Training Method, Device, Equipment and Medium for Suspension Stiffness Adjustment and Detection Model

Abstract

The present invention discloses a training method, device, equipment and medium for a suspension stiffness adjustment and detection model. The suspension stiffness adjustment method includes: obtaining attribute information and real-time status information of a tire; based on the attribute information and the real-time status information, obtaining the tire stiffness by using a pre-trained tire stiffness detection model; calculating an adjustment amount according to the tire stiffness, and adjusting the suspension stiffness. The embodiments of the present invention improve the efficiency and accuracy of suspension stiffness adjustment, and reduce the influence of interference factors on suspension stiffness adjustment.

Description

Technical Field

[0001] The present invention relates to the technical field of computer data processing, and particularly relates to a method, device, equipment and medium for training a suspension stiffness adjustment and detection model. Background Art

[0002] Currently, air suspensions have gradually become a common suspension used in vehicles.

[0003] The air suspension makes the ride comfort of the vehicle controllable.

[0004] However, the wheels are also components that have an important impact on the vertical vibration of the vehicle. The mechanical properties of the tires of existing vehicles are uncontrollable, but the tires themselves are greatly affected by factors such as temperature and tire pressure, which results in inconsistent vertical vibration performance of the vehicle in different environments, thus leading to a decrease in comfort. Summary of the Invention

[0005] The present invention provides a method, device, equipment and medium for training a suspension stiffness adjustment and detection model, which improves the efficiency and accuracy of suspension stiffness adjustment and reduces the influence of interference factors on suspension stiffness adjustment.

[0006] According to one aspect of the present invention, a method for adjusting suspension stiffness is provided, and the method includes:

[0007] Obtain the attribute information and real-time state information of the tire;

[0008] Based on the attribute information and the real-time state information, and based on a pre-trained tire stiffness detection model, obtain the tire stiffness;

[0009] Calculate the adjustment amount according to the tire stiffness, and adjust the suspension stiffness.

[0010] According to one aspect of the present invention, a method for training a stiffness detection model is provided, and the method includes:

[0011] Obtain sample data, where the sample data includes the attribute information, real-time state information and average stiffness information of the sample tire;

[0012] Use the sample data to train the initial model to obtain a tire stiffness detection model.

[0013] According to another aspect of the present invention, a suspension stiffness adjustment device is provided, which is characterized by including:

[0014] An input information acquisition module, configured to obtain the attribute information and real-time state information of the tire;

[0015] A tire stiffness acquisition module, configured to acquire tire stiffness based on the attribute information and the real-time status information and a pre-trained tire stiffness detection model;

[0016] A suspension stiffness adjustment module, configured to calculate an adjustment amount according to the tire stiffness and adjust the suspension stiffness.

[0017] According to another aspect of the present invention, there is provided a training device for a stiffness detection model, characterized by comprising:

[0018] A sample data acquisition module, configured to acquire sample data, where the sample data includes attribute information, real-time status information, and average stiffness information of a sample tire;

[0019] A model training module, configured to train the initial model by using the sample data to obtain a tire stiffness detection model.

[0020] According to another aspect of the present invention, there is provided an electronic device, where the electronic device includes:

[0021] At least one processor; and

[0022] A memory communicatively connected to the at least one processor; wherein,

[0023] The memory stores a computer program executable by the at least one processor, and when the computer program is executed by the at least one processor, the at least one processor is enabled to execute the suspension stiffness adjustment method or the training method for a stiffness detection model according to any embodiment of the present invention.

[0024] According to another aspect of the present invention, there is provided a computer-readable storage medium, where the computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the suspension stiffness adjustment method or the training method for a stiffness detection model according to any embodiment of the present invention is implemented.

[0025] According to another aspect of the present invention, there is provided a computer program product, characterized in that the computer program product includes a computer program, and when the computer program is executed by a processor, the suspension stiffness adjustment method or the training method for a stiffness detection model according to any embodiment of the present invention is implemented.

[0026] The technical solution of the embodiment of the present invention calculates the tire stiffness by acquiring the attributes and real-time status of the tire, calculates the adjustment amount, and adjusts the suspension stiffness, so as to compensate for the influence of the uncontrollable tire on the suspension stiffness, ensure the consistency of vehicle vertical vibration, enable the controllable suspension to achieve the controllable function, improve the ability of the suspension to resist deformation, and thus improve the ride comfort of the vehicle.

[0027] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0029] Figure 1 is a flowchart of a suspension stiffness adjustment method provided according to Embodiment 1 of the present invention;

[0030] Figure 2 is a flowchart of a suspension stiffness adjustment method provided according to Embodiment 2 of the present invention;

[0031] Figure 3 is a flowchart of a training method for a stiffness detection model provided according to Embodiment 3 of the present invention;

[0032] Figure 4 is a schematic diagram of an application scenario provided according to Embodiment 4 of the present invention;

[0033] Figure 5 is a scenario diagram of a suspension stiffness adjustment method provided according to Embodiment 4 of the present invention;

[0034] Figure 6 is a scenario diagram of a training method for a stiffness detection model provided according to Embodiment 4 of the present invention;

[0035] Figure 7 is a schematic structural diagram of a suspension stiffness adjustment device provided according to Embodiment 5 of the present invention;

[0036] Figure 8 is a schematic structural diagram of a training device for a stiffness detection model provided according to Embodiment 6 of the present invention;

[0037] Figure 9 is a schematic structural diagram of an electronic device for implementing the suspension stiffness adjustment method or the training method for the stiffness detection model according to the embodiments of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0038] To enable those skilled in the art to better understand the solution of the present invention, the following will clearly and completely describe the technical solution in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0039] It should be noted that the term "including" in the specification and claims of the present invention and any of its variations are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units does not necessarily limit to those clearly listed steps or units, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0040] Embodiment 1

[0041] Figure 1 FIG. 10 is a flowchart of a suspension stiffness adjustment method provided in Embodiment 1 of the present invention. This embodiment is applicable to the situation of adjusting the suspension stiffness. This method can be executed by a suspension stiffness adjustment device, which can be implemented in the form of hardware and / or software, and can be configured in an electronic device, such as a vehicle-mounted terminal. As Figure 1 shown, the method includes:

[0042] S110. Obtain the attribute information and real-time status information of the tire.

[0043] The attribute information is used to determine the nature of the tire itself. The attribute information may include the tire model and the tire brand, etc. The real-time status information is used to determine the status of the tire during operation. The real-time status information may include the tire pressure and temperature information. Among them, the temperature information may be the ambient temperature information during vehicle driving.

[0044] S120. Based on the attribute information and the real-time status information, and based on a pre-trained tire stiffness detection model, obtain the tire stiffness.

[0045] The tire stiffness detection model is used to input the attribute information and the real-time status information and output the tire stiffness. Specifically, the attribute information and the real-time status information of the four tires of the same vehicle are input into the tire stiffness detection model to obtain the tire stiffness of each tire. Among them, the tire stiffness is used to evaluate the ability of the tire to resist deformation.

[0046] S130. Calculate the adjustment amount according to the tire stiffness and adjust the suspension stiffness.

[0047] The adjustment amount is used to adjust the suspension stiffness. According to the tire stiffness, the deformation degree of the tire can be determined. Thus, according to the deformation degree of the tire, the adjustment amount can be determined so that the tire stiffness does not affect the suspension stiffness, and the deformation degree of the tire can be compensated in the suspension stiffness. Exemplarily, according to the tire stiffness and the standard stiffness of the tire, the deformation degree of the tire can be determined, and the adjustment amount can be calculated according to the preset corresponding relationship between the deformation degree and the adjustment amount. Among them, the corresponding relationship can be a numerical logical relationship, such as a proportional relationship. The suspension stiffness is used to evaluate the ability of the suspension to resist deformation. Among them, adjusting the suspension stiffness can be to adjust the parameters of the components that resist deformation so that the components that resist deformation in the suspension can accurately perform the function of resisting deformation, thereby reducing the deformation of the suspension and improving the driving stability of the vehicle. Generally, the tire stiffness and the suspension stiffness are inversely proportional. Exemplarily, when the tire pressure is high, the tire stiffness is high and the suspension stiffness is reduced; when the tire pressure is low, the tire stiffness is low and the suspension stiffness is increased; when the tire pressure is at the standard value, the tire stiffness is at the standard stiffness and the suspension stiffness does not need to be compensated.

[0048] Existing factors such as temperature change, tire pressure change, and tire model will all cause uncontrollable changes in the mechanical properties of the tire. Thus, the pre-adjusted suspension stiffness will be disturbed, thereby reducing the suspension stiffness.

[0049] The technical solution of the embodiment of the present invention calculates the tire stiffness by obtaining the attributes and real-time status of the tire, calculates the adjustment amount, and adjusts the suspension stiffness to compensate for the influence of the uncontrollable tire on the suspension stiffness, ensure the consistency of the vehicle vertical vibration, enable the controllable suspension to achieve the controllable function, improve the ability of the suspension to resist deformation, and thus improve the ride comfort of the vehicle.

[0050] Embodiment Two

[0051] Figure 2 FIG. is a flowchart of a suspension stiffness adjustment method provided by Embodiment Two of the present invention. This embodiment details the adjustment of the suspension stiffness, which specifically includes: adjusting the deformation-resistant components of the controllable suspension according to the adjustment amount. As Figure 2 shown, the method includes:

[0052] S210. Obtain the attribute information and real-time status information of the tire.

[0053] S220. Based on the attribute information and the real-time status information, obtain the tire stiffness based on a pre-trained tire stiffness detection model.

[0054] S230. Calculate the adjustment amount according to the tire stiffness, and adjust the deformation-resistant components of the controllable suspension according to the adjustment amount.

[0055] Only a controllable suspension can adjust the suspension stiffness. Exemplarily, the controllable suspension is an air suspension. The anti-deformation component is used to resist deformation to determine the suspension stiffness. Exemplarily, the anti-deformation component is an air spring or a hydraulic cylinder. Pressure adjustment is used to adjust the anti-deformation range of the anti-deformation component. Exemplarily, the anti-deformation component of the controllable suspension can be adjusted by adjusting the pressure of the air spring of the air suspension or the hydraulic pressure of the hydraulic cylinder of the controllable suspension.

[0056] Optionally, calculating the adjustment amount according to the tire stiffness includes: acquiring a standard stiffness of a vehicle to which the tire belongs; and calculating the adjustment amount according to the standard stiffness and the tire stiffness.

[0057] Standard stiffness refers to the standard stiffness of the tires when the vehicle leaves the factory. In other words, standard stiffness is the stiffness that can be achieved when the vehicle is put into use. The suspension stiffness is also determined based on the standard stiffness. In fact, in the case of standard stiffness, the developer configures the suspension stiffness for the vehicle so that the vehicle can run in the most appropriate state.

[0058] The adjustment amount is calculated based on the standard stiffness and the tire stiffness, and can be: the adjustment amount is determined based on the difference between the standard stiffness and the tire stiffness measured in real time. It can be understood that the preset steady-state driving condition of the vehicle can be achieved by compensating the tire stiffness in real time to the suspension stiffness. Therefore, the difference between the standard stiffness and the tire stiffness can be calculated and determined as the adjustment amount to adjust the suspension stiffness. Exemplarily, if the tire stiffness is greater than the standard stiffness, the sign of the adjustment amount is negative, and if the tire stiffness is less than the standard stiffness, the sign of the adjustment amount is positive.

[0059] By obtaining the standard stiffness and calculating the adjustment amount based on the real-time tire stiffness, the degree of tire deformation can be accurately measured, thereby compensating for the suspension stiffness and accurately adjusting the suspension stiffness to enable the vehicle to resist deformation as much as possible and improve vehicle driving stability.

[0060] Optionally, determining the tire stiffness according to the attribute information and the real-time status information based on a pre-trained tire stiffness detection model includes: uploading the attribute information and the real-time status information to a server, so that the server inputs the attribute information and the real-time status information into the pre-trained tire stiffness detection model to obtain the tire stiffness; and receiving the tire stiffness sent by the server.

[0061] The tire stiffness detection model can be deployed in the server, and the server calculates the tire stiffness based on the information. The server sends the calculated tire stiffness to the vehicle terminal. The vehicle terminal can be a smart vehicle terminal (TelematicBOX, T-BOX) in the Internet of Vehicles.

[0062] Among them, the vehicle terminal can obtain the real-time status information detected by in-vehicle sensors, such as tire pressure and temperature, through the bus, and send it to the server through the wireless network. The attribute information can be the information pre-stored in the vehicle terminal and sent to the server through the wireless network. It can also be that the vehicle terminal is associated with the user terminal, and the user terminal sends the attribute information and the corresponding relationship with the vehicle terminal to the server. The server queries the real-time status information sent by the vehicle terminal according to the corresponding relationship between the attribute information and the vehicle terminal, and establishes the corresponding relationship between the attribute information and the real-time status information, so as to calculate the tire stiffness of the vehicle to which the vehicle terminal belongs.

[0063] By calculating the tire stiffness through the server, the amount of calculation data of the vehicle terminal is reduced, the calculation efficiency and accuracy of the tire stiffness are improved, and at the same time, the acquisition cost of the tire stiffness of the vehicle terminal is reduced.

[0064] The technical solution of the embodiment of the present invention realizes precise control of the suspension by adjusting the deformation-resistant components of the controllable suspension, improves the accuracy of the suspension's resistance to deformation, and improves the driving stability of the vehicle.

[0065] Embodiment III

[0066] Figure 3 The present invention provides a flowchart of a training method for a stiffness detection model in Embodiment III. This embodiment is applicable to the situation of training a tire stiffness detection model. This method can be executed by a training device for the stiffness detection model. The training device for the stiffness detection model can be implemented in the form of hardware and / or software, and the training device for the stiffness detection model can be configured in an electronic device, such as a client or a server. Among them, the client can include a user terminal, a vehicle terminal, etc. As Figure 3 shown, the method includes:

[0067] S310. Obtain sample data, where the sample data includes attribute information, real-time status information, and average stiffness information of a sample tire.

[0068] The sample data is used to train the tire stiffness detection model. Specifically, the sample data can include attribute information of at least two sample tires of the same vehicle, the real-time status information of the vehicle during steady-state driving, and the average stiffness information calculated based on the attribute information and the real-time status information.

[0069] The average stiffness information refers to the stiffness information of at least two tires. In fact, it is impossible to accurately calculate the stiffness information of each tire, but the average value of the stiffness information of multiple tires can be calculated.

[0070] S320. Use the sample data to train the initial model to obtain a tire stiffness detection model.

[0071] The input of the initial model is the attribute information and real-time status information of the sample tire, and the output of the initial model is the tire stiffness of the sample tire. The initial model can be a machine learning model, specifically a neural network model. According to the tire stiffness and average stiffness information, a loss function is determined, and the initial model is trained according to the loss function, where the average stiffness information refers to the average stiffness of two tires, and the tire stiffness refers to the stiffness of a single tire. The stiffnesses of two tires can be constrained by the average stiffness of the two tires to calculate the loss function. For example, based on the difference between the average stiffness of two tires and the sum of the stiffnesses of the two tires, it is determined as the loss function. Exemplarily, the average stiffness information includes the average stiffness of the left tire, and the tire stiffness is the stiffness of the left front tire and the left rear tire. Calculate the sum of the stiffness of the left front tire and the left rear tire, and calculate the difference between the sum and the stiffness of the left tire to determine the loss function. In addition, the average stiffness information can also include the average stiffness of the right tire, the average stiffness of the front axle tires, and the average stiffness of the rear axle tires. The tire stiffness can include the stiffness of the left front tire, the stiffness of the left rear tire, the stiffness of the right front tire, and the stiffness of the right rear tire, etc. When the loss function is at the minimum value, or tends to be stable, or the number of iterations is greater than the set threshold, it is determined that the training of the initial model is completed, and the current initial model is determined as the tire stiffness detection model.

[0072] Optionally, the obtaining of the sample data includes: obtaining the real-time status information, where the real-time status information includes the tire pressure information and temperature information of the vehicle during the steady-state driving of the vehicle; obtaining the attribute information of the sample tire in the vehicle; calculating the average stiffness information of the sample tire during the steady-state driving of the vehicle; and determining the real-time status information, average stiffness information, and attribute information of the sample tire as the sample data.

[0073] The in-vehicle terminal detects the tire pressure of each tire through the sensors on the tires and determines it as the tire pressure information. The ambient temperature outside the vehicle can be detected through the sensors configured on the vehicle and determined as the temperature information. And the tire pressure information and temperature information are determined as the real-time status information of the sample tire. The server obtains the real-time status information sent by the in-vehicle terminal. The server obtains the attribute information sent by the in-vehicle terminal or the mobile phone client. The real-time status information and attribute information are used as the model input.

[0074] The average stiffness information can refer to the average stiffness information of the vehicle's tires under the condition of the obtained tire pressure information, temperature information, and attribute information. The average stiffness information can be calculated according to the existing stiffness calculation formula. The average stiffness information is used to detect the difference between the model output and the average stiffness information to train the model.

[0075] By determining real-time status information, average stiffness information, and attribute information as sample data to train a tire stiffness detection model, the detection accuracy of tire stiffness is improved, and different tire stiffnesses can be distinguished according to the real-time tire status and different tire types, thereby improving the accuracy of tire stiffness.

[0076] Optionally, calculating the average stiffness information of the sample tire during steady-state vehicle driving includes: calculating the deflection of the sample tire based on the body tilt angle, suspension height, ground slope, wheelbase, wheel radius, and ground clearance; and calculating the average stiffness information of the sample tire based on the deflection of the sample tire.

[0077] The body tilt angle can refer to the angle between the vehicle body and the ground, and can include pitch angle, roll angle, etc. The suspension height can refer to the height from the top end to the bottom end of the suspension. The vehicle wheelbase can refer to the distance between the center of the front axle and the center of the rear axle of the vehicle. The ground slope refers to the slope of the ground on which the vehicle is driving. The wheelbase refers to the distance between the centers of the front wheels, or the distance between the centers of the two rear wheels. The wheel radius can refer to the radius of the wheel, and usually the radii of the four wheels are the same. The ground clearance refers to the distance between the lowest point of the vehicle except the wheels and the ground. The deflection refers to the degree of tire deformation. The deflection of the sample tire includes: average deflection of the front axle wheels, average deflection of the rear axle wheels, deflection of the left wheels, and deflection of the right wheels. The average stiffness information includes average vertical stiffness of the front axle tires, average vertical stiffness of the rear axle tires, average vertical stiffness of the left wheels, and average vertical stiffness of the right wheels.

[0078] Among them, the road surface slope is obtained through a high-precision map, elevation map, or vehicle-mounted lidar; the suspension height and body tilt angle are obtained by receiving signals sent by the vehicle-mounted control node through the vehicle bus. Exemplarily, the suspension height can be detected according to a distance sensor installed at the top end of the suspension and a receiver installed at the bottom end of the suspension to detect the time when the distance sensor emits a signal. Another example is that linear Hall sensors can be installed at the center positions of the front and rear axles of the vehicle body, one at the front and one at the rear, and permanent magnets can be installed at the positions corresponding to the centers of the front and rear axles on the lower surface of the vehicle body chassis. When the vehicle body tilts, the shock-absorbing springs of the vehicle deform, causing the vehicle body to move up and down, resulting in a change in magnetic field strength. At this time, the Hall sensor outputs different voltage signals to the calculator according to different magnetic field strengths, thereby judging the deformation displacement of the shock-absorbing spring and further calculating the body tilt angle. In addition, there are other ways to detect the suspension height and body tilt angle, and no specific limitations are imposed on this.

[0079] When the vehicle is driving in a steady state, the main factors affecting the body tilt angle are road surface slope, suspension displacement, and tire vertical deformation, which can be expressed as follows:

[0080]

[0081] Among them, ω y Longitudinal tilt angle of the vehicle body; i x is the longitudinal slope of the road surface; H fl H is the height of the left front suspension; fr H is the height of the right front suspension; rl H is the height of the left rear suspension; rr is the right rear suspension height; L a is the vehicle wheelbase; f fl is the vertical deflection of the left front wheel; f fr is the vertical deflection of the right front wheel; f rl is the vertical deflection of the left rear wheel; f rr is the vertical deflection of the right rear wheel.

[0082] Similarly, the lateral tilt angle of the vehicle body should satisfy the following formula:

[0083]

[0084] Among them, ω x is the lateral tilt angle of the vehicle body; i y is the lateral slope of the road surface; L w The suspension height data is obtained from the vehicle bus and sent by the suspension height sensor.

[0085] The vehicle's actual ground clearance H can also be obtained through high-precision maps v , the ground clearance satisfies the following formula:

[0086] r w -(f rr +f rl +f fl +f fr ) / 4=H v -(H fl +H fr +H rl +H rr ) / 4

[0087] Among them, r w is the wheel radius.

[0088] By combining the above three equations, we can solve the average deflection of the vehicle's front axle wheels, the average deflection of the rear axle wheels, the average deflection of the left wheels, and the average deflection of the right wheels.

[0089] If the vehicle is equipped with a suspension vertical force sensor or smart tires, the vertical force of each wheel can be obtained from the vehicle bus, and the average vertical stiffness of each axle wheel is:

[0090]

[0091] Where: k fa is the average vertical stiffness of the front axle tire; kra is the average vertical stiffness of the rear axle tires; k lw is the average vertical stiffness of the left wheel; k rw is the average vertical stiffness of the right wheel; F fl is the vertical force of the left front wheel; F fr is the vertical force of the right front wheel; F rl is the vertical force of the left rear wheel; F rr is the vertical force of the right rear wheel.

[0092] During the steady - state driving of the vehicle, the tires rotate with real - time status information, and relevant information is calculated to obtain the average stiffness information, so as to accurately detect the average stiffness based on the tire pressure and the outside temperature of the vehicle, improve the accuracy rate of the average stiffness, thereby improving the representativeness of the sample data and the accuracy rate of the stiffness detection of the stiffness detection model.

[0093] In the embodiment of the present invention, by determining the attribute information, real - time status information, and average stiffness information of the vehicle as sample data, and using the sample data to train the initial model, the accuracy rate of the stiffness detection of the tire stiffness detection model can be improved. And because the stiffness information is difficult to accurately calculate, the generation complexity of the sample data can be reduced, the generation efficiency of the sample data can be improved, and the training efficiency of the tire stiffness detection model can be improved.

[0094] Embodiment 4

[0095] Figure 4 is a schematic diagram of an application scenario provided by Embodiment 4 of the present invention. Figure 5 is a scenario diagram of a suspension stiffness adjustment method provided by Embodiment 4 of the present invention. Figure 6 is a scenario diagram of a training method of a tire stiffness detection model provided by Embodiment 4 of the present invention.

[0096] As Figure 4 shown, the vehicle system includes an in - vehicle sensor 410, a wireless gateway 420, and a suspension controller 440. The vehicle system communicates with a server 430. Among them, the in - vehicle sensor 410 detects sensor information as real - time status information and transmits it to the server 430 through the wireless gateway 420. The server 430 obtains the tire stiffness based on the real - time status information and forwards it to the suspension controller 440 through the wireless gateway 420. The suspension controller 440 calculates the adjustment amount of the suspension stiffness according to the tire stiffness and controls the adjustment of the suspension stiffness.

[0097] As Figure 5 shown, the suspension stiffness adjustment method is specifically:

[0098] S510, obtain the attribute information of the current tires of the vehicle in the user's mobile application.

[0099] S520, The server checks whether there is a tire rigidity detection model. If so, it executes S550; otherwise, it executes S530.

[0100] S530, The in-vehicle terminal uploads the tire pressure information, the outside temperature information, and the average rigidity information of the four wheels.

[0101] S540, The server generates sample data, trains to obtain a tire rigidity detection model, and returns to execute S520.

[0102] S550, Through the in-vehicle terminal, upload the tire pressure information and the outside temperature information of the four wheels.

[0103] S560, The server calculates the current tire rigidity of the four wheels according to the tire rigidity detection model corresponding to the attribute information.

[0104] S570, The server sends the tire rigidity to the in-vehicle terminal to control the suspension controller to adjust the suspension stiffness.

[0105] Specifically, according to the tire rigidity, the adjustment amount is calculated by the following formula:

[0106] Suspension control is based on the current tire vertical stiffness data obtained from the cloud. If the standard tire stiffness of the front axle used during vehicle development is k fs and the standard tire stiffness of the rear axle is k rs , then the adjustment amount of the suspension stiffness is:

[0107]

[0108] where k sfl is the adjustment amount of the left front suspension stiffness; k sfr is the adjustment amount of the right front suspension stiffness; k srl is the adjustment amount of the left rear suspension stiffness; k srr is the adjustment amount of the right rear suspension stiffness.

[0109] The suspension stiffness adjustment amount can be combined with other suspension control methods to improve the consistency of the vehicle's vertical vibration performance and enhance the user's riding experience.

[0110] As Figure 6 shown, in the server, the training method of the tire rigidity detection model can be:

[0111] S610, Obtain the average rigidity information.

[0112] S620, Obtain the tire size and model.

[0113] S630, Obtain the current temperature and tire pressure.

[0114] S640, Train the neural network model.

[0115] S650, a tire stiffness detection model is trained.

[0116] Select the average stiffness information under the steady-state condition of the vehicle, real-time state information such as the tire pressure and temperature information at the current moment, and the attribute information of the vehicle's tires, and send them to the cloud server through the in-vehicle wireless gateway. A label of "tire brand - tire model - tire pressure - temperature - stiffness" can be formed on the server side, and the label is stored in the training dataset. When the size of the dataset meets the preset data volume threshold, using the tire brand, tire model, tire pressure, and temperature as inputs and the stiffness as the output, an artificial neural network is used for training to generate a tire stiffness detection model for specific brands and models, realizing accurate identification of tire stiffness.

[0117] Embodiment Five

[0118] Figure 7 It is a structural schematic diagram of a suspension stiffness adjustment device provided by Embodiment Five of the present invention. As Figure 7 shown, the device includes: an input information acquisition module 701, a tire stiffness acquisition module 702, and a suspension stiffness adjustment module 703.

[0119] Among them, the input information acquisition module 701 is used to acquire the attribute information and real-time state information of the tire;

[0120] The tire stiffness acquisition module 702 is used to obtain the tire stiffness based on the pre-trained tire stiffness detection model according to the attribute information and the real-time state information;

[0121] The suspension stiffness adjustment module 703 is used to calculate the adjustment amount according to the tire stiffness and adjust the suspension stiffness.

[0122] The technical solution of the embodiment of the present invention realizes compensation for the influence of uncontrollable tires on the suspension stiffness by acquiring the attributes and real-time states of the tires, calculating the tire stiffness, calculating the adjustment amount, and adjusting the suspension stiffness, ensuring the consistency of vehicle vertical vibration, enabling the controllable suspension to achieve the controllable function, improving the ability of the suspension to resist deformation, and thus improving the ride comfort of the vehicle.

[0123] Further, the suspension stiffness adjustment module 703 includes: a controllable suspension rigidity adjustment unit, which is used to adjust the deformation-resistant components of the controllable suspension according to the adjustment amount.

[0124] Further, the suspension stiffness adjustment module 703 includes: an adjustment amount calculation unit, which is used to obtain the standard stiffness of the vehicle to which the tire belongs; calculate the adjustment amount according to the standard stiffness and the tire stiffness.

[0125] The suspension stiffness adjustment device provided by the embodiments of the present invention can execute the suspension stiffness adjustment method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0126] Embodiment Six

[0127] Figure 8 It is a schematic structural diagram of a training device for a stiffness detection model provided by Embodiment Six of the present invention. As Figure 8 shown, the device includes: a sample data acquisition module 801 and a model training module 802.

[0128] Among them, the sample data acquisition module 801 is used to acquire sample data, and the sample data includes attribute information, real-time state information, and average stiffness information of a sample tire;

[0129] The model training module 802 is used to train the initial model with the sample data to obtain a tire stiffness detection model.

[0130] In the embodiments of the present invention, by determining the attribute information, real-time state information, and average stiffness information of a vehicle as sample data, and using the sample data to train the initial model, the rigidity detection accuracy of the tire stiffness detection model can be improved. And since the stiffness information is difficult to accurately calculate, the generation complexity of the sample data can be reduced, the generation efficiency of the sample data can be improved, and the training efficiency of the tire stiffness detection model can be improved.

[0131] Further, the sample data acquisition module 801 includes: a real-time state information acquisition unit for acquiring the real-time state information, where the real-time state information includes the tire pressure information and temperature information of the vehicle during the steady-state driving of the vehicle; an attribute information acquisition unit for acquiring the attribute information of the sample tire in the vehicle; an average stiffness information calculation unit for calculating the average stiffness information of the sample tire during the steady-state driving of the vehicle; and a sample data generation unit for determining the real-time state information, average stiffness information, and attribute information of the sample tire as the sample data.

[0132] Further, the average stiffness information calculation unit is specifically used for: calculating the deflection of the sample tire according to the body tilt angle, suspension height, ground slope, wheelbase, wheel radius, and ground clearance; and calculating the average stiffness information of the sample tire according to the deflection of the sample tire.

[0133] The training device for the stiffness detection model provided by the embodiments of the present invention can execute the training method for the stiffness detection model provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0134] Embodiment Seven

[0135] Figure 9 FIG. 2 shows a schematic structural diagram of an electronic device 10 that can be used to implement an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0136] As Figure 9 shown, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. The memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0137] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0138] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the suspension stiffness adjustment method or the training method of the stiffness detection model.

[0139] In some embodiments, the suspension stiffness adjustment method or the training method of the stiffness detection model may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed onto the electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by the processor 11, one or more steps of the suspension stiffness adjustment method or the training method of the stiffness detection model described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the suspension stiffness adjustment method or the training method of the stiffness detection model by any other suitable means (e.g., by means of firmware).

[0140] The various embodiments of the systems and techniques described above in this document may be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGA), application specific integrated circuits (ASIC), application specific standard products (ASSP), systems on a chip (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that may be executed and / or interpreted 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 a storage system, at least one input device, and at least one output device, and transmits the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0141] The computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer programs 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.

[0142] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage 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. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0143] To provide for interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can also be used to provide for interaction with the user; for example, 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, speech input, or tactile input).

[0144] The systems and techniques described herein can be implemented in a computing system that includes backend components (such as, for example, a data server), or a computing system that includes middleware components (such as, for example, an application server), or a computing system that includes frontend components (such as, for example, 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 by any form or medium of digital data communication (such as, for example, a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0145] A computing 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 client-server relationship is created by computer programs running on respective computers and having a client-server relationship with each other. The server can 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, and solves the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0146] It should be understood that various forms of processes shown above can be used, steps can be reordered, added or deleted. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.

[0147] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. 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 principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for adjusting suspension stiffness, characterized in that, it includes: Obtain the attribute information and real-time status information of the tire; Based on the attribute information and the real-time status information, and based on a pre-trained tire stiffness detection model, obtain the tire stiffness; According to the tire stiffness, calculate the adjustment amount and adjust the suspension stiffness; The calculating the adjustment amount according to the tire stiffness includes: Obtain the standard stiffness of the vehicle to which the tire belongs; Calculate the adjustment amount according to the standard stiffness and the tire stiffness; wherein, the tire stiffness and the suspension stiffness are inversely proportional.

2. The method according to claim 1, characterized in that, the adjusting the suspension stiffness includes: According to the adjustment amount, adjust the deformation resistance component of the controllable suspension.

3. A method for training a stiffness detection model, characterized in that, it includes: Obtain sample data, where the sample data includes the attribute information, real-time status information and average stiffness information of the sample tire; Use the sample data to train an initial model to obtain a tire stiffness detection model; Calculating the average stiffness information includes: According to the body tilt angle, suspension height, ground slope, wheelbase, wheel radius and ground clearance, calculate the deflection of the sample tire; According to the deflection of the sample tire, calculate the average stiffness information of the sample tire.

4. The method according to claim 3, characterized in that, the obtaining the sample data includes: Obtain the real-time status information, where the real-time status information includes the tire pressure information and temperature information of the vehicle during steady-state driving of the vehicle; Obtain the attribute information of the sample tire in the vehicle; Calculate the average stiffness information of the sample tire during steady-state driving of the vehicle; Determine the real-time status information, average stiffness information and attribute information of the sample tire as the sample data.

5. A suspension stiffness adjustment device, characterized in that, it includes: An input information acquisition module for obtaining the attribute information and real-time status information of the tire; A tire stiffness acquisition module for obtaining the tire stiffness based on the attribute information and the real-time status information and based on a pre-trained tire stiffness detection model; A suspension stiffness adjustment module for calculating the adjustment amount according to the tire stiffness and adjusting the suspension stiffness; The suspension stiffness adjustment module includes: An adjustment amount calculation unit for obtaining the standard stiffness of the vehicle to which the tire belongs; calculating the adjustment amount according to the standard stiffness and the tire stiffness; wherein, the tire stiffness and the suspension stiffness are inversely proportional.

6. A training device for a stiffness detection model, characterized in that, it includes: A sample data acquisition module for obtaining sample data, where the sample data includes the attribute information, real-time status information and average stiffness information of the sample tire; A model training module for using the sample data to train an initial model to obtain a tire stiffness detection model; An average stiffness information calculation unit for calculating the deflection of the sample tire according to the body tilt angle, suspension height, ground slope, wheelbase, wheel radius and ground clearance; calculating the average stiffness information of the sample tire according to the deflection of the sample tire.

7. An electronic device, characterized in that, the electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores a computer program executable by the at least one processor, and when the computer program is executed by the at least one processor, the at least one processor is enabled to execute the suspension stiffness adjustment method according to any one of claims 1-2, or execute the training method of the stiffness detection model according to any one of claims 3-4.

8. A computer-readable storage medium, characterized in that, the computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the suspension stiffness adjustment method according to any one of claims 1-2 is implemented, or the training method of the stiffness detection model according to any one of claims 3-4 is executed.

Images