Adjusting method and device of vehicle suspension, vehicle, equipment and storage medium

Abstract

The invention provides an adjusting method and device for a vehicle suspension, a vehicle, equipment and a storage medium. The method comprises the steps that gradient information and pavement hollowness information of a current driving road of the vehicle are obtained; inputting the gradient information and the pavement hollowness information into an adjusting model, performing smoothing algorithm processing on the gradient information by the adjusting model to generate a first suspension parameter, and performing fusion algorithm processing on the pavement hollowness information to generate a second suspension parameter; calculating and determining the suspension parameters of the vehicle according to the weighted sum of the first suspension parameters and the second suspension parameters, and adjusting the suspension of the vehicle by using the suspension parameters of the vehicle; wherein the weighting coefficient in the weighted sum comprises a first adjustment coefficient and a second adjustment coefficient. According to the method, the damping parameters more conforming to the actual condition can be obtained according to the road surface condition, a better damping effect is achieved, bumping and vibration of the vehicle are reduced, the driving stability and comfort are improved, and better riding experience is brought.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicles, and in particular, to a method and device for adjusting a vehicle suspension, a vehicle, a device, and a storage medium. Background Art

[0002] When we take a car, we often encounter bumpy roads, and some people are prone to motion sickness. At present, shock absorbers are all spring-based and mechanical, which can offset and filter the body vibrations caused by potholed roads, but cannot achieve a finer-grained shock absorption effect.

[0003] With the development of technology in the automotive field, suspensions are provided in many vehicle models to adjust vehicle shock absorption. The suspension can enable the vehicle to respond to road sections in corresponding modes according to the vehicle driving mode, achieving a shock absorption effect. However, such shock absorption parameters for driving modes cannot be adjusted according to real-time road conditions. In the case of complex road conditions, the calculation of suspension parameters requires combining real-time road information to obtain more practical shock absorption parameters for the road conditions, achieving a better shock absorption effect, reducing vehicle bumps and vibrations, improving driving stability and comfort, and bringing a better riding experience. Summary of the Invention

[0004] To solve the above problems, the present disclosure provides a method and device for adjusting a vehicle suspension, a vehicle, a device, and a storage medium. This method can obtain more practical shock absorption parameters for road conditions, achieve a better shock absorption effect, reduce vehicle bumps and vibrations, improve driving stability and comfort, and bring a better riding experience.

[0005] According to a first aspect of the present disclosure, there is provided a method for adjusting a vehicle suspension, including:

[0006] Obtaining slope information and road surface pothole degree information of the road on which the vehicle is currently traveling;

[0007] Inputting the slope information and the road surface pothole degree information into an adjustment model, and the adjustment model performs a smoothing algorithm process on the slope information to generate a first suspension parameter, and performs a fusion algorithm process on the road surface pothole degree information to generate a second suspension parameter; determining the suspension parameter of the vehicle according to the weighted sum of the first suspension parameter and the second suspension parameter, and adjusting the vehicle suspension using the suspension parameter of the vehicle; wherein, the weighting coefficients in the weighted sum include: a first adjustment coefficient and a second adjustment coefficient.

[0008] As an optional implementation manner of an embodiment of the present disclosure, the obtaining slope information of the road on which the vehicle is currently traveling includes:

[0009] Obtain the vehicle pitch data collected by the in-vehicle gyroscope. The vehicle pitch data includes the real-time driving data of the vehicle and the real-time change data of the vehicle's center of gravity. Calculate the slope length that the vehicle has traveled currently by performing weighted average calculation on the real-time driving data of the vehicle; perform fusion algorithm processing based on the slope length that the vehicle has traveled and the real-time change data of the vehicle's center of gravity to calculate the slope, and obtain the slope information of the current driving road relative to the horizon.

[0010] As an optional implementation manner of the embodiment of the present disclosure, the obtaining the road surface pothole information of the current driving road of the vehicle includes:

[0011] Obtain the point cloud data of the current driving road collected by the in-vehicle sensor, calculate the mean square deviation of all the point clouds in the point cloud data from the horizontal reference plane in the vertical direction of the vehicle, and form a data set with the mean square deviation set, and calculate the road surface flatness and the road surface longitudinal and cross-sectional data through the mapping relationship algorithm to obtain the road surface pothole information of the current driving road of the vehicle.

[0012] As an optional implementation manner of the embodiment of the present disclosure, the obtaining the slope information and the road surface pothole degree information of the current driving road of the vehicle includes:

[0013] Use the positioning information of the vehicle to obtain the longitude and latitude information of the current driving road of the vehicle, and obtain the pre-stored slope information and road surface pothole degree information of the current driving road from the cloud map or the offline map through the longitude and latitude information.

[0014] As an optional implementation manner of the embodiment of the present disclosure, the method further includes:

[0015] Obtain the vehicle vertical acceleration at the current moment collected by the in-vehicle gyroscope. When the vehicle vertical acceleration is lower than the preset acceleration, upload the slope information, the road surface pothole degree information, the suspension parameters, and the vehicle vertical acceleration at the current moment to the server.

[0016] As an optional implementation manner of the embodiment of the present disclosure, the training method of the adjustment model includes:

[0017] Obtain the historical slope information, the historical road surface pothole degree information, the historical suspension parameters, and the historical vehicle vertical acceleration during the vehicle driving process at at least one historical moment;

[0018] The historical slope information, historical road surface pothole degree information, and historical suspension parameters corresponding to historical moments when the historical vehicle vertical acceleration is within a preset range are combined to form a training data set. The adjustment model uses the historical slope information to generate the first suspension parameter, and uses the historical road surface pothole degree information to generate the second suspension parameter. The suspension parameter for each historical moment is determined according to the sum of the product of the first adjustment coefficient and the first suspension parameter and the product of the second adjustment coefficient and the second suspension parameter;

[0019] Train the adjustment model, adjust the first adjustment coefficient and the second adjustment coefficient. When the difference between the suspension parameters of all historical moments in the training data set and the historical suspension parameters meets the preset difference, the training of the adjustment model is completed.

[0020] According to a second aspect of the present disclosure, the present disclosure provides an adjustment device for a vehicle suspension, including:

[0021] An acquisition module that acquires the slope information and road surface pothole degree information of the road on which the vehicle is currently traveling;

[0022] A processing module for inputting the slope information and the road surface pothole degree information into an adjustment model, and the adjustment model performs a smoothing algorithm process on the slope information to generate a first suspension parameter, and performs a fusion algorithm process on the road surface pothole degree information to generate a second suspension parameter;

[0023] A determination module for calculating and determining the suspension parameter of the vehicle according to the weighted sum of the first suspension parameter and the second suspension parameter;

[0024] An adjustment module for adjusting the vehicle suspension by using the suspension parameter of the vehicle.

[0025] According to a third aspect of the present disclosure, the present disclosure provides a readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the adjustment method of the vehicle suspension as described in any one of the embodiments in the first aspect.

[0026] According to a fourth aspect of the present disclosure, the present disclosure provides an electronic device, including:

[0027] At least one processor; and

[0028] A memory communicatively connected to the at least one processor; wherein,

[0029] The memory stores instructions executable by the at least one processor. When the instructions are executed by the at least one processor, the at least one processor can implement the steps of the adjustment method of the vehicle suspension as described in any one of the embodiments in the first aspect.

[0030] According to a fifth aspect of the present disclosure, the present disclosure provides a vehicle, including: an adjustment device for a vehicle suspension as described in the second aspect above.

[0031] The technical solutions provided by the embodiments of the present disclosure have the following advantages compared with the prior art: The present disclosure provides a method for adjusting a vehicle suspension, including:

[0032] Obtain the slope information and road surface pothole degree information of the road on which the vehicle is currently traveling;

[0033] Input the slope information and the road surface pothole degree information into an adjustment model, and the adjustment model performs a smoothing algorithm process on the slope information to generate a first suspension parameter, and performs a fusion algorithm process on the road surface pothole degree information to generate a second suspension parameter; determine the suspension parameter of the vehicle according to the weighted sum of the first suspension parameter and the second suspension parameter, and use the suspension parameter of the vehicle to adjust the vehicle suspension; wherein, the weighting coefficients in the weighted sum include: a first adjustment coefficient and a second adjustment coefficient. By obtaining the slope information and road surface pothole degree information of the road on which the vehicle is currently traveling, calculating the suspension parameters through a pre-trained adjustment model in combination with the road surface information, and adjusting and controlling the vehicle suspension, since the suspension parameters are shock absorption parameters calculated in combination with real-time road surface data information, the shock absorption effect on the actual road conditions will be better than that achieved by the fixed shock absorption parameters in the driving mode, enabling the vehicle to cope with road sections under various complex conditions, achieving a good shock absorption effect, reducing the bumps and vibrations of the vehicle, improving the driving stability and comfort, and bringing a better riding experience. Description of the Drawings

[0034] The drawings here are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure.

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0036] Figure 1 It is a flowchart of a method for adjusting a vehicle suspension provided by the first aspect of the embodiments of the present disclosure;

[0037] Figure 2 It is a flowchart of training an adjustment model provided by the first aspect of the embodiments of the present disclosure;

[0038] Figure 3 It is a processing schematic diagram of training an adjustment coefficient provided by the first aspect of the embodiments of the present disclosure;

[0039] Figure 4 It is a schematic diagram of data processing for an adjustment model provided in the first aspect of the embodiments of the present disclosure;

[0040] Figure 5 It is a schematic structural diagram of an adjustment device for a vehicle suspension provided in the second aspect of the embodiments of the present disclosure;

[0041] Figure 6 It is a schematic structural diagram of an electronic device provided in the fourth aspect of the embodiments of the present disclosure. Detailed implementation manners

[0042] In order to more clearly understand the above objects, features, and advantages of the present disclosure, the solutions of the present disclosure will be further described below. It should be noted that, without conflict, the embodiments of the present disclosure and the features in the embodiments may be combined with each other.

[0043] In the following description, many specific details are set forth in order to fully understand the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only a part of the embodiments of the present disclosure, rather than all the embodiments.

[0044] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, the use of words such as "exemplary" or "for example" is intended to present relevant concepts in a specific manner. In addition, in the description of the embodiments of the present application, unless otherwise stated, the meaning of "a plurality of" refers to two or more.

[0045] It should be noted that, in this article, the term "comprising" or any other variant thereof is intended to cover a non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements not only includes those elements but also includes other elements not explicitly listed, or further includes elements inherent to such a process, method, article, or device. Without further limitations, an element defined by the statement "comprising a..." does not exclude the existence of additional identical elements in the process, method, article, or device comprising the element.

[0046] The embodiments of the present application provide a method for adjusting a vehicle suspension, which is specifically applied to a vehicle. Figure 1The following is a schematic flowchart of a method for adjusting a vehicle suspension provided in the first aspect of the embodiments of the present disclosure. This adjustment method can be executed by an adjustment device or equipment, which can be configured in a server, a processor, or a main control chip. Exemplarily, it can be arranged on the vehicle's in-vehicle computer side, domain controller side, etc. Refer to Figure 1 As shown, the method for adjusting the vehicle suspension includes the following steps S101 - S104:

[0047] S101. Obtain the slope information and road surface pothole degree information of the road on which the vehicle is currently traveling.

[0048] As an optional implementation manner, the obtaining of the slope information of the road on which the vehicle is currently traveling includes:

[0049] Obtain the vehicle pitch data collected by the in-vehicle gyroscope. The vehicle pitch data includes the real-time driving data of the vehicle and the real-time change data of the vehicle's center of gravity. Calculate the slope length that the vehicle has traveled currently through weighted average calculation of the real-time driving data of the vehicle; perform fusion algorithm processing based on the slope length that the vehicle has traveled and the real-time change data of the vehicle's center of gravity to calculate the slope, and obtain the slope information of the current driving road relative to the horizon. Specifically, an electronic device obtains the slope information of the current driving road of the vehicle, and collects the vehicle pitch data through the in-vehicle gyroscope installed on the vehicle. The in-vehicle gyroscope can sense the omnidirectional dynamic information of the moving object's left and right tilt (Roll), front and back tilt (Pitch), and left and right swing (Yaw). The six-axis sensor includes: a three-axis accelerometer and a three-axis gyroscope, which can sense data such as the vehicle's lateral acceleration and angular rotation in three directions of the three-dimensional space x, y, and z. In this embodiment, the six-axis sensor is taken as an example. The gyroscope collects the angular velocity, acceleration, angle, rotation speed of the center of gravity of the longitudinal axis, and rotation speed of the center of gravity axis of the four wheels of the vehicle. The angular velocity, acceleration, and rotation speed of the angle of the four wheels of the vehicle are respectively calculated by the weighted average method to obtain the slope length that the vehicle has traveled in real time. Based on the slope length that the vehicle has traveled and the rotation speeds of the center of gravity of the longitudinal axis and the center of gravity axis, perform fusion algorithm processing to obtain the roll angle, pitch angle, and yaw angle; the pitch angle, pitch angle, and yaw angle, that is, the vehicle pitch data. Calculate the slope information of the current driving road relative to the horizon by performing fusion data processing on the vehicle pitch data. The fusion algorithm can select various fusion methods for multi-sensor data, such as the Kalman filtering method, the Bayesian estimation method, and the fuzzy logic reasoning method. The fusion algorithm can combine the redundant or complementary information in space and time of various data obtained by the sensor, such as the vehicle pitch angle data obtained in this technical solution, according to the algorithm criteria to obtain the prediction of the road slope information. In this technical solution, the fusion algorithm is not limited, and a suitable fusion algorithm can be selected according to actual needs to calculate the slope information of the road. Any algorithm that can realize the estimation of environmental information through multi-data fusion can be applied in this technical solution.

[0050] As an alternative implementation, the obtaining of the road surface pothole information of the current driving road of the vehicle includes: obtaining the point cloud data of the current driving road collected by an in-vehicle sensor, calculating the mean square deviation of all the point clouds in the point cloud data from the horizontal reference plane in the vertical direction of the vehicle, and forming a data set with the mean square deviation set to calculate the road surface flatness and the road surface longitudinal and cross-sectional data through a mapping relationship algorithm, so as to obtain the road surface pothole information of the current driving road of the vehicle. Specifically, the in-vehicle sensor applied in this technical solution to the vehicle refers to a radar, and the radar can be any one or more of a TOF (Time of Flight, TOF) lidar, an FMCW (Frequency Modulated Continuous Wave, FMCW) lidar, a rotary lidar, or a 3D millimeter-wave radar, a 4D millimeter-wave radar, etc., which are sensors that detect and measure objects by resolving time and space information. Obtain the point cloud data of the current driving road collected by the radar. Specifically, taking a millimeter-wave radar as an example, millimeter waves are emitted outward through an antenna, and the receiver receives the target reflection signal. After being processed by the signal processor, the environmental information around the vehicle can be quickly and accurately obtained, such as the relative distance, relative speed, angle, movement direction, etc. between the vehicle and other objects. Then, according to the detected object information, target tracking and recognition are carried out, and then data fusion is carried out in combination with the vehicle body dynamic information to obtain the point cloud data of the current driving road. The point cloud data of the current driving road includes data information such as Doppler velocity, distance, horizontal angle, pitch angle, static and dynamic states, signal-to-noise ratio, height, and position. Through the point cloud data obtained by the radar, the distance of all the point clouds from the horizontal reference plane in the vertical direction of the vehicle can be obtained, and the mean square deviation of all the point clouds in the point cloud data from the horizontal reference plane in the vertical direction of the vehicle at each moment is calculated. The calculated mean square deviation data set is input into an optimized group mapping relationship algorithm, such as algorithms that can enhance the randomness and diversity of data particles, such as Tent mapping, Logistic mapping, Cubic mapping, Chebyshev mapping, etc., or similar algorithms such as time series prediction obtained by data preprocessing, network structure design, and parameter adjustment of recurrent neural network (RNN), long short-term memory network (LSTM), gated recurrent unit (GRU), convolutional neural network (CNN), attention mechanism (Attention), and hybrid model (Mix) are used to process the mean square deviation data to obtain the road surface flatness and the road surface longitudinal and cross-sectional information, that is, the pothole degree data, to obtain the road surface pothole information of the road in front of the vehicle.

[0051] As an alternative implementation, the obtaining of the slope information and road surface pothole degree information of the current driving road of the vehicle includes: obtaining the longitude and latitude information of the current driving road of the vehicle by using the positioning information of the vehicle, and obtaining the pre-stored slope information and road surface pothole degree information of the current driving road from the cloud map or the offline map through the longitude and latitude information. Specifically, using the positioning information of the vehicle means obtaining the positioning information and driving data of the vehicle through high-tech technologies such as GPS (Global Position System), whose full name is NAVSTAR GP (NAVigation Satellite Timing And Ranging Global Position System), combined with GIS geographic information technology (electronic map), GPRS wireless communication technology, distributed server technology, and Internet technology. This positioning information method collects data through satellites, and the positioning information is relatively accurate, but there will be information security problems; or through vehicle-mounted inertial navigation, that is, inputting accurate starting coordinates and ending coordinates into the navigation system, collecting attitude angles such as the roll angle and heading angle of the vehicle through the vehicle-mounted gyroscope, calculating the linear velocity of the vehicle in any direction according to the acceleration, integrating at the starting coordinates of the initial coordinates, using its fixed-axis property and precession property to stabilize the platform coordinate system or the mathematical platform in a certain space, measuring the carrier acceleration by the accelerometer, and thus integrating to obtain the velocity and displacement, and starting from the initial position to perform the positioning function, so that the coordinate position of the vehicle in time series can be obtained. However, as time accumulates, there will be position errors. This kind of positioning information has autonomy, concealment, and does not rely on external information, but there are errors in accuracy. Through the above technologies, information such as the longitude and latitude of the vehicle can be received, and the slope information and road surface pothole degree information of the current driving road can be obtained from the cloud map or the offline map. The slope information and road surface pothole degree information obtained here are the data information stored in the cloud map or the offline map. The slope information and road surface pothole degree information in the cloud map can be the data information collected by the map provider through the data collection vehicle and stored in the cloud server, as well as the data information collected by the vehicle itself through the vehicle-mounted gyroscope and vehicle-mounted sensors in the above implementation and stored in the cloud server. The data in the offline map refers to the data information synchronized to the cloud server when connecting to the server. When the vehicle is in an online state, the slope information and road surface pothole degree information of the current driving road corresponding to the cloud map are preferentially retrieved through the longitude and latitude information. When in an offline state or an overtime state, the slope information and road surface pothole degree information of the current driving road corresponding to the offline map are retrieved through the longitude and latitude information.

[0052] S102. Input the slope information and the road surface pothole degree information into an adjustment model. The adjustment model performs a smoothing algorithm process on the slope information to generate a first suspension parameter, and performs a fusion algorithm process on the road surface pothole degree information to generate a second suspension parameter.

[0053] As an alternative implementation, input the slope information and the road surface pothole degree information obtained in any implementation manner in step S101 into a pre-trained adjustment model. The adjustment model generates a first suspension parameter according to the slope information, and the first suspension parameter corresponds to the slope information data; the adjustment model generates a second suspension parameter according to the road surface pothole degree information, and the second suspension parameter corresponds to the road surface pothole degree information data. The first suspension parameter is mainly used to adjust the slope of the road surface. The first suspension parameter adjusts the pitch data information roll angle, rake angle, and trailing angle; side pitch angle, front pitch angle, and trailing pitch angle in the slope data. After the first suspension parameter, the pitch angle is linearly smoothed to achieve the shock absorption effect for the road surface slope condition; the second suspension parameter is mainly used to adjust the road surface pothole degree. The second suspension parameter adjusts the flatness of the road surface pothole degree information data and the longitudinal section data of the road surface. After the second suspension parameter, the flatness and longitudinal section of the road surface pothole degree are linearly smoothed to achieve the shock absorption effect for the road surface pothole degree condition.

[0054] S103. Calculate and determine the suspension parameter of the vehicle according to the weighted sum of the first suspension parameter and the second suspension parameter.

[0055] As an alternative implementation, perform a corresponding weighted summation of the first suspension parameter and the second suspension parameter generated in step S102 with a first adjustment coefficient and a second adjustment coefficient to determine the final vehicle suspension parameter. The initial values of the first adjustment coefficient and the second adjustment coefficient are preset values, which can be initially set according to the actual shock absorption situation. Subsequently, the adjustment model will calibrate and train the first adjustment coefficient and the second adjustment coefficient according to the specific shock absorption situation and data. The shock absorption data includes historical slope information, historical road surface pothole degree information, historical suspension parameters, historical vertical acceleration, etc. Use the algorithm of the loss function to calibrate and train to update the first adjustment coefficient and the second adjustment coefficient to obtain reasonable adjustment coefficient values, and perform a weighted summation process with the first suspension parameter and the second suspension parameter to determine the final suspension parameter, making the determination of the suspension parameter more accurate.

[0056] S104. Adjust the vehicle suspension using the suspension parameter of the vehicle.

[0057] As an alternative embodiment, according to the suspension parameters determined in step S103, since the parameters combine the slope information and pothole information of different road conditions with the input first suspension parameter and second suspension parameter, and the first adjustment coefficient and the second adjustment coefficient are continuously and reasonably adjusted according to big data, the calculation of the suspension parameters is more practical and accurate. The suspension parameters obtained through this technical solution can be compensated from the kinematic perspective for the front, rear, and roll center heights, and the position of the toe adjustment rod, spring stiffness and leverage ratio, bump stop and stiffness, jounce stop and stiffness, and control arm tilt angle can be optimized to adjust the vehicle suspension to damp the vehicle. It is reasonable to adjust and control the vehicle suspension with these suspension parameters. The vehicle suspension system adjusts according to the suspension parameters for the road conditions, reduces body vibration, and maintains body stability. Many current vehicles have suspension systems that can be actively controlled, such as electromagnetic suspension systems and air suspension systems, which can be actively adjusted in terms of height, stiffness, and damping coefficient, etc., so as to provide a better riding experience for passengers. When the driver is driving and sees the road conditions ahead, such as asphalt road, cement road, potholed road, or speed bump, etc., combined with the current vehicle speed, the driver can basically predict the vibration of the vehicle body. This technical solution collects road information through radar on the basis of the existing technology and combines the road information in the cloud for the control of the vehicle suspension system, which can effectively adjust the vehicle suspension and achieve a good damping effect.

[0058] The method for adjusting the vehicle suspension provided by the embodiment of the present application is specifically as follows: obtaining the slope information and road surface pothole information of the road where the vehicle is currently traveling; inputting the slope information and the road surface pothole information into an adjustment model, and the adjustment model performs a smoothing algorithm process on the slope information to generate a first suspension parameter, and performs a fusion algorithm process on the road surface pothole information to generate a second suspension parameter; calculating and determining the suspension parameters of the vehicle according to the weighted sum of the first suspension parameter and the second suspension parameter, and using the suspension parameters of the vehicle to adjust the vehicle suspension; wherein, the weighting coefficients in the weighted sum include: a first adjustment coefficient and a second adjustment coefficient. Most of the existing vehicle suspension adjustment methods adjust according to the suspension parameters preset for the vehicle driving mode. In this technical solution, in the case of complex road conditions, the calculation of the suspension parameters requires combining real-time road surface information to obtain more practical damping parameters for the road conditions, achieving a better damping effect, reducing vehicle jolts and vibrations, improving driving stability and comfort, and bringing a better riding experience.

[0059] As an extension and refinement of the above embodiment, refer to Figure 2 as shown Figure 2It is a schematic flowchart of a process for adjusting model training provided in the first aspect of the embodiments of the present disclosure. The training method includes the following steps S201-S205:

[0060] S201: Obtain historical slope information, historical road surface pothole information, historical suspension parameters, and historical vehicle vertical acceleration during vehicle driving at at least one historical moment.

[0061] As an optional implementation manner of the technical solution, the method further includes: obtaining the vehicle vertical acceleration at the current moment collected by an in-vehicle gyroscope, and when the vehicle vertical acceleration is lower than a preset acceleration, uploading the slope information, road surface pothole information, suspension parameters, and the vehicle vertical acceleration at the current moment to the server. Specifically, the acceleration data on the z-axis in the three-dimensional space can be sensed by a three-axis gyroscope, that is, the vehicle vertical acceleration. The vehicle vertical acceleration refers to the acceleration change of the vehicle in the vertical direction. By the change of the vehicle vertical acceleration, the change of the vehicle vibration amplitude can be detected, which is used to test the vehicle shock absorption effect in bumpy road sections and judge the degree of suspension adjustment optimization. If the vehicle vertical acceleration is large, it means that the adjustment parameters of the vehicle suspension are not optimized ideally. If the vehicle vertical acceleration is small, it means that the suspension adjustment parameters at this time have achieved a good adjustment effect. When the vehicle vertical acceleration is lower than the preset acceleration, the slope information, road surface pothole information, suspension parameters, and the vehicle vertical acceleration at the current moment are uploaded to the server, where the preset acceleration is a preset acceleration threshold, 0.1-0.3 m / s 2 (meters per second squared), and the preferred value is 0.20 m / s 2 , when the vertical acceleration of the vehicle is less than 0.20 m / s 2 , the slope information, road surface pothole information, suspension parameters, and the vehicle vertical acceleration at the corresponding moment are uploaded to the server to update the data set in the server.

[0062] As an optional implementation manner of the technical solution, according to the data set stored in the server in the above implementation manner, at least one set of historical slope information, historical road surface pothole information, historical suspension parameters, and historical vehicle vertical acceleration during vehicle driving at a historical moment is obtained from the data set as a set of training data.

[0063] S202: The adjustment model performs a smoothing algorithm process on the historical slope information to generate the first suspension parameter, and performs a fusion algorithm process on the historical road surface pothole information to generate the second suspension parameter.

[0064] As an alternative implementation of the present technical solution, the first suspension parameter is generated by using the historical slope information during the vehicle driving at at least one historical moment obtained in step S201, and the second suspension parameter is generated by using the road surface pothole degree information during the vehicle driving at at least one historical moment obtained in step S201. The generation method can adopt a deep learning model, for example, a time series-related deep learning model. The deep learning model includes but is not limited to Long-Short Term Memory (LSTM) model, Convolutional Recurrent Neural Network (CRN) model, time series-related Transformer, etc. The specific model architecture and the number of parameters are determined by the required prediction accuracy and computing power requirements. In addition, the deep learning model can be a combination of a time series-related deep learning model and a convolutional model, and the convolutional model can be a Convolutional Neural Network (CNN).

[0065] S203: Calculate and determine the suspension parameter at each historical moment according to the weighted sum of the first suspension parameter and the second suspension parameter.

[0066] As an alternative implementation of the present technical solution, according to the first suspension parameter and the second suspension parameter generated in step S202, the suspension parameter at each historical moment can be determined by weighted summation with the uncalibrated first adjustment coefficient and the second adjustment coefficient, that is, the initial values, or can be determined by corresponding weighted summation with the calibrated first adjustment coefficient and the second adjustment coefficient. The suspension parameter at each historical moment is determined according to the sum of the product of the first adjustment coefficient and the first suspension parameter and the product of the second adjustment coefficient and the second suspension parameter, where the initial values can be set according to the requirements for the shock absorption amplitude and shock absorption effect in combination with the actual situation.

[0067] S204: Train the adjustment model and adjust the first adjustment coefficient and the second adjustment coefficient.

[0068] As an alternative implementation of the present technical solution, the method for training the adjustment model and adjusting the first adjustment coefficient and the second adjustment coefficient may be to obtain the historical slope information, historical road surface pothole degree information, historical suspension parameters, and historical vehicle vertical acceleration during the vehicle driving at historical moments as a set of training data. For the same set of training parameters, the first adjustment coefficient and the second adjustment coefficient are adjusted proportionally linearly. The corresponding suspension parameters and vertical acceleration are output through the adjustment model. When the difference between the suspension parameters and the historical suspension parameters is within a preset difference range, and at the same time the speed difference between the vertical acceleration and the historical vertical acceleration is within a preset speed difference range, the first adjustment coefficient and the second adjustment coefficient are calibrated and updated.

[0069] S205: When the difference between the suspension parameters and the historical suspension parameters at all historical moments in the training dataset satisfies the preset difference, the training of the adjustment model is completed.

[0070] As an alternative implementation of the present technical solution, the model can be trained through a loss function. For example, the historical slope information, historical road surface pothole degree information, historical suspension parameters, and historical vehicle vertical acceleration during the vehicle driving at each historical moment are obtained as multiple sets of training data. For each set of training parameters, the first adjustment coefficient and the second adjustment coefficient are adjusted proportionally linearly. The corresponding suspension parameters and vertical acceleration are output through the adjustment model. When the difference between the suspension parameters and the historical suspension parameters is within a preset difference range, and at the same time the speed difference between the vertical acceleration and the historical vertical acceleration is within a preset speed difference range, the first adjustment coefficient and the second adjustment coefficient are calibrated and updated. When the difference between the suspension parameters and the historical suspension parameters at all historical moments in the training dataset satisfies the preset parameter difference, the training of the adjustment model is completed, so that the first adjustment coefficient and the second adjustment coefficient perform reasonable numerical weighting under different road surface data information, and the final suspension parameters are determined. The training of the model can be carried out in the vehicle or on the server, and then the trained model is saved to the vehicle.

[0071] Taking a specific model training as an example for description, as Figure 3 is a processing schematic diagram of adjustment coefficient training provided in the first aspect of the embodiments of the present disclosure; Figure 4 is a data processing schematic diagram of an adjustment model provided in the first aspect of the embodiments of the present disclosure, as Figure 3As shown in the figure, historical slope information, historical road surface pothole information, historical suspension parameters, and historical vertical acceleration data can be input into an adjustment model. The adjustment model can be a deep learning model, and the deep learning model includes, but is not limited to, Long-Short Term Memory (LSTM) model, Convolutional Recurrent Neural Network (CRN) model, time series-related Transformer, etc. After being trained by any of the above models, the adjustment model calibrates and updates the first adjustment coefficient and the second adjustment coefficient; as Figure 4 As shown in the figure, during the actual vehicle suspension adjustment process, the obtained slope information and road surface pothole information of the current driving road of the vehicle are input into the pre-trained adjustment model. The adjustment model generates the first suspension parameter using the slope information and generates the second suspension parameter using the road surface pothole information. The first adjustment coefficient and the second adjustment coefficient updated by calibrating the above adjustment model are weighted and summed corresponding to the first suspension parameter and the second suspension parameter, that is, the suspension parameter of the vehicle is determined according to the sum of the product of the first suspension parameter and the first adjustment coefficient and the second suspension parameter and the second adjustment coefficient, and the vehicle suspension is adjusted according to the suspension parameter of the vehicle.

[0072] Based on the same inventive concept, as an implementation of the above method, an embodiment of the present application also provides an adjustment device for a vehicle suspension. This embodiment corresponds to the foregoing method embodiment. For the convenience of reading, details of the foregoing method embodiment will not be repeated one by one in this embodiment. However, it should be clear that the adjustment device for a vehicle suspension in this embodiment can correspondingly implement all the contents of the foregoing method embodiment.

[0073] An embodiment of the present application provides an adjustment device for a vehicle suspension. Figure 5 FIG. is a schematic structural diagram of an adjustment device for a vehicle suspension provided in the second aspect of the embodiments of the present disclosure. As Figure 5 shown, the adjustment device 500 for the vehicle suspension includes:

[0074] An acquisition module that acquires slope information and road surface pothole information of the current driving road of the vehicle;

[0075] A processing module for inputting the slope information and the road surface pothole information into an adjustment model, and the adjustment model performs a smoothing algorithm process on the slope information to generate a first suspension parameter, and performs a fusion algorithm process on the road surface pothole information to generate a second suspension parameter;

[0076] A determination module for calculating and determining the suspension parameter of the vehicle according to the weighted sum of the first suspension parameter and the second suspension parameter;

[0077] An adjustment module for adjusting a vehicle suspension using suspension parameters of the vehicle.

[0078] As an optional implementation manner of an embodiment of the present application, the acquisition module is specifically configured to acquire slope information calculated from vehicle pitch data collected by an in-vehicle gyroscope, and acquire road surface pothole degree information calculated from point cloud data acquired by an in-vehicle sensor, or acquire slope information and road surface pothole degree information of a current driving road in a cloud map or an offline map.

[0079] As an optional implementation manner of an embodiment of the present application, the adjustment module is specifically configured to perform compensation from the kinematic perspective on the front, rear, and roll center heights according to the determined suspension parameters, optimize the position of the toe adjustment rod, spring stiffness and leverage ratio, rebound stop and stiffness, jounce stop and stiffness, and control arm tilt angle, and adjust the vehicle suspension to damp the vehicle.

[0080] Based on the same inventive concept, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the computing device is enabled to implement the method for adjusting the suspension of the vehicle provided in the above embodiment.

[0081] Based on the same inventive concept, an embodiment of the present disclosure further provides an electronic device. Figure 6 FIG. is a schematic structural diagram of an electronic device provided in the fourth aspect of the embodiments of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as, a personal digital processor, a cellular phone, a smart phone, a wearable device, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0082] As Figure 6As shown, the device 400 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a ROM (Read-Only Memory) 602 or a computer program loaded from a storage unit 608 to a RAM (Random Access Memory) 603. In RAM 603, various programs and data required for the operation of the device 600 can also be stored. The computing unit 601, ROM 602, and RAM 603 are connected to each other via a bus 604. An I / O (Input / Output) interface 605 is also connected to the bus 604.

[0083] A number of components in the device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0084] The computing unit 601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a CPU (Central Processing Unit), a GPU (Graphic Processing Units), various dedicated AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, a DSP (Digital Signal Processor), and any appropriate processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as a method for adjusting the suspension of a vehicle. For example, in some embodiments, the method for adjusting the suspension of a vehicle may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 400 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 403 and executed by the computing unit 601, one or more steps of the method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to execute the aforementioned communication method in any other appropriate manner (for example, by means of firmware).

[0085] The various embodiments of the systems and techniques described above in this document may be implemented in digital electronic circuitry, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application Specific Standard Products), SOCs (System On Chip), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which may be a special-purpose or general-purpose programmable processor that receives data and instructions from, and transmits data and instructions to, a storage system, at least one input device, and at least one output device.

[0086] The program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that the program codes, when executed by the processor or controller, cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on the machine, partially on the machine, as a stand-alone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0087] In the context of this disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a RAM, a ROM, an EPROM (Electrically Programmable Read-Only Memory), or a flash memory, an optical fiber, a CD-ROM (Compact Disc Read-Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0088] In order to provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (Cathode-Ray Tube) or an LCD (Liquid Crystal Display) monitor); and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0089] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a LAN (Local Area Network), a WAN (Wide Area Network), the Internet, and a blockchain network.

[0090] A computer system may include a client and a server. The client and the server are generally far from each other and usually interact via a communication network. The relationship between the client and the server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services ("Virtual Private Server", or simply "VPS"). The server may also be a server of a distributed system or a server combined with a blockchain.

[0091] Among them, it should be noted that artificial intelligence is a discipline that studies how to make a computer simulate certain thinking processes and intelligent behaviors of humans (such as learning, reasoning, thinking, planning, etc.), and it has both hardware-level technologies and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include several major directions such as computer vision technology, speech recognition technology, natural language processing technology, and machine learning / deep learning, big data processing technology, and knowledge graph technology.

[0092] Based on the same inventive concept, an embodiment of the present application further provides a vehicle, which includes an adjustment device for the suspension of the vehicle provided in the above embodiment or the electronic device provided in the above embodiment.

[0093] It should be understood that various forms of the processes shown above can be used, reordering, adding, or deleting steps. For example, the steps recited in this disclosure can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and no limitation is imposed herein.

[0094] The above specific embodiments do not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present disclosure shall be included within the protection scope of the present disclosure.

Claims

1. A method for adjusting a vehicle suspension, characterized in that, Including: Obtaining the slope information and road surface pothole degree information of the current driving road of the vehicle; Inputting the slope information and the road surface pothole degree information into an adjustment model, where the adjustment model performs a smoothing algorithm process on the slope information to generate first suspension parameters, and performs a fusion algorithm process on the road surface pothole degree information to generate second suspension parameters; determining the suspension parameters of the vehicle according to the weighted sum of the first suspension parameters and the second suspension parameters, and adjusting the vehicle suspension by using the suspension parameters of the vehicle; wherein, the weighting coefficients in the weighted sum include: a first adjustment coefficient and a second adjustment coefficient.

2. The method according to claim 1, wherein The obtaining of the slope information of the current driving road of the vehicle includes: Obtaining the vehicle pitch data collected by an in-vehicle gyroscope, where the vehicle pitch data includes the real-time driving data of the vehicle and the real-time change data of the vehicle center of gravity, and calculating the slope length that the vehicle has traveled currently through weighted average calculation of the real-time driving data of the vehicle; performing a fusion algorithm process based on the slope length that the vehicle has traveled and the real-time change data of the vehicle center of gravity to calculate the slope, and obtaining the slope information of the current driving road relative to the horizon.

3. The method according to claim 1, wherein The obtaining of the road surface pothole information of the current driving road of the vehicle includes: Obtaining the point cloud data of the current driving road collected by an in-vehicle sensor, calculating the mean square error of the distances of all point clouds in the point cloud data from the horizontal reference plane in the vertical direction of the vehicle, and forming a data set with the mean square error set and calculating the road surface flatness and the road surface longitudinal section data through a mapping relationship algorithm, and obtaining the road surface pothole information of the current driving road of the vehicle.

4. The method according to claim 1, characterized in that The obtaining of the slope information and the road surface pothole degree information of the current driving road of the vehicle includes: Using the positioning information of the vehicle to obtain the longitude and latitude information of the current driving road of the vehicle, and obtaining the pre-stored slope information and road surface pothole degree information of the current driving road from a cloud map or an offline map through the longitude and latitude information.

5. The method according to claim 1, wherein The method further includes: Obtaining the vehicle vertical acceleration at the current moment collected by an in-vehicle gyroscope, and when the vehicle vertical acceleration is lower than a preset acceleration, uploading the slope information, the road surface pothole degree information, the suspension parameters, and the vehicle vertical acceleration at the current moment to a server.

6. The method according to claim 1, wherein The training method of the adjustment model includes: Obtaining the historical slope information, the historical road surface pothole degree information, the historical suspension parameters, and the historical vehicle vertical acceleration during the vehicle driving process at at least one historical moment; Forming a training data set with the historical slope information, the historical road surface pothole degree information, and the historical suspension parameters corresponding to the historical moments when the historical vehicle vertical acceleration is within a preset range, and the adjustment model uses the historical slope information to generate the first suspension parameters, and uses the historical road surface pothole degree information to generate the second suspension parameters, and determining the suspension parameters of each historical moment according to the sum of the product of the first adjustment coefficient and the first suspension parameters and the product of the second adjustment coefficient and the second suspension parameters; Train the adjustment model, adjust the first adjustment coefficient and the second adjustment coefficient, and complete the training of the adjustment model when the difference between the suspension parameters and the historical suspension parameters at all historical moments in the training dataset meets the preset difference.

7. An adjustment device for a vehicle suspension, characterized in that, Comprising: An acquisition module, which acquires the slope information and the road surface pothole degree information of the current driving road of the vehicle; A processing module, configured to input the slope information and the road surface pothole degree information into the adjustment model, and the adjustment model performs smoothing algorithm processing on the slope information to generate a first suspension parameter, and performs fusion algorithm processing on the road surface pothole degree information to generate a second suspension parameter; A determination module, configured to calculate and determine the suspension parameter of the vehicle according to the weighted sum of the first suspension parameter and the second suspension parameter; An adjustment module, configured to adjust the vehicle suspension by using the suspension parameter of the vehicle.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, it implements the steps of the method according to any one of claims 1-6.

9. An electronic device, characterized in that, Comprising: At least one processor; And A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method according to any one of claims 1-6.

10. A vehicle, characterized in that, Comprises the adjustment device of the vehicle suspension according to claim 7.

Images