning and normalization processing on the steering data information; S3, transmitting the steering data information to the control system: transmitting the processed steering data information to the control system through the CAN bus, the control system calculates the steering angle based on the model predictive control, the control system generates a control signal, and transmits the control signal to the steering angle actuator through the CAN bus; S4, steering angle actuator control: after receiving the control signal generated by the control system, the steering angle actuator adjusts the steering angle of the wheel according to the control signal to ensure that the wheel rotates according to the angle of the control signal; S5, feedback data information: the control system receives the steering angle calculated by the model predictive control, the control system combines the vehicle state and road information, and dynamically generates feedback information of steering force and feel feedback through adaptive control, and transmits the feedback information to the feel simulator through the CAN bus; S6. Hand-feel simulator control: The hand-feel simulator imitates the force feedback characteristics of the traditional mechanical steering system based on feedback information. The hand-feel simulator adjusts the torque of the steering wheel through an electro-hydraulic drive device to simulate the hand-feel that the driver can feel in the traditional steering system. S7. Coordinated control and optimization adjustment: The feedback force of the feel simulator is synchronized with the change of wheel angle, and the steering parameters are adjusted through the feedback loop to optimize the driving experience. The driver's control habits are autonomously learned through machine learning, and the feedback strategy is gradually optimized.

2. The method for cooperatively controlling a rotation angle actuator and a hand feel simulator in a SBW system according to claim 1, characterized in that: The sensor group in S1 includes an angle sensor, a force sensor, a speed sensor, a gyroscope and a vibration sensor; The angle sensor is used to detect the rotation angle of the steering wheel; The force sensor is used to detect the force of the steering wheel rotation; The speed sensor is used to detect the speed of the vehicle; The gyroscope is used to detect the direction and tilt of the vehicle; The vibration sensor is used to detect vibration data generated by the vehicle when the vehicle is running and the road conditions.

3. The method for cooperatively controlling a rotation angle actuator and a hand feeling simulator in a SBW system according to claim 1, characterized in that: After calculating the steering angle, the control system in S5 transmits the steering angle to the steering angle actuator, and the control system directly uses the steering angle, vehicle status and road surface information to dynamically generate feedback information of steering force and feel feedback through adaptive control, and transmits the feedback information to the feel simulator through the CAN bus.

4. The method for cooperatively controlling a rotation angle actuator and a hand feeling simulator in a SBW system according to claim 1, characterized in that: The steering data information in S2 is denoised, cleaned and normalized in the same manner; The denoising is calculated as follows: Among them, w t is the weight of each data point of the steering data information and steering angle information, x i is the input steering data information and steering angle information, N is the window size, y t is the steering data information and steering angle information after filtering; and, Among them, σ t It is the standard deviation of the data within a certain time window. The larger the standard deviation, the more drastic the fluctuation of the steering data information and the steering angle information. More weight is given when the data changes drastically, and less weight is given when the changes are stable.

5. The method for cooperatively controlling the angle actuator and the hand feeling simulator in the SBW system according to claim 4, characterized in that: The calculation formula for the cleaning is as follows: Among them, x is the value of the data point, μ is the mean of the data set, σ is the standard deviation of the data set, and points with a value of Z greater than 3 or less than -3 are considered outliers and are removed; For the removed outliers or missing values, the mean is filled; and the mean calculation formula is as follows: Among them, x′ i is the value of non-missing data, n is the number of non-missing data; The calculation formula for the normalization process is as follows: Among them, x i is the input steering data information and steering angle information, x min is the minimum value in the data set, x max is the maximum value in the data set, scaling the steering data information and steering angle information to the range of [0, 1].

6. The method for cooperatively controlling a rotation angle actuator and a hand feeling simulator in a SBW system according to claim 1, characterized in that: The calculation formula of the model predictive control in S3 is as follows: x(k+1)=Ax(k)+Bu(k)+Δx(k), Among them, x(k) is the state of the system, u(k) is the control input, that is, the steering data information, A and B are the state transfer matrix and control input matrix of the system, △x(k) is the uncertainty term, that is, the factor affecting the vibration of the vehicle due to the road conditions during the vehicle's driving.

7. The method for cooperatively controlling the angle actuator and the hand feeling simulator in the SBW system according to claim 6, characterized in that: The goal of the model predictive control is to minimize the performance index within a limited prediction horizon: Among them, x(k|t) is the prediction of the future state at time t, x ref (k|t) is the desired reference trajectory or target state, is the weighted quadratic error term of the state error, Q is the weight matrix, is the weighted quadratic error term of the control input, R is the weight matrix of the control input, u(k|t) is the control input at time t, that is, the steering data information, and L is the number of steps in the prediction time domain, that is, when optimizing, the state and control input of the next L steps are considered.

8. The method for cooperatively controlling a rotation angle actuator and a hand feeling simulator in a SBW system according to claim 1, characterized in that: The calculation of the adaptive control in S5 is as follows: Assume the reference model is: Among them, y m is the output of the reference model, u m is the control input of the reference model, A m and B m are the parameters of the reference model, is the derivative of the reference model output, A m y m is the interaction term between the state in the reference model and its own dynamics, B m u m is the influence of the control input on the model state in the reference model; The state equation of the actual system is: Among them, y is the output of the actual system, is the derivative of the system state, u is the actual control input, and A and B are the parameters of the actual system.

9. The method for cooperatively controlling the angle actuator and the hand feeling simulator in the SBW system according to claim 8, characterized in that: The controller of the adaptive control is: Where K is the controller gain, is the estimated value of the system parameters, θ is the weight of the desired control input, u is the control input or output, that is, the signal acting on the controlled system to adjust the system state, y is the output of the system, is the quadratic term of the adaptive parameter; The error is defined as: e=yy m , Based on the error dynamics, the adaptive controller adjusts the control input of the system to make the error e converge. The parameter update law of the adaptive controller is usually based on the parameter estimator: in, Denotes the adaptive controller parameters, Γ is the adaptive gain matrix, which is used to control the rate of parameter update; Adaptive control controls the hand feel simulator through the system output y.

10. The method for cooperatively controlling a rotation angle actuator and a hand feeling simulator in a SBW system according to claim 1, characterized in that: The calculation formula of the machine learning is as follows: Among them, s t is the current state, a t is the current action, r t+1 From the state s t Take action a t The immediate reward obtained after, γ is the discount factor, which indicates the weight of future rewards, and α is the learning rate, which controls the step size of learning; DQN uses a deep neural network to approximate the Q function. The input of the network is the current state s t , the output is the Q value corresponding to each action a, that is in are the parameters of the neural network, namely weights and biases; Therefore, the Q function can be approximated as: The target Q value is calculated by the following formula: in: It is the parameter of the target network, which is a copy of the Q network and is updated every few steps to avoid instability during training; is the output of the target network, indicating that in the next state s t+1 Next, the Q-values ​​of all future actions; Q Network Updates: The training goal of DQN is to make the Q value of the network output close to the target Q value, and the mean square error is usually used as the loss function: The loss function represents the gap between the predicted Q value and the target Q value, and then the parameters of the Q network are updated through the back propagation algorithm. Optimize the error between the target Q value and the predicted Q value; It can autonomously learn the driver's control habits and gradually optimize the feedback strategy.

Images