Vehicle suspension system control method and system and storage medium

Abstract

The invention relates to a suspension system control method and system of a vehicle and a storage medium, and the method comprises the steps: carrying out the information fusion of a current road image, road point cloud information and the state information of the vehicle, and obtaining a target road unevenness grade which can reflect the condition of a target road after the historical road unevenness grade is considered; meanwhile, the feedforward damping force of the suspension system when the vehicle is about to run on the target road surface is predicted according to the unevenness level of the target road surface, and in the process that the vehicle runs on the target road surface based on the feedforward damping force, feedback damping force used for compensating the feedforward damping force can be calculated in real time according to vehicle body parameters of the vehicle; therefore, the vehicle can stably run on the target road surface, and the driving comfort performance of the vehicle under the condition of the unsmooth road surface based on the control strategy is further improved.

Description

Technical Field

[0001] The present invention relates to the field of automobiles, and in particular to a suspension system control method and system, and a storage medium for a vehicle. Background Art

[0002] As the performance and user experience of new energy vehicles continue to improve, users have higher and higher requirements for vehicle ride comfort, handling stability and safety. Traditional suspension control is mainly based on vibration state feedback control, but this method will have significant delays, and the initial impact is large when driving on uneven roads, resulting in a poor ride experience. In addition, semi-active suspension damping control is mainly based on classic control methods such as ceiling, floor, and acceleration damping. Parameter calibration is required based on the experience of engineers, and its control parameters are fixed after calibration under typical working conditions. In addition, traditional control methods do not consider the impact of unknown external disturbance forces, vehicle mass, and nonlinear characteristics of shock absorbers on ride smoothness. In complex road conditions and driving conditions, the vehicle's ride smoothness and handling performance need to be further improved. Therefore, it is necessary to design an adjustable damping force control method with low control delay and good adaptive robustness. Summary of the invention

[0003] One of the purposes of the present invention is to provide a vehicle suspension system control method and system, and a storage medium, which predicts the roughness level of the target road surface that the vehicle is about to pass through, and designs a feedforward control strategy to control the vehicle suspension system in advance. In addition, an anti-disturbance adaptive feedback control strategy is designed based on the real-time state of the vehicle to compensate for the feedforward control amount, thereby improving the driving comfort of the vehicle when passing through the uneven road surface.

[0004] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0005] A method for controlling a suspension system of a vehicle, comprising:

[0006] Acquire a current road surface image and road surface point cloud information of a target road surface in a first direction, as well as vehicle status information; the first direction is the driving direction of the vehicle;

[0007] Inputting the current road surface image, the road surface point cloud information and the state information into a preset road surface recognition model to obtain a target road surface roughness grade of the target road surface;

[0008] Predicting, according to the target road surface roughness level, a feedforward damping force required by a suspension system of the vehicle when the vehicle travels on the target road surface;

[0009] When the vehicle travels onto the target road surface based on the feedforward damping force, the feedback damping force is calculated in real time based on the body parameters of the vehicle, and the feedforward damping force is compensated in real time based on the feedback damping force, so that the vehicle travels smoothly on the target road surface.

[0010] In the above suspension system control method for a vehicle, the real-time calculation of the feedback damping force based on the body parameters of the vehicle includes:

[0011] Construct alternative Lyapunov functions;

[0012] Under the condition that the first-order derivative of the candidate Lyapunov function is maintained to be less than or equal to 0, determining a first calculation formula for the feedback damping force;

[0013] The feedback damping force is calculated according to the first calculation formula.

[0014] In the above-mentioned vehicle suspension system control method, the constructing of the candidate Lyapunov function includes:

[0015] Decoupling the suspension system into a plurality of sub-suspension systems at different locations, and establishing a two-degree-of-freedom vibration model based on the sub-suspension systems and the vehicle body parameters;

[0016] The alternative Lyapunov function is constructed based on the sliding mode variables determined by the two-degree-of-freedom vibration model, the radial basis neural network weight coefficient estimation error, the radial basis function estimation error, the radial basis center estimation error and the disturbance force estimation error uncertainty.

[0017] In the above-mentioned vehicle suspension system control method, the method further includes:

[0018] Determining a relative displacement of a lower mass of the suspension system and a relative velocity of the lower mass according to the two-degree-of-freedom vibration model;

[0019] The relative displacement of the lower mass is multiplied by a sliding mode gain coefficient and then added to the relative speed of the lower mass to obtain the sliding mode variable.

[0020] In the above-mentioned vehicle suspension system control method, the method further includes:

[0021] determining a nominal disturbance force and an estimated disturbance force based on the sliding mode variables;

[0022] Subtracting the estimated disturbance force from the nominal disturbance force to obtain a disturbance force estimation error; the disturbance force estimation error is composed of the product of the weight coefficient and the radial basis function estimation error, the product of the weight coefficient error and the radial basis function estimate, and the optimal approximation error.

[0023] Splitting the radial basis function estimation error into the product of the partial derivative of the radial basis function with respect to the radial basis center and the estimation error of the radial basis center, the product of the partial derivative of the radial basis function with respect to the radial basis width and the estimation error of the radial basis width, and the sum of the high-order terms after Taylor expansion of the radial basis function;

[0024] Obtaining the uncertainty of the disturbance force estimation error based on the product of the sliding mode variable, the uncertainty gain coefficient, and the first matrix, and the product of the sliding mode variable and the adjustable gain coefficient;

[0025] The first matrix is ​​composed of a first constant, a radial basis center estimate, a radial basis width estimate, and a weight coefficient estimate.

[0026] In the above-mentioned vehicle suspension system control method, the method further includes:

[0027] The radial basis function is obtained by subtracting the norm of the radial basis center from the sliding mode variable and dividing the result by the radial basis width;

[0028] Determine the product of the radial basis function and the weighting coefficient and the sum of the optimal approximation error as the nominal disturbance force;

[0029] The weight coefficient, radial basis center and radial basis width in the nominal disturbance force are replaced with corresponding estimates, and the optimal disturbance approximation error term is discarded to obtain the estimated disturbance force.

[0030] In the above-mentioned vehicle suspension system control method, the first variable in the first calculation formula includes a radial basis neural network weight coefficient, a radial basis center, a radial basis width, and a disturbance force estimation error uncertainty; and calculating the feedback damping force according to the first calculation formula includes:

[0031] Calculating the radial basis neural network weight coefficient, the radial basis center, the radial basis width and the disturbance force estimation error uncertainty in real time according to the real-time vehicle body parameters;

[0032] Substitute the radial basis neural network weight coefficient, the radial basis center, the radial basis width and the disturbance force estimation error uncertainty into the first calculation formula to obtain the feedback damping force.

[0033] In the above suspension system control method for a vehicle, the preset road surface recognition model includes at least a first model, a second model, and a third model; the step of inputting the current road surface image, the road surface point cloud information, and the state information into the preset road surface recognition model to obtain a target road surface roughness level of the target road surface includes:

[0034] Inputting the current road surface image into the first model, extracting first road surface features in the current road surface image using the first model, and converting the first road surface features into a first road surface roughness grade;

[0035] Inputting the road surface point cloud information into the second model, extracting second road surface features from the road surface point cloud information using the second model, and converting the second road surface features into a second road surface roughness grade;

[0036] Inputting the state information into the third model to obtain a third road surface roughness grade;

[0037] The first road surface roughness level, the second road surface roughness level, the third road surface roughness level, and the historical road surface roughness level of the target road surface are fused to obtain the target road surface roughness level.

[0038] In the above-mentioned vehicle suspension system control method, the method further includes:

[0039] Acquire historical road marking information corresponding to the target road; the historical road marking information is obtained after marking the target road when the vehicle historically travels to the target road;

[0040] The historical road surface marking information includes the historical road surface roughness level, historical road surface coordinates, historical road surface length and historical path curvature corresponding to the target road surface.

[0041] In the above suspension system control method for a vehicle, the state information includes a current first driving speed of the vehicle, and the method further includes:

[0042] Determining a current first position coordinate of the vehicle;

[0043] Determine a first distance between a first position of the vehicle and a starting position of the target road surface according to the first position coordinates and the historical road surface coordinates; the first position is a center position of a front axle on the vehicle;

[0044] Determining a first time required for the vehicle to travel to the starting position according to the first distance and the first travel speed;

[0045] When the first time duration is less than a first threshold value and / or the first distance is less than a second threshold value, the control strategy is started.

[0046] In the above-mentioned vehicle suspension system control method, the method further includes:

[0047] Determining a second time required for the vehicle to travel the target road surface according to the first driving speed and the historical road surface length;

[0048] When the control strategy is turned on and the second time period has elapsed, the control strategy is turned off.

[0049] In the above suspension system control method for a vehicle, after the real-time compensation of the feedforward damping force based on the feedback damping force is performed, the method further includes:

[0050] The height of the suspension system is adjusted to a target height, and / or the stiffness of an air spring in the suspension system is adjusted to a target stiffness.

[0051] In the above-mentioned vehicle suspension system control method, the method further includes:

[0052] determining an air suspension mode currently set for the vehicle;

[0053] The target height and the target stiffness are determined according to the air suspension mode, the historical path curvature, the state information, and the target road roughness level.

[0054] In the above-mentioned vehicle suspension system control method, the method further includes:

[0055] When it is detected that the vehicle is accelerating or braking while traveling on the target road surface, adjusting the target height according to the current second traveling speed of the vehicle and the first information of the vehicle;

[0056] The first information is the current pedal position of the accelerator pedal in the vehicle and / or the current pressure of the brake cylinder.

[0057] In the above-mentioned vehicle suspension system control method, the method further includes:

[0058] When the vertical acceleration of the front axle wheel of the vehicle is greater than a third threshold value, determining that the vehicle has reached the starting point of the target road surface, and determining the current first position coordinates and the current first time point of the vehicle;

[0059] When the vertical acceleration of the front axle wheel of the vehicle is less than a fourth threshold value, determining that the vehicle has left the target road surface, and determining a current second position coordinate and a current second time point of the vehicle;

[0060] Determine a first road length of the target road according to the first position coordinates and the second position coordinates, and / or the first time point, the second time point, and a third current driving speed of the vehicle;

[0061] A target path curvature is determined according to the first path curvature and the historical path curvature, and the historical road marking information is updated according to the target path curvature, the target road surface roughness level, the first road surface length, and the first position coordinates.

[0062] A suspension control system for a vehicle, the suspension control system for the vehicle comprising:

[0063] A binocular camera, used to obtain a current road surface image of a target road surface in a first direction;

[0064] A radar, used to obtain road surface point cloud information of the target road surface in the first direction; the first direction is the driving direction of the vehicle;

[0065] Body sensor, used to obtain vehicle status information;

[0066] A suspension controller is used to input the current road surface image, the road surface point cloud information and the state information into a preset road surface recognition model to obtain a target road surface roughness level of the target road surface; predict the feedforward damping force required by the suspension system of the vehicle when the vehicle travels on the target road surface according to the target road surface roughness level; when the vehicle travels on the target road surface based on the feedforward damping force, calculate the feedback damping force in real time based on the body parameters of the vehicle, and compensate the feedforward damping force in real time based on the feedback damping force, so that the vehicle can travel smoothly on the target road surface.

[0067] The present invention first fuses the current road surface image, road surface point cloud information, and vehicle status information, and obtains the target road surface roughness level that best reflects the target road surface condition after considering the historical road surface roughness level. Therefore, the most accurate control strategy can be obtained based on the target road surface roughness level, and the damping force of the shock absorber determined in the control strategy is obtained based on the feedback control damping force and the feedforward damping force, which can reduce the impact and vibration acceleration of the vehicle entering the target road surface, and further improve the driving comfort performance of the vehicle under uneven road conditions based on the control strategy. At the same time, the feedback control damping force can use the nonlinear characteristics of the radial basis neural network to design a self-learning control strategy to adaptively compensate for external disturbances, and the feedback control damping force can quickly eliminate the vibration acceleration of the vehicle body and wheels after the vehicle enters the target road surface. In addition, the radial basis neural network weight coefficient, the radial basis center, the radial basis width, and the real-time update law of the change rate of the uncertainty of the disturbance force estimation error proposed by the present invention greatly reduce the parameter calibration workload of the feedback control algorithm. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1A schematic flow chart of a method for controlling a suspension system of a vehicle provided by an embodiment of the present invention;

[0069] Figure 2 A schematic diagram of the structure of a suspension control system for a vehicle provided by an embodiment of the present invention;

[0070] Figure 3 A schematic diagram of an exemplary two-degree-of-freedom model provided by an embodiment of the present invention;

[0071] Figure 4 A schematic diagram of an exemplary process for determining a target road surface roughness grade provided by an embodiment of the present invention;

[0072] Figure 5 A schematic diagram of an exemplary process of determining a target height and a target stiffness provided in an embodiment of the present invention;

[0073] Figure 6 A schematic diagram of an exemplary process for determining the start time of a control strategy provided by an embodiment of the present invention;

[0074] Figure 7 A schematic diagram of an exemplary update process of historical road surface marking information provided by an embodiment of the present invention;

[0075] Figure 8 A schematic diagram of an exemplary process for determining an optimal special road surface roughness level provided in an embodiment of the present invention;

[0076] Fig. 9 An exemplary signal processing flow provided for an embodiment of the present invention Figure 1 ;

[0077] Fig.10 An exemplary signal processing flow provided for an embodiment of the present invention Figure 2 ;

[0078] Fig.11 A schematic diagram of the composition structure of a suspension control device for a vehicle provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0079] The following will describe the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention, not for limiting the scope of protection of the present invention.

[0080] As the performance and user experience of new energy vehicles continue to improve, users have higher and higher requirements for vehicle ride comfort, handling stability and safety. The gradual maturity of intelligent perception, intelligent networking and electronically controlled suspension technology provides a new technical path for improving the comprehensive performance of suspension. The suspension controller adjusts the height, damping and stiffness of the suspension system according to the vehicle driving state and road condition information to adapt to changes in road conditions, which can effectively improve the comfort of the vehicle. At present, semi-active suspension damping control is mainly based on classic control methods such as ceiling, floor, and acceleration damping. After the control parameters are calibrated, it is difficult to adapt to complex road conditions and changes in vehicle driving conditions, and it is impossible to guarantee smooth performance under multiple working conditions; there are problems such as large impact vibration and untimely control when vehicles pass through special roads such as speed bumps and manhole covers. At present, road condition prediction control based on pure machine vision has gradually emerged, but there is a lot of room for improvement in terms of road recognition accuracy, scene coverage and reliability. These problems are important factors that restrict the performance improvement of semi-active suspension systems. Road condition prediction control based on pure machine vision mainly includes the following methods:

[0081] 1. Apply vehicle speed and acceleration and other on-board driving data, use map navigation path information, and determine the boundary value of the semi-active suspension damping coefficient according to the road roughness level, functional level and category of the road section where the vehicle is located, and use the control algorithm to calculate the suspension damping coefficient value. This method can only control the suspension through feedback control, which has hysteresis.

[0082] 2. Use wheel vibration signals and road image recognition to calculate two road surface information and upload them to the cloud server. The adjustment instructions sent by the cloud server are obtained through the receiving module to control the suspension. However, this method does not consider the fusion of multi-modal road surface information and does not explain how to specifically control the suspension system.

[0083] 3. Use the received binocular images to reconstruct and extract the three-dimensional road point cloud, then calculate the road roughness level, and finally remind the driver through the indicator light according to the road roughness level. However, this method is to identify the road roughness through pure road images, and its accuracy and reliability need to be improved.

[0084] 4. Use high-precision map collection vehicles and positioning base station equipment to scan road slopes and elevations, establish local maps and global maps based on the acquired three-dimensional point cloud icon information, and then estimate the elevation information of the vehicle's driving area to control the height and damping of the vehicle's active suspension. However, this method is costly and time-consuming to produce high-precision maps. Moreover, changes in road conditions are difficult to update in real time in high-precision maps, and the maintenance cost of high-precision maps is very high.

[0085] Electronically controlled suspension has the advantages of low energy consumption, compact space, low cost and continuous damping control, and currently has good market application prospects in mid-to-high-end models. However, the control delay caused by signal transmission, feedback control calculation and actuator response makes the electronically controlled suspension system control have significant hysteresis, which restricts the electronically controlled suspension system from further improving the ride smoothness and handling stability of the vehicle. For example, air spring control also has the inherent problem of not adjusting quickly enough. Therefore, it is necessary to systematically solve the control hysteresis problem of semi-active suspension.

[0086] In view of the above technical problems, the present invention provides a vehicle suspension system control method, which is implemented by a vehicle suspension control system and can adjust the vehicle's suspension system before the vehicle reaches a special road surface, thereby improving the vehicle's riding smoothness, handling stability and safety under comprehensive working conditions.

[0087] Figure 1 A flow chart of a suspension system control method for a vehicle provided by an embodiment of the present invention is shown as follows: Figure 1 As shown, the steps S101 to S103 are included:

[0088] Step S101, obtaining a current road surface image and road surface point cloud information of a target road surface in a first direction, as well as vehicle status information; the first direction is a driving direction of the vehicle.

[0089] In the embodiment of the present invention, reference Figure 2 The vehicle's suspension control system 200 includes at least a binocular camera 2001 and a radar 2002, a body sensor 2003, an acceleration sensor 2004, a suspension height sensor 2005, a communication module 2006, a cloud server 2007, a vehicle networking module 2008, a suspension controller 2009, an air spring 2010 and a shock absorber 2011.

[0090] In some embodiments, the vehicle's suspension control system 200 obtains the current road surface image of the target road surface in the vehicle's driving direction through the binocular camera 2001 in the image acquisition device, obtains the road surface point cloud data of the target road surface through the radar 2002 in the image acquisition device, and at the same time, obtains the vehicle's status information through the body sensor 2003.

[0091] In some embodiments, the vehicle status information may be the vehicle's driving speed, or vibration acceleration and other status information; the specific status information may be determined based on actual conditions, and the embodiments of the present invention do not make specific limitations here.

[0092] Step S102: input the current road surface image, road surface point cloud information and status information into a preset road surface recognition model to obtain a target road surface roughness level of the target road surface.

[0093] In an embodiment of the present invention, after acquiring the current road surface image, road surface point cloud data and vehicle status information, the vehicle's suspension control system 200 inputs the current road surface image, road surface point cloud information and status information into a preset road surface recognition model through the suspension controller 2009 to obtain the target road surface roughness level of the target road surface.

[0094] In some embodiments, after the binocular camera 2001 obtains the current road surface image of the target road surface in the vehicle's driving direction, the current road surface image is uploaded to the cloud server 2007 through the Internet of Vehicles module 2008. At the same time, after the radar 2002 obtains the road surface point cloud data of the target road surface, the current road surface image is also uploaded to the cloud server 2007 through the Internet of Vehicles module 2008. In addition, after the body sensor 2003 obtains the vehicle status information, the current road surface image is also uploaded to the cloud server 2007 through the Internet of Vehicles module 2008. Based on this, the suspension controller 2009 needs to download the current road surface image, road surface point cloud data and status information from the cloud server 2007 to the suspension controller 2009, and then the current road surface image, road surface point cloud data and status information are respectively input into the preset road surface recognition model pre-trained in the suspension controller 2009 to obtain the target road surface roughness level of the target road surface.

[0095] In some embodiments, the target road surface roughness level refers to the degree of change of the target road surface from the ideal road surface elevation; the specific target road surface roughness level can be determined based on actual conditions, and the embodiments of the present invention do not make specific limitations here.

[0096] Step S103: predicting the feedforward damping force required by the suspension system of the vehicle when the vehicle travels on the target road surface according to the target road surface roughness grade.

[0097] In the embodiment of the present invention, after obtaining the target road surface roughness level of the target road surface, the suspension controller 2009 in the suspension control system 200 of the vehicle predicts the feedforward damping force required by the suspension system of the vehicle when the vehicle travels on the target road surface according to the target road surface roughness level.

[0098] In some embodiments, the suspension controller 2009 can predict the feedforward damping force required by the vehicle's suspension system when the vehicle is traveling on the target road surface based on the predicted target road surface roughness level for the target road surface, thereby being able to control the vehicle's suspension system in advance to pass the target road surface, thereby improving the vehicle's driving experience.

[0099] It can be understood that the present invention is mainly aimed at the suspension system control strategy when the vehicle is traveling on special road surfaces. Special road surfaces mainly include non-continuous road surfaces such as deceleration strips, manhole covers, damaged road surfaces, joint road surfaces, raised road surfaces, subsided road surfaces and long-wave road surfaces. Special road surfaces may bring uncomfortable experience to the driver or passengers of the vehicle. Based on the technical solution of the present invention, the vehicle can adjust its own suspension system before driving on the special road surface, and restore the suspension system after driving, thereby improving the driving experience on the special road surface.

[0100] Step S104: When the vehicle travels to the target road surface based on the feedforward damping force, the feedback damping force is calculated in real time based on the vehicle body parameters, and the feedforward damping force is compensated in real time based on the feedback damping force, so that the vehicle travels smoothly on the target road surface.

[0101] In some embodiments, after the suspension controller 2009 in the suspension control system 200 of the vehicle travels on the target road surface based on the feedforward damping force, due to the existence of uncertain interference forces on the target road surface, the suspension controller 2009 can also calculate the feedback damping force in real time based on the body parameters of the vehicle, and compensate the feedforward damping force in real time based on the feedback damping force to make the vehicle travel smoothly on the target road surface.

[0102] In an embodiment of the present invention, the target damping force of the shock absorber 2011 is determined based on one or more of the following: feedback control damping force, which is the damping force required for the vehicle to maintain stability when traveling on the target road surface; and feedforward damping force, which is the predicted damping force required for the vehicle to travel on the target road surface.

[0103] It is understandable that the feedback control damping force changes in real time and needs to continuously maintain the stability of the vehicle when driving on the target road. Therefore, the feedback control damping force will be continuously adjusted according to the driving process of the vehicle on the target road to maintain the stability of the vehicle.

[0104] In an embodiment of the present invention, the feedback damping force is calculated in real time based on the body parameters of the vehicle, and the method includes: constructing an alternative Lyapunov function; determining a first calculation formula for the feedback damping force while maintaining the first-order derivative of the alternative Lyapunov function to be less than or equal to 0; and calculating the feedback damping force according to the first calculation formula.

[0105] In an embodiment of the present invention, constructing an alternative Lyapunov function includes: decoupling a suspension system into a plurality of sub-suspension systems at different locations, and establishing a two-degree-of-freedom vibration model based on the sub-suspension systems and vehicle body parameters; constructing an alternative Lyapunov function based on sliding mode variables determined by the two-degree-of-freedom vibration model, radial basis neural network weight coefficient estimation errors, radial basis function estimation errors, radial basis center estimation errors, and disturbance force estimation error uncertainties.

[0106] Specifically, the suspension system is decoupled into four relatively independent suspension subsystems, and a two-degree-of-freedom vibration model of the suspension subsystem is established. The model consists of inertial force, spring force, shock absorber basic damping force, shock absorber adjustable damping force, and unknown disturbance force of random roads on the suspension system. The model parameters include the suspension system, the mass under the spring, wheelbase, track width, spring stiffness coefficient, shock absorber basic damping coefficient, and the position and velocity of the relative motion with the mass under the spring. The displacement and velocity of the relative motion with the mass under the spring are directly measured by the suspension height sensor and the wheel acceleration sensor, respectively, and then calculated by differentiation and integration.

[0107] In an embodiment of the present invention, the relative displacement of the lower mass of the suspension system and the relative speed of the lower mass are determined according to a two-degree-of-freedom vibration model; the relative displacement of the lower mass is multiplied by a sliding mode gain coefficient and then added to the relative speed of the lower mass to obtain a sliding mode variable.

[0108] In an embodiment of the present invention, the radial basis function is obtained by subtracting the norm of the radial basis center from the sliding mode variable and then dividing the result by the radial basis width; the product of the radial basis function and the weighting coefficient and the sum of the optimal approximation error are determined as the nominal disturbance force; the weighting coefficient, the radial basis center and the radial basis width in the nominal disturbance force are replaced with corresponding estimates, and the optimal disturbance approximation error term is discarded to obtain the estimated disturbance force.

[0109] Specifically, the relative displacement with respect to the lower mass is multiplied by the sliding mode gain coefficient, and then the relative velocity with respect to the lower mass is added to obtain the sliding mode variable. The sliding mode variable is subtracted from the norm of the radial basis center and then divided by the radial basis width to obtain the radial basis function. The radial basis function is multiplied by the weighting coefficient and then added to the optimal approximation error to obtain the nominal disturbance force. The weight coefficient, radial basis center, and radial basis width in the nominal disturbance force are replaced with the corresponding estimates, and the optimal disturbance approximation error term is discarded to obtain the estimated disturbance force.

[0110] In an embodiment of the present invention, a nominal disturbance force and an estimated disturbance force are determined based on a sliding mode variable; the estimated disturbance force is subtracted from the nominal disturbance force to obtain a disturbance force estimation error; the disturbance force estimation error is composed of the product of a weight coefficient and a radial basis function estimation error, the product of a weight coefficient error and a radial basis function estimate, and the sum of an optimal approximation error; the radial basis function estimation error is split into the product of a partial derivative of the radial basis function with respect to a radial basis center and an estimated error of the radial basis center, the product of a partial derivative of the radial basis function with respect to a radial basis width and an estimated error of the radial basis width, and the sum of high-order terms after Taylor expansion of the radial basis function; the uncertainty of the disturbance force estimation error is obtained based on the sliding mode variable, the uncertainty gain coefficient, and the product of a first matrix, and the product of the sliding mode variable and an adjustable gain coefficient; wherein the first matrix is ​​composed of a first constant, a radial basis center estimate, a radial basis width estimate, and a weight coefficient estimate.

[0111] Specifically, the estimated disturbance force is subtracted from the nominal disturbance force to obtain the disturbance force estimation error, and the disturbance force estimation error is transformed into three linear additions, the first term is the weight coefficient multiplied by the radial basis function estimation error, the second term is the weight coefficient error multiplied by the radial basis function estimate, and the third term is the optimal approximation error.

[0112] Furthermore, the radial basis function estimation error is linearized into the cumulative sum of three terms. The first term is the partial derivative of the radial basis function with respect to the radial basis center multiplied by the estimated error of the radial basis center. The second term is the partial derivative of the radial basis function with respect to the radial basis width multiplied by the estimated error of the radial basis width. The third term is all high-order terms after the Tyler series expansion of the radial basis function.

[0113] Furthermore, the uncertainty of the disturbance force estimation error is obtained by superposing two items. The first item is the sliding mode variable multiplied by the uncertainty gain coefficient and then multiplied by the column matrix composed of constants, radial basis center estimates, radial basis width estimates and weight coefficient estimates. The second item is the sliding mode variable multiplied by the adjustable gain coefficient.

[0114] In an embodiment of the present invention, the first variable in the first calculation formula includes the radial basis neural network weight coefficient, the radial basis center, the radial basis width, and the uncertainty of the disturbance force estimation error; calculating the feedback damping force according to the first calculation formula includes: calculating the radial basis neural network weight coefficient, the radial basis center, the radial basis width and the uncertainty of the disturbance force estimation error in real time according to the real-time vehicle body parameters; substituting the radial basis neural network weight coefficient, the radial basis center, the radial basis width and the uncertainty of the disturbance force estimation error into the first calculation formula to obtain the feedback damping force.

[0115] Specifically, the sliding mode variables, radial basis neural network weight coefficient estimation error, radial basis function estimation error, radial basis center estimation error and disturbance force estimation error uncertainty are squared respectively, and then divided by the adjustable weight coefficient and multiplied by one half to obtain the alternative Lyapunov function. The first-order derivative of the alternative Lyapunov function with respect to time is taken, and then the first-order derivatives of the radial basis neural network weight coefficient estimation error, radial basis function estimation error, radial basis center estimation error and concentrated disturbance estimation error uncertainty are respectively substituted into the first-order derivative of the alternative Lyapunov function, so that the first-order derivative of the alternative Lyapunov function is kept constant and less than zero. In the process of proving the stability of the suspension control system, the adjustable damping force calculation formula of the suspension system is finally constructed by deduction, as well as the real-time update law of the radial basis neural network weight coefficient change rate, radial basis center change rate, radial basis width change rate and disturbance force estimation error uncertainty change rate.

[0116] Furthermore, the real-time updated radial basis neural network weight coefficient change rate, radial basis center change rate, radial basis width change rate and concentrated disturbance estimation error uncertainty change rate are integrated and calculated to obtain the real-time updated radial basis neural network weight coefficient, radial basis center, radial basis width and concentrated disturbance estimation error uncertainty.

[0117] Furthermore, the updated radial basis neural network weight coefficient, radial basis center, radial basis width and disturbance force estimation error uncertainty are finally substituted into the adjustable damping force calculation formula to obtain the feedback damping force calculated based on the suspension system state.

[0118] The following is an exemplary calculation process of the feedback damping force given by the present invention:

[0119] 1. Reference Figure 3 , decouple the vehicle's suspension system into the left front, right front, left rear and right rear quarter suspension systems, simplify the quarter suspension system into a two-degree-of-freedom vibration model, and according to Newton's second law of mechanics, the dynamic equation of the mass on the spring is:

[0120]

[0121] In the above formula, m s is the mass on the spring, z s is the vertical displacement of the mass above the spring, is the vertical velocity of the mass on the spring, is the vertical acceleration of the mass on the spring, z u is the vertical displacement of the mass under the spring, is the vertical velocity of the mass under the spring, c s is the basic damping coefficient of the shock absorber in the sub-suspension system, ks is the coil spring stiffness of the shock absorber in the sub-suspension system, and f is the feedback damping force.

[0122] According to Newton's second law of mechanics, the second dynamic equation of the mass under the spring is:

[0123]

[0124] In the above formula, m u is the mass under the spring, are the vertical acceleration of the mass under the spring, k u is the vertical stiffness of the sub-suspension system corresponding to the tire, z r is the random road surface excitation of the target road surface.

[0125] 2. Establish a matrixed semi-active suspension control model, and organize formula (1) and formula (2) into a matrix vector form, which can be expressed as:

[0126]

[0127] In the above formula, d is the unknown concentrated disturbance vector, which includes parameter uncertainty, unmodeled dynamics, random road excitation and noise.

[0128] 3. Calculate the sliding mode variable s and its derivative

[0129]

[0130] In the above formula, λ is an adjustable gain coefficient matrix, which is defined as λ=diag(λ1,λ2).

[0131] 4. Use radial basis function neural network to calculate the nominal disturbance force. In order to overcome the influence of unknown disturbance force on the suspension control system, radial basis function neural network is used to estimate the external disturbance force. The nominal disturbance force d is defined as:

[0132] d=W T h(s,c,b)+ε a (6);

[0133] In the above formula, W is the optimal weight matrix, ε a is the optimal approximation error, which is bounded and satisfies ||ε a ||≤b ε , b ε is a positive definite constant. is the radial basis function vector, is the center vector of the radial basis function, is the central vector component of the radial basis function, m is the number of hidden layers of the radial basis neural network, and N is the number of radial basis centers. is the width vector of the radial basis function.

[0134] 5. Define the estimated disturbance force of the nominal disturbance force d for:

[0135]

[0136] In the above formula, is the estimated value of the weight matrix, is the center estimation vector of the radial basis function, is the width estimation vector of the radial basis function, s is the input of the neural network, is the output of the neural network.

[0137] 6. Calculate the disturbance force estimation error According to formula (6) and formula (7), we can get:

[0138]

[0139] In the above formula, is the estimated bias of the weight matrix W, Estimate the bias vector for the radial basis function.

[0140] 7. Transform the radial basis function vector Perform a Taylor series expansion:

[0141]

[0142] In the above formula, is the high-order term after Taylor series expansion. In addition, the A and B matrices can be expressed as:

[0143]

[0144]

[0145] Substituting formula (9) into formula (8), we can obtain the disturbance force estimation error of radial basis neural network: Third-party programs:

[0146]

[0147] The uncertainty of the disturbance force estimation error δ can be expressed as:

[0148]

[0149] Calculating the bounds associated with the perturbation vector, we obtain:

[0150]

[0151] According to the matrix inequality operation rules, from formula (14), the norm of δ can be expressed as:

[0152]

[0153] Add both sides of the inequality (15) Can be further converted to:

[0154]

[0155] The perturbation boundary gain matrix k in equation (16) is δ and the neural network estimation vector ν is defined as

[0156]

[0157] Furthermore, the estimated value of the uncertainty δ of the disturbance force estimation error is Defined as:

[0158]

[0159] 8. Prove the stability of the feedback damping force control algorithm and derive the calculated value and adaptive law of the adjustable damping force. Define the alternative Lyapunov function as:

[0160]

[0161] In the above formula, Γ w , Γ c , Γ b and Γ δ is an adjustable positive definite matrix, and tr(·) is the trace of the matrix.

[0162] Take the first-order derivative of the candidate Lyapunov function:

[0163]

[0164] 9. In the process of proving the stability of the control system, the following formula is constructed by deduction, where the feedback control damping force f can be expressed as:

[0165]

[0166] At the same time, the real-time update law of the radial basis neural network weight coefficient change rate is defined as:

[0167]

[0168] The real-time update law of the radial basis center change rate is defined as:

[0169]

[0170] The real-time update law of the radial basis width change rate is defined as:

[0171]

[0172] The real-time update law of the change rate of the uncertainty of the disturbance force estimation error is:

[0173]

[0174] Substituting formula (22) to formula (26) into formula (21), we obtain:

[0175]

[0176] According to Lyapunov's stability theorem, the suspension damping control system is determined to be asymptotically stable, and the disturbance estimation error will converge to near 0 within a finite time. The real-time updated radial basis neural network weight coefficient change rate, radial basis center change rate, radial basis width change rate and concentrated disturbance estimation error uncertainty change rate are integrated to obtain the real-time updated radial basis neural network weight coefficient, radial basis center, radial basis width and concentrated disturbance estimation error uncertainty. Finally, it is substituted into the feedback control damping force f calculation formula to obtain the feedback damping force of the suspension subsystem.

[0177] In some embodiments, the damping force of the vehicle's suspension system may also take into account one or more of the following: a handling stability control damping force and a safety ride control damping force.

[0178] Exemplarily, a hybrid skyhook control-ground hook control algorithm (SH-GH) is used to calculate the handling stability control damping force. The SH-GH algorithm is calculated based on the first velocity direction of the shock absorber 2011, the second velocity direction of the upper mass of the air spring 2010, and the acceleration direction of the upper mass of the air spring 2010.

[0179] As another example, when calculating the safe driving control damping force, it is necessary to first determine the current driving state of the vehicle based on the vehicle's status information, that is, whether the vehicle is currently in a stable driving state or an unstable driving state. If it is determined based on the vehicle's status information that the vehicle is currently in a stable driving state, the third damping force defaults to a preset value, such as 0; if it is determined based on the vehicle's status information that the vehicle is currently not in a stable driving state, the current driving speed of the vehicle is determined based on the status information, and the safe driving control damping force is calculated based on the current driving speed and the pre-calibrated damping force.

[0180] In the embodiment of the present invention, the preset road surface recognition model includes at least a first model, a second model and a third model; the suspension controller 2009 in the suspension control system 200 of the vehicle inputs the current road surface image, road surface point cloud information and state information into the preset road surface recognition model to obtain the target road surface roughness level of the target road surface, and the reference Figure 4 , including the following steps S401 to S404:

[0181] Step S401: input the current road surface image into the first model, extract the first road surface feature in the current road surface image using the first model, and convert the first road surface feature into a first road surface roughness grade.

[0182] In some embodiments, the first model is obtained by pre-training with sample road surface images. During daily driving, the vehicle can obtain sample road surface images during driving through the binocular camera 2001, and upload the sample road surface images to the cloud server 2007 through the Internet of Vehicles module 2008. At the same time, the sample road surface images can be output as first data samples for training the first model after feature annotation (manual annotation or automatic annotation). The first data sample includes a sample road surface image and a sample road surface type. First, the sample road surface image is input into the first model. The first model can extract the sample road surface image features in the sample road surface image. Then, the sample road surface image features are converted into a first sample road surface roughness level and a sample path curvature corresponding to the target road surface. Finally, the first model is trained based on the first sample road surface roughness level and the annotated sample road surface type.

[0183] In some embodiments, the vehicle can continuously collect road images and train the first model, and the vehicle networking module 2008 can periodically send the trained first model to the suspension controller 2009. At this time, after downloading the current road image from the cloud server 2007, the suspension controller 2009 can input the current road image into the trained first model, use the first model to extract the first road feature in the current road image, and convert the first road feature into a first road roughness level and a first path curvature.

[0184] Step S402: input the road surface point cloud information into the second model, use the second model to extract the second road surface features in the road surface point cloud information, and convert the second road surface features into a second road surface roughness grade.

[0185] In some embodiments, the second model is pre-trained through sample road surface point cloud information. During daily driving, the vehicle can use radar 2002 to scan the road surface in the direction of vehicle travel to obtain three-dimensional road surface point cloud coordinates, that is, sample road surface point cloud information. The sample road surface point cloud information is uploaded to the cloud server 2007 through the Internet of Vehicles module 2008. At the same time, the sample road surface image can be feature-labeled (manually or automatically) to establish a second data sample for deep learning, and the second data sample is used to train the second model, that is, the second data sample is used to iteratively train the second model, and finally a second model that meets the recognition accuracy is obtained.

[0186] In some embodiments, the vehicle can continuously collect road point cloud information and train the second model, and the vehicle networking module 2008 can periodically send the trained second model to the suspension controller 2009. At this time, after downloading the current road point cloud information from the cloud server 2007, the suspension controller 2009 can input the road point cloud information into the trained second model, use the neural network algorithm in the second model to extract the second road feature in the road point cloud information, and convert the second road feature into a second road roughness level.

[0187] Step S403: input the state information into the third model to obtain a third road surface roughness grade.

[0188] In some embodiments, the third model is obtained by pre-training with sample status information. During daily driving, the vehicle can obtain the vehicle status information, such as the vehicle's driving speed and vibration acceleration, through the body sensor 2003 to obtain sample status information. The sample status information is uploaded to the cloud server 2007 through the Internet of Vehicles module 2008. At the same time, the sample status information can be feature-labeled (manually or automatically) to establish a third data sample, and the third data sample is used to train the third model, that is, the third model is iteratively trained using the third data sample to finally obtain a third model that meets the recognition accuracy.

[0189] In some embodiments, the vehicle can continuously obtain the vehicle status information and train the third model, and the vehicle networking module 2008 can periodically send the trained third model to the suspension controller 2009. At this time, after downloading the current status information from the cloud server 2007, the suspension controller 2009 can input the status information into the trained third model, output the third road surface roughness level, and also output the first road surface length of the target road surface.

[0190] Step S404: fusing the first road surface roughness level, the second road surface roughness level, the third road surface roughness level, and the historical road surface roughness level of the target road surface to obtain a target road surface roughness level.

[0191] In some embodiments, after the suspension controller 2009 inputs the current road surface image, road surface point cloud information and status information into the first model, the second model and the third model respectively to obtain the first road surface roughness level, the second road surface roughness level and the third road surface roughness level for the target road surface under different evaluation dimensions, it can comprehensively determine the target road surface roughness level of the target road surface based on the historical road surface roughness levels in the historical road surface marking information for the target road surface issued by the Internet of Vehicles module 2008.

[0192] In an embodiment of the present invention, the suspension controller 2009 obtains historical road surface marking information corresponding to the target road surface; the historical road surface marking information is obtained when the vehicle historically travels to the target road surface and marks the target road surface; wherein the historical road surface marking information includes the historical road surface roughness level, historical road surface coordinates, historical road surface length and historical path curvature corresponding to the target road surface.

[0193] In some embodiments, while the vehicle is driving, the Internet of Vehicles module 2008 can send historical road surface marking information of the target road to the suspension controller 2009 based on the real-time positioning of the vehicle. The suspension controller 2009 can perform multi-modal information fusion of the first road surface roughness level, the second road surface roughness level, the third road surface roughness level and the historical road surface roughness level to obtain the most accurate target road surface roughness level of the target road.

[0194] In the embodiment of the present invention, after the suspension controller 2009 performs real-time compensation for the feedforward damping force based on the feedback damping force, it also includes: adjusting the height of the suspension system to the target height, and / or adjusting the stiffness of the air spring in the suspension system to the target stiffness.

[0195] In some embodiments, the suspension controller 2009 can pre-calculate the control strategy of the suspension system when passing through the target road surface, such as at what height the suspension system should pass through the target road surface, the target stiffness of the air spring 2010 in the suspension system, or the feedforward damping force of the shock absorber 2011 in the suspension system, etc., and then convert the target height of the suspension system, the target stiffness of the air spring 2010, or the feedforward damping force of the shock absorber 2011 into the target control current of the solenoid valve, so as to adjust the suspension system through the target control current at an appropriate time, such as adjusting the suspension system when the vehicle is about to enter the target road surface, etc.

[0196] In the embodiment of the present invention, the suspension controller 2009 determines the target height of the suspension system and the target stiffness of the air spring 2010, referring to Figure 5 , including the following steps S501 to S502:

[0197] Step S501: Determine the air suspension mode currently set for the vehicle.

[0198] In some embodiments, the suspension controller 2009 may determine the air suspension mode currently selected by the vehicle, and then may determine the height of the current suspension system of the vehicle according to the air suspension mode.

[0199] Step S502: determining a target height and a target stiffness according to the air suspension mode, historical path curvature, state information, and target road roughness level.

[0200] In some embodiments, after determining the height of the current suspension system of the vehicle, the suspension controller 2009 can input the signals corresponding to the currently set air suspension mode, historical path curvature, status information and target road roughness level into the signal processing module for signal analysis and validity judgment. Based on this, the signal processing module can input the processed signals into the air spring mode management module. The air spring mode management module can calculate the current mode of the air spring 2010 and the target stiffness of the air spring 2010. The suspension target height calculation module can calculate the target height of the suspension system. The air spring safety control module can calculate the flag position and safety height of the safety control of the air spring 2010. Finally, the air spring control module converts the target height of the suspension system and the target stiffness of the air spring 2010 into the target current of the corresponding solenoid valve.

[0201] In the embodiment of the present invention, after determining the control strategy, the suspension controller 2009 can also determine at what point in time to adjust the suspension system. Figure 6 , including the following steps S601 to S604:

[0202] Step S601: Determine the current first position coordinates of the vehicle.

[0203] In some embodiments, the suspension controller 2009 may continuously collect the current position coordinates of the vehicle, namely, the first position coordinates, during driving, so as to determine the activation time of the control strategy according to the first position coordinates.

[0204] Step S602: Determine a first distance between a first position of the vehicle and a starting position of a target road surface according to the first position coordinates and the historical road surface coordinates; the first position is a center position of a front axle on the vehicle.

[0205] In some embodiments, since the vehicle networking module 2008 is the historical road surface marking information corresponding to the target road surface sent by the suspension controller 2009, the first distance, that is, the lateral distance, between the center position of the front axle of the vehicle and the starting position of the target road surface can be determined based on the historical road surface coordinates included in the historical road surface marking information and the first position coordinates.

[0206] Step S603: Determine a first time duration required for the vehicle to travel to the starting position according to the first distance and the first travel speed.

[0207] In some embodiments, after determining the first distance between the center position of the front axle on the vehicle and the starting position of the target road surface, the suspension controller 2009 calculates the driving time required from the center position of the front axle on the vehicle to the starting position of the target road surface based on the first driving speed of the vehicle, that is, the first duration.

[0208] Step S604: When the first time duration is less than a first threshold value and / or the first distance is less than a second threshold value, adjust the suspension system.

[0209] In some embodiments, if the first duration is short or the first distance is short, it indicates that the vehicle is about to drive to the target road surface and the suspension system needs to be adjusted.

[0210] In an embodiment of the present invention, after adjusting the suspension system, the suspension controller 2009 also needs to determine at what point in time to restore the suspension system. The specific steps include: determining the second time required for the vehicle to travel the target road surface based on the first driving speed and the historical road length; and restoring the suspension system when the control strategy is turned on and the second time has passed.

[0211] In some embodiments, since the historical road marking information includes the historical road length, the suspension controller 2009 can calculate how long it takes to leave the target road according to the first driving speed and the historical road length. Based on this, the suspension system can be restored after adjusting the suspension system.

[0212] In an embodiment of the present invention, when the vehicle activates the control strategy and is driving on the target road surface, the target height of the suspension system can continue to be adjusted under special circumstances. The specific steps include: when it is detected that the vehicle is accelerating or braking while driving on the target road surface, the target height is determined according to the vehicle's current second driving speed and the vehicle's first information, and the target height is adjusted; wherein the first information is the pedal position of the current accelerator pedal in the vehicle, and / or the current pressure of the brake cylinder.

[0213] In some embodiments, when the suspension controller 2009 recognizes that the vehicle is accelerating or braking during driving, it calculates and determines the control amount for adjusting the height of the vehicle suspension system according to the second driving speed of the vehicle, the pedal position of the accelerator pedal, and / or the current pressure of the brake cylinder, thereby suppressing the pitch posture of the vehicle.

[0214] In the embodiment of the present invention, the suspension controller 2009 also needs to update the historical road marking information for the target road in the cloud server 2007, referring to Figure 7 , including the following steps S701 to S704:

[0215] Step S701: when the vertical acceleration of the front axle wheels of the vehicle is greater than a third threshold value, determine that the vehicle has reached the starting point of the target road surface, and determine the current first position coordinates and the current first time point of the vehicle.

[0216] In some embodiments, when a vehicle is about to enter a target road surface, since there is an elevation difference between the target road surface and the road surface on which the vehicle is traveling, when it is identified that the vertical acceleration of the front axle wheels of the vehicle is greater than a third threshold value, it can be determined that the vehicle has reached the starting point of the target road surface, and the starting coordinate point of the target road surface, that is, the first position coordinate, is calculated based on the size parameters of the vehicle, and the current first time point is recorded, and the first time point is used as the starting time point for the vehicle to enter the target road surface.

[0217] Step S702: When the vertical acceleration of the front axle wheels of the vehicle is less than a fourth threshold value, it is determined that the vehicle has left the target road surface, and the current second position coordinates and the current second time point of the vehicle are determined.

[0218] In some embodiments, when a vehicle is about to leave a target road, since there is an elevation difference between the target road and the ordinary road on which the vehicle is about to travel, when it is recognized that the vertical acceleration of the front axle wheels of the vehicle is less than a fourth threshold value, it can be determined that the vehicle has left the target road, and the end point coordinate point of the target road, that is, the second position coordinate, is calculated based on the size parameters of the vehicle, and the current second time point is recorded, and the second time point is used as the final time point when the vehicle leaves the target road.

[0219] Step S703: determine a first road surface length of the target road surface according to the first position coordinates and the second position coordinates, and / or the first time point, the second time point and the current third driving speed of the vehicle.

[0220] In some embodiments, after determining the starting coordinate point of the target road surface, i.e., the first position coordinate, and the ending coordinate point of the target road surface, i.e., the second position coordinate, the first road surface length of the target road surface can be calculated based on the first position coordinate and the second position coordinate. Alternatively, after determining the starting time point when the vehicle enters the target road surface, i.e., the first time point, and the final time point when the vehicle leaves the target road surface, and the second time point, the first road surface length of the target road surface is calculated based on the first time point, the second time point and the vehicle's driving speed.

[0221] Step S704: determine the target path curvature according to the first path curvature and the historical path curvature, and update the historical road marking information according to the target path curvature, the target road surface roughness level, the first road surface length and the first position coordinates.

[0222] In some embodiments, after determining the first path curvature of the target road surface according to the first model, the suspension controller 2009 may further calculate the actual path curvature of the target road section according to the first path curvature and the original path curvature.

[0223] In some embodiments, the historical road surface coordinates corresponding to the target road surface in the historical road surface marking information can be updated according to the first coordinate position, the historical road surface roughness level corresponding to the target road surface in the historical road surface marking information can be updated according to the target road surface roughness level, the historical road surface length corresponding to the target road surface in the historical road surface marking information can be updated according to the first road surface length, and the historical path curvature corresponding to the target road surface in the historical road surface marking information can be updated according to the actual path curvature to obtain updated road surface marking information. Based on this, before the vehicle enters the target road surface next time, the corresponding suspension system control strategy can be calculated according to the updated road surface marking information.

[0224] The embodiment of the present invention provides a suspension system control method for a vehicle, the method comprising: obtaining a current road surface image and road surface point cloud information of a target road surface in a first direction, and state information of a vehicle; the first direction is the driving direction of the vehicle; inputting the current road surface image, road surface point cloud information, and state information into a preset road surface recognition model to obtain a target road surface roughness level of the target road surface; determining a control strategy of the suspension system when the vehicle is driving on the target road surface according to the target road surface roughness level; using the above implementation scheme, firstly, the current road surface image, road surface point cloud information, and state information of the vehicle are fused, and after considering the historical road surface roughness level, the control strategy of the suspension system that best reflects the target road surface is obtained. The target road surface roughness level of the target road surface condition is obtained. Therefore, the most accurate control strategy can be obtained based on the target road surface roughness level, and the damping force of the shock absorber determined in the control strategy is obtained based on the feedback control damping force and the feedforward damping force, which can reduce the impact and vibration acceleration of the vehicle entering the target road surface, and further improve the driving comfort performance of the vehicle under uneven road conditions based on the control strategy. At the same time, the feedback control damping force can immediately design a self-learning control strategy for the nonlinear characteristics of the radial basis function neural network to adaptively compensate for external disturbances. Therefore, the feedback control damping force can quickly eliminate the vibration acceleration of the vehicle body and wheels after the vehicle enters the target road surface.

[0225] Based on the above embodiments, the present invention provides an exemplary vehicle suspension system control method, which is applied to the vehicle suspension control system, referring to Figure 2 , the specific steps are as follows:

[0226] Step S1, the vehicle networking module 2008 receives the road surface image information (the sample road surface image in the above embodiment), the three-dimensional road surface point cloud (the sample road surface point cloud information in the above embodiment) and the vehicle status parameters (the sample status information in the above embodiment) collected by the vehicle, and uploads them to the cloud server 2007, and uses the road surface image information, the three-dimensional road surface point cloud and the vehicle status parameters to train the special road surface recognition model (the preset road surface recognition model in the above embodiment).

[0227] Step S1.1, obtain road surface image information in the direction of vehicle travel through the binocular camera 2001, the vehicle networking module 2008 uploads the road surface image information to the cloud server 2007, and then stores the road surface image information, and forms a road surface image sample data set after feature annotation; use the road surface image sample data set to train the first road surface recognition model (the first model in the above embodiment), and output the first road surface recognition model that meets the recognition accuracy requirement.

[0228] Step S1.2, obtain the three-dimensional road point cloud in the direction of vehicle travel through the radar 2002, the vehicle networking module 2008 uploads the three-dimensional road point cloud to the cloud server 2007 and stores it, and establishes a road point cloud training sample through feature annotation; use the road point cloud training sample to iteratively train the second road recognition model (the second model in the above embodiment) to obtain a second road recognition model that meets the recognition accuracy.

[0229] Step S1.3, the vehicle state parameters of the vehicle are obtained through the body sensor 2003, and the vehicle networking module 2008 uploads the vehicle state parameters to the cloud server 2007 and stores them to establish a vehicle state data set; the vehicle state data set is used to iteratively train the third road surface recognition model based on the vehicle state (the third model in the above embodiment) to obtain a third road surface recognition model that meets the recognition accuracy requirements.

[0230] Step S2, the vehicle networking module 2008 downloads the pre-trained special road surface recognition model and the special road surface information marked on the map (the historical road surface marking information in the above embodiment) to the suspension controller 2009. The pre-trained special road surface recognition model includes a first road surface recognition model, a second road surface recognition model, and a third road surface recognition model, and the special road surface information includes a special road surface roughness level (the historical road surface roughness level in the above embodiment), a special road surface length (the historical road surface length in the above embodiment), and a path curvature (the historical path curvature in the above embodiment).

[0231] Step S3, the vehicle networking module 2008 receives the current road surface image information (the current road surface image in the above embodiment), the three-dimensional road surface point cloud (the road surface point cloud information in the above embodiment) and the vehicle state parameters (the state information in the above embodiment) collected by the vehicle and uploads them to the cloud server 2007, and the suspension controller 2009 downloads them from the cloud server 2007, and then inputs the downloaded current road surface image information, three-dimensional road surface point cloud and vehicle state parameters into the first road surface recognition model, the second road surface recognition model and the third road surface recognition model respectively to obtain the first special road surface roughness level and path curvature, the second special road surface roughness level and the third special road surface roughness level.

[0232] Step S3.1, reference Figure 8 , input the current road surface image information 801 into the first road surface recognition model 802, use the first road surface recognition model 802 to extract the first road surface feature in the current road surface image information 801, and convert the first road surface feature into a first special road surface roughness grade and path curvature.

[0233] Step S3.2, reference Figure 8, the three-dimensional road surface point cloud 803 is input into the second road surface recognition model 804, the second road surface recognition model 804 is used to extract the second road surface features in the three-dimensional road surface point cloud 803, and the second road surface features are converted into a second special road surface roughness grade.

[0234] Step S3.3, reference Figure 8 , the vehicle state parameter 805 is input into the third road surface recognition model 806, the third road surface recognition model 806 is used to extract the third road surface feature in the vehicle state parameter 805, and the third road surface feature is converted into a third special road surface roughness grade.

[0235] Step S4: Reference Figure 8 , using the special road surface information 807 marked on the map, the first special road surface roughness level, the second special road surface roughness level and the third special road surface roughness level, multimodal road surface information fusion 808 is performed to obtain the optimal special road surface roughness level 809 (the target road surface roughness level in the above embodiment).

[0236] Step S4.1, the vehicle networking module 2008 sends the special road surface information marked on the map to the suspension controller 2009 according to the real-time positioning of the vehicle. The special road surface information includes the original roughness level of the special road surface, the original length of the special road surface and the original path curvature. After obtaining the original roughness level of the special road surface, the suspension controller 2009 can use multimodal road surface information fusion to fuse the first special road surface roughness level, the second special road surface roughness level, the third special road surface roughness level and the special road surface inequality level to calculate the optimal special road surface roughness level.

[0237] Step S4.2, when the front axle wheel is vertically stimulated by the special road surface, the acceleration sensor 2004 is used to identify the characteristics of the front axle wheel vertical acceleration signal and determine the starting point of the special road surface, record the current vehicle position information and timestamp, and calculate the special road surface position coordinates in combination with the vehicle's size parameters. Similarly, when the acceleration sensor 2004 identifies the characteristics of the front axle wheel acceleration signal and determines that the vehicle has exited the special road surface, the current vehicle position information and timestamp are recorded. Based on the vehicle position information, timestamp and vehicle speed when the vehicle enters and exits the special road surface as described above, the length of the special road surface is comprehensively calculated.

[0238] Step S5, calculating the target damping force of ride comfort control, handling stability control, driving safety control and special road feedforward control.

[0239] Specific, reference Fig. 9, the CAN signal output by the communication module, the sensor signal output by the body sensor 2003 and the suspension height sensor 2005 are input to the signal processing module 901 for analysis and effective judgment, and then the shock absorber mode management module 902 outputs the current mode of the shock absorber 2011, and then the self-learning anti-disturbance damping control module 903, the handling stability control module 904, the driving safety control module 905 and the special road feedforward control module 906 respectively calculate the self-learning anti-disturbance control damping force (the feedback control damping force in the above embodiment), the handling stability target damping force, the safe driving target damping force and the special road feedforward target damping force (the feedforward damping force in the above embodiment) of the shock absorber 2011. The optimal damping force arbitration module 907 arbitrates the damping force calculated as described above to obtain the optimal damping force of the shock absorber 2011, that is, the target damping force, and then calculates the target current of the solenoid valve of the shock absorber 2011 through the solenoid valve target current module 1008.

[0240] Step S5.2: Calculate the control amount of adjusting the stiffness of the air spring 2010 and the damping force of the shock absorber 2011 according to the original path curvature sent from the map, the driver input and the vehicle driving state, so as to suppress the roll posture of the vehicle. When it is recognized that the vehicle is accelerating or braking, calculate the target damping force of the shock absorber for suppressing the pitch posture of the vehicle according to the vehicle driving speed and the accelerator pedal position or the brake cylinder pressure.

[0241] Step S6: Calculate the suspension height and the stiffness control amount of the air spring 2010 according to the air suspension mode selected by the user, the driver input, the vehicle speed, and the special road roughness level.

[0242] Step S6.1, reference Fig.10 , the CAN signal and the sensor signal are input into the signal processing module 901 for signal analysis and validity judgment, the air spring mode management module 1001 calculates the current mode of the air spring 2010, the suspension target height and stiffness, the suspension target height calculation module 1002 calculates the suspension target height according to the air spring mode and the vehicle status signal, the air spring safety control module 1003 outputs the flag position and target height of the air spring safety control according to the vehicle status signal, and finally the air spring control module 1004 calculates the target current of the development solenoid valve.

[0243] Step S6.2: If the lateral distance between the center of the front axle of the vehicle and the special road surface is greater than a critical value or the driving time is greater than a critical value, the suspension adjustment function will be suppressed. Otherwise, the damping force of the shock absorber 2011 will be adjusted according to the special road surface roughness level.

[0244] Step S6.3: Convert the target height of the suspension system, the target stiffness of the air spring, and the target damping force of the shock absorber into the target control current of the corresponding solenoid valve.

[0245] Step S7, calculating the actual path curvature of the target road section according to the first path curvature and the original path curvature, uploading the optimal special road surface roughness level, special road surface length, actual path curvature and vehicle position information to the cloud server 2007, and marking them on the map.

[0246] It can be understood that the suspension control method of the vehicle proposed in the present invention first uses binocular cameras, radars and vehicle status signals to determine the special road surface roughness level, special road surface length and path curvature of the target road surface through multimodal information fusion, and at the same time combines the special road surface information sent by the cloud server to calculate the optimal special road surface information through secondary information fusion, and then uses the nonlinear approximation characteristics of the radial basis neural network and the suspension vibration state feedback to propose a self-learning anti-disturbance semi-active suspension damping control strategy, and the weight matrix, center vector and width vector of the radial basis neural network can realize online self-learning, so as to use the changes in the vehicle driving conditions to provide the adaptive robustness of the semi-active suspension damping control. Under the action of the controller, the suspension height, shock absorber damping and air spring stiffness are adjusted in advance beyond the visual range, and the adjustable damping force of the semi-active suspension is self-learned and anti-disturbance controlled based on the suspension state feedback, thereby improving the driving smoothness of the vehicle.

[0247] Based on the above embodiment, in another embodiment of the present invention, a suspension control system for a vehicle is provided. Figure 2 A schematic diagram of the structure of a vehicle suspension control system provided by the present invention is shown in FIG. Figure 2 As shown, the suspension control system 200 of the vehicle includes:

[0248] A binocular camera 2001 is used to obtain a current road surface image of a target road surface in a first direction;

[0249] Radar 2002, used to obtain road surface point cloud information of the target road surface in the first direction; the first direction is the driving direction of the vehicle;

[0250] The vehicle body sensor 2003 is used to obtain the status information of the vehicle;

[0251] The suspension controller 2009 is used to input the current road surface image, the road surface point cloud information and the state information into a preset road surface recognition model to obtain a target road surface roughness level of the target road surface; predict the feedforward damping force required by the suspension system of the vehicle when the vehicle travels on the target road surface according to the target road surface roughness level; when the vehicle travels on the target road surface based on the feedforward damping force, calculate the feedback damping force in real time based on the body parameters of the vehicle, and compensate the feedforward damping force in real time based on the feedback damping force, so that the vehicle can travel smoothly on the target road surface.

[0252] In some embodiments, the vehicle suspension control system 200 further includes: a model building module and a determination module;

[0253] The model building module is used to construct an alternative Lyapunov function;

[0254] The determining module is used to determine the first calculation formula of the feedback damping force while maintaining the first-order derivative of the candidate Lyapunov function to be less than or equal to 0;

[0255] The data processing module is further used to calculate the feedback damping force according to the first calculation formula.

[0256] In some embodiments, the model building module is also used to decouple the suspension system into multiple sub-suspension systems in different parts, and establish a two-degree-of-freedom vibration model based on the sub-suspension systems and the vehicle body parameters; the alternative Lyapunov function is constructed based on the sliding mode variables, radial basis neural network weight coefficient estimation errors, radial basis function estimation errors, radial basis center estimation errors and disturbance force estimation error uncertainties determined by the two-degree-of-freedom vibration model.

[0257] In some embodiments, the vehicle suspension control system 200 further includes: a computing module;

[0258] The determination module is further used to determine the relative displacement of the lower mass of the suspension system and the relative speed of the lower mass according to the two-degree-of-freedom vibration model;

[0259] The calculation module is used to multiply the relative displacement of the lower mass by the sliding mode gain coefficient, and add the relative speed of the lower mass to obtain the sliding mode variable.

[0260] In some embodiments, the determination module is further used to determine a nominal disturbance force and an estimated disturbance force based on the sliding mode variable;

[0261] The calculation module is further used to subtract the estimated disturbance force from the nominal disturbance force to obtain a disturbance force estimation error; the disturbance force estimation error is composed of the product of the weight coefficient and the radial basis function estimation error, the product of the weight coefficient error and the radial basis function estimate, and the optimal approximation error.

[0262] The calculation module is further used to split the radial basis function estimation error into the product of the partial derivative of the radial basis function with respect to the radial basis center and the estimation error of the radial basis center, the product of the partial derivative of the radial basis function with respect to the radial basis width and the estimation error of the radial basis width, and the sum of the high-order terms after Taylor expansion of the radial basis function;

[0263] The calculation module is also used to obtain the uncertainty of the disturbance force estimation error based on the product of the sliding mode variable, the uncertainty gain coefficient, and the first matrix, and the product of the sliding mode variable and the adjustable gain coefficient; wherein the first matrix is ​​composed of a first constant, a radial basis center estimate, a radial basis width estimate, and a weight coefficient estimate.

[0264] In some embodiments, the calculation module is further used to obtain a radial basis function by subtracting the norm of the radial basis center from the sliding mode variable and dividing the result by the radial basis width;

[0265] The determination module is further used to determine the product of the radial basis function and the weighting coefficient and the sum of the optimal approximation error as the nominal disturbance force;

[0266] The calculation module is also used to replace the weight coefficient, radial basis center and radial basis width in the nominal disturbance force with corresponding estimates, and discard the optimal disturbance approximation error term to obtain the estimated disturbance force.

[0267] In some embodiments, the calculation module is also used to calculate the radial basis neural network weight coefficient, the radial basis center, the radial basis width and the disturbance force estimation error uncertainty in real time according to the real-time vehicle body parameters; the radial basis neural network weight coefficient, the radial basis center, the radial basis width and the disturbance force estimation error uncertainty are substituted into the first calculation formula to obtain the feedback damping force.

[0268] In some embodiments, the vehicle suspension control system 200 further includes: an input module;

[0269] The input module is used to input the current road surface image into the first model, extract the first road surface feature in the current road surface image using the first model, and convert the first road surface feature into a first road surface roughness level; input the road surface point cloud information into the second model, extract the second road surface feature in the road surface point cloud information using the second model, and convert the second road surface feature into a second road surface roughness level; input the state information into the third model to obtain a third road surface roughness level; and fuse the first road surface roughness level, the second road surface roughness level, the third road surface roughness level, and the historical road surface roughness level of the target road surface to obtain the target road surface roughness level.

[0270] In some embodiments, the vehicle suspension control system 200 further includes: an acquisition module;

[0271] The acquisition module is used to acquire historical road marking information corresponding to the target road; the historical road marking information is obtained when the vehicle historically travels to the target road and marks the target road; wherein the historical road marking information includes a historical road roughness grade, historical road coordinates, historical road length, and historical path curvature corresponding to the target road.

[0272] In some embodiments, the determination module is also used to determine the current first position coordinates of the vehicle; determine the first distance between the first position of the vehicle and the starting position of the target road surface based on the first position coordinates and the historical road surface coordinates; the first position is the center position of the front axle on the vehicle; determine the first time required for the vehicle to travel to the starting position based on the first distance and the first driving speed; when the first time is less than a first threshold value, and / or the first distance is less than a second threshold value, start the control strategy.

[0273] In some embodiments, the determination module is also used to determine the second time required for the vehicle to travel the target road surface based on the first driving speed and the historical road surface length; when the control strategy is turned on and the second time period has passed, the control strategy is turned off.

[0274] In some embodiments, the vehicle suspension control system 200 further includes: a regulating module;

[0275] The adjustment module is used to adjust the height of the suspension system to a target height and / or adjust the stiffness of the air spring in the suspension system to a target stiffness.

[0276] In some embodiments, the determination module is further used to determine the air suspension mode currently set for the vehicle; and to determine the target height and the target stiffness according to the air suspension mode, the historical path curvature, the state information, and the target road roughness level.

[0277] In some embodiments, the determination module is further used to determine the air suspension mode currently set for the vehicle; and to determine the target height and the target stiffness according to the air suspension mode, the historical path curvature, the state information, and the target road roughness level.

[0278] In some embodiments, the determination module is also used to adjust the target height according to the vehicle's current second driving speed and the vehicle's first information when it is detected that the vehicle is accelerating or braking while driving on the target road surface; wherein the first information is the pedal position of the current accelerator pedal in the vehicle, and / or the current pressure of the brake cylinder.

[0279] In some embodiments, the determination module is further used to determine that the vehicle has reached the starting point of the target road surface and determine the current first position coordinates and the current first time point of the vehicle when the vertical acceleration of the front axle wheels of the vehicle is greater than a third threshold value; determine that the vehicle has left the target road surface and determine the current second position coordinates and the current second time point of the vehicle when the vertical acceleration of the front axle wheels of the vehicle is less than a fourth threshold value; determine the first road surface length of the target road surface according to the first position coordinates and the second position coordinates, and / or the first time point, the second time point and the current third driving speed of the vehicle; determine the target path curvature according to the first path curvature and the historical path curvature, and update the historical road surface marking information according to the target path curvature, the target road surface roughness level, the first road surface length and the first position coordinates.

[0280] The embodiment of the present invention provides a suspension control system for a vehicle, the system comprising: a binocular camera for acquiring a current road surface image of a target road surface in a first direction; a radar for acquiring road surface point cloud information of the target road surface in the first direction; the first direction is the driving direction of the vehicle; a body sensor for acquiring the state information of the vehicle; a suspension controller for inputting the current road surface image, road surface point cloud information and state information into a preset road surface recognition model to obtain a target road surface roughness level of the target road surface; predicting the feedforward damping force required by the suspension system of the vehicle when the vehicle is driving on the target road surface according to the target road surface roughness level; when the vehicle drives on the target road surface based on the feedforward damping force, calculating the feedback damping force in real time based on the body parameters of the vehicle, and compensating the feedforward damping force in real time based on the feedback damping force, so that the vehicle can drive smoothly on the target road surface; adopting With the above implementation scheme, the current road surface image, road surface point cloud information, and vehicle status information are first fused, and the target road surface roughness level that best reflects the target road surface condition is obtained after considering the historical road surface roughness level. Therefore, the most accurate control strategy can be obtained based on the target road surface roughness level, and the damping force of the shock absorber determined in the control strategy is obtained based on the feedback control damping force and the feedforward damping force, which can reduce the impact and vibration acceleration of the vehicle entering the target road surface, and further improve the driving comfort performance of the vehicle under uneven road conditions based on the control strategy. At the same time, the feedback control damping force can immediately design a self-learning control strategy for the nonlinear characteristics of the radial basis function neural network to adaptively compensate for external disturbances. Therefore, the feedback control damping force can quickly eliminate the vibration acceleration of the vehicle body and wheels after the vehicle enters the target road surface.

[0281] Fig.11 The present invention provides a schematic diagram of the structure of a vehicle suspension control device. In practical applications, based on the same disclosure concept of the above embodiments, Fig.11 As shown, the vehicle suspension control device 11 of this embodiment includes: a processor 110 , a memory 111 and a communication bus 112 .

[0282] In the process of a specific embodiment, the above-mentioned model building module, determination module, calculation module, input module, acquisition module and adjustment module can be implemented by a processor 110 located on the suspension control device 11 of the vehicle, and the above-mentioned processor 110 can be at least one of an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing image processing device (DSPD), a programmable logic image processing device (PLD), a field programmable gate array (FPGA), a CPU, a controller, a microcontroller, and a microprocessor. It can be understood that for the suspension control device 11 of different vehicles, the electronic device used to implement the above-mentioned processor function can also be other, and this embodiment does not specifically limit it.

[0283] In the embodiment of the present invention, the communication bus 112 is used to realize the connection and communication between the processor 110 and the memory 111; when the processor 110 executes the running program stored in the memory 111, the following vehicle suspension system control method is realized:

[0284] Acquire a current road surface image and road surface point cloud information of a target road surface in a first direction, as well as vehicle status information; the first direction is the driving direction of the vehicle;

[0285] Inputting the current road surface image, the road surface point cloud information and the state information into a preset road surface recognition model to obtain a target road surface roughness grade of the target road surface;

[0286] Predicting, according to the target road surface roughness level, a feedforward damping force required by a suspension system of the vehicle when the vehicle travels on the target road surface;

[0287] When the vehicle travels onto the target road surface based on the feedforward damping force, the feedback damping force is calculated in real time based on the body parameters of the vehicle, and the feedforward damping force is compensated in real time based on the feedback damping force, so that the vehicle travels smoothly on the target road surface.

[0288] In some embodiments, the processor 110 is further used to construct an alternative Lyapunov function; determine a first calculation formula for the feedback damping force while maintaining the first-order derivative of the alternative Lyapunov function to be less than or equal to 0; and calculate the feedback damping force according to the first calculation formula.

[0289] In some embodiments, the processor 110 is further used to decouple the suspension system into multiple sub-suspension systems at different locations, and establish a two-degree-of-freedom vibration model based on the sub-suspension systems and the vehicle body parameters; and construct the alternative Lyapunov function based on the sliding mode variables, radial basis neural network weight coefficient estimation errors, radial basis function estimation errors, radial basis center estimation errors, and disturbance force estimation error uncertainties determined by the two-degree-of-freedom vibration model.

[0290] In some embodiments, the processor 110 is further used to determine the relative displacement of the lower mass of the suspension system and the relative speed of the lower mass according to the two-degree-of-freedom vibration model; multiply the relative displacement of the lower mass by the sliding mode gain coefficient, and add the relative speed of the lower mass to obtain the sliding mode variable.

[0291] In some embodiments, the processor 110 is also used to determine a nominal disturbance force and an estimated disturbance force based on the sliding mode variable; subtract the estimated disturbance force from the nominal disturbance force to obtain a disturbance force estimation error; the disturbance force estimation error is composed of the product of a weight coefficient and a radial basis function estimation error, the product of a weight coefficient error and a radial basis function estimate, and the sum of an optimal approximation error; split the radial basis function estimation error into a product of a partial derivative of the radial basis function with respect to a radial basis center and an estimated error of the radial basis center, a product of a partial derivative of the radial basis function with respect to a radial basis width and an estimated error of the radial basis width, and the sum of higher-order terms after Taylor expansion of the radial basis function; obtain the uncertainty of the disturbance force estimation error based on the product of the sliding mode variable, the uncertainty gain coefficient, and a first matrix, and the product of the sliding mode variable and an adjustable gain coefficient; wherein the first matrix is ​​composed of a first constant, a radial basis center estimate, a radial basis width estimate, and a weight coefficient estimate.

[0292] In some embodiments, the processor 110 is further used to obtain a radial basis function by subtracting the norm of the radial basis center from the sliding mode variable and then dividing the result by the radial basis width; determining the product of the radial basis function and the weighting coefficient and the sum of the optimal approximation error as the nominal disturbance force; replacing the weighting coefficient, the radial basis center and the radial basis width in the nominal disturbance force with corresponding estimates, and discarding the optimal disturbance approximation error term to obtain the estimated disturbance force.

[0293] In some embodiments, the processor 110 is also used to calculate the radial basis neural network weight coefficient, the radial basis center, the radial basis width and the disturbance force estimation error uncertainty in real time according to the real-time vehicle body parameters; substitute the radial basis neural network weight coefficient, the radial basis center, the radial basis width and the disturbance force estimation error uncertainty into the first calculation formula to obtain the feedback damping force.

[0294] In some embodiments, the processor 110 is further used to input the current road surface image into the first model, extract the first road surface feature in the current road surface image using the first model, and convert the first road surface feature into a first road surface roughness level; input the road surface point cloud information into the second model, extract the second road surface feature in the road surface point cloud information using the second model, and convert the second road surface feature into a second road surface roughness level; input the status information into the third model to obtain a third road surface roughness level; and perform information fusion on the first road surface roughness level, the second road surface roughness level, the third road surface roughness level, and the historical road surface roughness level of the target road surface to obtain the target road surface roughness level.

[0295] In some embodiments, the processor 110 is further used to obtain historical road surface marking information corresponding to the target road surface; the historical road surface marking information is obtained when the vehicle historically travels to the target road surface and marks the target road surface; wherein the historical road surface marking information includes a historical road surface roughness grade, historical road surface coordinates, historical road surface length, and historical path curvature corresponding to the target road surface.

[0296] In some embodiments, the processor 110 is also used to determine the current first position coordinates of the vehicle; determine the first distance between the first position of the vehicle and the starting position of the target road surface based on the first position coordinates and the historical road surface coordinates; the first position is the center position of the front axle on the vehicle; determine the first time required for the vehicle to travel to the starting position based on the first distance and the first driving speed; when the first time is less than a first threshold value, and / or the first distance is less than a second threshold value, start the control strategy.

[0297] In some embodiments, the processor 110 is further used to determine a second time required for the vehicle to travel the target road surface based on the first driving speed and the historical road surface length; when the control strategy is turned on and the second time period has passed, the control strategy is turned off.

[0298] In some embodiments, the processor 110 is further configured to adjust the height of the suspension system to a target height, and / or adjust the stiffness of an air spring in the suspension system to a target stiffness.

[0299] In some embodiments, the processor 110 is further used to determine the air suspension mode currently set for the vehicle; and determine the target height and the target stiffness according to the air suspension mode, the historical path curvature, the state information, and the target road roughness level.

[0300] In some embodiments, the processor 110 is also used to adjust the target height according to the current second driving speed of the vehicle and the first information of the vehicle when it is detected that the vehicle is accelerating or braking while driving on the target road surface; wherein the first information is the pedal position of the current accelerator pedal in the vehicle, and / or the pressure of the current brake cylinder.

[0301] In some embodiments, the processor 110 is further used to determine that the vehicle has reached the starting point of the target road surface and the current first position coordinates and the current first time point of the vehicle when the vertical acceleration of the front axle wheels of the vehicle is greater than a third threshold value; determine that the vehicle has left the target road surface and the current second position coordinates and the current second time point of the vehicle when the vertical acceleration of the front axle wheels of the vehicle is less than a fourth threshold value; determine a first road surface length of the target road surface according to the first position coordinates and the second position coordinates, and / or the first time point, the second time point and the current third driving speed of the vehicle; determine a target path curvature according to the first path curvature and the historical path curvature, and update the historical road surface marking information according to the target path curvature, the target road surface roughness level, the first road surface length and the first position coordinates.

[0302] An embodiment of the present invention provides a storage medium having a computer program stored thereon. The computer-readable storage medium stores one or more programs. The one or more programs can be executed by one or more processors and are applied to a suspension control system of a vehicle. The computer program implements the suspension system control method of the vehicle as described above.

[0303] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0304] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0305] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0306] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0307] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for controlling a suspension system of a vehicle, characterized in that: The method comprises: Acquire a current road surface image and road surface point cloud information of a target road surface in a first direction, as well as vehicle status information; the first direction is the driving direction of the vehicle; Inputting the current road surface image, the road surface point cloud information and the state information into a preset road surface recognition model to obtain a target road surface roughness grade of the target road surface; Predicting, according to the target road surface roughness level, a feedforward damping force required by a suspension system of the vehicle when the vehicle travels on the target road surface; When the vehicle travels onto the target road surface based on the feedforward damping force, the feedback damping force is calculated in real time based on the body parameters of the vehicle, and the feedforward damping force is compensated in real time based on the feedback damping force, so that the vehicle travels smoothly on the target road surface.

2. The vehicle suspension system control method according to claim 1, characterized in that: The real-time calculation of the feedback damping force based on the body parameters of the vehicle includes: Construct alternative Lyapunov functions; Under the condition that the first-order derivative of the candidate Lyapunov function is maintained to be less than or equal to 0, determining a first calculation formula for the feedback damping force; The feedback damping force is calculated according to the first calculation formula.

3. The vehicle suspension system control method according to claim 2, characterized in that: The constructing of the candidate Lyapunov function comprises: Decoupling the suspension system into a plurality of sub-suspension systems at different locations, and establishing a two-degree-of-freedom vibration model based on the sub-suspension systems and the vehicle body parameters; The alternative Lyapunov function is constructed based on the sliding mode variables determined by the two-degree-of-freedom vibration model, the radial basis neural network weight coefficient estimation error, the radial basis function estimation error, the radial basis center estimation error and the disturbance force estimation error uncertainty.

4. The vehicle suspension system control method according to claim 3, characterized in that: The method further comprises: Determining the relative displacement of the lower mass of the suspension system and the relative velocity of the lower mass according to the two-degree-of-freedom vibration model; The relative displacement of the lower mass is multiplied by a sliding mode gain coefficient and then added to the relative speed of the lower mass to obtain the sliding mode variable.

5. The vehicle suspension system control method according to claim 3, characterized in that: The method further comprises: determining a nominal disturbance force and an estimated disturbance force based on the sliding mode variables; Subtracting the estimated disturbance force from the nominal disturbance force to obtain a disturbance force estimation error; the disturbance force estimation error is composed of the product of the weight coefficient and the radial basis function estimation error, the product of the weight coefficient error and the radial basis function estimate, and the optimal approximation error. Splitting the radial basis function estimation error into the product of the partial derivative of the radial basis function with respect to the radial basis center and the estimation error of the radial basis center, the product of the partial derivative of the radial basis function with respect to the radial basis width and the estimation error of the radial basis width, and the sum of the high-order terms after Taylor expansion of the radial basis function; Obtaining the uncertainty of the disturbance force estimation error based on the product of the sliding mode variable, the uncertainty gain coefficient, and the first matrix, and the product of the sliding mode variable and the adjustable gain coefficient; The first matrix is ​​composed of a first constant, a radial basis center estimate, a radial basis width estimate, and a weight coefficient estimate.

6. The vehicle suspension system control method according to claim 5, characterized in that: The method further comprises: The radial basis function is obtained by subtracting the norm of the radial basis center from the sliding mode variable and dividing the result by the radial basis width; Determine the product of the radial basis function and the weighting coefficient and the sum of the optimal approximation error as the nominal disturbance force; The weight coefficient, radial basis center and radial basis width in the nominal disturbance force are replaced with corresponding estimates, and the optimal disturbance approximation error term is discarded to obtain the estimated disturbance force.

7. The vehicle suspension system control method according to claim 2, characterized in that: The first variable in the first calculation formula includes a radial basis neural network weight coefficient, a radial basis center, a radial basis width, and a disturbance force estimation error uncertainty; and calculating the feedback damping force according to the first calculation formula includes: Calculating the radial basis neural network weight coefficient, the radial basis center, the radial basis width and the disturbance force estimation error uncertainty in real time according to the real-time vehicle body parameters; Substitute the radial basis neural network weight coefficient, the radial basis center, the radial basis width and the disturbance force estimation error uncertainty into the first calculation formula to obtain the feedback damping force.

8. The vehicle suspension system control method according to any one of claims 1 to 7, characterized in that: The preset road surface recognition model includes at least a first model, a second model and a third model; the inputting the current road surface image, the road surface point cloud information and the state information into the preset road surface recognition model to obtain the target road surface roughness level of the target road surface includes: Inputting the current road surface image into the first model, extracting first road surface features in the current road surface image using the first model, and converting the first road surface features into a first road surface roughness grade; Inputting the road surface point cloud information into the second model, extracting second road surface features from the road surface point cloud information using the second model, and converting the second road surface features into a second road surface roughness grade; Inputting the state information into the third model to obtain a third road surface roughness grade; The first road surface roughness level, the second road surface roughness level, the third road surface roughness level, and the historical road surface roughness level of the target road surface are fused to obtain the target road surface roughness level.

9. The vehicle suspension system control method according to claim 8, characterized in that: The method further comprises: Acquire historical road marking information corresponding to the target road; the historical road marking information is obtained after marking the target road when the vehicle historically travels to the target road; The historical road surface marking information includes the historical road surface roughness level, historical road surface coordinates, historical road surface length and historical path curvature corresponding to the target road surface.

10. The vehicle suspension system control method according to claim 9, characterized in that: The state information includes a current first driving speed of the vehicle, and the method further includes: Determining a current first position coordinate of the vehicle; Determine a first distance between a first position of the vehicle and a starting position of the target road surface according to the first position coordinates and the historical road surface coordinates; the first position is a center position of a front axle on the vehicle; Determining a first time required for the vehicle to travel to the starting position according to the first distance and the first travel speed; When the first time duration is less than a first threshold value and / or the first distance is less than a second threshold value, the control strategy is started.

11. The vehicle suspension system control method according to claim 10, characterized in that: The method further comprises: Determining a second time required for the vehicle to travel the target road surface according to the first driving speed and the historical road surface length; When the control strategy is turned on and the second time period has elapsed, the control strategy is turned off.

12. The vehicle suspension system control method according to claim 1, characterized in that: After the feedforward damping force is compensated in real time based on the feedback damping force, the method further comprises: The height of the suspension system is adjusted to a target height, and / or the stiffness of an air spring in the suspension system is adjusted to a target stiffness.

13. The vehicle suspension system control method according to claim 12, characterized in that: The method further comprises: determining an air suspension mode currently set for the vehicle; The target height and the target stiffness are determined according to the air suspension mode, the historical path curvature, the state information, and the target road roughness level.

14. The vehicle suspension system control method according to claim 1, characterized in that: The method further comprises: When it is detected that the vehicle is accelerating or braking while traveling on the target road surface, adjusting the target height according to the current second traveling speed of the vehicle and the first information of the vehicle; The first information is the current pedal position of the accelerator pedal in the vehicle and / or the current pressure of the brake cylinder.

15. The vehicle suspension system control method according to claim 14, characterized in that: The method further comprises: When the vertical acceleration of the front axle wheel of the vehicle is greater than a third threshold value, determining that the vehicle has reached the starting point of the target road surface, and determining the current first position coordinates and the current first time point of the vehicle; When the vertical acceleration of the front axle wheel of the vehicle is less than a fourth threshold value, determining that the vehicle has left the target road surface, and determining a current second position coordinate and a current second time point of the vehicle; Determine a first road length of the target road according to the first position coordinates and the second position coordinates, and / or the first time point, the second time point, and a third current driving speed of the vehicle; A target path curvature is determined according to the first path curvature and the historical path curvature, and the historical road marking information is updated according to the target path curvature, the target road surface roughness level, the first road surface length, and the first position coordinates.

16. A suspension control system for a vehicle, characterized in that: The system comprises: A binocular camera, used to obtain a current road surface image of a target road surface in a first direction; A radar, used to obtain road surface point cloud information of the target road surface in the first direction; the first direction is the driving direction of the vehicle; A body sensor, used to obtain status information of the vehicle; A suspension controller is used to input the current road surface image, the road surface point cloud information and the state information into a preset road surface recognition model to obtain a target road surface roughness level of the target road surface; predict the feedforward damping force required by the suspension system of the vehicle when the vehicle travels on the target road surface according to the target road surface roughness level; when the vehicle travels on the target road surface based on the feedforward damping force, calculate the feedback damping force in real time based on the body parameters of the vehicle, and compensate the feedforward damping force in real time based on the feedback damping force, so that the vehicle can travel smoothly on the target road surface.

17. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the method according to any one of claims 1 to 15 is implemented.

Images