An intelligent automobile stability control method based on driver characteristics

Abstract

The application discloses an intelligent automobile stability control method based on driver characteristics, which comprises a vehicle state information acquisition module, a driver style recognition module, a vehicle additional yaw moment calculation module and a moment distribution execution module. The vehicle state information acquisition module is used for acquiring various dynamic parameters such as vehicle slip rate, yaw angular velocity, roll angle, tire force and adhesion coefficient; the driver style recognition module combines driving behavior factors, environmental adaptability factors and risk perception and decision factors, and recognizes the driver style category based on a neural network model; the vehicle additional yaw moment calculation module calculates additional yaw moments of the yaw angular velocity, the mass center side slip angle and the lateral load transfer rate according to different styles; and the moment distribution execution module judges the execution mode according to the vehicle state coefficient and calculates the output moment of each wheel.

Description

Technical Field

[0001] The present invention belongs to the field of automobile safety, relates to the field of electric vehicle stability control, and specifically relates to an intelligent automobile stability control method based on driver characteristics. Background Art

[0002] With the continued development of intelligent connected vehicles and autonomous driving technologies, vehicle stability control under complex road conditions and extreme driving conditions has become a key research area in vehicle safety technology. Traditional vehicle stability control systems are primarily based on vehicle dynamics models, maintaining vehicle stability through feedback control of parameters such as lateral acceleration, yaw rate, and tire forces. However, these approaches generally employ a unified control logic, lacking the ability to adapt to individual driver differences and operational characteristics. This inability to dynamically adjust control strategies to suit different driving styles and behavioral patterns results in deficiencies in control accuracy and handling comfort.

[0003] In actual driving, a driver's control behavior, environmental adaptability, and risk perception and decision-making abilities directly impact the vehicle's dynamic response and safety performance. Different driver styles exhibit significant differences in their throttle, steering, and brake operation, yet existing stability control systems fail to fully integrate driver behavior information to optimize control strategies. Furthermore, under extreme driving conditions, the vehicle's torque distribution and posture adjustment requirements are highly dependent on the driver's behavior pattern, making it difficult to achieve personalized application of additional yaw torque using traditional methods. Therefore, there is an urgent need for a driver-based intelligent vehicle stability control method that can integrate multi-source driving behavior information, adaptively adjust vehicle control strategies, and enhance vehicle handling stability and active safety performance. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent vehicle stability control method based on driver characteristics to solve the problems faced in the above background technology.

[0005] In order to achieve the above object, the present invention provides the following solution:

[0006] An intelligent vehicle stability control method based on driver characteristics includes a vehicle state information acquisition module, a driver style recognition module, a vehicle additional yaw moment calculation module, and a torque distribution execution module;

[0007] The vehicle status information acquisition module is used to obtain the vehicle's actual center of mass sideslip angle β, the vehicle's actual yaw angular velocity ω, and the vehicle's actual lateral acceleration a y , front wheel slip rate λ f , rear wheel slip rate λ r , vehicle longitudinal speed v x , front axle vertical load Fzf , rear axle vertical load F zr , body roll angle Road adhesion coefficient μ, vehicle wheelbase W, center of mass height h CG , lateral force F on the front wheel yf ; Lateral force F on the rear wheel yr 、The longitudinal force F acting on the vehicle x , the lateral force F acting on the vehicle y ;

[0008] The driver style recognition module is used to calculate the control behavior factor, environmental adaptability factor, risk perception and decision-making factor, and thus calculate the driver's comprehensive evaluation factor based on multiple evaluation factors to determine the driver's driving style;

[0009] The manipulation behavior factor S c The calculation formula is as follows:

[0010]

[0011] Where, is the average value of the steering wheel angular velocity; δ s,max is the maximum value of the steering wheel angular velocity; is the average value of the steering wheel angular acceleration; a s,max is the maximum value of the steering wheel angular acceleration; is the average value of the throttle opening change rate; ΔT a,max is the maximum value of the throttle opening change rate; is the average value of the brake pedal pressure change rate; ΔP b,max is the maximum value of the brake pedal pressure change rate; N acc N is the number of rapid accelerations per kilometer; acc,max N is the maximum number of rapid accelerations per kilometer; brk N is the number of sudden brakes per kilometer; brk,max The maximum number of emergency braking times per kilometer;

[0012] The environmental adaptability factor S e The calculation formula is as follows:

[0013]

[0014] Where, is the average value of the following distance change rate; Δd f,max The maximum value of the following distance change rate; N l is the number of lane changes per kilometer; N l,max is the maximum number of lane changes per kilometer; is the average value of the speed adjustment range in the curve; Δv c,maxThe maximum value of the speed adjustment range in the curve; t rg Traffic light response time; is the average response time of traffic lights; σ rg is the standard deviation of traffic light response time;

[0015] The risk perception and decision factor S r The calculation formula is as follows:

[0016]

[0017] Where, is the average following distance; d f,max is the maximum following distance; t b is the brake advance time; t b,max The maximum value of the brake advance time; R s is the overspeed time ratio; R s,max is the maximum value of the overspeed time ratio; R close is the triggering frequency of forward collision warning and lane departure warning; T dis Distract the driver's attention for a long time; dis,max The maximum time the driver's attention is distracted;

[0018] The driver style recognition module uses a fully connected neural network algorithm to determine the driver style category based on the driver's control behavior score, environmental adaptability score, risk perception and decision-making score. The specific structure is designed as follows:

[0019] The input layer consists of three nodes, corresponding to the control behavior factor, the environmental adaptability factor, and the risk perception and decision-making factor. The hidden layer adopts a three-layer structure, including the first hidden layer, the second hidden layer, and the third hidden layer. The first hidden layer, the second hidden layer, and the third hidden layer contain 64, 32, and 16 neurons, respectively. The output layer consists of one node, and the output is the driver's style.

[0020] The calculation formula for the driver style judgment is:

[0021]

[0022] Where S c 、S e 、S r They are manipulation behavior factor, environmental adaptability factor, risk perception and decision factor; Z (1) ,Z (2) ,Z (3) ,Z (4) is the output of the first hidden layer, the second hidden layer, the third hidden layer and the output layer after linear transformation; W (1) ,W (2),W (3) ,W (4) are the weight matrices from the input layer to the first hidden layer, from the first hidden layer to the second hidden layer, from the second hidden layer to the third hidden layer, and from the third hidden layer to the output layer; b (1) ,b (2) ,b (3) ,b (4) are the bias terms for the first hidden layer, the second hidden layer, the third hidden layer, and the output layer, respectively; ReLU is the activation function, defined as ReLU(x) = max(0, x), to enhance the nonlinear expression capability of the network; P(y = k|X) represents the probability that the input data X is classified as category k. Its calculation process is Softmax normalization to ensure that the output is a probability distribution. The three neurons correspond to the probabilities of aggressive, balanced, and conservative, respectively. is the exponential transformation score of the kth category; The index sum of scores for all categories; It means that among all possible categories k, the k that maximizes the expression on the right is selected. A, B, and C represent the driver style of aggressive, balanced, and conservative respectively;

[0023] The vehicle additional yaw moment calculation module is configured to receive the driver style information output by the driver style recognition module and apply different additional yaw moments for conservative, balanced, and aggressive drivers, respectively. The additional yaw moment is calculated by combining an additional yaw moment for controlling the yaw angular velocity, an additional yaw moment for controlling the sideslip angle of the center of mass, and an additional yaw moment for controlling the lateral load transfer rate.

[0024] The torque distribution execution module calculates the vehicle driving state coefficient by considering the yaw instability factor and the roll instability factor, determines the vehicle execution mode according to the vehicle driving state coefficient, and calculates the torque of each wheel for the four-wheel independent drive mode and the four-wheel independent braking mode respectively.

[0025] The vehicle additional yaw moment calculation module is used to calculate the vehicle additional yaw moment according to the driver's style;

[0026] When the driver's style is conservative, the calculation formula of the vehicle additional yaw moment ΔM is:

[0027]

[0028] Where, β is the actual side slip angle of the vehicle's center of mass; β * is the ideal vehicle center of mass sideslip angle; ΔM ω The additional yaw moment to control the yaw rate; ΔM β is the additional yaw moment to control the sideslip angle of the center of mass; s β is the coefficient that controls the steepness of the transition;

[0029] When the driver's style is balanced, the calculation formula of the vehicle's additional yaw moment ΔM is:

[0030]

[0031] Where, LTR is the actual lateral load transfer rate of the vehicle; LTR * is the ideal lateral load transfer rate of the vehicle; β is the actual side slip angle of the vehicle's center of mass; β * is the ideal side slip angle of the vehicle's center of mass; E β is the threshold of the vehicle's center of mass sideslip angle; ΔM ω The additional yaw moment to control the yaw rate; ΔM β The additional yaw moment to control the sideslip angle of the center of mass; ΔM LTR Additional yaw moment to control the lateral load transfer rate;

[0032] When the driver's style is aggressive, the calculation formula of the vehicle's additional yaw moment ΔM is:

[0033] ΔM=(1-lnS yaw )ΔM β +lnS lateral ΔM LTR

[0034] Where, ΔM β The additional yaw moment to control the sideslip angle of the center of mass; ΔM LTR The additional yaw moment to control the lateral load transfer rate; S yaw is the yaw instability factor; S lateral is the roll instability factor;

[0035] The yaw instability factor S yaw The calculation formula is as follows:

[0036]

[0037] Where, β is the actual side slip angle of the vehicle's center of mass; β * is the ideal center of mass sideslip angle of the vehicle; ω is the actual yaw rate of the vehicle; ω * is the ideal yaw rate of the vehicle; v x is the longitudinal speed of the vehicle; μ is the road adhesion coefficient; is the roll angular velocity; LTR is the actual lateral load transfer rate of the vehicle; LTR * is the ideal lateral load transfer rate of the vehicle; F yf is the lateral force on the front wheel; F yr is the lateral force on the rear wheel;

[0038] The roll instability factor Slateral The calculation formula is as follows:

[0039]

[0040] Where, The maximum roll angle allowed for the vehicle body; is the vehicle body roll angle; LTR is the actual lateral load transfer rate of the vehicle; LTR * is the ideal lateral load transfer rate of the vehicle; v x is the longitudinal speed of the vehicle; for suspension roll damping; is the body roll inertia moment; is the suspension roll stiffness; F zf is the vertical load on the front axle; F zr is the vertical load on the rear axle.

[0041] The vehicle additional yaw moment calculation module controls the additional yaw moment ΔM of the yaw angular velocity ω The calculation formula is as follows:

[0042]

[0043] Where ω is the actual yaw rate of the vehicle; * is the desired yaw rate of the vehicle; δ f is the actual steering wheel angle of the vehicle; is the ideal steering wheel angle of the vehicle; F yf is the lateral force on the front wheel; F yr is the lateral force on the rear wheel; a y is the actual lateral acceleration of the vehicle; is the ideal lateral acceleration of the vehicle; LTR is the actual lateral load transfer rate of the vehicle;

[0044] The additional yaw moment ΔM that controls the sideslip angle of the center of mass β The calculation formula is as follows:

[0045]

[0046] Where, β is the actual side slip angle of the vehicle's center of mass; β * is the ideal side slip angle of the vehicle's center of mass; a y is the actual lateral acceleration of the vehicle; is the ideal lateral acceleration of the vehicle; F yf is the lateral force on the front wheel; F yr is the lateral force on the rear wheel; v x is the longitudinal speed of the vehicle; LTR is the actual lateral load transfer rate of the vehicle;

[0047] The additional yaw moment ΔM that controls the lateral load transfer rate LTR The calculation formula is as follows:

[0048]

[0049] Where ω is the actual yaw rate of the vehicle; * is the desired yaw rate of the vehicle; LTR * is the ideal lateral load transfer rate of the vehicle; is the vehicle roll angular velocity; β is the vehicle's actual center of mass sideslip angle; β * is the ideal side slip angle of the vehicle's center of mass; a y is the actual lateral acceleration of the vehicle; is the ideal lateral acceleration of the vehicle; v x is the longitudinal speed of the vehicle; δ f is the actual steering wheel angle of the vehicle; is the ideal steering wheel angle of the vehicle;

[0050] The calculation formula of the actual vehicle lateral load transfer rate LTR is as follows:

[0051]

[0052] Where a y is the actual lateral acceleration of the vehicle; h CG is the height of the center of mass; W is the wheelbase of the vehicle; F zf is the vertical load on the front axle; F zr is the vertical load on the rear axle; is the body roll angle; is the roll angular velocity; is the roll angular acceleration; is the suspension roll stiffness; is the suspension roll damping; μ is the road adhesion coefficient; ω is the actual yaw angular velocity of the vehicle.

[0053] The torque distribution execution module is used to distribute the torque of the four wheels, and the vehicle execution mode is determined by the vehicle state driving coefficient;

[0054] The vehicle state driving coefficient calculation formula is as follows:

[0055]

[0056] Where S yaw is the yaw instability factor; S lateral is the roll instability factor; v x F is the longitudinal speed of the vehicle; x is the longitudinal force on the vehicle; F y is the lateral force on the vehicle; a yis the actual lateral acceleration of the vehicle; is the actual yaw angular velocity of the vehicle; LTR is the actual lateral load transfer rate of the vehicle; h CG is the height of the center of mass; W is the vehicle wheelbase;

[0057] When the driving coefficient 0≤S driver When <1, the vehicle execution mode selects the four-wheel independent drive mode;

[0058] In the four-wheel independent drive mode, the calculation formula for the torque applied to each wheel is as follows:

[0059]

[0060]

[0061] Where, T fl 、T fr 、T rl 、T rr are the driving torques of the left front wheel, right front wheel, left rear wheel, and right rear wheel respectively; T d is the total driving torque; f ,λ r are the slip rates of the front and rear wheels respectively; F zf is the vertical load on the front axle; F zr is the vertical load on the rear axle; v x is the longitudinal speed of the vehicle; is the vehicle body roll angle; ω is the actual vehicle yaw rate; μ is the road adhesion coefficient; ΔM is the vehicle additional yaw moment; W is the vehicle wheelbase; β is the vehicle actual center of mass sideslip angle; LTR is the vehicle actual lateral load transfer rate; a y is the actual lateral acceleration of the vehicle; h CG is the height of the center of mass;

[0062] When the driving state driving coefficient S driver When ≥1, the vehicle execution mode selects the four-wheel independent braking mode;

[0063] In the four-wheel independent braking mode, the calculation formula for the torque applied by each wheel is as follows:

[0064]

[0065] Where B fl 、B fr 、B rl 、B rr are the braking torques of the left front wheel, right front wheel, left rear wheel, and right rear wheel respectively; B d is the total braking torque; β is the actual side slip angle of the vehicle's center of mass; F x is the longitudinal force acting on the vehicle; is the roll angular velocity; ΔM is the additional yaw moment of the vehicle; W is the vehicle wheelbase; δ f is the front wheel turning angle; μ is the road adhesion coefficient; v x is the longitudinal speed of the vehicle; ω is the actual yaw rate of the vehicle; LTR is the actual lateral load transfer rate of the vehicle; a x is the vehicle longitudinal acceleration; F zf is the vertical load on the front axle; F zr is the vertical load on the rear axle; h CG is the centroid height.

[0066] The beneficial effects of the present invention are:

[0067] 1. The present invention can collect the vehicle's dynamic state and the driver's control behavior, risk perception, and environmental adaptation characteristics in real time, and use a multi-factor evaluation model and neural network algorithm to identify driving style, thereby realizing personalized vehicle stability control strategy selection and enhancing the system's adaptability to differences in driver behavior.

[0068] 2. This invention constructs additional yaw moment models for three types of driving styles, adjusting key indicators such as yaw rate, sideslip angle at the center of mass, and lateral load transfer rate respectively, effectively improving the vehicle's dynamic response accuracy and driving stability under different driving styles, and avoiding the degradation of control performance caused by a unified control strategy.

[0069] 3. The present invention further combines the vehicle state coefficient to intelligently select four-wheel independent drive or four-wheel independent braking mode, and dynamically adjusts the output torque in combination with the torque distribution model of each wheel, thereby achieving refined control of the vehicle posture under extreme working conditions, improving the vehicle's yaw stability and roll suppression capabilities, and enhancing active safety performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] The present invention will be further described below in conjunction with the accompanying drawings:

[0071] Figure 1 This is a framework diagram of an intelligent vehicle stability control method based on driver characteristics proposed in the present invention. DETAILED DESCRIPTION

[0072] The present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0073] See Figure 1 The present invention provides an intelligent vehicle stability control method based on driver characteristics, comprising a vehicle state information acquisition module, a driver style recognition module, a vehicle additional yaw moment calculation module, and a torque distribution execution module;

[0074] The vehicle status information acquisition module is used to obtain the vehicle's actual center of mass sideslip angle β, the vehicle's actual yaw angular velocity ω, and the vehicle's actual lateral acceleration a y , front wheel slip rate λ f , rear wheel slip rate λ r , vehicle longitudinal speed v x , front axle vertical load F zf , rear axle vertical load F zr , body roll angle , road adhesion coefficient μ, vehicle wheelbase W, center of mass height h CG , lateral force F on the front wheel yf ; Lateral force F on the rear wheel yr 、The longitudinal force F acting on the vehicle x , the lateral force F acting on the vehicle y ;

[0075] The driver style recognition module is used to calculate the control behavior factor, environmental adaptability factor, risk perception and decision-making factor, and thus calculate the driver's comprehensive evaluation factor based on multiple evaluation factors to determine the driver's driving style;

[0076] The manipulation behavior factor S c The calculation formula is as follows:

[0077]

[0078] Where, is the average value of the steering wheel angular velocity; δ s,max is the maximum value of the steering wheel angular velocity; is the average value of the steering wheel angular acceleration; a s,max is the maximum value of the steering wheel angular acceleration; is the average value of the throttle opening change rate; ΔT a,max is the maximum value of the throttle opening change rate; is the average value of the brake pedal pressure change rate; ΔP b,max is the maximum value of the brake pedal pressure change rate; N acc N is the number of rapid accelerations per kilometer; acc,max N is the maximum number of rapid accelerations per kilometer; brk N is the number of sudden brakes per kilometer; brk,max The maximum number of emergency braking times per kilometer;

[0079] The environmental adaptability factor S e The calculation formula is as follows:

[0080]

[0081] Where, is the average value of the following distance change rate; Δd f,max The maximum value of the following distance change rate; N l is the number of lane changes per kilometer; N l,max is the maximum number of lane changes per kilometer; is the average value of the speed adjustment range in the curve; Δv c,max The maximum value of the speed adjustment range in the curve; t rg Traffic light response time; is the average response time of traffic lights; σ rg is the standard deviation of traffic light response time;

[0082] The risk perception and decision factor S r The calculation formula is as follows:

[0083]

[0084] Where, d f is the average following distance; d f,max is the maximum following distance; t b is the brake advance time; t b,max The maximum value of the brake advance time; R s is the overspeed time ratio; R s,max is the maximum value of the overspeed time ratio; R close is the triggering frequency of forward collision warning and lane departure warning; T dis Distract the driver's attention for a long time; dis,max The maximum time the driver's attention is distracted;

[0085] The driver style recognition module uses a fully connected neural network algorithm to determine the driver style category based on the driver's control behavior score, environmental adaptability score, risk perception and decision-making score. The specific structure is designed as follows:

[0086] The input layer consists of three nodes, corresponding to the control behavior factor, the environmental adaptability factor, and the risk perception and decision-making factor. The hidden layer adopts a three-layer structure, including the first hidden layer, the second hidden layer, and the third hidden layer. The first hidden layer, the second hidden layer, and the third hidden layer contain 64, 32, and 16 neurons, respectively. The output layer consists of one node, and the output is the driver's style.

[0087] The calculation formula for the driver style judgment is:

[0088]

[0089] Where S c 、S e 、S rThey are manipulation behavior factor, environmental adaptability factor, risk perception and decision factor; Z (1) ,Z (2) ,Z (3) ,Z (4) is the output of the first hidden layer, the second hidden layer, the third hidden layer and the output layer after linear transformation; W (1) ,W (2) ,W (3) ,W (4) are the weight matrices from the input layer to the first hidden layer, from the first hidden layer to the second hidden layer, from the second hidden layer to the third hidden layer, and from the third hidden layer to the output layer; b (1) ,b (2) ,b (3) ,b (4) are the bias terms for the first hidden layer, the second hidden layer, the third hidden layer, and the output layer, respectively; ReLU is the activation function, defined as ReLU(x) = max(0, x), to enhance the nonlinear expression capability of the network; P(y = k|X) represents the probability that the input data X is classified as category k. Its calculation process is Softmax normalization to ensure that the output is a probability distribution. The three neurons correspond to the probabilities of aggressive, balanced, and conservative, respectively. is the exponential transformation score of the kth category; The index sum of scores for all categories; It means that among all possible categories k, the k that maximizes the expression on the right is selected. A, B, and C represent the driver style of aggressive, balanced, and conservative respectively;

[0090] The vehicle additional yaw moment calculation module is configured to receive the driver style information output by the driver style recognition module and apply different additional yaw moments for conservative, balanced, and aggressive drivers, respectively. The additional yaw moment is calculated by combining an additional yaw moment for controlling the yaw angular velocity, an additional yaw moment for controlling the sideslip angle of the center of mass, and an additional yaw moment for controlling the lateral load transfer rate.

[0091] The torque distribution execution module calculates the vehicle driving state coefficient by considering the yaw instability factor and the roll instability factor, determines the vehicle execution mode according to the vehicle driving state coefficient, and calculates the torque of each wheel for the four-wheel independent drive mode and the four-wheel independent braking mode respectively.

[0092] The vehicle additional yaw moment calculation module is used to calculate the vehicle additional yaw moment according to the driver's style;

[0093] When the driver's style is conservative, the calculation formula of the vehicle additional yaw moment ΔM is:

[0094]

[0095] Where, β is the actual side slip angle of the vehicle's center of mass; β * is the ideal vehicle center of mass sideslip angle; ΔM ω The additional yaw moment to control the yaw rate; ΔM β is the additional yaw moment to control the sideslip angle of the center of mass; s β is the coefficient that controls the steepness of the transition;

[0096] When the driver's style is balanced, the calculation formula of the vehicle's additional yaw moment ΔM is:

[0097]

[0098] Where, LTR is the actual lateral load transfer rate of the vehicle; LTR * is the ideal lateral load transfer rate of the vehicle; β is the actual side slip angle of the vehicle's center of mass; β * is the ideal side slip angle of the vehicle's center of mass; E β is the threshold of the vehicle's center of mass sideslip angle; ΔM ω The additional yaw moment to control the yaw rate; ΔM β The additional yaw moment to control the sideslip angle of the center of mass; ΔM LTR Additional yaw moment to control the lateral load transfer rate;

[0099] When the driver's style is aggressive, the calculation formula of the vehicle's additional yaw moment ΔM is:

[0100] ΔM=(1-lnS yaw )ΔM β +lnS lateral ΔM LTR

[0101] Where, ΔM β The additional yaw moment to control the sideslip angle of the center of mass; ΔM LTR The additional yaw moment to control the lateral load transfer rate; S yaw is the yaw instability factor; S lateral is the roll instability factor;

[0102] The yaw instability factor S yaw The calculation formula is as follows:

[0103]

[0104] Where, β is the actual side slip angle of the vehicle's center of mass; β * is the ideal center of mass sideslip angle of the vehicle; ω is the actual yaw rate of the vehicle; ω * is the ideal yaw rate of the vehicle; v x is the longitudinal speed of the vehicle; μ is the road adhesion coefficient; is the roll angular velocity; LTR is the actual lateral load transfer rate of the vehicle; LTR * is the ideal lateral load transfer rate of the vehicle; F yf is the lateral force on the front wheel; F yr is the lateral force on the rear wheel;

[0105] The roll instability factor S lateral The calculation formula is as follows:

[0106]

[0107] Where, The maximum roll angle allowed for the vehicle body; is the vehicle body roll angle; LTR is the actual lateral load transfer rate of the vehicle; LTR * is the ideal lateral load transfer rate of the vehicle; v x is the longitudinal speed of the vehicle; for suspension roll damping; is the body roll inertia moment; is the suspension roll stiffness; F zf is the vertical load on the front axle; F zr is the vertical load on the rear axle.

[0108] The vehicle additional yaw moment calculation module controls the additional yaw moment ΔM of the yaw angular velocity ω The calculation formula is as follows:

[0109]

[0110] Where ω is the actual yaw rate of the vehicle; * is the desired yaw rate of the vehicle; δ f is the actual steering wheel angle of the vehicle; δ f * is the ideal steering wheel angle of the vehicle; F yf is the lateral force on the front wheel; F yr is the lateral force on the rear wheel; a y is the actual lateral acceleration of the vehicle; a y * is the ideal lateral acceleration of the vehicle; LTR is the actual lateral load transfer rate of the vehicle;

[0111] The additional yaw moment ΔM that controls the sideslip angle of the center of mass β The calculation formula is as follows:

[0112]

[0113] Where, β is the actual side slip angle of the vehicle's center of mass; β * is the ideal side slip angle of the vehicle's center of mass; a yis the actual lateral acceleration of the vehicle; is the ideal lateral acceleration of the vehicle; F yf is the lateral force on the front wheel; F yr is the lateral force on the rear wheel; v x is the longitudinal speed of the vehicle; LTR is the actual lateral load transfer rate of the vehicle;

[0114] The additional yaw moment ΔM that controls the lateral load transfer rate LTR The calculation formula is as follows:

[0115]

[0116] Where ω is the actual yaw rate of the vehicle; * is the desired yaw rate of the vehicle; LTR * is the ideal lateral load transfer rate of the vehicle; is the vehicle roll angular velocity; β is the vehicle's actual center of mass sideslip angle; β * is the ideal side slip angle of the vehicle's center of mass; a y is the actual lateral acceleration of the vehicle; is the ideal lateral acceleration of the vehicle; v x is the longitudinal speed of the vehicle; δ f is the actual steering wheel angle of the vehicle; is the ideal steering wheel angle of the vehicle;

[0117] The calculation formula of the actual vehicle lateral load transfer rate LTR is as follows:

[0118]

[0119] Where a y is the actual lateral acceleration of the vehicle; h CG is the height of the center of mass; W is the wheelbase of the vehicle; F zf is the vertical load on the front axle; F zr is the vertical load on the rear axle; is the body roll angle; is the roll angular velocity; is the roll angular acceleration; is the suspension roll stiffness; is the suspension roll damping; μ is the road adhesion coefficient; ω is the actual yaw angular velocity of the vehicle.

[0120] The torque distribution execution module is used to distribute the torque of the four wheels, and the vehicle execution mode is determined by the vehicle state driving coefficient;

[0121] The vehicle state driving coefficient calculation formula is as follows:

[0122]

[0123] Where S yaw is the yaw instability factor; S lateral is the roll instability factor; v x F is the longitudinal speed of the vehicle; x is the longitudinal force on the vehicle; F y is the lateral force on the vehicle; a y is the actual lateral acceleration of the vehicle; is the actual yaw angular velocity of the vehicle; LTR is the actual lateral load transfer rate of the vehicle; h CG is the height of the center of mass; W is the vehicle wheelbase;

[0124] When the driving coefficient 0≤S driver When <1, the vehicle execution mode selects the four-wheel independent drive mode;

[0125] In the four-wheel independent drive mode, the calculation formula for the torque applied to each wheel is as follows:

[0126]

[0127] Where, T fl 、T fr 、T rl 、T rr are the driving torques of the left front wheel, right front wheel, left rear wheel, and right rear wheel respectively; T d is the total driving torque; f ,λ r are the slip rates of the front and rear wheels respectively; F zf is the vertical load on the front axle; F zr is the vertical load on the rear axle; v x is the longitudinal speed of the vehicle; is the vehicle body roll angle; ω is the actual vehicle yaw rate; μ is the road adhesion coefficient; ΔM is the vehicle additional yaw moment; W is the vehicle wheelbase; β is the vehicle actual center of mass sideslip angle; LTR is the vehicle actual lateral load transfer rate; a y is the actual lateral acceleration of the vehicle; h CG is the height of the center of mass;

[0128] When the driving state driving coefficient S driver When ≥1, the vehicle execution mode selects the four-wheel independent braking mode;

[0129] In the four-wheel independent braking mode, the calculation formula for the torque applied by each wheel is as follows:

[0130]

[0131]

[0132] Where B fl 、B fr 、B rl 、B rr are the braking torques of the left front wheel, right front wheel, left rear wheel, and right rear wheel respectively; B d is the total braking torque; β is the actual side slip angle of the vehicle's center of mass; F x is the longitudinal force acting on the vehicle; is the roll angular velocity; ΔM is the additional yaw moment of the vehicle; W is the vehicle wheelbase; δ f is the front wheel turning angle; μ is the road adhesion coefficient; v x is the longitudinal speed of the vehicle; ω is the actual yaw rate of the vehicle; LTR is the actual lateral load transfer rate of the vehicle; a x is the vehicle longitudinal acceleration; F zf is the vertical load on the front axle; F zr is the vertical load on the rear axle; h CG is the centroid height.

Claims

1. An intelligent vehicle stability control method based on driver characteristics, characterized in that: It includes vehicle status information acquisition module, driver style recognition module, vehicle additional yaw moment calculation module, and torque distribution execution module; The vehicle status information acquisition module is used to obtain the vehicle's actual center of mass sideslip angle β, the vehicle's actual yaw angular velocity ω, and the vehicle's actual lateral acceleration a y , front wheel slip rate λ f , rear wheel slip rate λ r , vehicle longitudinal speed v x , front axle vertical load F zf , rear axle vertical load F zr , body roll angle Road adhesion coefficient μ, vehicle wheelbase W, center of mass height h CG , lateral force F on the front wheel yf ; Lateral force F on the rear wheel yr 、The longitudinal force F acting on the vehicle x , the lateral force F acting on the vehicle y ; The driver style recognition module is used to calculate the control behavior factor, environmental adaptability factor, risk perception and decision-making factor, and thus calculate the driver's comprehensive evaluation factor based on multiple evaluation factors to determine the driver's driving style; The manipulation behavior factor S c The calculation formula is as follows: Where, is the average value of the steering wheel angular velocity; δ s,max is the maximum value of the steering wheel angular velocity; is the average value of the steering wheel angular acceleration; a s,max is the maximum value of the steering wheel angular acceleration; is the average value of the throttle opening change rate; ΔT a,max is the maximum value of the throttle opening change rate; is the average value of the brake pedal pressure change rate; ΔP b,max is the maximum value of the brake pedal pressure change rate; N acc N is the number of rapid accelerations per kilometer; acc,max N is the maximum number of rapid accelerations per kilometer; brk N is the number of sudden brakes per kilometer; brk,max The maximum number of emergency braking times per kilometer; The environmental adaptability factor S e The calculation formula is as follows: Where, is the average value of the following distance change rate; Δd f,max The maximum value of the following distance change rate; N l is the number of lane changes per kilometer; N l,max is the maximum number of lane changes per kilometer; is the average value of the speed adjustment range in the curve; Δv c,max The maximum value of the speed adjustment range in the curve; t rg Traffic light response time; is the average response time of traffic lights; σ rg is the standard deviation of traffic light response time; The risk perception and decision factor S r The calculation formula is as follows: Where, is the average following distance; d f,max is the maximum following distance; t b Provides time for braking; t b,max The maximum value of the brake advance time; R s is the overspeed time ratio; R s,max is the maximum value of the overspeed time ratio; R close is the triggering frequency of forward collision warning and lane departure warning; T dis Provides driver distraction time; T dis,max The maximum time the driver's attention is distracted; The driver style recognition module uses a fully connected neural network algorithm to determine the driver style category based on the driver's control behavior score, environmental adaptability score, risk perception and decision-making score. The specific structure is designed as follows: The input layer consists of three nodes, corresponding to the control behavior factor, the environmental adaptability factor, and the risk perception and decision-making factor. The hidden layer adopts a three-layer structure, including the first hidden layer, the second hidden layer, and the third hidden layer. The first hidden layer, the second hidden layer, and the third hidden layer contain 64, 32, and 16 neurons, respectively. The output layer consists of one node, and the output is the driver's style. The calculation formula for the driver style judgment is: Where S c 、S e 、S r They are manipulation behavior factor, environmental adaptability factor, risk perception and decision factor; Z (1) ,Z (2) ,Z (3) ,Z (4) is the output of the first hidden layer, the second hidden layer, the third hidden layer and the output layer after linear transformation; W (1) ,W (2) ,W (3) ,W (4) are the weight matrices from the input layer to the first hidden layer, from the first hidden layer to the second hidden layer, from the second hidden layer to the third hidden layer, and from the third hidden layer to the output layer; b (1) ,b (2) ,b (3) ,b (4) are the bias items of the first hidden layer, the second hidden layer, the third hidden layer and the output layer respectively; ReLU is the activation function, which is defined as ReLU(x)=max(0,x) to enhance the nonlinear expression ability of the network; P(y=k|X) represents the probability that the input data X is classified as category k. Its calculation process is Softmax normalization to ensure that the output is a probability distribution. The three neurons correspond to the radical, balanced and conservative types respectively. The probability of type; is the exponential transformation score of the kth category; The index sum of scores for all categories; It means that among all possible categories k, the k that maximizes the expression on the right is selected. A, B, and C represent the driver style of aggressive, balanced, and conservative respectively; The vehicle additional yaw moment calculation module is configured to receive the driver style information output by the driver style recognition module and apply different additional yaw moments for conservative, balanced, and aggressive drivers, respectively. The additional yaw moment is calculated by combining an additional yaw moment for controlling the yaw angular velocity, an additional yaw moment for controlling the sideslip angle of the center of mass, and an additional yaw moment for controlling the lateral load transfer rate. The torque distribution execution module calculates the vehicle driving state coefficient by considering the yaw instability factor and the roll instability factor, determines the vehicle execution mode according to the vehicle driving state coefficient, and calculates the torque of each wheel for the four-wheel independent drive mode and the four-wheel independent braking mode respectively.

2. The intelligent vehicle stability control method based on driver characteristics according to claim 1, characterized in that: The vehicle additional yaw moment calculation module is used to calculate the vehicle additional yaw moment according to the driver's style; When the driver's style is conservative, the calculation formula of the vehicle additional yaw moment ΔM is: Where β is the actual side slip angle of the vehicle's center of mass; β * is the ideal vehicle center of mass sideslip angle; ΔM ω The additional yaw moment to control the yaw rate; ΔM β is the additional yaw moment to control the sideslip angle of the center of mass; s β is the coefficient that controls the steepness of the transition; When the driver's style is balanced, the calculation formula of the vehicle's additional yaw moment ΔM is: Where, LTR is the actual lateral load transfer rate of the vehicle; LTR * is the ideal lateral load transfer rate of the vehicle; β is the actual side slip angle of the vehicle's center of mass; β * is the ideal side slip angle of the vehicle's center of mass; E β is the threshold of the vehicle's center of mass sideslip angle; ΔM ω The additional yaw moment to control the yaw rate; ΔM β The additional yaw moment to control the sideslip angle of the center of mass; ΔM LTR Additional yaw moment to control the lateral load transfer rate; When the driver's style is aggressive, the calculation formula of the vehicle's additional yaw moment ΔM is: ΔM=(1-lnS yaw )ΔM β +lnS lateral ΔM LTR Where, ΔM β The additional yaw moment to control the sideslip angle of the center of mass; ΔM LTR The additional yaw moment to control the lateral load transfer rate; S yaw is the yaw instability factor; S lateral is the roll instability factor; The yaw instability factor S yaw The calculation formula is as follows: Where β is the actual side slip angle of the vehicle's center of mass; β * is the ideal center of mass sideslip angle of the vehicle; ω is the actual yaw rate of the vehicle; ω * is the ideal yaw rate of the vehicle; v x is the longitudinal speed of the vehicle; μ is the road adhesion coefficient; is the roll angular velocity; LTR is the actual lateral load transfer rate of the vehicle; LTR * is the ideal lateral load transfer rate of the vehicle; F yf is the lateral force on the front wheel; F yr is the lateral force on the rear wheel; The roll instability factor S lateral The calculation formula is as follows: Where, The maximum roll angle allowed for the vehicle body; is the vehicle body roll angle; LTR is the actual lateral load transfer rate of the vehicle; LTR * is the ideal lateral load transfer rate of the vehicle; v x is the longitudinal speed of the vehicle; for suspension roll damping; is the body roll inertia moment; is the suspension roll stiffness; F zf is the vertical load on the front axle; F zr is the vertical load on the rear axle.

3. The intelligent vehicle stability control method based on driver characteristics according to claim 1, characterized in that: The vehicle additional yaw moment calculation module controls the additional yaw moment ΔM of the yaw angular velocity ω The calculation formula is as follows: Where ω is the actual yaw rate of the vehicle; * is the desired yaw rate of the vehicle; δ f is the actual steering wheel angle of the vehicle; is the ideal steering wheel angle of the vehicle; F yf is the lateral force on the front wheel; F yr is the lateral force on the rear wheel; a y is the actual lateral acceleration of the vehicle; is the ideal lateral acceleration of the vehicle; LTR is the actual lateral load transfer rate of the vehicle; The additional yaw moment ΔM that controls the sideslip angle of the center of mass β The calculation formula is as follows: Where β is the actual side slip angle of the vehicle's center of mass; β * is the ideal side slip angle of the vehicle's center of mass; a y is the actual lateral acceleration of the vehicle; is the ideal lateral acceleration of the vehicle; F yf is the lateral force on the front wheel; F yr is the lateral force on the rear wheel; v x is the longitudinal speed of the vehicle; LTR is the actual lateral load transfer rate of the vehicle; The additional yaw moment ΔM that controls the lateral load transfer rate LTR The calculation formula is as follows: Where ω is the actual yaw rate of the vehicle; * is the desired yaw rate of the vehicle; LTR * is the ideal lateral load transfer rate of the vehicle; is the vehicle's roll angular velocity; β is the vehicle's actual center of mass sideslip angle; β * is the ideal side slip angle of the vehicle's center of mass; a y is the actual lateral acceleration of the vehicle; is the ideal lateral acceleration of the vehicle; v x is the longitudinal speed of the vehicle; δ f is the actual steering wheel angle of the vehicle; is the ideal steering wheel angle of the vehicle; The calculation formula of the actual vehicle lateral load transfer rate LTR is as follows: Where a y is the actual lateral acceleration of the vehicle; h CG is the height of the center of mass; W is the wheelbase of the vehicle; F zf is the vertical load on the front axle; F zr is the vertical load on the rear axle; is the body roll angle; is the roll angular velocity; is the roll angular acceleration; is the suspension roll stiffness; is the suspension roll damping; μ is the road adhesion coefficient; ω is the actual yaw angular velocity of the vehicle.

4. The intelligent vehicle stability control method based on driver characteristics according to claim 1, characterized in that: The torque distribution execution module is used to distribute the torque of the four wheels, and the vehicle execution mode is determined by the vehicle state driving coefficient; The vehicle state driving coefficient calculation formula is as follows: Where S yaw is the yaw instability factor; S lateral is the roll instability factor; v x F is the longitudinal speed of the vehicle; x is the longitudinal force on the vehicle; F y is the lateral force on the vehicle; a y is the actual lateral acceleration of the vehicle; is the actual yaw angular velocity of the vehicle; LTR is the actual lateral load transfer rate of the vehicle; h CG is the height of the center of mass; W is the vehicle wheelbase; When the driving coefficient 0≤S driver When <1, the vehicle execution mode selects the four-wheel independent drive mode; In the four-wheel independent drive mode, the calculation formula for the torque applied to each wheel is as follows: Where, T fl 、T fr 、T rl 、T rr are the driving torques of the left front wheel, right front wheel, left rear wheel, and right rear wheel respectively; T d is the total driving torque; f ,λ r are the slip rates of the front and rear wheels respectively; F zf is the vertical load on the front axle; F zr is the vertical load on the rear axle; v x is the longitudinal speed of the vehicle; is the vehicle body roll angle; ω is the actual vehicle yaw rate; μ is the road adhesion coefficient; ΔM is the vehicle additional yaw moment; W is the vehicle wheelbase; β is the vehicle actual center of mass sideslip angle; LTR is the vehicle actual lateral load transfer rate; a y is the actual lateral acceleration of the vehicle; h CG is the height of the center of mass; When the driving state driving coefficient S driver When ≥1, the vehicle execution mode selects the four-wheel independent braking mode; In the four-wheel independent braking mode, the calculation formula for the torque applied by each wheel is as follows: Where B fl 、B fr 、B rl 、B rr are the braking torques of the left front wheel, right front wheel, left rear wheel, and right rear wheel respectively; B d is the total braking torque; β is the actual side slip angle of the vehicle's center of mass; F x is the longitudinal force acting on the vehicle; is the roll angular velocity; ΔM is the additional yaw moment of the vehicle; W is the vehicle wheelbase; δ f is the front wheel turning angle; μ is the road adhesion coefficient; v x is the longitudinal speed of the vehicle; ω is the actual yaw rate of the vehicle; LTR is the actual lateral load transfer rate of the vehicle; a x is the vehicle longitudinal acceleration; F zf is the vertical load on the front axle; F zr is the vertical load on the rear axle; h CG is the centroid height.

Images