Friction compensation method, device and equipment for steering system and storage medium

Abstract

The invention discloses a friction compensation method, device and equipment of a steering system and a storage medium, relates to the technical field of electric power steering systems, and can realize continuous updating of friction compensation of the steering system so as to improve the accuracy of the friction compensation of the steering system. According to the specific scheme, the current tubular column angle and the current rotating speed of the steering system are obtained; inputting the current tubular column angle and the current rotating speed into a preset target neural network model, and predicting to obtain a current friction torque of the steering system; wherein the target neural network model is a neural network model based on a radial basis function, the target neural network model is obtained by training historical data of a steering system, and the historical data comprises historical tubular column angles and corresponding historical rotating speeds of multiple groups of steering processes; the current friction torque is input into a preset steering system motion equation, and the current friction compensation torque of the steering system is obtained; and performing friction compensation on the steering system according to the friction compensation torque.

Description

Technical Field

[0001] The present application relates to the technical field of electric power steering systems, and particularly to a method, device, equipment and storage medium for friction compensation of a steering system. Background Art

[0002] Electric Power Steering (EPS) has been widely used in automotive steering technology. Since the entire steering system has multiple transmission devices, the resistance torque caused by friction in the transmission pair during steering wheel operation is inevitable. And during the manufacturing process, usually each friction force is random within a certain range. As the service time of the steering system increases, wear occurs inside the steering system, which may make the feel of the steering system become heavier. Therefore, it is necessary to compensate for the friction of the steering system.

[0003] Currently, generally, the friction force of the steering system is compensated by a fixed friction compensation curve. However, as the components in the steering system age, the friction coefficient in the steering system will change accordingly. The original friction compensation curve will not provide sufficient advantages in driving experience, and there may be a risk of sudden changes in the force on the steering wheel due to inaccurate use of the friction model, resulting in the hysteresis characteristics of the friction force. This is very serious for the experience and safety requirements during intelligent driving, especially autonomous driving. Therefore, a method for friction compensation of the steering system that can be continuously updated is needed. Summary of the Invention

[0004] The present application provides a method, device, equipment and storage medium for friction compensation of a steering system, which can achieve continuous update of the friction compensation of the steering system, and thus can improve the accuracy of the friction compensation of the steering system.

[0005] To achieve the above object, the present application adopts the following technical solutions:

[0006] In the first aspect of the embodiments of the present application, a method for friction compensation of a steering system is provided, and the method includes:

[0007] Obtain the current column angle and the current rotation speed of the steering system;

[0008] Input the current column angle and the current rotation speed into a preset target adaptive neural network control model to predict the current friction torque of the steering system;

[0009] Wherein, the target adaptive neural network control model is a neural network model based on a radial basis function for optimizing the adaptive control rate, and the target neural network model is trained using historical data of the steering system, and the historical data includes: multiple groups of historical column angles and corresponding historical rotation speeds;

[0010] Input the current frictional torque into a preset adaptive control steering system model to obtain the current friction compensation torque of the steering system;

[0011] Perform friction compensation on the steering system according to the friction compensation torque.

[0012] As a possible implementation, before obtaining the current column angle and current rotational speed of the steering system, the method further includes:

[0013] Obtain historical data of the steering system, where the historical data includes: historical column angles and corresponding historical rotational speeds of multiple steering processes;

[0014] Perform N training processes on the neural network model using the historical data until a preset condition is met, then obtain the target neural network model;

[0015] Wherein, the i-th model training process includes, i≥1, and i is a positive integer:

[0016] Input a set of historical column angles and corresponding rotational speeds into the current neural network model to obtain the predicted frictional torque of the steering system;

[0017] Input the predicted frictional torque into the motion equation of the adaptive control steering system to obtain the corresponding predicted friction compensation torque;

[0018] Determine the error between the response of the adaptive control steering system with the predicted friction compensation torque and the ideal steering system;

[0019] If the error is less than a preset threshold, then use the current adaptive neural network control model as the target adaptive neural network control model.

[0020] As a possible implementation, the motion equation of the steering system is:

[0021]

[0022] Where, T a is the resultant force of the basic motor assist torque and the hand force in the steering system, T f is the frictional torque, T comp is the friction compensation torque, c is the system damping coefficient, is the rotational speed, J is the moment of inertia of the steering system, is the column angular acceleration.

[0023] As a possible implementation, the target neural network model includes a prediction function, and the prediction function includes a Gaussian basis function; inputting the current pipe string angle and the current rotation speed into a preset target neural network model to predict the current friction torque of the steering system includes:

[0024] Calculating the current friction torque of the steering system by using the prediction function in the target neural network model;

[0025] The prediction function is:

[0026] T f =ω T h(x)+ε

[0027]

[0028] where T f is the friction torque, ω T is the transpose matrix of the model weight matrix, ε is the approximation error of the model, h(x) is the Gaussian basis function, q is the pipe string angle, is the rotation speed, c i is the center value of the i-th basis function, with the same dimension as the input quantity, and b j is a parameter representing the width of the function.

[0029] As a possible implementation, after using the current neural network model as the target neural network model, the method further includes:

[0030] Determining the mapping relationships among a plurality of different pipe string angles, rotation speeds, and friction compensation torques;

[0031] Determining the mapped friction compensation torque corresponding to the current vehicle speed, the current pipe string angle, and the current rotation speed according to the mapping relationships.

[0032] As a possible implementation, after determining the mapped friction compensation torque corresponding to the current pipe string angle and the current rotation speed according to the mapping relationships, the method further includes:

[0033] If the difference between the system response of the adaptive control system of the current friction compensation torque model and the response in the ideal state is greater than a preset threshold, retraining the target adaptive neural network control model.

[0034] As a possible implementation, before obtaining the current pipe string angle and the current rotation speed of the steering system, the method further includes:

[0035] Obtaining the current vehicle speed, the current steering wheel angle, and the current angular velocity of the steering wheel rotation;

[0036] If the current vehicle speed, the steering wheel angle, and the current angular velocity of the steering wheel rotation are all within the corresponding threshold ranges, obtain the current column angle and the current rotation speed of the steering system.

[0037] In a second aspect of the embodiments of the present application, a steering system friction compensation device is provided. The device includes:

[0038] An acquisition module, configured to acquire the current column angle and the current rotation speed of the steering system;

[0039] A prediction module, configured to input the current column angle and the current rotation speed into a preset target neural network model to predict the current friction torque of the steering system;

[0040] Wherein, the target neural network model is a neural network model based on a radial basis function, and the target neural network model is trained using historical data of the steering system. The historical data includes: historical column angles and corresponding historical rotation speeds of multiple steering processes;

[0041] A determination module, configured to input the current friction torque into a preset adaptive control steering system model to obtain the current friction compensation torque of the steering system;

[0042] A processing module, configured to perform friction compensation on the steering system according to the friction compensation torque.

[0043] In a third aspect of the embodiments of the present application, an electronic device is provided, including a memory and a processor. The memory stores a computer program, and when the computer program is executed by the processor, the steering system friction compensation method in the first aspect of the embodiments of the present application is implemented.

[0044] In a fourth aspect of the embodiments of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steering system friction compensation method in the first aspect of the embodiments of the present application is implemented.

[0045] The beneficial effects brought by the technical solutions provided by the embodiments of the present application at least include:

[0046] The steering system friction compensation method based on adaptive neural network control provided by the embodiments of the present application obtains the current vehicle speed, current column angle, and current rotation speed of the steering system, and inputs the current column angle and the current rotation speed into a preset target neural network model to predict the current friction torque of the steering system; wherein, the target neural network model is a neural network model based on radial basis functions, and the target neural network model is a neural network model based on radial basis functions. The target neural network model is trained using the historical data of the steering system. The historical data includes multiple groups of historical column angles and corresponding historical rotation speeds, and is used to input the current friction torque into a preset adaptive control steering system model to obtain the current friction compensation torque of the steering system. Finally, the steering system is friction-compensated according to the friction compensation torque, so that continuous update of the steering system friction compensation can be realized, and thus the accuracy of the steering system friction compensation can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a flowchart of a steering system friction compensation method provided by an embodiment of the present application;

[0048] Figure 2 It is a structural diagram of a steering system friction compensation device provided by an embodiment of the present application;

[0049] Figure 3 It is a structural diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0050] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0051] Hereinafter, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present disclosure, unless otherwise stated, "a plurality" means two or more.

[0052] In addition, the use of "based on" or "according to" means open and inclusive, because a process, step, calculation, or other action "based on" or "according to" one or more conditions or values can in practice be based on additional conditions or values beyond.

[0053] An embodiment of the present application provides a method for friction compensation of a steering system, as Figure 1 shown. The method includes the following steps:

[0054] Step 101: Obtain the current column angle and the current rotation speed of the steering system.

[0055] Among them, the column of the steering system is an important part of the steering system, mainly used to control the driving direction of the vehicle, transmit torque, absorb the energy during vehicle impact, and provide a comfortable driving experience for the driver.

[0056] The current rotation speed is the column rotation speed corresponding to the current column angle. Adjusting the column angle can ensure that the driver is in a comfortable and safe position when operating the steering wheel, thereby improving driving convenience and safety. In addition, the adjustment of the column angle of the steering column also involves certain mechanical requirements, such as the steering column height adjustment force and the holding force, etc., to ensure that unnecessary burdens are not imposed on the driver during the adjustment process.

[0057] Step 102: Input the current column angle and the current rotation speed into a preset target neural network model to predict the current friction torque of the steering system.

[0058] Among them, the target neural network model is a neural network model based on the Radial Basis Function (RBF). The target neural network model is trained using the historical data of the steering system. The historical data includes: multiple groups of historical column angles and corresponding historical rotation speeds during the steering process. The network structure of the RBF neural network model includes an input layer, a hidden layer, and an output layer.

[0059] Step 103: Input the current friction torque into a preset motion equation of the steering system to obtain the current friction compensation torque of the steering system.

[0060] Step 104: Perform friction compensation on the steering system according to the friction compensation torque.

[0061] The steering system friction compensation method provided by the embodiments of the present application obtains the current column angle and the current rotation speed of the steering system, and inputs the current column angle and the current rotation speed into a preset target neural network model to predict the current friction torque of the steering system; wherein, the target neural network model is a neural network model based on a radial basis function, and the target neural network model is trained using the historical data of the steering system, and the historical data includes: multiple sets of historical column angles and corresponding historical rotation speeds during the steering process, and is used to input the current friction torque into a preset adaptive control steering system equation to obtain the current friction compensation torque of the steering system, and finally perform friction compensation on the steering system according to the friction compensation torque, so as to realize the continuous update of the steering system friction compensation, and further improve the accuracy of the steering system friction compensation.

[0062] Optionally, before obtaining the current column angle and the current rotation speed of the steering system, the method further includes:

[0063] Obtain the historical data of the steering system, where the historical data includes: multiple sets of historical column angles and corresponding historical rotation speeds during the steering process; use the historical data to perform N training processes on the neural network model respectively within different vehicle speed ranges until the preset conditions are met, then the target adaptive neural network control model is obtained;

[0064] Wherein, the i-th model training process includes, i≥1, and i is a positive integer:

[0065] Input a historical column angle and a corresponding historical rotation speed into the current neural network model to obtain the predicted friction torque of the steering system;

[0066] Input the predicted friction torque into the steering system motion equation to obtain the corresponding predicted friction compensation torque;

[0067] Determine the error between the predicted friction torque and the predicted friction compensation torque;

[0068] If the error is less than the preset threshold, then use the current neural network model as the target neural network model.

[0069] Wherein, the above steering system motion equation can be:

[0070]

[0071] Wherein, T a is the resultant force of the basic assist torque of the motor and the hand force in the steering system, T f is the friction torque, T compis the friction compensation torque, c is the system damping coefficient, is the rotational speed, J is the moment of inertia of the steering system, is the angular acceleration of the pipe string.

[0072] In addition, the target neural network model includes a prediction function, and the prediction function includes a Gaussian basis function; the step of inputting the current pipe string angle and the current rotational speed into a preset target neural network model to predict the current frictional torque of the steering system includes:

[0073] Calculating the current frictional torque of the steering system by using the prediction function in the target neural network model;

[0074] The prediction function is:

[0075] T f = ω T h(x) + ε

[0076]

[0077] where T f is the frictional torque, ω T is the transpose matrix of the model weight matrix, ε is the approximation error of the model, h(x) is the Gaussian basis function, q is the pipe string angle, is the rotational speed, c i is the center value of the i-th basis function, with the same dimension as the input quantity, b j is a parameter representing the width of the function.

[0078] Optionally, after using the current neural network model as the target neural network model, the method further includes:

[0079] Determining the mapping relationships among a plurality of different pipe string angles, rotational speeds, and friction compensation torques, and determining the mapped friction compensation torque corresponding to the current pipe string angle and the current rotational speed according to the mapping relationships.

[0080] That is to say, the method of steps 101 to 104 can be used to calculate the friction compensation torques corresponding to different pipe string angles and rotational speeds under multiple working conditions, so as to obtain the mapping relationships among a plurality of different pipe string angles, rotational speeds, and friction compensation torques. In this way, the mapped friction compensation torque corresponding to the current pipe string angle and the current rotational speed can be determined according to the mapping relationships in the subsequent process.

[0081] Optionally, before obtaining the current pipe string angle and the current rotational speed of the steering system, the method further includes:

[0082] Obtaining the current vehicle speed, the current steering wheel angle, and the current angular velocity of the steering wheel rotation;

[0083] If the current vehicle speed, the steering wheel angle, and the current angular velocity of the steering wheel rotation are all within the corresponding threshold ranges, obtain the current column angle and the current rotational speed of the steering system.

[0084] Among them, the threshold range of the current vehicle speed is from the minimum limit value of the vehicle speed to the maximum limit value of the vehicle speed. The absolute value of the steering wheel angle is less than the maximum limit value of the steering wheel angle. The angular velocity of the steering wheel rotation is greater than the minimum limit value of the angular velocity of the steering wheel rotation and less than the maximum limit value of the angular velocity of the steering wheel rotation.

[0085] After detecting that the current vehicle speed, the steering wheel angle, and the current angular velocity of the steering wheel rotation are all within the corresponding threshold ranges, step 101 can be executed to implement the steering system friction compensation method, thereby improving the safety of the steering system friction compensation.

[0086] The steering system friction compensation method provided by the embodiments of the present application obtains the current column angle and the current rotational speed of the steering system, and inputs the current column angle and the current rotational speed into a preset target neural network model to predict the current friction torque of the steering system; among them, the target neural network model is a neural network model based on a radial basis function, and the target neural network model is trained using historical data of the steering system. The historical data includes: historical column angles and corresponding historical rotational speeds of multiple steering processes. Then, the current friction torque is input into a preset steering system motion equation to obtain the current friction compensation torque of the steering system. Finally, the steering system is friction-compensated according to the friction compensation torque, so that continuous update of the steering system friction compensation can be realized, and further, the accuracy of the steering system friction compensation can be improved. Compared with the traditional method of taking the average value or a fixed value of the friction force detection at different positions, the present application calculates the friction torque of the steering system more accurately, reducing the influence of manufacturing errors on the accuracy of the steering friction compensation. In addition, the friction compensation method of the present application has better platform applicability, reducing the dependence on the calibration technology to a certain extent. Adaptive control can calculate more stably and quickly, and has better robustness than linear control, making the driving feel smoother and the control more accurate, and can be used in the case of hands-off driving.

[0087] The embodiments of the present application provide a steering system friction compensation device, as Figure 2 shown, the device includes:

[0088] An acquisition module 11, configured to acquire the current column angle and the current rotational speed of the steering system;

[0089] A prediction module 12, configured to input the current column angle and the current rotational speed into a preset target neural network model to predict the current friction torque of the steering system;

[0090] Among them, the target neural network model is a neural network model based on radial basis functions, and the target neural network model is trained using historical data of the steering system. The historical data includes: historical string angles and corresponding historical rotational speeds during multiple steering processes.

[0091] A determination module 13, configured to input the current frictional torque into a preset steering system motion equation to obtain the current friction compensation torque of the steering system.

[0092] A processing module 14, configured to perform friction compensation on the steering system according to the friction compensation torque.

[0093] In one embodiment, the device further includes a training module 15, and the training module 15 is configured to:

[0094] Obtain historical data of the steering system. The historical data includes: historical string angles and corresponding historical rotational speeds during multiple steering processes.

[0095] Perform N training processes on the neural network model using the historical data until a preset condition is met, and then obtain the target neural network model.

[0096] Among them, the i-th model training process includes, where i ≥ 1 and i is a positive integer:

[0097] Input a historical string angle and a corresponding historical rotational speed into the current neural network model to obtain the predicted frictional torque of the steering system.

[0098] Input the predicted frictional torque into the steering system motion equation to obtain the corresponding predicted friction compensation torque.

[0099] Determine the error between the predicted frictional torque and the predicted friction compensation torque.

[0100] If the error is less than a preset threshold, use the current neural network model as the target neural network model.

[0101] In one embodiment, the steering system motion equation is:

[0102]

[0103] Among them, T a is the resultant force of the motor basic assist torque and the hand force in the steering system, T f is the frictional torque, T comp is the friction compensation torque, c is the system damping coefficient, is the rotational speed, J is the moment of inertia of the steering system, is the angular acceleration of the pipe string.

[0104] In one embodiment, the target neural network model includes a prediction function, and the prediction function includes a Gaussian basis function; the prediction module 12 is specifically configured to:

[0105] Calculate the current frictional torque of the steering system by using the prediction function in the target neural network model;

[0106] The prediction function is:

[0107] T f = ω T h(x) + ε

[0108]

[0109] where T f is the frictional torque, ω T is the transpose matrix of the model weight matrix, ε is the approximation error of the model, h(x) is the Gaussian basis function, q is the pipe string angle, is the rotational speed, c i is the central value of the i-th basis function, with the same dimension as the input quantity, b j is a parameter representing the width of the function.

[0110] In one embodiment, the processing module 14 is further configured to:

[0111] Determine the mapping relationships among multiple different pipe string angles, rotational speeds, and friction compensation torques;

[0112] Determine the mapped friction compensation torque corresponding to the current pipe string angle and the current rotational speed according to the mapping relationships.

[0113] In one embodiment, the processing module 14 is further configured to:

[0114] If the difference between the current friction compensation torque and the mapped friction compensation torque determined according to the mapping relationships at the same pipe string angle and the same rotational speed is greater than a preset threshold, retrain the target neural network model.

[0115] In one embodiment, the acquisition module 11 is further configured to:

[0116] Acquire the current vehicle speed, the current steering wheel angle, and the current angular velocity of the steering wheel rotation;

[0117] If the current vehicle speed, the steering wheel angle, and the current angular velocity of the steering wheel rotation are all within the corresponding threshold ranges, acquire the current pipe string angle and the current rotational speed of the steering system.

[0118] The steering system friction compensation device provided in this embodiment can execute the above-mentioned embodiment of the steering system friction compensation method. The implementation principle and technical effects are similar, and will not be elaborated here.

[0119] For the specific limitations of the steering system friction compensation device, reference can be made to the limitations on the steering system friction compensation method in the above text, which will not be elaborated here. Each module in the above-mentioned steering system friction compensation device can be implemented in whole or in part by software, hardware, and their combination. The above-mentioned modules can be embedded in the processor of the electronic device in hardware form or be independent of it, or be stored in the memory of the electronic device in software form, so as to facilitate the processor to call and execute the operations corresponding to the above-mentioned modules.

[0120] The execution subject of the steering system friction compensation method provided in the embodiments of this application can be an electronic device, which can be a computer device, a terminal device, a server, or a server cluster. The embodiments of this application do not make specific limitations on this.

[0121] Figure 3 It is a schematic internal structure diagram of an electronic device provided in the embodiments of this application. As Figure 3 shown, the electronic device includes a processor and a memory connected through a system bus. Among them, the processor is used to provide computing and control capabilities. The memory may include a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The computer program can be executed by the processor to implement the steps of the steering system friction compensation method provided in the above-mentioned various embodiments. The internal memory provides a high-speed cache operating environment for the operating system and computer program in the non-volatile storage medium.

[0122] Those skilled in the art can understand that Figure 3 the internal structure diagram of the electronic device shown in

[0123] is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the electronic device to which the solution of this application is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine some components, or have a different component layout.

[0124] In another embodiment of this application, a computer-readable storage medium is further provided, on which a computer program is stored. When the computer program is executed by a processor, it implements the steps of the steering system friction compensation method as in the embodiments of this application.

[0125] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using a software program, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer execution instructions are loaded and executed on a computer, the processes or functions according to the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from a website, computer, server, or data center to another website, computer, server, or data center by wire (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more media integrated therein. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)), etc.

[0126] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0127] The above embodiments only represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the appended claims.

Claims

1. A method for friction compensation of a steering system, characterized in that, The method includes: Obtaining the current column angle and current rotational speed of the steering system; Inputting the current column angle and the current rotational speed into a preset target adaptive neural network controller to predict the current frictional torque of the steering system; Wherein, the target neural network model is a neural network model based on a radial basis function, and the target neural network model is trained using historical data of the steering system, and the historical data is: multiple sets of column angles and rotational speeds collected during multiple historical steering processes; Inputting the current frictional torque into a preset adaptive control steering system model to obtain the current friction compensation torque of the steering system; Performing friction compensation on the steering system according to the friction compensation torque.

2. The method according to claim 1, wherein Before obtaining the current column angle and current rotational speed of the steering system, the method further includes: Obtaining historical data of the steering system, where the historical data includes: multiple sets of historical column angles and corresponding historical rotational speeds of the steering process; Performing N training processes on the neural network model using the historical data until a preset condition is met, then obtaining the target neural network model; Wherein, the i-th model training process includes, i≥1 and i is a positive integer: Inputting a set of historical column angles and corresponding rotational speeds into the current neural network model to obtain the predicted frictional torque of the steering system; Inputting the predicted frictional torque into the motion equation of the adaptive control steering system to obtain the corresponding predicted friction compensation torque; Determining the error between the adaptive control steering system with the predicted friction compensation torque and the response of the ideal steering system; If the error is less than a preset threshold, then using the current adaptive neural network control model as the target adaptive neural network control model.

3. The method according to claim 1 or 2, characterized in that The motion equation of the steering system is: Among them, T a is the resultant force of the motor basic assist torque and the hand force in the steering system, T f is the frictional torque, T comp is the friction compensation torque, c is the damping coefficient of the steering system, is the rotational speed, J is the moment of inertia of the steering system, is the angular acceleration.

4. The method according to claim 1, wherein The target neural network model includes a prediction function, and the prediction function includes a Gaussian basis function; inputting the current column angle and the current rotational speed into the preset target neural network model to predict the current frictional torque of the steering system includes: Using the prediction function in the target neural network model to calculate the current frictional torque of the steering system; The prediction function is: T f = ω T h(x) + ε where, T f is the frictional torque, ω T is the transpose matrix of the model weight matrix, ε is the approximation error of the model, h(x) is the Gaussian basis function, q is the pipe string angle, is the pipe string rotation speed, c i is the central value of the i-th function, b j is the parameter representing the width of the function.

5. The method according to claim 2, characterized in that After using the current neural network model as the target neural network model, the method further includes: Determining the mapping relationships among multiple different column angles, rotational speeds, and friction compensation torques; Determining the mapped friction compensation torque corresponding to the current vehicle speed, current column angle, and current rotational speed according to the mapping relationships.

6. The method according to claim 5, wherein After determining the mapped friction compensation torque corresponding to the current column angle and current rotational speed according to the mapping relationships, the method further includes: If the difference between the system response of the adaptive control system of the current friction compensation torque model and the response in the ideal state is greater than a preset threshold, then retraining the target neural network model.

7. The method according to claim 1, characterized in that, Before obtaining the current column angle and current rotational speed of the steering system, the method further includes: Obtaining the current vehicle speed, current steering wheel angle, and current angular velocity of the steering wheel rotation; If the current vehicle speed, the steering wheel angle, and the current angular velocity of the steering wheel rotation are all within the corresponding threshold ranges, obtain the current column angle and the current rotational speed of the steering system.

8. A steering system friction compensation device, characterized in that, The device includes: an acquisition module, configured to acquire the current column angle and the current rotational speed of the steering system; a prediction module, configured to input the current column angle and the current rotational speed into a preset target neural network model to predict the current frictional torque of the steering system; wherein the target neural network model is a neural network model based on a radial basis function, and the target neural network model is trained using historical data of the steering system, and the historical data includes: historical column angles and corresponding historical rotational speeds of multiple steering processes; a determination module, configured to input the current frictional torque into a preset adaptive control steering system model to obtain the current friction compensation torque of the steering system; a processing module, configured to perform friction compensation on the steering system according to the friction compensation torque.

9. An electronic device, characterized in that, comprises a memory and a processor, the memory stores a computer program, and when the computer program is executed by the processor, it implements the steering system friction compensation method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, stores a computer program thereon, and when the computer program is executed by a processor, it implements the steering system friction compensation method according to any one of claims 1 to 7.

Images