An electric vehicle wheel slip prediction method and system

Abstract

This invention relates to the field of automotive technology, specifically to a method and system for predicting wheel slippage in electric vehicles. The method includes: acquiring various types of data from different road surfaces and driving electric vehicles; obtaining a set of all data units based on these data types; offline training of a neural network model using all data units to obtain a trained model; porting the trained model to a motor MCU controller; inputting the electric vehicle's data unit set into the motor MCU controller to predict wheel slippage; and when wheel slippage occurs, implementing torque reduction and torque transfer measures on the drive motor of the wheel exhibiting slippage tendency via the VCU. This invention improves driving safety and vehicle controllability through the predictive analysis of electric vehicle wheel slippage, and also enhances the user experience.

Description

Technical Field

[0001] This invention relates to the field of automotive technology, and in particular to a method and system for predicting wheel slippage in electric vehicles. Background Technology

[0002] Electric vehicles have many advantages, such as energy saving and environmental protection, strong power, good NVH (Motor Vehicle Noise) performance, and smooth driving. Research on their key technologies has attracted the attention of various car companies.

[0003] Because electric vehicles may experience varying risks of wheel slippage under different road conditions (such as ice, snow, rain, and mud), the prediction method needs to be flexible and adaptable. This method also needs high real-time performance, capable of quickly identifying and reacting to potential slippage risks. Therefore, a wheel slippage prediction method for electric vehicles needs to be designed. Such a method can not only improve driving safety, especially in adverse weather conditions, but also support future intelligent driving and autonomous driving technologies. With the continuous development of artificial intelligence and sensing technologies, prediction accuracy and response speed will gradually improve, ensuring a safer driving experience. Therefore, research on wheel slippage prediction for electric vehicles is of great significance.

[0004] Electric vehicles are powered by electric motors, which are characterized by high torque output and fast torque response. This makes electric vehicles prone to tire slippage on low-traction surfaces. Traditional cars use ESP (Electronic Stability Program) to calculate vehicle and wheel speeds, then calculate the slip ratio to detect slippage, and adjust the output torque of the electric motor and the braking force on the drive wheels to achieve anti-slip control. ESP anti-slip control requires the cooperation of various sensors and actuators, making it expensive to implement; compared to the fast response of electric motors, its timeliness is also low, and by the time control is applied after slippage has already occurred, the experience is already poor. Summary of the Invention

[0005] This invention provides a method and system for predicting wheel slippage in electric vehicles, which addresses existing problems.

[0006] The objective of this invention can be achieved through the following technical solutions:

[0007] The first aspect of this invention is to provide a method for predicting wheel slippage in electric vehicles, comprising:

[0008] Acquire various types of data on electric vehicles traveling on different road surfaces, and obtain all data unit sets from these data types; based on all data unit sets, perform offline training on the neural network model to obtain a trained model;

[0009] The trained model is ported to the motor MCU controller; the data unit set of the electric vehicle is input into the motor MCU controller to predict wheel slippage; when the wheel slips, the VCU implements torque reduction and torque transfer measures for the drive motor of the wheel with slippage tendency.

[0010] Furthermore, the acquisition of various types of data from electric vehicles traveling on different road surfaces, and the obtaining of all data unit sets through these various types of data, includes:

[0011] by Milliseconds are the duration of a data unit set. The sampling time interval is milliseconds, and all data unit sets of electric vehicles on different surface adhesion are obtained. Each data unit set contains multiple types of data, including: motor rotational angular velocity and angular acceleration, motor output torque, vehicle speed and vehicle acceleration, tire speed and tire acceleration, steering wheel angle, and accelerator pedal signal.

[0012] in, This is the preset time length parameter. This is the preset time interval parameter.

[0013] Furthermore, the offline training of the neural network model based on all data unit sets includes:

[0014] By marking the slip state corresponding to each data unit set, we can obtain a slip state feature corresponding to each data unit set; among them, there are only two slip state features, namely slipping and not slipping;

[0015] All data unit sets and the slippage state features corresponding to each data unit set are input into the neural network model for offline training to obtain the trained model.

[0016] Furthermore, the motor MCU controller includes: a processor core, a memory, and an input / output interface.

[0017] Furthermore, the memory includes a program memory and a data memory.

[0018] Furthermore, the step of inputting the electric vehicle's data unit set into the motor MCU controller to predict wheel slippage includes:

[0019] Before obtaining the current time The data unit set within milliseconds is recorded as the data unit set at the current moment. The data unit set at the current moment is input into the motor MCU controller. Then, the motor MCU controller predicts the state information of the electric vehicle wheel slippage after the current moment.

[0020] in, This is the preset time length parameter.

[0021] Furthermore, the measures implemented by the VCU to reduce torque and transfer torque to the drive motor of the wheel exhibiting slippage when the wheel slips include:

[0022] When the wheels of an electric vehicle slip, the VCU (Vehicle Control Unit) implements torque reduction and torque transfer measures on the drive motors of the wheels with slippage tendency based on the slippage status information of all wheels of the electric vehicle, thereby reducing the overall slippage of the electric vehicle.

[0023] A second aspect of the present invention is to provide an electric vehicle wheel slippage prediction system, comprising:

[0024] Data acquisition module: used to collect various types of data on electric vehicles driving on different surfaces with different adhesion in history;

[0025] Model training module: used to train neural network models offline based on various types of historical data to obtain trained models;

[0026] Wheel slippage prediction and adjustment module: This module is used to transfer the trained model to the motor MCU controller. It inputs various types of data of the electric vehicle from a period of time before the current moment into the motor MCU controller to predict the wheel slippage situation at the current moment. When wheel slippage occurs, the VCU implements torque reduction and torque transfer measures on the drive motor of the wheel with slippage tendency.

[0027] A third aspect of the present invention is to provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the aforementioned method for predicting wheel slippage in an electric vehicle.

[0028] A fourth aspect of the present invention is to provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method for predicting wheel slippage in an electric vehicle.

[0029] Compared with the prior art, the beneficial effects of the present invention are:

[0030] Based on all data unit sets, the neural network model is trained offline to obtain a trained model. Offline training improves the efficiency and accuracy of model training, ensures the stability of wheel slippage prediction, and reduces the burden of real-time computing. The trained model is then ported to the motor MCU controller. The electric vehicle's data unit set is input into the motor MCU controller to predict wheel slippage. When wheel slippage occurs, the VCU implements torque reduction and torque transfer measures for the drive motor of the wheel with slippage tendency. Through the prediction and analysis of electric vehicle wheel slippage, the user's driving safety and vehicle controllability are improved, as well as the user experience. Attached Figure Description

[0031] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0032] Figure 1 A flowchart illustrating the method for predicting wheel slippage in electric vehicles provided by the present invention;

[0033] Figure 2 This invention provides a flowchart of an electric vehicle wheel slippage prediction system;

[0034] Figure 3 This is a schematic diagram of a motor MCU controller. Detailed Implementation

[0035] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0036] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0037] To address the problems existing in the background technology, a method and system for predicting wheel slippage in electric vehicles has been developed, which has significant practical implications.

[0038] like Figure 1 As shown, the first aspect of the present invention is to provide a method for predicting wheel slippage in electric vehicles, comprising the following steps:

[0039] Step S001: Obtain various types of data for electric vehicles traveling on different road surfaces.

[0040] It should be noted that because the motor resolver has a faster sampling period, more data can be collected from the motor. More data can reduce the impact of data errors and improve the accuracy of model training. Therefore, making full use of the motor speed and angular velocity collected by the resolver sensor is beneficial for judging the slippage trend.

[0041] Specifically, data was collected on the driving conditions of electric vehicles on wet, slippery, icy, and snowy roads with varying degrees of adhesion, in order to... Milliseconds are the duration of a data unit set. The sampling time interval is milliseconds, and all data units of the electric vehicle are collected on different road surfaces.

[0042] In this embodiment, the time length parameter of the preset data unit set is... Preset sampling time interval parameter In this embodiment, the sampling time interval and the time length of the data unit set are not specifically limited, and the implementer can determine them according to the specific circumstances.

[0043] One data unit contains multiple types of data, including: motor rotational angular velocity and angular acceleration, motor output torque, vehicle speed and vehicle acceleration, tire speed and tire acceleration, steering wheel angle, and accelerator pedal signal.

[0044] Specifically, the motor's rotational angular velocity and angular acceleration are acquired by a motor resolver sensor; the motor's output torque is acquired by a torque sensor; tire speed and tire acceleration are acquired by a tire sensor; the tire sensor can also acquire the vehicle's speed, and the vehicle's acceleration is acquired by an acceleration sensor; the steering wheel angle is acquired by a steering wheel angle sensor; and the accelerator pedal signal is acquired by a pedal position sensor and converted into an electrical signal.

[0045] This completes the set of data units for all different road surfaces in history.

[0046] Step S002: Train the neural network model offline based on various types of data.

[0047] By marking the slip state corresponding to each data unit set, we can obtain a slip state feature corresponding to each data unit set; among them, there are only two slip state features, namely slipping and not slipping.

[0048] All data unit sets and the corresponding slippage state features for each data unit set are input into the neural network model for offline training, resulting in the trained neural network model. During training, the model's accuracy should be trained to over 90%.

[0049] It's important to note that LSTM (Long Short-Term Memory) is a special type of recurrent neural network (RNN) structure designed to address the vanishing and exploding gradient problems that traditional RNNs (Recurrent Neural Networks) encounter when processing long-sequence data. Due to its powerful memory capabilities, LSTM can retain dependencies over extended periods, making it particularly suitable for tasks involving time series data and long-term dependencies. It also models long-term information to a certain extent, thus demonstrating excellent performance in analyzing and predicting time-series data.

[0050] Therefore, in this embodiment, the neural network model uses an LSTM model to predict the wheel slippage of the electric vehicle. Since there are only two states of slippage, the loss function in the LSTM model is the binary cross-entropy loss function. During training, historical data is divided into training, validation, and test sets, with a ratio of 8:1:1.

[0051] At this point, the trained LSTM model is obtained.

[0052] Step S003: Transfer the trained model to the motor MCU controller.

[0053] A motor MCU (Microcontroller Unit) controller is a miniature electronic device that integrates computer processing capabilities, enabling it to control other devices or perform specific tasks; such as... Figure 3 As shown, the motor MCU controller includes: a processor core, memory, and input / output interfaces; the memory includes: program memory and data memory.

[0054] The processor core is responsible for executing instructions and processing data, controlling all computations and data flows, executing program code, and performing logical judgments and arithmetic operations.

[0055] The memory is the data storage component of an MCU, mainly divided into program memory and data memory. Program memory stores the static program code. When the MCU starts up, the processor core reads the program code from program memory and executes these instructions. Data memory stores runtime data, including variables, temporary data, intermediate results, etc. When the processor executes instructions, it may need to use data memory to temporarily store data.

[0056] The input interface is used to receive data and signals collected by the sensor; the received data and signals are then processed by the MCU.

[0057] The output interface is used to output the MCU's processing results to external devices, such as driving LED displays (LED Display Driver), controlling motors, sending data to the display screen, controlling relays, etc.; and to provide information reminders to users through external devices.

[0058] Since the trained model corresponds to a program, the trained model will be ported to the program memory.

[0059] Step S004: Input various types of data from the electric vehicle into the motor MCU controller to predict wheel slippage; when a wheel slips, the VCU implements torque reduction and torque transfer measures for the drive motor of the wheel with slippage tendency.

[0060] Before obtaining the current time The data unit set within milliseconds is recorded as the data unit set at the current moment. The data unit set at the current moment is input into the motor MCU controller. Then, the motor MCU controller predicts the state information of the electric vehicle wheel slippage after the current moment.

[0061] When the wheels of an electric vehicle slip, the VCU (Vehicle Control Unit) implements torque reduction and torque transfer measures on the drive motors of the wheels with slipping tendencies based on the slipping status information of all wheels of the electric vehicle, thereby reducing the overall slipping situation of the electric vehicle.

[0062] At this point, the prediction of wheel slippage and the corresponding measures have been completed.

[0063] like Figure 2 As shown, the second aspect of the present invention is to provide an electric vehicle wheel slippage prediction system, comprising the following modules: a data acquisition module 101; a model training module 102; and a wheel slippage prediction and adjustment module 103.

[0064] Data acquisition module 101: used to collect various types of data on electric vehicles traveling on different surfaces with different adhesion in history;

[0065] Model training module 102: Used to train neural network models offline based on various types of historical data to obtain trained models;

[0066] Wheel slippage prediction and adjustment module 103: It is used to transfer the trained model to the motor MCU controller, input various types of electric vehicle data from a period of time before the current moment into the motor MCU controller to predict the wheel slippage situation at the current moment; when wheel slippage occurs, the VCU implements torque reduction and torque transfer measures for the drive motor of the wheel with slippage tendency.

[0067] A third aspect of the present invention is to provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement a method for predicting wheel slippage in an electric vehicle.

[0068] A method for predicting wheel slippage in electric vehicles includes the following steps:

[0069] S001, acquire various types of data for electric vehicles traveling on different road surfaces;

[0070] S002, perform offline training on neural network models based on various types of data;

[0071] S003, port the trained model to the motor MCU controller;

[0072] S004 inputs various types of data from the electric vehicle into the motor MCU controller to predict wheel slippage. When a wheel slips, the VCU implements torque reduction and torque transfer measures for the drive motor of the wheel with slippage tendency.

[0073] A fourth aspect of the present invention is to provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements a method for predicting wheel slippage in an electric vehicle.

[0074] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM (Compact Disc Read-Only Memory), optical storage, etc.) containing computer-usable program code.

[0075] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, systems, and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0076] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0077] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0078] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for predicting wheel slippage in electric vehicles, characterized in that, include: Acquire various types of data on electric vehicles traveling on different road surfaces, and obtain all data unit sets from these data types, including... Milliseconds are the duration of a data unit set. The sampling time interval is milliseconds, acquiring all data unit sets of the electric vehicle under different surface adhesion conditions. Each data unit set contains multiple data types, including: motor rotational angular velocity and angular acceleration, motor output torque, vehicle speed and acceleration, tire speed and acceleration, steering wheel angle, and accelerator pedal signal. This is the preset time length parameter. This is a preset time interval parameter; Based on all data unit sets, the neural network model is trained offline to obtain a trained model. This includes labeling the slip state corresponding to each data unit set, which yields a slip state feature for each data unit set. There are only two slip state features: slipping and not slipping. All data unit sets and the slip state features corresponding to each data unit set are input into the neural network model for offline training to obtain a trained model. The trained model is then ported to the motor MCU controller; the electric vehicle's data unit set is input into the motor MCU controller to predict wheel slippage, including obtaining the data from the previous moment. The data unit set within a millisecond is recorded as the data unit set at the current moment. This current data unit set is then input into the motor MCU controller. The motor MCU controller then predicts the wheel slippage status information of the electric vehicle after the current moment. The preset time length parameter is used; when the wheel slips, the VCU implements torque reduction and torque transfer measures for the drive motor of the wheel with slippage tendency. This includes, when the wheel of the electric vehicle slips, the VCU implements torque reduction and torque transfer measures for the drive motor of the wheel with slippage tendency based on the slippage status information of all wheels of the electric vehicle, so as to reduce the overall slippage of the electric vehicle.

2. The method for predicting wheel slippage in an electric vehicle according to claim 1, characterized in that, The motor MCU controller includes: a processor core, memory, and input / output interfaces.

3. The method for predicting wheel slippage in an electric vehicle according to claim 2, characterized in that, The memory includes: program memory and data memory.

4. A wheel slippage prediction system for electric vehicles, characterized in that, include: Data acquisition module: Used to acquire various types of data from electric vehicles traveling on different road surfaces, and to obtain all data unit sets from these data types, including... Milliseconds are the duration of a data unit set. The sampling time interval is milliseconds, acquiring all data unit sets of the electric vehicle under different surface adhesion conditions. Each data unit set contains multiple data types, including: motor rotational angular velocity and angular acceleration, motor output torque, vehicle speed and acceleration, tire speed and acceleration, steering wheel angle, and accelerator pedal signal. This is the preset time length parameter. This is a preset time interval parameter; Model training module: This module is used to train the neural network model offline based on all data unit sets to obtain a trained model. This includes labeling the slip state corresponding to each data unit set, thus obtaining a slip state feature for each data unit set. There are only two slip state features: slipping and no slipping. All data unit sets and the slip state features corresponding to each data unit set are input into the neural network model for offline training to obtain a trained model. Wheel slippage prediction and adjustment module: Used to port the trained model to the motor MCU controller; inputs the electric vehicle's data unit set to the motor MCU controller to predict wheel slippage, including obtaining data from the current moment before the event. The data unit set within a millisecond is recorded as the data unit set at the current moment. This current data unit set is then input into the motor MCU controller. The motor MCU controller then predicts the wheel slippage status information of the electric vehicle after the current moment. The preset time length parameter is used; when the wheel slips, the VCU implements torque reduction and torque transfer measures for the drive motor of the wheel with slippage tendency. This includes, when the wheel of the electric vehicle slips, the VCU implements torque reduction and torque transfer measures for the drive motor of the wheel with slippage tendency based on the slippage status information of all wheels of the electric vehicle, so as to reduce the overall slippage of the electric vehicle.

5. An electronic device, characterized in that, The device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the electric vehicle wheel slippage prediction method according to any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the electric vehicle wheel slippage prediction method according to any one of claims 1-3.

Images