Steering mode switching method based on intelligent electric vehicle
By using a fully connected neural network in electric vehicles for comprehensive evaluation of driving status and dynamic steering mode switching, the problem of inability to effectively comprehensively evaluate multidimensional factors in the prior art is solved, and more efficient handling and higher safety are achieved.
Patent Information
- Application Number
- CN202510379955.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-28
- Publication Date
- 2025-05-30
AI Technical Summary
The existing electric vehicle steering control system cannot effectively comprehensively evaluate multi-dimensional factors, resulting in insufficient control, lagging response or excessive energy consumption under complex road conditions or special operating requirements, making it difficult to meet the dual requirements of intelligent vehicles for efficient handling and safety.
The information acquisition module based on the wireless vehicle perception system is adopted, and the driving state comprehensive evaluation module is integrated with multi-source perception information, and the driving state comprehensive evaluation factor is calculated using a fully connected neural network, and the steering mode is dynamically switched, including the front wheel steering mode, four-wheel steering mode and oblique steering mode.
It significantly improves the intelligence level and personalized adaptability of steering control, improves the vehicle's handling accuracy and response efficiency under multiple operating conditions, optimizes the vehicle's handling performance, reduces the risk of side slips, and improves the stability, safety and ride comfort of the vehicle.
Smart Images

Figure CN120056971A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of vehicle handling stability, relates to electric vehicle steering control technology, and particularly relates to a steering mode switching method based on intelligent electric vehicles. Background Art
[0002] With the continuous development of intelligent electric vehicles and autonomous driving technologies, the vehicle's maneuverability, adaptability, and human-machine collaboration performance have increasingly become research hotspots. Currently, most steering control systems are still mainly designed with a fixed structure or based on a single driving mode, unable to actively adjust according to different driving states. Especially under complex road conditions or special operation requirements, the traditional steering mode switching method lacks flexibility and is difficult to meet the dual requirements of efficient handling and safety for intelligent vehicles.
[0003] During actual driving, factors such as vehicle state, road environment, driver operation behavior, and the interaction between tires and the ground are highly coupled, directly affecting the vehicle's dynamic response and stability. Existing systems often cannot comprehensively evaluate these multi-dimensional factors, nor can they perform reasonable dynamic switching of the steering mode according to the driving state, easily leading to insufficient handling, response lag, or excessive energy consumption. Therefore, there is an urgent need to propose a steering control method that can integrate multi-source perception information and achieve intelligent mode switching based on multi-factor comprehensive evaluation to improve the handling flexibility and stable safety of intelligent electric vehicles under various working conditions. Summary of the Invention
[0004] The purpose of the present invention is to provide a steering mode switching method based on intelligent electric vehicles to solve the problems faced in the above background art.
[0005] To achieve the above purpose, the present invention provides the following solutions:
[0006] A steering mode switching method based on intelligent electric vehicles, including an information acquisition module based on a wireless vehicle perception system, a driving state comprehensive evaluation module, a steering mode selection module, and a steering driving unit execution module;
[0007] The information acquisition module based on the wireless vehicle perception system is used to obtain the following information of the vehicle in real time: vehicle longitudinal driving speed v x , vehicle lateral driving speed v y , lateral acceleration a y , yaw angular velocity ω, front wheel steering angle δ f , front wheel side slip angle α f , rear wheel side slip angle α r , steering wheel angle δ sw , tire longitudinal force F x , tire vertical force F z , body roll angle φ, front wheel lateral force Fyf 、Lateral force of the rear wheel F yr 、Pitch angular velocity q, front suspension compression Z f 、Rear suspension compression Z r 、Distance from the center of mass to the front axle l f 、Distance from the center of mass to the rear axle l r 、Cornering stiffness of the front axle C f 、Cornering stiffness of the rear axle C r ;
[0008] The comprehensive driving state evaluation module determines the comprehensive driving state of the vehicle based on multiple evaluation factors, and calculates the vehicle driving state factor, road condition and environment factor, driver behavior and reaction factor, tire dynamic characteristic factor, and vehicle dynamic stability factor;
[0009] The vehicle driving state factor S vehicle is calculated as follows:
[0010]
[0011] In the formula, v x is the longitudinal driving speed of the vehicle; v y is the lateral driving speed of the vehicle; ω is the yaw angular velocity; a y is the lateral acceleration; α f is the front wheel side slip angle; α r is the rear wheel side slip angle; S sr is the vehicle steering response factor;
[0012] The road condition and environment factor S road is calculated as follows:
[0013]
[0014] In the formula, S weather is the weather influence factor; S temperature is the temperature influence factor; S visibility Visibility influence factor;
[0015] The driver behavior and reaction factor S driver is calculated as follows:
[0016]
[0017] In the formula, S control is the driver operation factor; S cognition is the driver cognitive reaction factor; S physiology is the driver physiological state factor;
[0018] The tire dynamic characteristic factor S tire is calculated as follows:
[0019]
[0020] Wherein, S slip is the tire slip factor; S load is the tire load factor;
[0021] The vehicle dynamic stability S stability is calculated as follows:
[0022]
[0023] Wherein, S yaw is the yaw stability factor; S lateral is the roll stability factor; S pitch is the pitch stability factor;
[0024] The steering mode selection module includes front-wheel steering mode, four-wheel steering mode, and diagonal steering mode; the threshold of the front-wheel steering mode is set as α 1 , the threshold of the four-wheel steering mode is α 2 , and the threshold of the diagonal steering mode is α 3 , and the corresponding steering mode is selected according to the magnitude relationship between the driving state comprehensive evaluation factor S and each threshold;
[0025] The steering driving unit execution module is used to calculate the wheel angles under the three modes of front-wheel steering mode, four-wheel steering mode, and diagonal steering mode;
[0026] When the vehicle selects the front-wheel steering mode, the inner front wheel angle δ 2in-f and the outer front wheel angle δ 2out-f depend on the vehicle turning radius R, the front and rear wheelbase L, and the front wheel track W, and the inner rear wheel angle δ 2in-r and the outer rear wheel angle δ 2out-r are both 0;
[0027] When the vehicle selects the four-wheel steering mode, the inner front wheel angle δ 4in-f and the outer front wheel angle δ 4out-f depend on the vehicle turning radius R, the front and rear wheelbase L, and the front wheel track W, and the inner rear wheel angle δ 4in-r depends on the inner front wheel angle δ 4in-f , the front axle cornering stiffness C f , the rear axle cornering stiffness C r , the total vehicle mass m, the vehicle longitudinal driving speed v x , the distance l from the center of mass to the front axle f , the distance l from the center of mass to the rear axle r , the yaw angular velocity ω, and the outer rear wheel angle δ 4out-rDepending on the outer front wheel angle δ 4out-f , the cornering stiffness C of the front axle f , the cornering stiffness C of the rear axle r , the total vehicle mass m, the longitudinal vehicle speed v x , the distance l from the center of mass to the front axle f , the distance l from the center of mass to the rear axle r , the yaw rate ω;
[0028] When the vehicle selects the diagonal steering mode, the steering angles of the four wheels are the same, and the wheel steering angle depends on the distance l from the center of mass to the front axle f , the distance l from the center of mass to the rear axle r , the cornering stiffness C of the front axle f , the cornering stiffness C of the rear axle r , the wheelbase L between the front and rear axles, the total vehicle mass m, the longitudinal vehicle speed v x , the turning radius R of the vehicle.
[0029] For the driving state comprehensive evaluation module, the vehicle steering response factor S sr The calculation formula is as follows:
[0030]
[0031] In the formula, α f is the front wheel side slip angle; α r is the rear wheel side slip angle; a y is the lateral acceleration; ω is the yaw rate; v x is the longitudinal vehicle speed; v y is the lateral vehicle speed;
[0032] For the weather influence factor S weather The calculation formula is as follows:
[0033]
[0034] In the formula, H is the wetness. When H = 0, the road surface is completely dry. When H = 1, the road surface is completely wet; H a is the air humidity; P r is the precipitation; S d is the snow thickness; P a is the air pressure; W is the wind speed;
[0035] For the temperature influence factor S temperature The calculation formula is as follows:
[0036]
[0037] In the formula, D t is the day-night temperature difference; T is the ambient temperature; T dis the dew point temperature; T g is the surface temperature; P r is the precipitation; T w is the wind chill index;
[0038] The visibility influence factor S visibility has the following calculation formula:
[0039]
[0040] In the formula, V d is the visibility; F d is the fog density; A q is the air pollution index; L is the light intensity; U v is the ultraviolet index; R n is the optical refractive index;
[0041] The driver operation factor S control has the following calculation formula:
[0042]
[0043] In the formula, δ sw is the steering wheel angle; is the steering wheel angular velocity; A p is the throttle pedal opening; A b is the brake pedal opening; F pb is the switching frequency of the throttle and brake per minute; F pa is the rotation frequency of the steering wheel per minute;
[0044] The driver cognitive reaction factor S cognition has the following calculation formula:
[0045]
[0046] In the formula, τ d is the driver reaction time; P is the pupil diameter change rate; H m is the head rotation angle; C l is the cognitive load index; T s is the driver's line of sight deviation time; P v is the complexity of the traffic conditions within the field of vision; A w is the driver's alertness level;
[0047] The driver physiological state factor S physiology has the following calculation formula:
[0048]
[0049] In the formula, H r is the heart rate; S pis the pressure index; F t is the fatigue index; R r is the breathing rate; C s is the drowsiness score.
[0050] The driving state comprehensive evaluation module, the tire slip factor S slip has the following calculation formula:
[0051]
[0052] In the formula, λ is the tire slip ratio; α f is the front wheel side slip angle; α r is the rear wheel side slip angle; F x is the tire longitudinal force; μ is the road surface adhesion coefficient;
[0053] The tire load factor S load has the following calculation formula:
[0054]
[0055] In the formula, F z is the tire vertical force; ΔF z is the dynamic change amount of the tire vertical load; κ is the tire deflection deformation rate; K s is the suspension stiffness;
[0056] The yaw stability factor S yaw has the following calculation formula:
[0057]
[0058] In the formula, ω is the yaw angular velocity; is the yaw angular acceleration; α f is the front wheel side slip angle; α r is the rear wheel side slip angle; μ is the road surface adhesion coefficient;
[0059] The roll stability factor S lateral has the following calculation formula:
[0060]
[0061] In the formula, a y is the lateral acceleration; F yf is the front wheel lateral force; F yr is the rear wheel lateral force; φ is the body roll angle; μ is the road surface adhesion coefficient;
[0062] The pitch stability factor S pitch has the following calculation formula:
[0063]
[0064] where q is the pitch angular velocity; is the pitch angular acceleration; Z f is the front suspension compression; Z r is the rear suspension compression; K s is the suspension stiffness.
[0065] The driving state comprehensive evaluation module calculates the driving state comprehensive evaluation factor by using a fully connected neural network according to the vehicle driving state factor, road condition and environment factor, driver behavior and reaction factor, tire dynamic characteristic factor, and vehicle dynamic stability factor. The specific structural design is as follows:
[0066] The input layer includes 5 nodes, corresponding to the vehicle driving state factor, road condition and environment factor, driver behavior and reaction factor, tire dynamic characteristic factor, and vehicle dynamic stability factor respectively; the hidden layer adopts a 3-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 include 64, 32, and 16 neurons respectively; the output layer includes 1 node, and the output is the driving state comprehensive evaluation factor;
[0067]
[0068] where S is the driving state comprehensive evaluation factor; S vehicle is the vehicle driving state factor; S road is the road condition and environment factor; S driver is the driver behavior and reaction factor; S tire is the tire dynamic characteristic factor; S stability is the vehicle dynamic stability factor; Z (1) ,Z (2) ,Z (3) are the outputs after linear transformation of the first hidden layer, the second hidden layer, and the third hidden layer; 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 respectively; b (1) ,b (2) ,b (3) ,b (4) are the bias terms of 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 non-linear expression ability of the network;
[0069] When the driving state comprehensive evaluation factor S satisfies 0 ≤ α 1 ≤ S < α2 When it is the case, the steering mode selection module selects the front-wheel steering mode;
[0070] When the comprehensive evaluation factor S of the driving state satisfies α 2 ≤S<α 3 When it is the case, the steering mode selection module selects the four-wheel steering mode;
[0071] When the comprehensive evaluation factor S of the driving state satisfies α 3 ≤S≤1, the steering mode selection module selects the diagonal steering mode.
[0072] For the steering and driving unit execution module, the calculation formulas for the steering angles of the front and rear wheels in the front-wheel steering mode are as follows:
[0073]
[0074] δ 2in-r =0
[0075] δ 2out-r =0
[0076] In the formula, δ 2in-f , δ 2out-f , δ 2in-r , δ 2out-r are respectively the inner front-wheel steering angle, outer front-wheel steering angle, inner rear-wheel steering angle, and outer rear-wheel steering angle in the front-wheel steering mode; L is the front and rear wheelbase; R is the vehicle turning radius; W is the front-wheel track.
[0077] For the steering and driving unit execution module, the calculation formulas for the steering angles of the front and rear wheels in the four-wheel steering mode are as follows:
[0078]
[0079] In the formula, δ 4in-f , δ 4out-f , δ 4in-r , δ 4out-r are respectively the inner front-wheel steering angle, outer front-wheel steering angle, inner rear-wheel steering angle, and outer rear-wheel steering angle in the front-wheel steering mode; L is the front and rear wheelbase; R is the vehicle turning radius; W is the front-wheel track; C f , C r are respectively the cornering stiffness of the front and rear axles; m is the total vehicle mass; v x is the vehicle longitudinal driving speed; l f , l r are respectively the distances from the center of mass to the front and rear axles; ω is the yaw angular velocity.
[0080] For the steering and driving unit execution module, the calculation formulas for the steering angles of the front and rear wheels in the diagonal steering mode are as follows:
[0081]
[0082] δ xout-f = δ xin-f
[0083] δ xin-r = δ xin-f
[0084] δ xout-r = δ xin-f
[0085] wherein, δ xin-f , δ xout-f , δ xin-r , δ xout-r are respectively the inner front wheel angle, outer front wheel angle, inner rear wheel angle, and outer rear wheel angle in the diagonal steering mode; l f , l r are respectively the distances from the center of mass to the front axle and the rear axle; C f , C r are respectively the cornering stiffness of the front axle and the rear axle; L is the wheelbase between the front and rear axles; m is the total mass of the vehicle; v x is the longitudinal driving speed of the vehicle; R is the turning radius of the vehicle.
[0086] The beneficial effects of the present invention are as follows:
[0087] 1. The present invention can obtain vehicle states, road environments, and driver behavior characteristics through multi-source sensing information fusion, use a fully connected neural network to comprehensively evaluate the driving state, realize dynamic switching of the steering mode, and significantly improve the intelligent level and personalized adaptation ability of steering control.
[0088] 2. By constructing a complete multi-factor evaluation system covering vehicle dynamic response, environmental interference degree, driver cognitive state, and tire working conditions, the present invention can effectively identify the optimal steering mode in complex driving scenarios and improve the handling accuracy and response efficiency of the vehicle under multiple working conditions.
[0089] 3. According to the comprehensive evaluation results, the present invention intelligently selects the front-wheel steering, four-wheel steering, or diagonal steering mode, accurately calculates the wheel angles for different modes, effectively optimizes the overall vehicle handling performance, reduces the risk of sideslip, and improves the stability, safety, and ride comfort of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS
[0090] The present invention will be further described below with reference to the accompanying drawings:
[0091] Figure 1 is a method for switching steering modes based on intelligent electric vehicles proposed by the present invention. DETAILED DESCRIPTION OF THE INVENTION
[0092] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.
[0093] Refer to Figure 1 , a steering mode switching method for an intelligent electric vehicle according to the present invention includes an information acquisition module based on a wireless vehicle perception system, a comprehensive driving state evaluation module, a steering mode selection module, and a steering driving unit execution module;
[0094] The information acquisition module based on the wireless vehicle perception system is used to obtain the following information of the vehicle in real time: the longitudinal driving speed v of the vehicle x , the lateral driving speed v of the vehicle y , the lateral acceleration a y , the yaw angular velocity ω, the front wheel steering angle δ f , the front wheel side slip angle α f , the rear wheel side slip angle α r , the steering wheel angle δ sw , the longitudinal force F of the tire x , the vertical force F of the tire z , the body roll angle φ, the lateral force F of the front wheel yf , the lateral force F of the rear wheel yr , the pitch angular velocity q, the front suspension compression Z f , the rear suspension compression Z r , the distance l from the center of mass to the front axle f , the distance l from the center of mass to the rear axle r , the cornering stiffness C of the front axle f , the cornering stiffness C of the rear axle r ;
[0095] The comprehensive driving state evaluation module judges the comprehensive driving state of the vehicle according to various evaluation factors, and calculates the vehicle driving state factor, the road condition and environment factor, the driver behavior and reaction factor, the tire dynamic characteristic factor, and the vehicle dynamic stability factor;
[0096] The calculation formula of the vehicle driving state factor S vehicle is as follows:
[0097]
[0098] In the formula, v x is the longitudinal driving speed of the vehicle; v y is the lateral driving speed of the vehicle; ω is the yaw angular velocity; a y is the lateral acceleration; α f is the front wheel side slip angle; α r is the rear wheel side slip angle; S sr is the vehicle steering response factor;
[0099] The road condition and environmental factor Sroad The calculation formula is as follows:
[0100]
[0101] Wherein, S weather is the weather influence factor; S temperature is the temperature influence factor; S visibility is the visibility influence factor;
[0102] The driver behavior and response factor S driver The calculation formula is as follows:
[0103]
[0104] Wherein, S control is the driver operation factor; S cognition is the driver cognitive response factor; S physiology is the driver physiological state factor;
[0105] The tire dynamic characteristic factor S tire The calculation formula is as follows:
[0106]
[0107] Wherein, S slip is the tire slip factor; S load is the tire load factor;
[0108] The vehicle dynamic stability S stability The calculation formula is as follows:
[0109]
[0110] Wherein, S yaw is the yaw stability factor; S lateral is the roll stability factor; S pitch is the pitch stability factor;
[0111] The steering mode selection module includes front-wheel steering mode, four-wheel steering mode, and diagonal steering mode; the threshold of the front-wheel steering mode is set as α 1 , the threshold of the four-wheel steering mode is α 2 , the threshold of the diagonal steering mode is α 3 , and the corresponding steering mode is selected according to the magnitude relationship between the driving state comprehensive evaluation factor S and each threshold;
[0112] The steering driving unit execution module is used to calculate the wheel angles in the three modes of front-wheel steering mode, four-wheel steering mode, and diagonal steering mode;
[0113] When the vehicle selects the front-wheel steering mode, the inner front wheel steering angle δ 2in-f and the outer front wheel steering angle δ 2out-f depend on the vehicle turning radius R, the front and rear wheelbase L, and the front wheel track W. The inner rear wheel steering angle δ 2in-r and the outer rear wheel steering angle δ 2out-r are both 0;
[0114] When the vehicle selects the four-wheel steering mode, the inner front wheel steering angle δ 4in-f and the outer front wheel steering angle δ 4out-f depend on the vehicle turning radius R, the front and rear wheelbase L, and the front wheel track W. The inner rear wheel steering angle δ 4in-r depends on the inner front wheel steering angle δ 4in-f , the cornering stiffness C f of the front axle, the cornering stiffness C r of the rear axle, the total vehicle mass m, the vehicle longitudinal driving speed v x , the distance l f from the center of mass to the front axle, the distance l r from the center of mass to the rear axle, and the yaw rate ω. The outer rear wheel steering angle δ 4out-r depends on the outer front wheel steering angle δ 4out-f , the cornering stiffness C f of the front axle, the cornering stiffness C r of the rear axle, the total vehicle mass m, the vehicle longitudinal driving speed v x , the distance l f from the center of mass to the front axle, the distance l r from the center of mass to the rear axle, and the yaw rate ω;
[0115] When the vehicle selects the diagonal steering mode, the steering angles of the four wheels are the same. The wheel steering angle depends on the distance l f from the center of mass to the front axle, the distance l r from the center of mass to the rear axle, the cornering stiffness C f of the front axle, the cornering stiffness C r of the rear axle, the front and rear wheelbase L, the total vehicle mass m, the vehicle longitudinal driving speed v x , and the vehicle turning radius R.
[0116] For the driving state comprehensive evaluation module, the calculation formula of the vehicle steering response factor S sr is as follows:
[0117]
[0118] In the formula, α f is the front wheel side slip angle; α r is the rear wheel side slip angle; a y is the lateral acceleration; ω is the yaw rate; v x is the vehicle longitudinal driving speed; v yis the lateral driving speed of the vehicle;
[0119] The weather influence factor S weather has the following calculation formula:
[0120]
[0121] In the formula, H is the wetness degree. When H = 0, the road surface is completely dry. When H = 1, the road surface is completely wet; H a is the air humidity; P r is the precipitation; S d is the snow thickness; P a is the air pressure; W is the wind speed;
[0122] The temperature influence factor S temperature has the following calculation formula:
[0123]
[0124] In the formula, D t is the day-night temperature difference; T is the ambient temperature; T d is the dew point temperature; T g is the surface temperature; P r is the precipitation; T w is the wind chill index;
[0125] The visibility influence factor S visibility has the following calculation formula:
[0126]
[0127] In the formula, V d is the visibility; F d is the fog density; A q is the air pollution index; L is the light intensity; U v is the ultraviolet index; R n is the optical refractive index;
[0128] The driver operation factor S control has the following calculation formula:
[0129]
[0130] In the formula, δ sw is the steering wheel angle; is the steering wheel angular velocity; A p is the throttle pedal opening; A b is the brake pedal opening; F pb is the switching frequency of the throttle and brake per minute; F pa is the rotation frequency of the steering wheel per minute;
[0131] The driver cognitive response factor S cognition has the following calculation formula:
[0132]
[0133] In the formula, τ d is the driver response time; P is the pupil diameter change rate; H m is the head rotation angle; C l is the cognitive load index; T s is the driver's line of sight deviation time; P v is the complexity of traffic conditions within the field of vision; A w is the driver alertness level;
[0134] The driver physiological state factor S physiology has the following calculation formula:
[0135]
[0136] In the formula, H r is the heart rate; S p is the stress index; F t is the fatigue index; R r is the breathing rate; C s is the drowsiness score.
[0137] The driving state comprehensive evaluation module, the tire slip factor S slip has the following calculation formula:
[0138]
[0139] In the formula, λ is the tire slip ratio; α f is the front wheel side slip angle; α r is the rear wheel side slip angle; F x is the tire longitudinal force; μ is the road surface adhesion coefficient;
[0140] The tire load factor S load has the following calculation formula:
[0141]
[0142] In the formula, F z is the tire vertical force; ΔF z is the dynamic change amount of the tire vertical load; κ is the tire flexure deformation rate; K s is the suspension stiffness;
[0143] The yaw stability factor S yaw has the following calculation formula:
[0144]
[0145] In the formula, ω is the yaw rate; is the yaw acceleration; α f is the front wheel side slip angle; α r is the rear wheel side slip angle; μ is the road surface adhesion coefficient;
[0146] The roll stability factor S lateral The calculation formula is as follows:
[0147]
[0148] In the formula, a y is the lateral acceleration; F yf is the front wheel lateral force; F yr is the rear wheel lateral force; φ is the body roll angle; μ is the road surface adhesion coefficient;
[0149] The pitch stability factor S pitch The calculation formula is as follows:
[0150]
[0151] In the formula, q is the pitch angular velocity; is the pitch angular acceleration; Z f is the front suspension compression; Z r is the rear suspension compression; K s is the suspension stiffness.
[0152] The driving state comprehensive evaluation module calculates the driving state comprehensive evaluation factor by using a fully connected neural network according to the vehicle driving state factor, road condition and environment factor, driver behavior and reaction factor, tire dynamic characteristic factor, and vehicle dynamic stability factor. The specific structure design is as follows:
[0153] The input layer includes 5 nodes, corresponding to the vehicle driving state factor, road condition and environment factor, driver behavior and reaction factor, tire dynamic characteristic factor, and vehicle dynamic stability factor respectively; the hidden layer adopts a 3-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 include 64, 32, and 16 neurons respectively; the output layer includes 1 node, and the output is the driving state comprehensive evaluation factor;
[0154]
[0155] In the formula, S is the driving state comprehensive evaluation factor; S vehicle is the vehicle driving state factor; S road is the road condition and environment factor; S driver is the driver behavior and reaction factor; Stire is the tire dynamic characteristic factor; S stability is the vehicle dynamic stability factor; Z (1) , Z (2) , Z (3) are the outputs after linear transformation of the first hidden layer, the second hidden layer, and the third hidden layer; 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 respectively; b (1) , b (2) , b (3) , b (4) are the bias terms of 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 non-linear expression ability of the network;
[0156] When the comprehensive evaluation factor S of the driving state satisfies 0 ≤ α 1 ≤ S < α 2 , the steering mode selection module selects the front-wheel steering mode;
[0157] When the comprehensive evaluation factor S of the driving state satisfies α 2 ≤ S < α 3 , the steering mode selection module selects the four-wheel steering mode;
[0158] When the comprehensive evaluation factor S of the driving state satisfies α 3 ≤ S ≤ 1, the steering mode selection module selects the diagonal steering mode.
[0159] For the steering driving unit execution module, the calculation formulas for the steering angles of the front and rear wheels in the front-wheel steering mode are as follows:
[0160]
[0161] δ 2in-r = 0
[0162] δ 2out-r = 0
[0163] In the formula, δ 2in-f , δ 2out-f , δ 2in-r , δ 2out-r are the inner front-wheel steering angle, the outer front-wheel steering angle, the inner rear-wheel steering angle, and the outer rear-wheel steering angle in the front-wheel steering mode respectively; L is the front and rear wheelbase; R is the vehicle turning radius; W is the front wheel track.
[0164] The steering and driving unit execution module, the corner calculation formulas for the front and rear wheels in the four-wheel steering mode are as follows:
[0165]
[0166] In the formula, δ 4in-f , δ 4out-f , δ 4in-r , δ 4out-r are respectively the inner front wheel angle, outer front wheel angle, inner rear wheel angle, and outer rear wheel angle in the front-wheel steering mode; L is the front and rear wheelbase; R is the vehicle turning radius; W is the front wheel track; C f , C r are respectively the cornering stiffness of the front and rear axles; m is the total vehicle mass; v x is the vehicle longitudinal driving speed; l f , l r are respectively the distances from the center of mass to the front and rear axles; ω is the yaw angular velocity.
[0167] The steering and driving unit execution module, the corner calculation formulas for the front and rear wheels in the diagonal steering mode are as follows:
[0168]
[0169] δ xout-f = δ xin-f
[0170] δ xin-r = δ xin-f
[0171] δ xout-r = δ xin-f
[0172] In the formula, δ xin-f , δ xout-f , δ xin-r , δ xout-r are respectively the inner front wheel angle, outer front wheel angle, inner rear wheel angle, and outer rear wheel angle in the diagonal steering mode; l f , l r are respectively the distances from the center of mass to the front axle and the rear axle; C f , C r are respectively the cornering stiffness of the front axle and the rear axle; L is the front and rear wheelbase; m is the total vehicle mass; v x is the vehicle longitudinal driving speed; R is the vehicle turning radius.
Claims
1. A steering mode switching method based on a smart electric vehicle, characterized in that: It includes an information collection module based on a wireless vehicle perception system, a driving state comprehensive evaluation module, a steering mode selection module, and a steering driving unit execution module; The information acquisition module based on the wireless vehicle perception system is used to obtain the following information of the vehicle in real time: the longitudinal speed v of the vehicle x , vehicle lateral speed v y , lateral acceleration a y , yaw rate ω, front wheel turning angle δ f , steering wheel angle δ sw 、Front wheel slip angle α f 、Rear wheel slip angle α r , tire longitudinal force F x , Tire vertical force F z , body roll angle φ, front wheel lateral force F yf , rear wheel lateral force F yr , pitch angular velocity q, front suspension compression Z f , rear suspension compression Z r , the distance from the center of mass to the front axle l f , the distance from the center of mass to the rear axle l r 、Front axle cornering stiffness C f , rear axle cornering stiffness C r ; The driving state comprehensive evaluation module determines the comprehensive driving state of the vehicle according to multiple evaluation factors, and calculates the vehicle driving state factor, Road conditions and environmental factors, driver behavior and reaction factors, tire dynamic characteristics factors, and vehicle dynamic stability factors; The vehicle driving state factor S vehicle The calculation formula is as follows: In the formula, v x is the longitudinal speed of the vehicle; v y is the lateral speed of the vehicle; ω is the yaw angular velocity; a y is the lateral acceleration; α f is the front wheel slip angle; α r is the rear wheel slip angle; S sr is the vehicle steering response factor; The road condition and environmental factor S road The calculation formula is as follows: In the formula, S weather is the weather influencing factor; S temperature is the temperature influence factor; S visibility Visibility influencing factors; The driver behavior and reaction factor S driver The calculation formula is as follows: In the formula, S control is the driver operation factor; S cognition is the driver's cognitive response factor; S physiology is the driver's physiological state factor; The tire dynamic characteristic factor S tire The calculation formula is as follows: In the formula, S slip is the tire slip factor; S load is the tire load factor; The vehicle dynamic stability S stability The calculation formula is as follows: In the formula, S yaw is the yaw stability factor; S lateral is the roll stability factor; S pitch is the pitch stability factor; The steering modes included in the steering mode selection module include front-wheel steering mode, four-wheel steering mode, and oblique steering mode; the threshold of the front-wheel steering mode is set to α1, the threshold of the four-wheel steering mode is set to α2, and the threshold of the oblique steering mode is set to α3, and the corresponding steering mode is selected according to the relationship between the driving state comprehensive evaluation factor S and each threshold value; The steering driving unit execution module is used to calculate the wheel angles in three modes: front wheel steering mode, four wheel steering mode, and oblique steering mode; When the vehicle selects the front wheel steering mode, the inner front wheel turning angle δ 2in-f and the outer front wheel turning angle δ 2out-f Depends on the vehicle turning radius R, front and rear wheelbase L, front wheel track W, inner rear wheel turning angle δ 2in-r and the outer rear wheel turning angle δ 2out-r All are 0; When the vehicle selects the four-wheel steering mode, the inner front wheel turning angle δ 4in-f and the outer front wheel turning angle δ 4out-f Depends on the vehicle turning radius R, front and rear wheelbase L, front wheel track W, inner rear wheel turning angle δ 4in-r Depends on the inner front wheel turning angle δ 4in-f 、Front axle cornering stiffness C f , rear axle cornering stiffness C r , total vehicle mass m, longitudinal vehicle speed v x , the distance from the center of mass to the front axle l f , the distance from the center of mass to the rear axle l r , yaw rate ω, outer rear wheel turning angle δ 4out-r Depends on the outer front wheel turning angle δ 4out-f 、Front axle cornering stiffness C f , rear axle cornering stiffness C r , total vehicle mass m, longitudinal vehicle speed v x , the distance from the center of mass to the front axle l f , the distance from the center of mass to the rear axle l r , yaw angular velocity ω; When the vehicle is in oblique steering mode, the four wheels have the same turning angle, which depends on the distance l from the center of mass to the front axle. f , the distance from the center of mass to the rear axle l r 、Front axle cornering stiffness C f , rear axle cornering stiffness C r , front and rear wheelbase L, total vehicle mass m, vehicle longitudinal speed v x , vehicle turning radius R.
2. According to claim 1, a steering mode switching method based on a smart electric vehicle is characterized in that: The driving state comprehensive evaluation module, the vehicle steering response factor S sr The calculation formula is as follows: In the formula, α f is the front wheel slip angle; α r is the rear wheel slip angle; a y is the lateral acceleration; ω is the yaw angular velocity; v x is the longitudinal speed of the vehicle; v y is the lateral speed of the vehicle; The weather influence factor S weather The calculation formula is as follows: Where H is the slipperiness. When H = 0, the road surface is completely dry. When H = 1, the road surface is completely slippery. a is the air humidity; P r is the precipitation; S d is the thickness of snow; P a is air pressure; W is wind speed; The temperature influence factor S temperature The calculation formula is as follows: Where D t is the temperature difference between day and night; T is the ambient temperature; T d is the dew point temperature; T g is the surface temperature; P r is the precipitation; T w is the wind chill index; The visibility influencing factor S visibility The calculation formula is as follows: Where V d F is visibility; d is the fog density; A q is the air pollution index; L is the light intensity; U v is the UV index; R n is the optical refractive index; The driver operation factor S control The calculation formula is as follows: In the formula, δ sw is the steering wheel angle; is the steering wheel angular velocity; A p is the accelerator pedal opening; A b is the brake pedal opening; F pb F is the switching frequency between accelerator and brake per minute; pa is the rotation frequency of the steering wheel per minute; The driver cognitive response factor S cognition The calculation formula is as follows: In the formula, τ d is the driver's reaction time; P is the pupil diameter change rate; H m is the head rotation angle; C l is the cognitive load index; T s P is the driver's line of sight deviation time; v A is the complexity of traffic conditions within the field of view; w The driver's alertness level; The driver's physiological state factor S physiology The calculation formula is as follows: In the formula, H r is the heart rate; S p is the pressure index; F t is fatigue index; R r is the respiratory rate; C s Score sleepiness.
3. According to claim 1, a steering mode switching method based on a smart electric vehicle is characterized in that: The driving state comprehensive evaluation module, the tire slip factor S slip The calculation formula is as follows: Where λ is the tire slip rate; α f is the front wheel slip angle; α r is the rear wheel slip angle; F x is the tire longitudinal force; μ is the road adhesion coefficient; The tire load factor S load The calculation formula is as follows: In the formula, F z is the tire vertical force; ΔF z is the dynamic change of the tire vertical load; κ is the tire flexural deformation rate; K s is the suspension stiffness; The yaw stability factor S yaw The calculation formula is as follows: Where ω is the yaw angular velocity; is the yaw angular acceleration; α f is the front wheel slip angle; α r is the rear wheel slip angle; μ is the road adhesion coefficient; The roll stability factor S lateral The calculation formula is as follows: In the formula, a y is the lateral acceleration; F yf is the lateral force of the front wheel; F yr is the lateral force of the rear wheel; φ is the body roll angle; μ is the road adhesion coefficient; The pitch stability factor S pitch The calculation formula is as follows: Where q is the pitch angular velocity; is the pitch angular acceleration; Z f is the front suspension compression; Z r is the compression of the rear suspension; K s is the suspension stiffness.
4. According to claim 1, a steering mode switching method based on a smart electric vehicle is characterized in that: The driving state comprehensive evaluation module uses a fully connected neural network to calculate the driving state comprehensive evaluation factor based on the vehicle driving state factor, road condition and environmental factors, driver behavior and reaction factors, tire dynamic characteristic factors, and vehicle dynamic stability factors. The specific structure design is as follows: The input layer includes 5 nodes, corresponding to the vehicle driving state factor, road condition and environment factor, driver behavior and reaction factor, tire dynamic characteristic factor, and vehicle dynamic stability factor respectively; the hidden layer adopts a 3-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 include 64, 32, and 16 neurons respectively; the output layer includes 1 node, and the output is the comprehensive evaluation factor of the driving state; Where S is the comprehensive evaluation factor of driving status; S vehicle is the vehicle driving state factor; S road is the road condition and environmental factors; S driver is the driver behavior and reaction factor; S tire is the tire dynamic characteristic factor; S stability is the vehicle dynamic stability factor; Z (1) ,Z (2) ,Z (3) is the output of the first hidden layer, the second hidden layer and the third hidden 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; When the driving state comprehensive evaluation factor S satisfies 0≤α1≤S<α2, the steering mode selection module selects the front wheel steering mode; When the driving state comprehensive evaluation factor S satisfies α2≤S<α3, the steering mode selection module selects the four-wheel steering mode; When the driving state comprehensive evaluation factor S satisfies α3≤S≤1, the steering mode selection module selects the oblique steering mode.
5. According to claim 1, a steering mode switching method based on a smart electric vehicle is characterized in that: The steering driving unit execution module calculates the turning angle of the front and rear wheels in the front wheel steering mode as follows: d 2in-r =0 d 2out-r =0 In the formula, δ 2in-f , δ 2out-f , δ 2in-r , δ 2out-r They are the inner front wheel turning angle, outer front wheel turning angle, inner rear wheel turning angle and outer rear wheel turning angle in front-wheel steering mode; L is the front and rear wheelbase; R is the vehicle turning radius; W is the front wheel track.
6. According to claim 1, a steering mode switching method based on a smart electric vehicle is characterized in that: The steering driving unit execution module calculates the turning angle of the front and rear wheels in the four-wheel steering mode as follows: In the formula, δ 4in-f , δ 4out-f , δ 4in-r , δ 4out-r They are the inner front wheel angle, outer front wheel angle, inner rear wheel angle, and outer rear wheel angle in front wheel steering mode; L is the front and rear wheelbase; R is the turning radius of the vehicle; W is the front wheel track; C f , C r are the cornering stiffness of the front and rear axles respectively; m is the total mass of the vehicle; v x is the longitudinal speed of the vehicle; l f , l r are the distances from the center of mass to the front and rear axes respectively; ω is the yaw angular velocity.
7. The method for switching steering modes based on a smart electric vehicle according to claim 1, characterized in that: The steering driving unit execution module calculates the turning angle of the front and rear wheels in the oblique steering mode as follows: d xout-f =d xin-f d xin-r =d xin-f d xout-r =d xin-f In the formula, δ xin-f , δ xout-f , δ xin-r , δ xout-r They are the inner front wheel angle, outer front wheel angle, inner rear wheel angle, and outer rear wheel angle in the oblique steering mode; f , l r are the distances from the center of mass to the front and rear axles respectively; C f , C r are the lateral stiffness of the front and rear axles respectively; L is the front and rear wheelbase; m is the total mass of the vehicle; v x is the longitudinal speed of the vehicle; R is the turning radius of the vehicle.
Citation Information
Cited By
Three-axis angle module vehicle path planning method considering steering mode switching
CN122481783A
A vehicle four-wheel steering mode competition and reinforcement learning fusion control method
CN122724569A