Method and system for pre-judging wheel slip of electric automobile

Abstract

The invention relates to the technical field of automobiles, in particular to an electric automobile wheel slip pre-judgment method and system, and the method comprises the steps: obtaining various types of data of different attached road surfaces and running electric automobiles, and obtaining all data unit sets through the various types of data; according to all the data unit sets, performing offline training on the neural network model to obtain a trained model; transplanting the trained model to a motor MCU controller; a data unit set of the electric automobile is input into a motor MCU controller to pre-judge the wheel slip condition; and when the wheels slip, torque reduction and torque transfer measures are carried out on the driving motors of the wheels which tend to slip through the VCU. According to the invention, through the pre-judgment analysis of the wheel slip of the electric vehicle, the driving safety of a user and the controllability of the vehicle are improved, and the user experience is also improved.

Description

Technical Field

[0001] The present invention relates to the field of automobile technology, and in particular to a method and system for predicting wheel slippage of an electric vehicle. Background Art

[0002] Electric vehicles have many advantages such as energy saving and environmental protection, strong power, good NVH (Motor Vehicle Noise) performance, and smooth driving. The research on their key technologies has received attention from various automobile companies.

[0003] Since electric vehicles may have different skidding risks under different road conditions (such as ice, snow, rain, mud, etc.), the prediction method needs to be able to adapt flexibly; the prediction method needs to have high real-time performance, and be able to judge whether there is a skidding risk in a very short time and respond in time, so it is necessary to design a method for predicting electric vehicle wheel skidding; the designed electric vehicle wheel skidding prediction can not only improve driving safety, especially in bad weather conditions, but also provide support for future intelligent driving and autonomous driving technologies. With the continuous development of artificial intelligence and sensing technology, the prediction accuracy and response speed will gradually improve to ensure a safer driving experience, so the research on electric vehicle wheel skidding prediction is of great significance.

[0004] The driving force of electric vehicles comes from electric motors, which have the characteristics of large output torque and fast torque response, which makes it very easy for electric vehicles to have tire slippage on low-adhesion roads. Traditional cars use ESP (Electronic Stability Program) to calculate the vehicle speed and wheel speed, and then calculate the slip rate to determine slippage, and achieve anti-skid control by adjusting the output torque of the motor and the braking force on the drive wheel. ESP's anti-skid control requires the cooperation of various sensors and actuators, which is expensive to implement; compared with the rapid response of the motor, its timeliness is not high, and the experience is not good when control is implemented in the case of slippage. Summary of the invention

[0005] The invention provides a method and system for predicting wheel slip of an electric vehicle, which are used to solve the existing problems.

[0006] The purpose of the present invention can be achieved through the following technical solutions: The first aspect of the present invention is to provide a method for predicting wheel slip of an electric vehicle, comprising: Obtain various types of data of electric vehicles running on different adhesion roads, and obtain all data unit sets through various types of data; perform offline training on the neural network model based on all data unit sets to obtain a trained model; The trained model is transplanted to the motor MCU controller; the data unit set of the electric vehicle is input into the motor MCU controller to predict the wheel slip; when the wheel slips, the VCU is used to implement torque reduction and torque transfer measures on the drive motor of the wheel with a slipping tendency.

[0007] Furthermore, the acquisition of various types of data of the electric vehicle running on different adhesion roads, and obtaining all data unit sets through various types of data, include: by Milliseconds is the length of time for a data unit set. The sampling time interval is milliseconds, and all data unit sets of electric vehicles on different adhesion roads are obtained; wherein a data unit set contains multiple types of data, including: motor rotation angular velocity and angular acceleration, motor output torque, vehicle speed and vehicle acceleration, tire speed and tire acceleration, steering wheel angle, accelerator pedal signal; in, To preset the time length parameter, It is the preset time interval parameter.

[0008] Furthermore, the offline training of the neural network model according to all data unit sets includes: By marking the corresponding slip state after each data unit set, it can be obtained that each data unit set corresponds to a slip state feature; among them, there are only two slip state features, namely slip and no slip; 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.

[0009] Furthermore, the motor MCU controller includes: a processor core, a memory, and an input and output interface.

[0010] Furthermore, the memory includes: a program memory and a data memory.

[0011] Furthermore, the step of inputting the data unit set of the electric vehicle into the motor MCU controller to predict the wheel slipping includes: Get the current time before 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, and then the motor MCU controller predicts the state information of the electric vehicle wheel slipping after the current moment; in, It is the preset time length parameter.

[0012] Furthermore, when the wheel slips, the measures of reducing torque and transferring torque to the drive motor of the wheel with the slipping tendency by the VCU include: When the wheels of an electric vehicle slip, the VCU implements torque reduction and torque transfer measures on the drive motors of the wheels with a slipping tendency based on the slipping status information of all the wheels of the electric vehicle, so as to reduce the overall slippage of the electric vehicle.

[0013] The second aspect of the present invention is to provide an electric vehicle wheel slip prediction system, comprising: Data collection module: used to collect various types of data of electric vehicles running on different adhesion roads in history; Model training module: used to perform offline training on the neural network model based on various types of historical data to obtain a trained model; Wheel slip prediction and adjustment module: used to transplant the trained model to the motor MCU controller, input various types of data of the electric vehicle in a period of time before the current moment into the motor MCU controller to predict the wheel slip at the current moment; when the wheel slips, the VCU implements torque reduction and torque transfer measures on the drive motor of the wheel with slipping tendency.

[0014] The 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 implements the electric vehicle wheel slip prediction method when executing the computer program.

[0015] A fourth aspect of the present invention is to provide a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for predicting wheel slip of an electric vehicle is implemented.

[0016] Compared with the prior art, the present invention has the following beneficial effects: 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 slip prediction, and reduces the burden of real-time calculation; the trained model is transplanted to the motor MCU controller; the data unit set of the electric vehicle is input into the motor MCU controller to predict wheel slip; when the wheel slips, the VCU implements torque reduction and torque transfer measures on the drive motor of the wheel with a slipping tendency; through the predictive analysis of the electric vehicle wheel slip, the user's driving safety and vehicle controllability are improved, and the user experience is also improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 The present invention provides a flow chart of a method for predicting wheel slippage of an electric vehicle; Figure 2 The present invention provides a flow chart of a system for predicting wheel slippage in an electric vehicle; Figure 3 This is a schematic diagram of the motor MCU controller. DETAILED DESCRIPTION

[0019] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0020] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0021] In view of the problems existing in the background technology, a method and system for predicting wheel slip of electric vehicles are studied and designed, which has important practical significance.

[0022] like Figure 1 As shown, the first aspect of the present invention is to provide a method for predicting wheel slip of an electric vehicle, comprising the following steps: Step S001: Acquire various types of data of electric vehicles running on different adhesion road surfaces.

[0023] It should be noted that since the sampling cycle of the motor resolver is faster, more data can be collected through 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 of the speed collected by the resolver sensor is beneficial to the judgment of the slip trend.

[0024] Specifically, the conditions of electric vehicles traveling on slippery ice and snow roads with different adhesion levels are collected. Milliseconds is the length of time for a data unit set. Milliseconds are the sampling time intervals, and all data unit sets of electric vehicles on different adhesion road surfaces are collected.

[0025] In this embodiment, the time length parameter of the preset data unit set is , preset sampling time interval parameters In this embodiment, the sampling time interval and the time length of the data unit set are not specifically limited, and the implementer may determine them according to the specific situation.

[0026] Among them, one data unit contains multiple types of data; including: motor rotation 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.

[0027] Among them, the motor rotation angular velocity and angular acceleration are collected through the motor resolver sensor; the motor output torque is collected through the torque sensor; the tire speed and tire acceleration are collected through the tire sensor; the tire sensor can also collect the vehicle speed, and the vehicle acceleration is collected through the acceleration sensor; the steering wheel angle is collected through the steering wheel angle sensor; the accelerator pedal signal is collected through the pedal position sensor and converted into an electrical signal.

[0028] At this point, all data unit sets of different adhesion road surfaces in history are obtained.

[0029] Step S002: Perform offline training on the neural network model based on various types of data.

[0030] By marking the corresponding slip state after each data unit set, it can be obtained that each data unit set corresponds to a slip state feature; wherein, there are only two types of slip state features, namely slip and no slip.

[0031] 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 neural network model. In the training process, the accuracy of the model should be trained to reach more than 90%.

[0032] It should be noted that the LSTM (Long Short-Term Memory) model is a special recurrent neural network (RNN) structure designed to solve the gradient vanishing and gradient exploding problems of traditional RNN (Recurrent Neural Network) when processing long sequence data. LSTM has a strong memory capacity and can remember long-term dependencies. It is particularly suitable for tasks that need to process time series and long-term dependencies, and can model long-term information to a certain extent. Therefore, the use of LSTM models to analyze and predict time series data has a good effect.

[0033] Therefore, in this embodiment, the neural network model uses an LSTM model to predict the slippage of the electric vehicle wheels; since there are only two states of slippage, the loss function in the LSTM model uses a binary cross entropy loss function. In the training process, the historical data is divided into a training set, a validation set, and a test set, and the ratio of the training set, the validation set, and the test set is 8:1:1.

[0034] At this point, the trained LSTM model is obtained.

[0035] Step S003: transplant the trained model to the motor MCU controller.

[0036] Motor MCU (Microcontroller Unit) controller is a microelectronic device with integrated computer processing functions that can control other devices or perform specific tasks; such as Figure 3 As shown, the motor MCU controller includes: a processor core, a memory, and an input and output interface; the memory includes: a program memory and a data memory.

[0037] The processor core is responsible for executing instructions and processing data, controlling all calculations and data flow, executing program code, and performing logical judgments and arithmetic operations.

[0038] The memory is the data storage part of the MCU, which is mainly divided into program memory and data memory. Among them, the program memory stores the fixed program code. When the MCU starts, the processor core will read the program code from the program memory and execute these instructions. The data memory stores the data during runtime, including variables, temporary data, intermediate results, etc. When the processor executes instructions, the processor may need to use the data memory to temporarily store data.

[0039] The input interface is used to receive data and signals collected by the sensor; the received data and signals are used for MCU processing.

[0040] The output interface is used to output the processing results of the MCU to external devices, such as driving LED displays (LED DisplayDriver, LED display driver), controlling motors, sending data to display screens, controlling relays, etc.; and providing information reminders to users through external devices.

[0041] Since the trained model corresponds to the program, the trained model will be transplanted into the program memory.

[0042] Step S004: Various types of data of the electric vehicle are input into the motor MCU controller to predict wheel slippage; when the wheel slips, the VCU implements torque reduction and torque transfer measures on the drive motor of the wheel with a slipping tendency.

[0043] Get the current time before 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, and then the motor MCU controller predicts the state information of the electric vehicle wheel slip after the current moment.

[0044] When the wheels of an electric vehicle slip, the VCU (Vehicle Control Unit) implements torque reduction and torque transfer measures on the drive motor of the wheel with slipping tendency based on the slip status information of all the wheels of the electric vehicle, so as to reduce the overall slip of the electric vehicle.

[0045] At this point, the prediction of wheel slip is completed and corresponding measures are taken.

[0046] like Figure 2 As shown, the second aspect of the present invention is to provide an electric vehicle wheel slip prediction system, comprising the following modules: a data acquisition module 101; a model training module 102; and a wheel slip prediction and adjustment module 103.

[0047] Data collection module 101: used to collect various types of data of electric vehicles running on different adhesion roads in history; Model training module 102: used to perform offline training on the neural network model according to various types of historical data to obtain a trained model; Wheel slip prediction and adjustment module 103: used to transplant the trained model to the motor MCU controller, input various types of data of the electric vehicle within a period of time before the current moment into the motor MCU controller, to predict the wheel slip at the current moment; when the wheel slips, the VCU implements torque reduction and torque transfer measures on the drive motor of the wheel with a slipping tendency.

[0048] The 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 implements a method for predicting wheel slippage of an electric vehicle when executing the computer program.

[0049] A method for predicting wheel slip of an electric vehicle comprises the following steps: S001, obtaining various types of data of electric vehicles running on different adhesion roads; S002, offline training of the neural network model based on various types of data; S003, transplant the trained model to the motor MCU controller; S004, various types of data of the electric vehicle are input into the motor MCU controller to predict wheel slippage; when the wheel slips, the VCU implements torque reduction and torque transfer measures on the drive motor of the wheel with a slipping tendency.

[0050] A fourth aspect of the present invention is to provide a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, a method for predicting wheel slip of an electric vehicle is implemented.

[0051] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM (Compact Disc Read-Only Memory), optical storage, etc.) containing computer-usable program code.

[0052] The present invention is described with reference to flowcharts and / or block diagrams of methods, systems, and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process in the flowchart. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0053] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0054] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0055] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does 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 an electric vehicle, characterized in that: include: Obtain various types of data of electric vehicles running on different adhesion roads, and obtain all data unit sets through various types of data; perform offline training on the neural network model based on all data unit sets to obtain a trained model; The trained model is transplanted to the motor MCU controller; the data unit set of the electric vehicle is input into the motor MCU controller to predict the wheel slip; when the wheel slips, the VCU is used to implement torque reduction and torque transfer measures on the drive motor of the wheel with a slipping tendency.

2. The method for predicting wheel slip of an electric vehicle according to claim 1, characterized in that: The method of obtaining various types of data of electric vehicles running on different adhesion roads and obtaining all data unit sets through various types of data includes: by Milliseconds is the length of time for a data unit set. The sampling time interval is milliseconds, and all data unit sets of electric vehicles on different adhesion roads are obtained; wherein a data unit set contains multiple types of data, including: motor rotation angular velocity and angular acceleration, motor output torque, vehicle speed and vehicle acceleration, tire speed and tire acceleration, steering wheel angle, accelerator pedal signal; in, To preset the time length parameter, It is the preset time interval parameter.

3. The method for predicting wheel slip of an electric vehicle according to claim 1, characterized in that: The offline training of the neural network model according to all data unit sets includes: By marking the corresponding slip state after each data unit set, it can be obtained that each data unit set corresponds to a slip state feature; among them, there are only two slip state features, namely slip and no slip; 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.

4. The method for predicting wheel slip of an electric vehicle according to claim 1, characterized in that: The motor MCU controller includes: a processor core, a memory, and an input and output interface.

5. The method for predicting wheel slip of an electric vehicle according to claim 4, characterized in that: The memory includes: a program memory and a data memory.

6. The method for predicting wheel slip of an electric vehicle according to claim 1, characterized in that: The method of inputting the data unit set of the electric vehicle into the motor MCU controller to predict the wheel slipping situation includes: Get the current time before 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, and then the motor MCU controller predicts the state information of the electric vehicle wheel slipping after the current moment; in, It is the preset time length parameter.

7. The method for predicting wheel slip of an electric vehicle according to claim 1, characterized in that: When the wheel slips, the VCU implements torque reduction and torque transfer measures on the drive motor of the wheel with a slipping tendency, including: When the wheels of an electric vehicle slip, the VCU implements torque reduction and torque transfer measures on the drive motors of the wheels with a slipping tendency based on the slipping status information of all the wheels of the electric vehicle, so as to reduce the overall slippage of the electric vehicle.

8. An electric vehicle wheel slip prediction system, characterized in that: include: Data collection module: used to collect various types of data of electric vehicles running on different adhesion roads in history; Model training module: used to perform offline training on the neural network model based on various types of historical data to obtain a trained model; Wheel slip prediction and adjustment module: used to transplant the trained model to the motor MCU controller, input various types of data of the electric vehicle in a period of time before the current moment into the motor MCU controller to predict the wheel slip at the current moment; When a wheel slips, the VCU will implement torque reduction and torque transfer measures on the drive motor of the wheel with a tendency to slip.

9. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for predicting wheel slip of an electric vehicle as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for predicting wheel slip of an electric vehicle as described in any one of claims 1-7 is implemented.

Images