Vehicle rollover prevention method, device, terminal and storage medium

Abstract

The present invention provides a method, device, terminal and storage medium for preventing a vehicle from rolling over. The method comprises: judging whether the vehicle has a tendency to roll over based on the lateral load transfer rate of the vehicle; if the vehicle has a tendency to roll over, calculating an additional yaw moment for suppressing the vehicle from rolling over based on the lateral load transfer rate and a radial basis function neural network PID controller; determining a target wheel based on the lateral load transfer rate, and calculating a target braking moment based on the additional yaw moment, so as to brake the target wheel based on the target braking moment. The present invention judges whether the vehicle has a tendency to roll over based on the lateral load transfer rate, and calculates an additional yaw moment for suppressing the vehicle from rolling over through a radial basis function neural network PID controller when the vehicle has a tendency to roll over, so as to improve the calculation speed of the additional yaw moment, and brake the target wheel in time before the rollover occurs, thereby improving the response speed and anti-rollover effect of the vehicle.

Description

Technical Field

[0001] The present invention relates to the field of vehicle control technology, and in particular to a vehicle rollover prevention method, device, terminal and storage medium. Background Art

[0002] Wheeled robots and large trucks have narrow wheelbases, high heights, heavy loads, and high centers of gravity. When these vehicles make sharp or large turns, they are prone to tilting or even overturning.

[0003] At present, in the automotive industry, the more common anti-rollover methods that can effectively improve the stability of the vehicle include: differential braking control technology, active / semi-active suspension control technology, active lateral stabilizer technology, active steering technology, active braking, etc. However, the differential braking control technology brakes the outer wheel only when the wheel is about to leave the ground, and the anti-rollover effect is poor. Active suspension control technology and active lateral stabilizer can increase the rollover threshold and suppress vehicle rollover, but they are slow to take effect and cannot meet the requirements of rapid anti-rollover response. Summary of the invention

[0004] The embodiments of the present invention provide a vehicle rollover prevention method, device, terminal and storage medium to solve the problem of slow response of vehicle rollover prevention.

[0005] In a first aspect, an embodiment of the present invention provides a method for preventing a vehicle from rolling over, comprising:

[0006] Determine whether the vehicle has a rollover tendency based on the lateral load transfer rate of the vehicle;

[0007] If the vehicle has a tendency to roll over, an additional yaw moment for suppressing the vehicle's rollover is calculated based on the lateral load transfer rate and the radial basis neural network PID controller;

[0008] A target wheel is determined based on the lateral load transfer rate, and a target braking torque is calculated based on the additional yaw moment to brake the target wheel based on the target braking torque.

[0009] In a possible implementation, judging whether the vehicle has a rollover tendency based on the lateral load transfer rate of the vehicle includes:

[0010] If the lateral load transfer rate of the vehicle shows an upward trend within a set time period, and the maximum value of the lateral load transfer rate within the set time period is greater than a set threshold, it is determined that the vehicle has a rollover tendency.

[0011] In a possible implementation, the radial basis neural network PID controller includes a radial basis neural network and a PID controller;

[0012] The additional yaw moment for suppressing vehicle rollover is calculated based on the lateral load transfer rate and the radial basis neural network PID controller, including:

[0013] The PID controller is tuned based on the radial basis function neural network, the real-time lateral load transfer rate of the vehicle and the rate of change of the lateral load transfer rate.

[0014] The lateral load transfer rate is input into the PID controller after parameter tuning to obtain the additional yaw moment used to suppress vehicle rollover.

[0015] In a possible implementation, before performing parameter tuning on the PID controller based on the radial basis function neural network, the real-time lateral load transfer rate of the vehicle, and the rate of change of the lateral load transfer rate, the method further includes:

[0016] The weight, network center and basis width of the radial basis neural network are trained based on the gradient descent algorithm and the training sample set to obtain a trained radial basis neural network; the training sample set includes a plurality of training samples, the training samples are the real-time lateral load transfer rate and the change rate of the lateral load transfer rate of the vehicle at a certain moment, and the labels of the training samples are the parameters of the PID controller;

[0017] Accordingly, the PID controller is parameterized based on the radial basis function neural network, the real-time lateral load transfer rate of the vehicle, and the change rate of the lateral load transfer rate, including:

[0018] The PID controller parameters are tuned based on the trained radial basis function neural network, the real-time lateral load transfer rate of the vehicle and the change rate of the lateral load transfer rate.

[0019] In a possible implementation manner, determining the target wheel based on the lateral load transfer rate includes:

[0020] determining the rollover direction of the vehicle based on the lateral load transfer rate;

[0021] If the vehicle rolls over to the left, the target wheel is the left front wheel;

[0022] If the vehicle rolls over to the right, the target wheel is the right front wheel.

[0023] In a possible implementation, calculating the target braking torque based on the additional yaw torque includes:

[0024] The additional yaw moment is distributed based on the target vehicle, the braking force distribution formula, the left wheel vertical load, and the right wheel vertical load to obtain the target braking moment; the braking force distribution formula is:

[0025]

[0026] Among them, a is the distance between the center of gravity of the vehicle and the front axle, b is the distance between the center of gravity of the vehicle and the rear axle, m is the mass of the vehicle, and F zl Indicates the vertical load on the left wheel, F zr is the vertical load on the right wheel, F fl is the target braking torque of the left front wheel, F fr is the target braking torque of the right front wheel, M is the additional yaw torque, and R is the wheel radius.

[0027] In a second aspect, an embodiment of the present invention provides an anti-rollover device for a vehicle, comprising:

[0028] A rollover judgment module, used to judge whether the vehicle has a rollover tendency based on the lateral load transfer rate of the vehicle;

[0029] A moment calculation module, used for calculating an additional yaw moment for suppressing the vehicle from rolling over based on a lateral load transfer rate and a radial basis neural network PID controller when the vehicle has a tendency to roll over;

[0030] The torque distribution module is used to determine the target wheel based on the lateral load transfer rate and calculate the target braking torque based on the additional yaw moment, so as to brake the target wheel based on the target braking torque.

[0031] In a third aspect, an embodiment of the present invention provides a terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the method described in the first aspect or any possible implementation manner of the first aspect are implemented.

[0032] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect or any possible implementation method of the first aspect are implemented.

[0033] The embodiment of the present invention provides a method, device, terminal and storage medium for preventing a vehicle from rolling over. The method includes: judging whether the vehicle has a tendency to roll over based on the lateral load transfer rate of the vehicle; if the vehicle has a tendency to roll over, calculating an additional yaw moment for suppressing the vehicle from rolling over based on the lateral load transfer rate and a radial basis neural network PID controller; determining a target wheel based on the lateral load transfer rate, and calculating a target braking moment based on the additional yaw moment, so as to brake the target wheel based on the target braking moment. The present invention judges whether the vehicle has a tendency to roll over based on the lateral load transfer rate, and calculates an additional yaw moment for suppressing the vehicle from rolling over through a radial basis neural network PID controller when the vehicle has a tendency to roll over, so as to improve the calculation speed of the additional yaw moment, and timely brake the target wheel before the rollover occurs, thereby improving the response speed and anti-rollover effect of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0035] Figure 1 is a flow chart of an implementation method of a vehicle rollover prevention method provided by an embodiment of the present invention;

[0036] Figure 2 is a vehicle rollover dynamics model diagram provided by an embodiment of the present invention;

[0037] Figure 3 It is a schematic diagram of the structure of a radial basis neural network PID controller provided by an embodiment of the present invention;

[0038] Figure 4 is a schematic diagram of the structure of a radial basis neural network provided by an embodiment of the present invention;

[0039] Figure 5 is a curve diagram of a steering wheel angle change of a vehicle in a simulation experiment provided by an embodiment of the present invention;

[0040] FIG6( a ) is a comparison diagram of simulation results of the lateral load transfer rate of a vehicle provided by an embodiment of the present invention;

[0041] FIG6( b ) is a comparison diagram of simulation results of the yaw angular acceleration of a vehicle provided in an embodiment of the present invention;

[0042] FIG6( c ) is a comparison diagram of simulation results of the yaw acceleration of a vehicle provided in one embodiment of the present invention;

[0043] FIG6( d ) is a comparison diagram of simulation results of the center of mass sideslip angle of a vehicle provided in one embodiment of the present invention;

[0044] Figure 7 is a schematic structural diagram of a vehicle rollover prevention device provided by one embodiment of the present invention;

[0045] Figure 8 is a schematic diagram of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0047] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0048] See also Figure 1 , which shows a flow chart of the implementation of the vehicle rollover prevention method provided by an embodiment of the present invention, and is described in detail as follows:

[0049] Step 101 : determining whether the vehicle has a rollover tendency based on the lateral load transfer rate of the vehicle.

[0050] In this embodiment, the lateral load transfer rate (LTR) refers to the ratio of the difference between the vertical loads on the wheels on both sides of the vehicle to the sum of the vertical loads, that is, Obviously, when the vehicle is running in a stable state, the LTR value of the vehicle is 0, and when the LTR value of the vehicle is ±1 or close to ±1, the vehicle will roll over. In order to suppress the rollover in time when the vehicle is about to roll over, the present invention predicts whether the vehicle has a rollover tendency through the lateral load transfer rate of the vehicle.

[0051] The lateral load transfer rate in this embodiment can be calculated as follows:

[0052] (1) Establish a three-degree-of-freedom model of the vehicle, including lateral motion, yaw motion, and roll motion;

[0053]

[0054]

[0055] in: Figure 2is the vehicle rollover dynamics model diagram, such as Figure 2 As shown, I z is the moment of inertia of the vehicle mass around the Z axis; I x is the moment of inertia of the vehicle mass around the X-axis; a is the distance between the center of gravity of the vehicle and the front axle, and b is the distance between the center of gravity of the vehicle and the rear axle; is the vehicle's roll angle, is the vehicle's roll angular velocity, is the roll angular acceleration of the vehicle; k is the suspension roll stiffness; c is the suspension damping coefficient; c a is the front axle tire cornering stiffness, c b is the tire cornering stiffness of the rear axle; δ is the front wheel turning angle; ω r is the yaw angular velocity, ω r The first derivative of ; β is the sideslip angle of the center of mass; v x is the longitudinal velocity of the center of mass; F y1 is the lateral force on the two wheels of the front axle, F y2 is the lateral force on the two wheels of the rear axle; α1 is the sideslip angle of the front axle tire, and α2 is the sideslip angle of the rear axle tire.

[0056] (2) Based on the three-degree-of-freedom model, the moment balance is taken for the roll center, and the moment balance equation is established for the contact reaction point between the inner wheel of the vehicle and the ground, which can be obtained:

[0057]

[0058] Using the same method, the moment balance equation is established for the outer wheel of the vehicle roll, and the following is obtained:

[0059]

[0060] Among them, F zl is the vertical load on the left wheel, F zr is the vertical load on the right wheel, a y is the lateral acceleration of the vehicle, h is the height of the vehicle's center of mass, and T is the wheelbase.

[0061] (3) Substitute the two moment balance equations in (2) into the calculation formula of LTR. Smaller, take The LTR is:

[0062]

[0063] Among them, a y is the lateral acceleration of the vehicle, h is the height of the vehicle's center of mass, and T is the wheelbase.

[0064] Step 102 : If the vehicle has a rollover tendency, an additional yaw moment for suppressing the vehicle rollover is calculated based on the lateral load transfer rate and the radial basis neural network PID controller.

[0065] In this embodiment, the lateral load transfer rate is an indicator for measuring the rollover tendency of the vehicle. The radial basis function neural network PID controller is a PID controller whose parameters are adjusted by the radial basis function neural network. The direction of the additional yaw moment is opposite to the rollover direction of the vehicle. After being applied to the vehicle, it can suppress the rollover tendency of the vehicle, thereby preventing the vehicle from rolling over. The lateral load transfer rate is input into the PID controller to determine the additional yaw moment that is suitable for the rollover state of the vehicle.

[0066] Step 103 : determining a target wheel based on the lateral load transfer rate, and calculating a target braking torque based on the additional yaw moment, so as to brake the target wheel based on the target braking torque.

[0067] In this embodiment, when the vehicle rolls over, the forces on each wheel are different. After braking different wheels to different degrees, the additional yaw moment on the vehicle as a whole is also different. Therefore, the additional yaw moment to be applied can be distributed to the appropriate wheel according to the rollover situation of the vehicle, thereby preventing the vehicle from rolling over.

[0068] In a possible implementation, judging whether the vehicle has a rollover tendency based on the lateral load transfer rate of the vehicle includes:

[0069] If the lateral load transfer rate of the vehicle shows an upward trend within a set time period, and the maximum value of the lateral load transfer rate within the set time period is greater than a set threshold, it is determined that the vehicle has a rollover tendency.

[0070] In this embodiment, the set time period and the set threshold can be determined based on the vehicle data. The faster the vehicle speed, the shorter the set time period can be. Similarly, the higher the center of gravity of the vehicle and the smaller the wheelbase, the smaller the set threshold can be, ensuring that the vehicle's rollover trend is discovered in time.

[0071] In a possible implementation, the radial basis function neural network PID controller includes a radial basis function neural network and a PID controller.

[0072] Accordingly, in step 102, the additional yaw moment for suppressing the vehicle rollover is calculated based on the lateral load transfer rate and the radial basis neural network PID controller, including:

[0073] The PID controller is tuned based on the radial basis function neural network, the real-time lateral load transfer rate of the vehicle and the rate of change of the lateral load transfer rate.

[0074] The lateral load transfer rate is input into the PID controller after parameter tuning to obtain the additional yaw moment used to suppress vehicle rollover.

[0075] In this embodiment, the control error of the PID controller is:

[0076] e(k)=r(k)-y out (k)

[0077] r(k) is the expected value of the lateral load transfer rate of the vehicle. In this embodiment, r(k) is set to 0. out (k) is the real-time value of the lateral load transfer rate of the vehicle.

[0078]

[0079] Among them, u(k) is the output value of the PID controller, K is the proportional coefficient of the neuron, and x c1 ,x c2 ,x c3 is the input value of the PID controller, w c1 ,w c2 ,w c3 For x c1 ,x c2 ,x c3 The weight of .

[0080] The three inputs to the PID controller are:

[0081] x c1 =e(k)-e(k-1)

[0082] x c2 =e(k)

[0083] x c3 =e(k)-2e(k-1)+e(k-2)

[0084] According to the recursion principle, we can get:

[0085] u(k)=u(k-1)+K p (e(k)-e(k-1))+K i e(k)+K d (e(k)-2e(k)-2e(k

[0086] -1)+e(k-2))

[0087] The index function for tuning the parameters of the PID controller is:

[0088]

[0089] PID controller parameter K p , Ki , K d The adjustment is performed using the gradient descent method:

[0090]

[0091] in, is the Jacobian information obtained by radial basis neural network identification, ΔK p , ΔK i , ΔK d Respectively represent K p , K i , K d The adjusted amount, K p = K before adjustment p +ΔK p , the adjusted K i = K before adjustment i +ΔK i , the adjusted K d = K before adjustment d +ΔK d .

[0092] Figure 3 Schematic diagram of the structure of the radial basis neural network PID controller provided by one embodiment of the present invention. Figure 3 As shown in FIG. 1 , the parameters of the PID controller in the radial basis function neural network PID controller are adjusted by the radial basis function neural network, and the control error e(k) is input into the PID controller after parameter adjustment to obtain the output value u(k), where e(k) is the real-time output value y according to the lateral load transfer rate of the vehicle. iut (k) and the expected value r(k). u(k) is used to brake the vehicle and is also used to input the radial basis function neural network. The radial basis function neural network adjusts the parameters of the PID controller according to u(k).

[0093] In this embodiment, the PID controller can calculate the additional yaw moment that matches the lateral load transfer rate and adjust the lateral load transfer rate of the vehicle to the desired lateral load transfer rate. The parameters of the PID controller will affect the adjustment efficiency of the lateral load transfer rate of the vehicle and the stability of the system. If fixed parameters are used in the PID controller, the adjustment time of the lateral load transfer rate will be long, resulting in poor effect of suppressing the rollover of the vehicle. Therefore, in this embodiment, the parameters of the PID controller are adjusted in real time through the radial basis function neural network, and the parameters of the PID controller are adjusted accordingly according to the lateral load transfer rate of the vehicle, which can shorten the adjustment time of the lateral load transfer rate and improve the effect of suppressing the rollover of the vehicle.

[0094] In a possible implementation, before performing parameter tuning on the PID controller based on the radial basis function neural network, the real-time lateral load transfer rate of the vehicle, and the rate of change of the lateral load transfer rate, the method further includes:

[0095] The weight, network center and basis width of the radial basis neural network are trained based on the gradient descent algorithm and the training sample set to obtain a trained radial basis neural network; the training sample set includes a plurality of training samples, the training samples are the real-time lateral load transfer rate and the change rate of the lateral load transfer rate of the vehicle at a certain moment, and the labels of the training samples are the parameters of the PID controller;

[0096] Accordingly, the PID controller is parameterized based on the radial basis function neural network, the real-time lateral load transfer rate of the vehicle, and the change rate of the lateral load transfer rate, including:

[0097] The PID controller parameters are tuned based on the trained radial basis function neural network, the real-time lateral load transfer rate of the vehicle and the change rate of the lateral load transfer rate.

[0098] In this embodiment, the radial basis neural network is a three-layer neural network, including an input layer, a hidden layer, and an output layer. Figure 4 As shown. The basic idea of ​​the radial basis neural network is to use the radial basis as the "basis" of the hidden unit to form the hidden layer space, so that the input vector can be directly mapped to the hidden layer space without the need for weight connection. When the center point of the radial basis neural network is determined, this mapping relationship is also determined. The mapping from the hidden layer space to the output space is linear, that is, the output of the network is the linear weighted sum of the hidden unit outputs, and the weight here is the network adjustable parameter. Among them, the role of the hidden layer is to map the vector from low dimension to high dimension, and the linearly inseparable situation in low dimension can become linearly separable in high dimension. The mapping from input to output of the radial basis neural network is nonlinear, but the output of the radial basis neural network is linear with respect to the adjustable parameters. The weight of the network can be directly solved by a set of linear equations, thereby greatly accelerating the learning speed and avoiding the local minimum problem. In this embodiment, the input vector of the radial basis neural network is X=[x1,x2,...,x n ] T , the radial basis vectors are H = [h1,h2,...,h j ,...,h m ] T , where h j is the Gaussian basis function:

[0099]

[0100] Among them, c j =[c j1 ,cj2 ,…,c jn ] T , j = 1, 2, ... n is the center vector of the radial basis neural network. The baseband vector of the radial basis neural network is:

[0101] B=[b1,b2,b3,…b j ,…,b n ] T

[0102] Among them, b j is the basis width parameter of the jth node in the hidden layer, which is used to represent the width of the basis function around the center. The weight vector of the radial basis neural network is:

[0103] W=[w1,w2,w3,…w j ,…,w n ] T

[0104] Among them, w j is the weight vector of the jth node in the hidden layer.

[0105] The output vector of the radial basis neural network is:

[0106] y m (k)=w1(k)h1(k)+w2(k)h2(k)+w3(k)h3(k)+…+w n (k)h n (k)

[0107] The performance objective function of the radial basis neural network is:

[0108]

[0109] Among them, y m (k) is the output of the radial basis neural network.

[0110] By using the gradient descent method, the formula for iterating the weight, center vector and baseband vector is:

[0111] w j (k) = w j (k-1)+η(y out (k)-y m (k))h j +α(w j (k-1)-w j (k-2))

[0112]

[0113] Among them, η is the learning efficiency; α is the momentum factor.

[0114] The calculation formula of Jacobian is:

[0115]

[0116] In a possible implementation manner, determining the target wheel based on the lateral load transfer rate includes:

[0117] determining the rollover direction of the vehicle based on the lateral load transfer rate;

[0118] If the vehicle rolls over to the left, the target wheel is the left front wheel;

[0119] If the vehicle rolls over to the right, the target wheel is the right front wheel.

[0120] In this embodiment, according to the relationship between the braking force of each wheel and the change in the yaw moment, the yaw moment generated by each wheel is slightly different, and the braking effect of the front outer wheel is the best. Therefore, the additional yaw moment used to suppress the vehicle rollover is only applied to the front wheels of the vehicle for braking, and the rear wheels are not braked.

[0121] In a possible implementation, calculating the target braking torque based on the additional yaw torque includes:

[0122] The additional yaw moment is distributed based on the target vehicle, the braking force distribution formula, the left wheel vertical load, and the right wheel vertical load to obtain the target braking moment; the braking force distribution formula is:

[0123]

[0124] Among them, a is the distance between the center of gravity of the vehicle and the front axle, b is the distance between the center of gravity of the vehicle and the rear axle, m is the mass of the vehicle, and F zl Indicates the vertical load on the left wheel, F zr is the vertical load on the right wheel, F fl is the target braking torque of the left front wheel, F fr is the target braking torque of the right front wheel, M is the additional yaw torque, and R is the wheel radius.

[0125] In this embodiment, the motion equation of the vehicle in the yaw direction before differential braking is applied is:

[0126]

[0127] The equation of motion of the vehicle in the yaw direction after differential braking is applied is:

[0128]

[0129] Among them, F yfl is the lateral force on the left front wheel of the vehicle; F yfris the lateral force on the right front wheel of the vehicle; F yrl is the lateral force on the left rear wheel of the vehicle; f yrr is the lateral force acting on the right rear wheel of the vehicle; M is the anti-yaw moment generated during differential braking.

[0130] M can be expressed as:

[0131]

[0132] Among them, F x The ground braking force applied to the braked wheel.

[0133] The wheel braking force is distributed according to the ratio of the wheel vertical load.

[0134]

[0135] Among them, F zl is the vertical load on the left wheel, F zr is the vertical load on the right wheel.

[0136] The calculation formula of braking force is:

[0137] The calculation formula of braking torque is:

[0138] T bf =F f R

[0139] T br =F r R

[0140] Among them, T bf is the front wheel braking torque, T br is the rear wheel braking torque, R is the wheel rolling radius, F f is the front wheel braking force, F r For rear wheel braking force.

[0141] In a specific embodiment, the effect of the vehicle rollover prevention method provided by the present invention is verified by a simulation platform, and the specific steps are as follows:

[0142] First, a joint simulation platform was built with the help of CarSim and Matlab / Simulink software. The platform construction steps are divided into two steps:

[0143] (1) Build subsystems based on the function definition according to the role definition of CarSim and Matlab / Simulink software. For CarSim software: set vehicle parameters and simulation conditions in CarSim through parameterized settings and customization; use CarSim's built-in vehicle dynamics parameters and tire model as simulation evaluation parameters. For Matlab / Simulink software: build the control strategy designed in this paper.

[0144] (2) CarSim and Simulink joint simulation verification is carried out based on CarSim’s rich external information interaction interface.

[0145] During the simulation, the vehicle parameters are shown in Table 1:

[0146] Table 1

[0147] parameter Vehicle Length Vehicle width Vehicle height weight Climbing performance Wheel radius Wheelbase Wheelbase Numeric 820mm 695mm 356mm 60kg 30° 150mm 602mm 504mm

[0148] Next, a double lane change condition simulation experiment was conducted in the simulation system. The double lane change condition can fully test the anti-roll performance of the vehicle. The initial test speed was set to 90 km / h, the road adhesion coefficient was 0.85, and the input direction angle was Figure 5 As shown. Figure 5 It can be seen that the peak value of the input steering wheel angle is 150°, which shows that the set working conditions are relatively harsh on the vehicle undergoing the simulation experiment, and can fully test the effect of the anti-rollover method provided by the present invention.

[0149] Figures 6(a), 6(b), 6(c), and 6(d) are simulation results of various parameters of the double lane change condition. It can be seen that when the vehicle speed is 90km / h, the lateral load transfer rate reaches the set threshold value of 0.8 when the vehicle travels to 5.9s, and continues to rise until the vehicle travels to 6.1s, the lateral load transfer rate value is 1, and the vehicle rolls over. At this time, the peak value of the lateral load transfer rate is quickly reduced to within the threshold through the work of the PID brake controller, and the radial basis neural network PID controller is slightly better than the traditional PID controller. Due to the emergency turn of the vehicle, the yaw angular acceleration increases rapidly, reaching a peak value of -0.45deg / s at 6.1s. 2, the differential braking controller quickly controls the yaw acceleration within the range where the vehicle tends to become unstable. As the yaw acceleration decreases, the yaw velocity also decreases. The range of the sideslip angle of the center of mass decreases from -0.78deg to 0.88deg to -0.43deg to 0.48deg, and the change is gentle, with no obvious mutation. The stability performance index of the wheeled robot under the radial basis function neural network PID control is lower than that of the conventional PID control system. Therefore, the possibility of vehicle rollover increases with the increase in vehicle speed. The radial basis function neural network PID control is more effective in improving the lateral stability of the wheeled robot and suppressing rollover.

[0150] The embodiment of the present invention provides a method, device, terminal and storage medium for preventing a vehicle from rolling over. The method includes: judging whether the vehicle has a tendency to roll over based on the lateral load transfer rate of the vehicle; if the vehicle has a tendency to roll over, calculating an additional yaw moment for suppressing the vehicle from rolling over based on the lateral load transfer rate and a radial basis neural network PID controller; determining a target wheel based on the lateral load transfer rate, and calculating a target braking moment based on the additional yaw moment, so as to brake the target wheel based on the target braking moment. The present invention judges whether the vehicle has a tendency to roll over based on the lateral load transfer rate, and calculates an additional yaw moment for suppressing the vehicle from rolling over through a radial basis neural network PID controller when the vehicle has a tendency to roll over, so as to improve the calculation speed of the additional yaw moment, and timely brake the target wheel before the rollover occurs, thereby improving the response speed and anti-rollover effect of the vehicle.

[0151] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0152] The following is an embodiment of the device of the present invention. For details not described in detail therein, reference may be made to the corresponding method embodiment described above.

[0153] Figure 7 The structure diagram of the anti-rollover device of a vehicle provided by an embodiment of the present invention is shown. For the convenience of description, only the part related to the embodiment of the present invention is shown, which is described in detail as follows:

[0154] like Figure 7 As shown, the anti-rollover device 7 of the vehicle includes:

[0155] A rollover judgment module 71, used to judge whether the vehicle has a rollover tendency based on the lateral load transfer rate of the vehicle;

[0156] A moment calculation module 72, for calculating an additional yaw moment for suppressing the vehicle from rolling over based on a lateral load transfer rate and a radial basis neural network PID controller when the vehicle has a tendency to roll over;

[0157] The torque distribution module 73 is used to determine the target wheel based on the lateral load transfer rate and calculate the target braking torque based on the additional yaw torque, so as to brake the target wheel based on the target braking torque.

[0158] In a possible implementation, the rollover determination module 71 is specifically configured to:

[0159] When the lateral load transfer rate of the vehicle shows an upward trend within a set time period and the maximum value of the lateral load transfer rate within the set time period is greater than a set threshold, it is determined that the vehicle has a rollover tendency.

[0160] In a possible implementation, the radial basis neural network PID controller includes a radial basis neural network and a PID controller;

[0161] The torque calculation module 72 is specifically used for:

[0162] The PID controller is tuned based on the radial basis function neural network, the real-time lateral load transfer rate of the vehicle and the rate of change of the lateral load transfer rate.

[0163] The lateral load transfer rate is input into the PID controller after parameter tuning to obtain the additional yaw moment used to suppress vehicle rollover.

[0164] In a possible implementation, the torque calculation module 72 is further used for:

[0165] Before the PID controller is parameterized based on the radial basis neural network, the real-time lateral load transfer rate of the vehicle and the rate of change of the lateral load transfer rate, the weight, network center and basis width of the radial basis neural network are trained based on the gradient descent algorithm and the training sample set to obtain a trained radial basis neural network; the training sample set includes a plurality of training samples, the training samples are the real-time lateral load transfer rate and the rate of change of the lateral load transfer rate of the vehicle at a certain moment, and the labels of the training samples are the parameters of the PID controller;

[0166] The PID controller parameters are tuned based on the trained radial basis function neural network, the real-time lateral load transfer rate of the vehicle and the change rate of the lateral load transfer rate.

[0167] In a possible implementation, the torque distribution module 73 is specifically used to:

[0168] determining the rollover direction of the vehicle based on the lateral load transfer rate;

[0169] If the vehicle rolls over to the left, the target wheel is the left front wheel;

[0170] If the vehicle rolls over to the right, the target wheel is the right front wheel.

[0171] In a possible implementation, the torque distribution module 73 is specifically used to:

[0172] The additional yaw moment is distributed based on the target vehicle, the braking force distribution formula, the left wheel vertical load, and the right wheel vertical load to obtain the target braking moment; the braking force distribution formula is:

[0173]

[0174] Among them, a is the distance between the center of gravity of the vehicle and the front axle, b is the distance between the center of gravity of the vehicle and the rear axle, m is the mass of the vehicle, and F zl Indicates the vertical load on the left wheel, F zr is the vertical load on the right wheel, F fl is the target braking torque of the left front wheel, F fr is the target braking torque of the right front wheel, M is the additional yaw torque, and R is the wheel radius.

[0175] The anti-rollover device of the vehicle provided by the embodiment of the present invention includes: a rollover judgment module, which is used to judge whether the vehicle has a rollover tendency based on the lateral load transfer rate of the vehicle; a torque calculation module, which is used to calculate the additional yaw moment for suppressing the vehicle rollover based on the lateral load transfer rate and the radial basis neural network PID controller when the vehicle has a rollover tendency; and a torque distribution module, which is used to determine the target wheel based on the lateral load transfer rate, and calculate the target braking moment based on the additional yaw moment, so as to brake the target wheel based on the target braking moment. The present invention judges whether the vehicle has a rollover tendency by the lateral load transfer rate, and calculates the additional yaw moment for suppressing the vehicle rollover by the radial basis neural network PID controller when the vehicle has a rollover tendency, which can improve the calculation speed of the additional yaw moment, and brake the target wheel in time before the rollover occurs, thereby improving the response speed and anti-rollover effect of the vehicle.

[0176] Figure 8 is a schematic diagram of a terminal provided by an embodiment of the present invention. Figure 8 As shown, the terminal 8 of this embodiment includes: a processor 80, a memory 81, and a computer program 82 stored in the memory 81 and executable on the processor 80. When the processor 80 executes the computer program 82, the steps in the above-mentioned various vehicle rollover prevention method embodiments are implemented, such as Figure 1 Alternatively, when the processor 80 executes the computer program 82, the functions of the modules in the above-mentioned device embodiments are realized, for example, Figure 7 The functions of modules 71 to 73 are shown.

[0177] Exemplarily, the computer program 82 may be divided into one or more modules, which are stored in the memory 81 and executed by the processor 80 to implement the present invention. The one or more modules may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program 82 in the terminal 8. For example, the computer program 82 may be divided into Figure 7 Modules 71 to 73 are shown.

[0178] The terminal 8 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal 8 may include, but is not limited to, a processor 80 and a memory 81. Those skilled in the art will appreciate that Figure 8 It is only an example of terminal 8 and does not constitute a limitation on terminal 8. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal may also include input and output devices, network access devices, buses, etc.

[0179] The processor 80 may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), advanced RISC machine (ARM) architecture processors or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0180] The memory 81 may be an internal storage unit of the terminal 8, such as a hard disk or memory of the terminal 8. The memory 81 may also be an external storage device of the terminal 8, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal 8. Further, the memory 81 may also include both an internal storage unit of the terminal 8 and an external storage device. The memory 81 is used to store the computer program and other programs and data required by the terminal. The memory 81 may also be used to temporarily store data that has been output or is to be output.

[0181] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0182] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0183] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0184] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0185] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0186] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0187] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned anti-rollover method embodiments of each vehicle can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practices in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practices, computer-readable media does not include electrical carrier signals and telecommunication signals.

[0188] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for preventing a vehicle from rolling over, characterized in that: include: determining whether the vehicle has a rollover tendency based on a lateral load transfer rate of the vehicle; If the vehicle has a rollover tendency, calculating an additional yaw moment for suppressing the vehicle from rolling over based on the lateral load transfer rate and a radial basis neural network PID controller; determining a target wheel based on the lateral load transfer rate, and calculating a target braking torque based on the additional yaw moment, so as to brake the target wheel based on the target braking torque; The radial basis neural network PID controller comprises a radial basis neural network and a PID controller; The additional yaw moment for suppressing the vehicle rollover is calculated based on the lateral load transfer rate and a radial basis neural network PID controller, comprising: Performing parameter tuning on the PID controller based on the radial basis function neural network, the real-time lateral load transfer rate of the vehicle, and the rate of change of the lateral load transfer rate; Inputting the lateral load transfer rate into a PID controller after parameter tuning to obtain an additional yaw moment for suppressing the vehicle from rolling over; Before performing parameter tuning on the PID controller based on the radial basis function neural network, the real-time lateral load transfer rate of the vehicle, and the rate of change of the lateral load transfer rate, the method further includes: The weight, network center and basis width of the radial basis neural network are trained based on a gradient descent algorithm and a training sample set to obtain a trained radial basis neural network; the training sample set includes a plurality of training samples, the training samples are the real-time lateral load transfer rate and the change rate of the lateral load transfer rate of the vehicle at a certain moment, and the labels of the training samples are the parameters of the PID controller; Accordingly, the PID controller is parameterized based on the radial basis function neural network, the real-time lateral load transfer rate of the vehicle, and the rate of change of the lateral load transfer rate, including: The PID controller is parameterized based on the trained radial basis function neural network, the real-time lateral load transfer rate of the vehicle, and the rate of change of the lateral load transfer rate.

2. The method for preventing a vehicle from rolling over according to claim 1, characterized in that: The determining whether the vehicle has a rollover tendency based on the lateral load transfer rate of the vehicle includes: If the lateral load transfer rate of the vehicle shows an upward trend within a set time period, and the maximum value of the lateral load transfer rate within the set time period is greater than a set threshold, it is determined that the vehicle has a rollover tendency.

3. The method for preventing a vehicle from rolling over according to claim 1, characterized in that: The determining of the target wheel based on the lateral load transfer rate comprises: determining a rollover direction of the vehicle based on the lateral load transfer rate; If the rollover direction of the vehicle is to the left, the target wheel is the left front wheel; If the rollover direction of the vehicle is to the right, the target wheel is the right front wheel.

4. The method for preventing a vehicle from rolling over according to claim 3, characterized in that: The calculating the target braking torque based on the additional yaw moment comprises: The additional yaw moment is distributed based on the target vehicle, the braking force distribution formula, the left wheel vertical load and the right wheel vertical load to obtain the target braking moment; the braking force distribution formula is: Where a is the distance between the center of gravity of the vehicle and the front axle, b is the distance between the center of gravity of the vehicle and the rear axle, m is the mass of the vehicle, and F zl Indicates the vertical load on the left wheel, F zr is the vertical load on the right wheel, F fl is the target braking torque of the left front wheel, F fr is the target braking torque of the right front wheel, M is the additional yaw torque, and R is the wheel radius.

5. A vehicle rollover prevention device, characterized in that: include: A rollover judgment module, used for judging whether the vehicle has a rollover tendency based on the lateral load transfer rate of the vehicle; a moment calculation module, configured to calculate an additional yaw moment for suppressing the vehicle from rolling over based on the lateral load transfer rate and a radial basis neural network PID controller when the vehicle has a tendency to roll over; a torque distribution module, configured to determine a target wheel based on the lateral load transfer rate, and calculate a target braking torque based on the additional yaw moment, so as to brake the target wheel based on the target braking torque; The radial basis neural network PID controller comprises a radial basis neural network and a PID controller; The torque calculation module is specifically used for: Performing parameter tuning on the PID controller based on the radial basis function neural network, the real-time lateral load transfer rate of the vehicle, and the rate of change of the lateral load transfer rate; Inputting the lateral load transfer rate into a PID controller after parameter tuning to obtain an additional yaw moment for suppressing the vehicle from rolling over; The torque calculation module is also used for: Before the PID controller is parameterized based on the radial basis function neural network, the real-time lateral load transfer rate of the vehicle and the rate of change of the lateral load transfer rate, the weight, network center and basis width of the radial basis function neural network are trained based on a gradient descent algorithm and a training sample set to obtain a trained radial basis function neural network; the training sample set includes a plurality of training samples, the training samples are the real-time lateral load transfer rate and the rate of change of the lateral load transfer rate of the vehicle at a certain moment, and the labels of the training samples are the parameters of the PID controller; Accordingly, the PID controller is parameterized based on the radial basis function neural network, the real-time lateral load transfer rate of the vehicle, and the rate of change of the lateral load transfer rate, including: The PID controller is parameterized based on the trained radial basis function neural network, the real-time lateral load transfer rate of the vehicle, and the rate of change of the lateral load transfer rate.

6. The vehicle rollover prevention device according to claim 5, characterized in that: The rollover judgment module is specifically used for: When the lateral load transfer rate of the vehicle shows an upward trend within a set time period and the maximum value of the lateral load transfer rate within the set time period is greater than a set threshold, it is determined that the vehicle has a rollover tendency.

7. A terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images