Design method and system for variable transmission ratio of steer-by-wire vehicle based on fuzzy neural network

Abstract

The application provides a kind of based on fuzzy neural network's drive-by-wire vehicle variable transmission ratio design method and system, belongs to vehicle drive-by-wire field.For solving the problem that the gain method exists when low speed steering angle transmission ratio is too small, high speed sensitivity is small;Existing intelligent algorithm is too dependent on the experience and data sample quality of designer.The application includes establishing based on closed-loop driver-vehicle system, using the quadratic cost function of vehicle dynamic state design a kind of multi-objective evaluation method, obtained the data relationship between vehicle ideal variable transmission ratio characteristic and vehicle longitudinal velocity and steering wheel angle;Through fuzzy RBF network establishes nonlinear control model, based on nonlinear model learning obtains global optimal solution.The application improves the robustness of control system, can provide stable and reliable transmission ratio under various vehicle conditions, solves the problem of light and spirit of steering system, thereby improves the experience of driver under various vehicle conditions, and improves the steering stability and safety of vehicle.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle steer-by-wire, in particular to a steer-by-wire vehicle variable transmission ratio design method and system based on fuzzy neural network. BACKGROUND

[0002] The transmission ratio of the mechanical steering adopted by the traditional steering system is fixed, which cannot solve the contradiction between light and agile steering. The steer-by-wire system cancels the mechanical connection between the steering wheel and the steering wheel, realizes structural decoupling, widens the torque transmission and angle transmission characteristics of the vehicle, and can flexibly change the angle transmission ratio to reduce the steering load of the driver, thereby improving the steering stability of the vehicle.

[0003] At present, the common steer-by-wire variable transmission ratio design methods mainly include the following problems:

[0004] The steer-by-wire variable transmission ratio design method based on the "constant gain method" is difficult to establish a mathematical model for a complex or nonlinear system:

[0005] The "constant yaw rate gain method" only considers setting the steady-state yaw rate gain as a constant value, which ensures consistent steering characteristics at different vehicle speeds, but makes the steering angle transmission ratio too small at low speed, and does not consider the influence of lateral acceleration gain on the driver.

[0006] The "constant lateral acceleration gain design method" will make the steering angle transmission ratio too large at high speed, resulting in too small steering sensitivity at high speed, which is not conducive to driving safety.

[0007] The steer-by-wire variable transmission ratio design method based on "fuzzy algorithm, genetic algorithm, particle swarm optimization algorithm and other intelligent algorithm hybrid gain method" relies too much on the designer's experience and data sample quality, and the steering variable angle transmission ratio has unclear physical meaning.

[0008] The steer-by-wire variable transmission ratio design method based on "constant gain method" or "intelligent algorithm" is difficult to provide stable and reliable transmission ratio under special working conditions.

[0009] In order to solve the limitations of the variable transmission ratio design scheme based on the "constant gain method" and "intelligent algorithm", the application establishes a closed-loop driver-vehicle system, designs a multi-objective evaluation method by using a quadratic cost function of the vehicle dynamic state, obtains the data relationship between the ideal variable transmission ratio characteristic of the vehicle and the vehicle longitudinal speed and steering wheel angle, and then establishes a nonlinear control model by using a fuzzy RBF network, and learns the global optimal solution based on the nonlinear model. SUMMARY

[0010] The technical problem solved by the application is:

[0011] In order to solve the problems that the existing constant gain method cannot balance the yaw rate and lateral acceleration gain, the steering angle transmission ratio is too small at low speed and too large at high speed, the existing intelligent algorithms based on fuzzy algorithm, genetic algorithm and particle swarm optimization algorithm are too dependent on the designer's experience and data sample quality, and the physical meaning of the steering angle transmission ratio is not clear.

[0012] The technical scheme adopted by the application to solve the above technical problems is:

[0013] The application provides a variable transmission ratio design method for a steer-by-wire vehicle based on a fuzzy neural network, which comprises the following steps:

[0014] S100, a linear two-degree-of-freedom vehicle dynamics model based on Newton's second law is established;

[0015] S200, a dynamics model based on a closed-loop driver-vehicle system is established;

[0016] S300, a multi-objective evaluation method based on a quadratic cost function of the vehicle dynamic state is designed, which is used to evaluate the relationship between the ideal variable steering ratio characteristic of the vehicle and the vehicle longitudinal speed and steering wheel angle;

[0017] S400, a nonlinear control model is constructed based on a fuzzy neural network of an RBF model, and a global optimal solution of the variable transmission ratio is obtained.

[0018] Further, in step S100, the linear two-degree-of-freedom vehicle dynamics model based on Newton's second law is:

[0019]

[0020] In the formula, a is the distance from the vehicle mass center to the front axle; b is the distance from the vehicle mass center to the rear axle; C f , and C r are the lateral stiffness of the front and rear tires of the vehicle respectively; m is the mass of the vehicle; I Z is the moment of inertia; v xis the longitudinal vehicle speed; δ is the front wheel steering angle; β is the vehicle's center of mass side slip angle; ω r is the vehicle yaw rate.

[0021] Further, in step S200, define additional state variables: Y is the lateral displacement, ψ is the vehicle's yaw angle relative to the road;

[0022] At the same time, where v y is the vehicle lateral motion speed, is the vehicle lateral acceleration; so as to obtain the closed-loop driver-vehicle system dynamics model:

[0023]

[0024] Further, in step S300, define the steering ratio as: In the formula, is the steer-by-wire steering ratio; δ s is the steering wheel angle; δ p is the steering gear angle; δ f is the front wheel steering angle; is the steering actuator steering ratio; τ is the steering ratio compensation coefficient calculated by the control algorithm.

[0025] Further, S310, for the ideal transmission ratio characteristic varies with vehicle speed, consider the steering ratio τ min relative to the lower limit value of the vehicle speed; in addition, also use the upper limit τ max to avoid slow response when driving at high speed;

[0026] The relationship between the compensation coefficient τ and the longitudinal vehicle speed v x is described by a nonlinear function of the following formula:

[0027]

[0028] Where v0 is the threshold value when the vehicle is driving at low speed; v1 is the threshold value when the vehicle is driving at high speed;

[0029] In order to determine the relationship between the compensation coefficient τ and the longitudinal vehicle speed V x , a multi-objective evaluation index system of vehicle handling performance is designed; based on the dynamic state of the vehicle, the evaluation model is constructed by a quadratic cost function:

[0030]

[0031] In the formula, J e is an index to evaluate the performance of the vehicle's trajectory tracking, which describes the lateral displacement deviation when the vehicle is driving, where e is the lateral displacement deviation when the vehicle is driving, e tJ is a lateral deviation technical index threshold value;J b J is an index for evaluating the difficulty of the driver operating the vehicle, describing the driving comfort and steering load of the driver, and the greater the index, the greater the difficulty of the driver operating the vehicle;J c andJ r J is a rollover risk evaluation index during vehicle driving, describing the influence of lateral acceleration a y and roll angle on the handling stability, and t represents the duration of the driving experiment;

[0032] In order to evaluate the steering transmission ratio in multiple targets, the normalized performance index J is calculated using the above quadratic cost function, as shown in the following formula:

[0033]

[0034] In the formula, ω1, ω2, ω3, and ω4 are all weighting coefficients.

[0035] Further, S320, for the ideal transmission ratio characteristic with the steering wheel angle, the yaw rate gain in the steering control process is an important parameter reflecting the handling performance of the vehicle, and the relationship between the yaw rate gain and the steering wheel angle is defined as:

[0036]

[0037] The yaw rate gain of the vehicle decreases with the increase of the steering wheel angle, so the response between the steering wheel angle of the vehicle and the yaw rate of the vehicle is nonlinear; in order to make the yaw rate gain of the vehicle relatively linear, a variable steering ratio compensation τ' is added, so that the yaw rate gain of the vehicle is unchanged when the steering wheel angle changes; τ' is shown in the following formula:

[0038]

[0039] wherein, is the yaw rate gain relative to the front wheel angle, which is derived from the vehicle dynamics model:

[0040]

[0041] Further, in step S400, the four-layer RBF type fuzzy neural network includes an input layer, a membership function layer, a rule layer, and an output layer, wherein,

[0042] In the input layer, each node of the layer is directly connected with each component of the input quantity, for transmitting the input variable to the next layer; the input variable is the vehicle longitudinal speed v x and the steering wheel angle δ s ​​; the output of each input node i of the layer is represented as: f1(i) = x i i = 1,2.

[0043] In the membership function layer, each node of the layer has the function of membership function, adopts Gaussian function as the membership function, and five fuzzy sets of Gaussian membership functions are designed: minimum, small, medium, large and maximum; for the jth node: Wherein, c ij and b j are the mean and standard deviation of the jth fuzzy set Gaussian function of the ith input variable; The square of the Euclidean distance between the input vector i and the center of the hidden layer neuron represents the matching degree of the input i to the fuzzy rule;

[0044] In the rule layer, the layer completes the fuzzy rule matching through the connection with the fuzzy layer, and the fuzzy operation is realized between the nodes; the output of each node k is the product of all input signals of the node:

[0045]

[0046] Wherein, N i is the number of the ith input membership function, that is, the number of the corresponding fuzzy layer nodes;

[0047] In the output layer, the output of each node of the layer is the weighted sum of all input signals of the node, that is:

[0048]

[0049] Wherein, l is the serial number of the output layer node, and w is the connection weight matrix of the output node and each node of the third layer.

[0050] Further, in the RBF type fuzzy neural network, the adjustable parameters include: the weight coefficient of the rule; the mean c ij of the Gaussian function, the parameter of the input membership function; the standard deviation b j , the parameter of the input membership function.

[0051] A fuzzy neural network-based design system for variable transmission ratio of a steer-by-wire vehicle, the system has program modules corresponding to the above steps, and executes the steps in the above fuzzy neural network-based design method for variable transmission ratio of a steer-by-wire vehicle.

[0052] A computer readable storage medium, the computer readable storage medium stores a computer program, the computer program is configured to be called by a processor to realize the steps of the fuzzy neural network-based design method for variable transmission ratio of a steer-by-wire vehicle.

[0053] Compared with the prior art, the beneficial effects of the present invention are:

[0054] This invention discloses a steer-by-wire vehicle variable transmission ratio design method and system based on fuzzy neural networks. By using a fuzzy RBF neural network-based steer-by-wire variable transmission ratio design method, the robustness of the control system is improved, providing a stable and reliable transmission ratio under various vehicle conditions. Experiments have shown that it provides a smaller transmission ratio at low speeds of 10 km / h, meeting the requirements for steering sensitivity and ease of operation at low speeds; and provides a larger transmission ratio at high speeds of 120 km / h, making the vehicle steering "sluggish," thus solving the problem of "light" and "sensitive" steering systems. This improves the driver's experience under various vehicle conditions, while also enhancing the vehicle's handling stability and safety. Attached Figure Description

[0055] Figure 1 This is a flowchart of a method for designing a variable transmission ratio for a steer-by-wire vehicle based on a fuzzy neural network, as described in an embodiment of the present invention.

[0056] Figure 2 This is a structural diagram of the fuzzy RBF neural network controller in an embodiment of the present invention;

[0057] Figure 3 This is a model diagram of a vehicle with a steer-by-wire system, as shown in an embodiment of the present invention.

[0058] Figure 4 This is a graph showing the relationship between vehicle speed, steering wheel angle, and ideal transmission ratio in an embodiment of the present invention.

[0059] Figure 5 These are comparison diagrams of the steering wheel angle curves of variable transmission ratio and fixed transmission ratio under double lane change conditions at different vehicle speeds in embodiments of the present invention. Among them, (a) is a comparison diagram of the steering wheel angle curves of variable transmission ratio and fixed transmission ratio under double lane change conditions at a vehicle speed of 10km / h, (b) is a comparison diagram of the steering wheel angle curves of variable transmission ratio and fixed transmission ratio under double lane change conditions at a vehicle speed of 60km / h, and (c) is a comparison diagram of the steering wheel angle curves of variable transmission ratio and fixed transmission ratio under double lane change conditions at a vehicle speed of 120km / h. Detailed Implementation

[0060] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0061] Specific Implementation Plan 1: Combining Figures 1 to 2 As shown, this invention provides a method for designing variable gear ratios for steerable vehicles based on fuzzy neural networks, comprising the following steps:

[0062] S100. Establish a linear two-degree-of-freedom vehicle dynamics model based on Newton's second law:

[0063]

[0064] where a is the distance from the center of mass to the front axle; b is the distance from the center of mass to the rear axle; C f , C r are the cornering stiffness of the front and rear tires, respectively; m is the mass of the vehicle; I Z is the moment of inertia; v x is the longitudinal vehicle speed; δ is the front wheel steering angle; β is the side slip angle of the center of mass; ω r is the yaw rate of the vehicle.

[0065] S200, when considering the driver steering the vehicle to move relative to the road, two additional state variables need to be defined: Y is the lateral displacement, and ψ is the yaw angle of the vehicle relative to the road.

[0066] At the same time, v y is the lateral vehicle speed, is the lateral vehicle acceleration, so as to obtain a closed-loop driver-vehicle system dynamics model:

[0067]

[0068] S300, a multi-objective evaluation method is designed based on the quadratic cost function of the vehicle dynamic state, specifically including,

[0069] In order to evaluate the dynamic state of the vehicle, the relationship between the ideal variable steering ratio characteristic of the vehicle and the longitudinal speed and steering wheel angle of the vehicle needs to be obtained;

[0070] wherein the steering ratio of the vehicle steering system is defined as: wherein, is the steering ratio of the steer-by-wire system; δ s is the steering wheel angle; δ f is the front wheel steering angle; δ p is the steering gear angle; is the steering ratio of the steering actuator; τ is the steering ratio compensation coefficient calculated by the control algorithm;

[0071] S310, the ideal transmission ratio characteristic varies with vehicle speed: when the vehicle is traveling at a low speed of 25 km / h or less, the desired steering ratio is relatively small, so as to improve the steering flexibility and maneuverability; on the other hand, in order to improve the driving stability and safety at high vehicle speeds of 100 km / h or more, the steering ratio needs to be increased to reduce the steering sensitivity; due to the mechanical position limit on the steering rack, the lower limit value of the steering ratio τ min relative to the vehicle speed; in addition, an upper limit τ max is also adopted to avoid slow response when driving at high speed.

[0072] Based on the above analysis, the relationship between the compensation coefficient τ and the longitudinal vehicle speed v x can be described by a non-linear function shown in the following formula:

[0073]

[0074] v0 is the threshold value when the vehicle is running at a low speed; v1 is the threshold value when the vehicle is running at a high speed;

[0075] In order to determine the relationship between the compensation coefficient τ and the longitudinal vehicle speed V x , a multi-objective evaluation index system of vehicle handling performance is designed; based on the dynamic state of the vehicle, the evaluation model is represented by the following quadratic cost function:

[0076]

[0077] In the formula, J e is the key index to evaluate the good or bad of the trajectory tracking performance of the vehicle, e is the lateral deviation of the trajectory tracking when the vehicle is running, e t is the lateral deviation technical index threshold value, which describes the lateral displacement deviation when the vehicle is running; J b is the key index to evaluate the difficulty of the driver to manipulate the vehicle, which describes the driving comfort and steering load, and the larger the index, the greater the difficulty of the driver to manipulate the vehicle; J c and J r are the rollover risk evaluation indexes of the vehicle during running, which describe the influence of the lateral acceleration a y and the roll angle on the handling stability, and t represents the duration of the driving experiment;

[0078] In order to evaluate the steering transmission ratio, the above cost function is used to calculate the normalized performance index J, as shown in the following formula; generally, the smaller the performance index, the better the handling stability and comfort of the vehicle under the transmission ratio:

[0079]

[0080] In the formula: ω1, ω2, ω3, ω4 are all weighting coefficients;

[0081] S320, ideal transmission ratio characteristic changes with steering wheel angle:

[0082] The yaw rate gain in the steering control process is an important parameter reflecting the handling performance of the vehicle, and the relationship between the yaw rate gain and the steering wheel angle is defined as:

[0083]

[0084] Vehicle yaw rate gain With the increase of steering wheel angle, the response between the steering wheel angle and the vehicle yaw rate is nonlinear, especially the driver is difficult to manipulate when the steering wheel needs large angle; in order to make the vehicle yaw rate gain relatively linear, a variable steering ratio compensation τ' is added, so that the vehicle yaw rate gain is not changed when the steering wheel angle changes; τ' is as follows:

[0085]

[0086] Wherein, is the yaw rate gain relative to the front wheel angle, which can be derived from the vehicle dynamics model:

[0087]

[0088] S400, four-layer RBF type fuzzy neural network is used as a nonlinear control model, specifically including,

[0089] Since the vehicle steer-by-wire system is a complex nonlinear system with multiple inputs and single output, in order to solve this nonlinear control problem, the fuzzy neural network based on RBF model is used; based on the data relationship between the ideal variable transmission ratio characteristic of the vehicle and the vehicle longitudinal speed and the steering wheel angle obtained above, the fuzzy neural network controller is trained; the structure of the proposed fuzzy neural network is as shown in Figure 2 The four-layer design is described as follows:

[0090] First layer: input layer

[0091] Each node of this layer is directly connected with each component of the input quantity, for transmitting the input variable to the next layer; the input variable is the vehicle longitudinal speed v x and the steering wheel angle δ s ; the output of each input node i of this layer is represented as: f1(i)=x i i=1,2.

[0092] Second layer: membership function layer, i.e. fuzzy layer

[0093] Each node of this layer has the function of membership function, and adopts Gaussian function as the membership function, and five Gaussian membership functions are designed, i.e. very small (VS), small (S), medium (M), large (B) and very large (VB); for the jth node:

[0094]

[0095] Wherein, c ij and b j ​The mean and standard deviation of the jth fuzzy set Gaussian function of the ith input variable, respectively; The square of the Euclidean distance between the input vector i and the center of the hidden layer neuron, representing the matching degree of the input i to the fuzzy rule;

[0096] The third layer: the rule layer, that is, the fuzzy reasoning layer

[0097] This layer completes the fuzzy rule matching through the connection with the fuzzification layer, and realizes fuzzy operation between nodes; the output of each node k is the product of all input signals of the node:

[0098]

[0099] Wherein, N i is the number of the ith input membership function, that is, the number of nodes of the corresponding fuzzification layer;

[0100] The fourth layer: the output layer

[0101] The output of each node of this layer is the weighted sum of all input signals of the node, that is:

[0102]

[0103] Wherein, l is the serial number of the output layer node, w is the connection weight matrix of the output node and each node of the third layer, is the transmission ratio of the steer-by-wire system;

[0104] In the RBF type fuzzy neural network, there are three types of adjustable parameters:

[0105] The first type is the weight coefficient of the rule;

[0106] The second type is the mean c ij of the Gaussian function; and the parameter of the input membership function;

[0107] The third type is the standard deviation b j of the Gaussian function; and the parameter of the input membership function.

[0108] Specific implementation scheme two: the present application provides a variable transmission ratio design system for a steer-by-wire vehicle based on a fuzzy neural network, which has program modules corresponding to the above steps, and executes the steps in the above variable transmission ratio design method for a steer-by-wire vehicle based on a fuzzy neural network when running.

[0109] The other combinations and connection relationships of the present implementation scheme are the same as those of specific implementation scheme one.

[0110] Specific embodiment three: the present application provides a computer readable storage medium, the computer readable storage medium stores a computer program, the computer program is configured to realize the steps of the method for designing the variable transmission ratio of the steer-by-wire vehicle based on the fuzzy neural network when the processor is called.

[0111] Other combinations and connection relationships of the present embodiment are the same as those of specific embodiment one.

[0112] Simulation experiment: the feasibility of the application is verified by Carsim / Simulink joint simulation, and the default B-ClassHatchback vehicle model in Carsim is selected for simulation modeling. The parameters of the car model are shown in the following table.

[0113]

[0114] Since the original whole vehicle model in Carsim is a traditional mechanical steering system, when establishing the whole vehicle model of the steer-by-wire system, the original steering system needs to be replaced. In the Steering System subsystem of the whole vehicle characteristic setting interface, set OPT_STEER_EXT = 0, and replace the whole steering part in the original vehicle model with the built steer-by-wire system.

[0115] In the CarSim / Simulink joint simulation, the parameters input into the whole vehicle model of CarSim are the ideal front wheel steering angle after correction. The parameters output to the Simulink dynamics model include the actual front wheel steering angle, vehicle speed, yaw rate, lateral acceleration, steering wheel angle and simulation time. The whole vehicle model with the steer-by-wire system built is as shown in Figure 3 .

[0116] In order to verify the correctness of the built variable transmission ratio steer-by-wire model, the steer-by-wire model is simulated and compared with the existing mechanical steering model in Carsim. In the simulation, the influence of road changes and external disturbances is ignored, and the response of the relevant indicators of the two models is compared under the premise of the same working conditions and other conditions. It can be seen from Figure 4 and Figure 5 that the variable transmission ratio design method of the steer-by-wire system based on the fuzzy RBF neural network improves the robustness of the control system, provides stable and reliable transmission ratio under various vehicle conditions, provides smaller transmission ratio under low-speed working conditions of 10km / h, meets the requirements of steering sensitivity and operation lightness at low speed; provides larger transmission ratio under high-speed working conditions of 120km / h, makes the automobile steering "dull", solves the problem of "light" and "spirit" of the steering system, thereby improving the experience of the driver under various vehicle conditions, and improving the steering stability and safety of the vehicle.

[0117] Although the present application has been disclosed with reference to the above embodiments, the scope of the present application is not limited to the above. Various changes and modifications can be made to the present application without departing from the spirit and scope of the present application, and such changes and modifications are intended to fall within the scope of the present application.

Claims

1. A method for design of variable gear ratio for steer-by-wire vehicle based on fuzzy neural network, characterized in that, The method comprises the following steps: S100, establishing a linear two-degree-of-freedom vehicle dynamics model based on Newton's second law is: wherein is the distance from the vehicle center of mass to the front axle; is the distance from the vehicle center of mass to the rear axle; , are the cornering stiffness of the front and rear tires, respectively; is the vehicle mass; is the moment of inertia; is the longitudinal vehicle speed; is the front wheel steering angle; is the vehicle center of mass side slip angle; is the vehicle yaw rate; S200, establishing a dynamics model based on a closed-loop driver-vehicle system; Define additional state variables: is the lateral displacement, is the yaw angle of the car relative to the road; At the same time, , , , wherein, is the vehicle lateral motion velocity, is the vehicle lateral acceleration; thus obtaining a closed loop driver-vehicle system dynamics model: S300, a multi-objective evaluation method is designed based on a quadratic cost function of a vehicle dynamic state, which is used to evaluate the relationship between an ideal variable steering ratio characteristic of a vehicle and a vehicle longitudinal speed and a steering wheel rotation angle; The steering ratio is defined as: wherein is the steering ratio of the steer-by-wire system; is the steering wheel angle; is the steering gear angle; is the front wheel angle; is the steering actuator steering ratio; is the steering ratio compensation factor calculated by the control algorithm; S400, a nonlinear control model is constructed based on a RBF model of a fuzzy neural network, and a global optimal solution of a variable transmission ratio is obtained.

2. The fuzzy neural network based design method of vehicle variable gear ratio for steer-by-wire vehicle according to claim 1, wherein: S310, for the ideal transmission ratio characteristic changes with vehicle speed, considering the lower limit value of the steering ratio compensation coefficient relative to the vehicle speed ; in addition, the upper limit is also adopted to avoid slow response when driving at high speed; Compensation coefficient and longitudinal vehicle speed The relationship between the longitudinal vehicle speed and the longitudinal acceleration is described by a non-linear function of the form: wherein, is a threshold value for the vehicle to travel in a low speed section; is a threshold value for the vehicle to travel in a high speed section; To determine the compensation coefficient The relationship between the longitudinal vehicle speed A multi-objective evaluation index system of vehicle handling performance is designed; based on the dynamic state of the vehicle, the evaluation model is constructed by a quadratic cost function: In the formula, is an index for evaluating the track tracking performance of the vehicle, and describes the lateral displacement deviation of the vehicle during driving, wherein, is the lateral displacement deviation of the vehicle during driving, is a technical index threshold value of the lateral displacement deviation; is an index for evaluating the difficulty of the driver operating the vehicle, and describes the driving comfort and steering load of the driver, and the larger the index, the greater the difficulty of the driver operating the vehicle; and is an index for evaluating the rollover risk of the vehicle during driving, and describes the influence of the lateral acceleration and the roll angle on the handling stability of the vehicle, represents the duration of the driving test; For multi-objective evaluation of the steering transmission ratio, the normalized performance indicator is calculated using the above quadratic cost function as shown in the following equation: wherein: , , , are weighting factors.

3. The fuzzy neural network based design method of a variable gear ratio for a steer-by- wire vehicle according to claim 2, characterized in that: S320, for the ideal transmission ratio characteristic changes with steering wheel angle, the yaw rate gain in the steering control process is an important parameter reflecting the vehicle handling performance, the yaw rate gain is defined as: Vehicle yaw rate gain The vehicle yaw rate gain is reduced as the steering wheel angle increases, so the response between the steering wheel angle and the vehicle yaw rate is non-linear; to make the vehicle yaw rate gain relatively linear, a variable steering ratio compensation is added The vehicle yaw rate gain is made constant as the steering wheel angle changes As shown in the following equation:​ where, is the yaw rate gain with respect to the front wheel angle, derived from the vehicle dynamics model: 。 4. The fuzzy neural network based design method of a variable gear ratio for a steer-by- wire vehicle according to claim 3, characterized in that: In the RBF type fuzzy neural network, the adjustable parameters include: the weight coefficients of the rules, the mean value and the standard deviation of the Gaussian function; the mean value and the standard deviation of the Gaussian function are the parameters of the input membership function.

5. A fuzzy neural network based design system for variable gear ratio of steer-by-wire vehicle characterized by: The system has program modules corresponding to the steps of any one of claims 1-4, and when running, the steps in the above method for designing a variable transmission ratio of a steer-by-wire vehicle based on a fuzzy neural network are executed.

6. A computer-readable storage medium, characterized in that: The computer readable storage medium stores a computer program configured to realize the steps of the method for designing a variable transmission ratio of a steer-by-wire vehicle based on a fuzzy neural network in any one of claims 1-4 when called by the processor.

Images