Distributed electric vehicle steering stability early warning method, device, equipment and medium

Abstract

The invention provides a distributed electric vehicle steering stability early warning method, device, equipment and medium, and relates to the technical field of vehicle steering stability monitoring, the method comprises the following steps: building a digital twin model, realizing comprehensive mapping of a physical entity and a virtual entity, using CarSim and MATLAB / Simulink joint simulation platform, fusing multi-source data, and realizing early warning of the steering stability of a distributed electric vehicle. And the accuracy and reliability of the model are improved. Specifically, an LSTM neural network algorithm is adopted, key operation parameters of a vehicle are monitored and analyzed in real time, the maximum side slip angle and the yaw velocity are predicted, and therefore potential steering stability faults are warned in advance. Through comparison with real-time data acquired by a vehicle sensor, the system can accurately evaluate the driving state of the vehicle, and early warning is given out in time when abnormity is detected, so that a driver is reminded to take corresponding measures.

Description

Technical Field

[0001] The present invention relates to the technical field of automobile steering stability monitoring, and in particular to a distributed electric vehicle steering stability early warning method, device, equipment and medium. Background Art

[0002] With the continuous progress of the automobile industry, electric vehicles, as a clean energy vehicle, have developed rapidly. Among the many types of electric vehicles, distributed drive electric vehicles have gradually become a research hotspot with their unique driving mode and structural advantages. This type of electric vehicle simplifies the mechanical transmission structure by eliminating the traditional complex transmission equipment, which not only reduces the failure rate, but also improves the utilization rate of the interior space, making the vehicle show higher flexibility and controllability during driving. However, it is precisely this simplification of the structure that also makes the driving stability of distributed drive electric vehicles face new challenges. Due to the increase in the degree of freedom of the vehicle, its stability during turning, driving and braking has decreased. In actual driving, especially in the face of complex working conditions, such as ice and snow roads with poor adhesion conditions, the dynamic characteristics of the wheels will change from a linear state to a nonlinear state, causing the key parameters of the vehicle such as the yaw angular velocity to deviate from the ideal value. With the increase of vehicle speed and steering angle, the adhesion between the wheel and the road may reach the limit, causing dangerous situations such as side slip, deviation, and tail swing, which seriously threatens driving safety.

[0003] The existing distributed drive electric vehicles cannot obtain the vehicle's operating status in time during driving due to the lack of effective real-time monitoring methods. This means that if the driver operates improperly, the vehicle may quickly enter an uncontrollable state, further increasing the driving risk. In addition, in terms of steering stability prediction, the existing technology has not yet fully utilized deep learning methods. This leads to deficiencies in predicting potential failures when distributed drive electric vehicles are turning, and it is impossible to accurately warn in advance, thereby failing to effectively avoid possible dangerous situations, affecting the overall driving stability of the vehicle.

[0004] In view of this, this application is filed. Summary of the invention

[0005] The present invention provides a distributed electric vehicle steering stability warning method, device, equipment and medium, which can at least partially improve the above-mentioned problems.

[0006] To achieve the above object, the present invention adopts the following technical solutions: A distributed electric vehicle steering stability early warning method, comprising: Acquire a perception data set collected by a sensor component configured on the electric vehicle, and establish a virtual entity corresponding to the electric vehicle based on the perception data set; Acquire a virtual data set of the virtual entity, and fuse the virtual data set with the perception data set based on digital twin technology to generate a data twin simulation data set; The data twin simulation data set is calculated using an LSTM neural network model to generate a distributed electric vehicle steering instability prediction value, wherein the distributed electric vehicle steering instability prediction value includes a center of mass sideslip angle prediction value and a yaw angular velocity prediction value; Perform early warning processing on the distributed electric vehicle steering instability prediction value, generate an early warning result or output the distributed electric vehicle steering instability prediction value.

[0007] The present invention also provides a distributed electric vehicle steering stability warning device, which includes: A virtual entity establishing unit, used to obtain a perception data set collected by a sensor component configured on the electric vehicle, and establish a virtual entity corresponding to the electric vehicle based on the perception data set; A digital twin unit, used to obtain a virtual data set of the virtual entity, fuse the virtual data set with the perception data set based on the digital twin technology, and generate a data twin simulation data set; An LSTM neural network unit is used to calculate the data twin simulation data set using an LSTM neural network model to generate a distributed electric vehicle steering instability prediction value, wherein the distributed electric vehicle steering instability prediction value includes a center of mass sideslip angle prediction value and a yaw angular velocity prediction value; The early warning unit is used to perform early warning processing on the distributed electric vehicle steering instability prediction value, generate an early warning result or output the distributed electric vehicle steering instability prediction value.

[0008] The present invention also provides a distributed electric vehicle steering stability warning device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the distributed electric vehicle steering stability warning method as described in any one of the above.

[0009] The present invention also provides a readable storage medium storing a computer program, wherein the computer program can be executed by a processor of a device where the storage medium is located to implement a distributed electric vehicle steering stability warning method as described in any one of the above.

[0010] In summary, the distributed electric vehicle steering stability warning method realizes the comprehensive mapping of physical entities and virtual entities by constructing a digital twin model and using the CarSim and MATLAB / Simulink joint simulation platform, and integrates multi-source data, thereby improving the accuracy and reliability of the model; it aims to solve the problems existing in the driving stability of distributed drive electric vehicles. Specifically, the distributed electric vehicle steering stability warning method adopts the LSTM neural network algorithm to monitor and analyze the key operating parameters of the vehicle in real time, predict the maximum center of mass sideslip angle and yaw angular velocity, so as to warn of potential steering stability failures in advance. By comparing with the real-time data obtained by the vehicle sensor, the system can accurately evaluate the driving state of the vehicle, and issue a warning in time when an abnormality is detected, reminding the driver to take corresponding measures. It not only improves the monitoring accuracy and real-time performance of the steering fault of distributed electric vehicles, but also uses deep learning methods to improve the prediction accuracy of special faults. In addition, the multi-source data fusion characteristics of the method make the monitoring of the vehicle state more comprehensive, effectively solving the defects of the prior art. In this way, the method provides a strong guarantee for the safe driving of distributed drive electric vehicles and ensures the stability and reliability of the vehicle under various complex working conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 It is a flow chart of a distributed electric vehicle steering stability warning method provided by the first embodiment of the present invention; Figure 2 Schematic diagram of the framework structure of a distributed electric vehicle steering stability warning method provided by the first embodiment of the present invention; Figure 3 It is a schematic diagram of the data twin simulation data set generation process provided by an embodiment of the present invention; Figure 4 It is a basic flow chart of the LSTM neural network model provided by an embodiment of the present invention; Figure 5 is a schematic diagram of a steering stability warning control process provided by an embodiment of the present invention; Figure 6 The embodiment of the present invention provides Schematic diagram of the stable region of the phase plane method; Figure 7 It is a module schematic diagram of a distributed electric vehicle steering stability warning device provided by the second embodiment of the present invention. DETAILED DESCRIPTION

[0012] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0013] refer to Figure 1 , Figure 2 As shown, the first embodiment of the present invention discloses a distributed electric vehicle steering stability warning method, which can be executed by a distributed electric vehicle steering stability warning device (hereinafter referred to as the warning device), and in particular, executed by one or more processors in the warning device to implement the following method: S1, acquiring a perception data set collected by a sensor component configured on the electric vehicle, and establishing a virtual entity corresponding to the electric vehicle based on the perception data set; Specifically, step S1 includes: acquiring a perception data set collected by a sensor component configured on the electric vehicle, wherein the perception data set includes SOC data, wheel speed, torque, steering wheel angle, acceleration, and braking force; Establishing a Simulink simulation model based on the perception data set, wherein the Simulink simulation model includes a seven-degree-of-freedom dynamic model of longitudinal, lateral, yaw motion and four wheel rotation, an ideal two-degree-of-freedom model, a magic formula tire model and a longitudinal driver model; The Simulink simulation model and the Carsim vehicle model are fused to generate a virtual entity corresponding to the electric vehicle, wherein the vehicle parameters and the power source in the Carsim vehicle model are modified according to the Simulink simulation model.

[0014] In this embodiment, a perception data set collected by sensor components configured on the electric vehicle is obtained. These sensor components include wheel speed sensors, steering wheel steering angle sensors, acceleration sensors and torque sensors, etc. They can collect real-time operating status data of the electric vehicle, such as SOC (State of Charge, battery power status) data, wheel speed, torque, steering wheel angle, acceleration and braking force, etc. These perception data sets provide basic data support for establishing virtual entities.

[0015] Among them, the driving conditions in the working environment of the vehicle are relatively complex, and different changes in working conditions will affect the running state of the vehicle body. First, various sensors installed on the vehicle are used to obtain data in real time, and then the data collected under different working conditions are associated with the running state. The working conditions that may be involved are shown in Table 1.

[0016] Table 1 Automobile steering driving conditions

[0017] Based on the collected perception data set, a simulation model corresponding to the electric vehicle is built in the Simulink environment. The Simulink simulation model is a highly complex system model that covers the seven-degree-of-freedom dynamics model of longitudinal, lateral, yaw motion, and four wheel rotation. In addition, the model also includes an ideal two-degree-of-freedom model, a magic formula tire model, and a longitudinal driver model. These models together constitute a comprehensive vehicle dynamics simulation framework that can accurately simulate the dynamic behavior of electric vehicles under various working conditions. The Simulink simulation model can combine actual operation with theoretical simulation to improve the accuracy of the digital twin model.

[0018] The Simulink simulation model and the Carsim vehicle model are further integrated. Carsim is a professional vehicle dynamics simulation software, and its built-in vehicle model is usually centralized drive. In order to adapt to the characteristics of distributed drive electric vehicles, it is necessary to modify the vehicle parameters and power sources in the Carsim vehicle model. Specifically, the original power system in Carsim is cut off and external interface power input is used instead. Import and export interfaces are defined in CarSim. The input interface includes the four wheel motor braking torque and hydraulic braking torque, while the output interface includes longitudinal vehicle speed, four wheel speeds, yaw angular velocity, left front wheel and right front wheel wheel angle and other information.

[0019] Through the above fusion processing, a virtual entity corresponding to the electric vehicle is generated. This virtual entity not only contains the real-time perception data collected from the physical entity (i.e. the actual electric vehicle), but also integrates the virtual data of the Simulink simulation model and the Carsim vehicle model. This fusion enables the virtual entity to more accurately reflect the state and behavior of the electric vehicle in actual driving, providing a solid foundation for subsequent steering stability warning.

[0020] S2, obtaining a virtual data set of the virtual entity, fusing the virtual data set with the perception data set based on digital twin technology, and generating a data twin simulation data set; Specifically, step S2 includes: obtaining a virtual data set of the virtual entity, wherein the virtual data set includes slip rate, vehicle speed, yaw angular velocity, vehicle sideslip angle, lateral acceleration, and yaw moment; Calculating the sensed data set and the virtual data set based on an MPC control algorithm; The data calculated by the MPC control algorithm is processed by HIL hardware-in-the-loop testing, and a data twin simulation data set is constructed based on the test results.

[0021] See also Figure 3In this embodiment, these virtual data sets are generated by integrating the Simulink simulation model and the Carsim vehicle model, covering key parameters such as slip rate, vehicle speed, yaw rate, vehicle sideslip angle, lateral acceleration, yaw moment, etc. These parameters can fully reflect the dynamic behavior of electric vehicles in a virtual environment and provide virtual data support for the construction of digital twin models.

[0022] Next, based on the digital twin technology, the virtual data set is deeply integrated with the perception data set obtained in step S1. This fusion process is the core application of digital twin technology. It combines the actual operating data of the physical entity with the simulation data of the virtual entity to generate a comprehensive and accurate data twin simulation data set. This data fusion not only covers the real-time operating status of the electric vehicle, but also includes the dynamic changes that may occur under various working conditions, thereby providing a richer data foundation for subsequent analysis and early warning. The real-time operating status of the distributed braking vehicle can be determined by the vehicle mass, slope, speed v, torque T, input angle , acceleration / deceleration a, braking torque T, battery charge state, these 9 parameters indicate that the Simulink and Carsim joint simulation based on MPC control can obtain more robust data, in order to realize the intelligentization of the steering stability warning of distributed electric vehicles, ensure the real-time interactivity between the physical entity and the twin model, and the reliability of the model. The HIL hardware-in-the-loop test is used to verify the simulation results. If the results of the two are consistent, the operating data is output to build a multi-condition data set; if the results of the two are inconsistent, the model is adjusted and optimized to realize the automatic learning function of the model.

[0023] Specifically, in order to further improve the accuracy and reliability of the data, the distributed electric vehicle steering stability warning method adopts an MPC (Model Predictive Control) control algorithm to calculate the perception data set and the virtual data set. The MPC control algorithm is an advanced control strategy that can optimize future control signals based on the current state of the system and the prediction model. In this embodiment, the MPC control algorithm can predict the dynamic behavior of the electric vehicle in the future and optimize the control strategy to ensure the stability and safety of the vehicle by calculating the perception data set and the virtual data set. After the calculation is completed, the data processed by the MPC control algorithm is subjected to HIL (Hardware in the Loop) hardware-in-the-loop test. HIL testing is an effective verification method that combines actual hardware components with simulation models to simulate real working conditions, thereby verifying the effectiveness and accuracy of the control strategy. In this patent, the HIL test is used to verify whether the data processed by the MPC control algorithm can accurately reflect the actual operating status of the electric vehicle and ensure the reliability of the data twin simulation data set.

[0024] Finally, based on the results of the HIL test, the final data twin simulation data set is constructed. This data set not only contains verified accurate data, but also integrates the dual advantages of physical entities and virtual entities, providing a solid data foundation for the steering stability warning system of electric vehicles. Through this data fusion and verification process, this method can achieve real-time monitoring and accurate prediction of the driving status of electric vehicles, and warn of potential steering stability problems in advance, thereby improving the safety and reliability of the vehicle.

[0025] In short, the distributed electric vehicle steering stability warning method generates a highly accurate and reliable data twin simulation data set through the deep integration of virtual data sets and perception data sets, as well as the rigorous verification of MPC control algorithms and HIL hardware-in-the-loop tests. This data set can not only fully reflect the dynamic behavior of electric vehicles, but also predict possible steering stability problems in the future and provide timely warning information to drivers. This warning system based on digital twin technology significantly improves the driving stability and safety of electric vehicles under complex working conditions, and provides strong technical support for the widespread application of electric vehicles.

[0026] S3, using an LSTM neural network model to calculate the data twin simulation data set to generate a distributed electric vehicle steering instability prediction value, wherein the distributed electric vehicle steering instability prediction value includes a center of mass sideslip angle prediction value and a yaw angular velocity prediction value; See also Figure 4Specifically, in this embodiment, after obtaining the physical data collected by the sensor and the virtual data obtained by the simulation model, the data are fused to construct a multi-condition digital twin simulation data set. The data is trained using the LSTM artificial neural network to predict the maximum yaw angular velocity and the sideslip angle of the center of mass based on the real-time input parameters such as vehicle mass, pedal (acceleration, deceleration), vehicle speed, speed, steering wheel angle step input, and motor torque.

[0027] In this embodiment, a data twin simulation data set that integrates physical entity perception data and virtual entity simulation data is deeply analyzed through advanced deep learning technology to generate a prediction value of steering instability of distributed electric vehicles. These prediction values ​​mainly include the predicted values ​​of the sideslip angle at the center of mass and the predicted values ​​of the yaw angular velocity, which are important indicators for evaluating the steering stability of the vehicle. The LSTM neural network model is a deep learning model specially designed for processing and predicting time series data, which can effectively learn long-term dependencies in the data. In this method, the LSTM model is trained to identify and predict the steering stability of distributed electric vehicles under different driving conditions. By inputting the data twin simulation data set, the LSTM model can learn the dynamic behavior patterns of the vehicle under various complex conditions, including its performance under different road adhesion conditions, different loads, different speeds and different steering angles.

[0028] During the training process, the LSTM model uses historical data in the data twin simulation data set to learn the changing trends of the vehicle's center of mass slip angle and yaw rate. These historical data contain detailed information about the vehicle in normal driving and potential unstable states, allowing the model to accurately predict future steering stability. Once the model training is completed, it can receive new data twin simulation data in real time and quickly generate center of mass slip angle prediction values ​​and yaw rate prediction values.

[0029] S4, performing early warning processing on the distributed electric vehicle steering instability prediction value, generating an early warning result or outputting the distributed electric vehicle steering instability prediction value.

[0030] Specifically, step S4 includes: determining whether the yaw rate prediction value is greater than a preset yaw rate deviation instability threshold value; If yes, output the fault cause and give a voice warning; If not, output the yaw rate prediction value.

[0031] Determining whether the predicted value of the sideslip angle of the center of mass is within a preset stable region; If yes, output the predicted value of the center of mass sideslip angle; If not, the fault cause will be output and a voice warning will be given.

[0032] Preferably, using The phase plane method determines the preset stable region, wherein two straight lines in the phase plane that are symmetrical and parallel to the origin serve as the boundaries of the stable region.

[0033] Preferably, the constraint relationship condition for judging whether the predicted value of the center of mass sideslip angle is within a preset stable region is: , , |, , where B1 and B2 are stability boundary constants, is the yaw rate predicted by the LSTM artificial neural network, K is the threshold value of the yaw rate deviation, is the center of mass sideslip angle predicted by the LSTM neural network, C is the center of mass sideslip angle instability prediction value, and D is the yaw rate instability prediction value.

[0034] See also Figure 5 In this embodiment, the prediction value of steering instability of distributed electric vehicles is processed for early warning. This processing process is a key link, which aims to judge the steering stability of the vehicle based on the prediction value generated by the LSTM neural network model, and issue early warning information in time to ensure driving safety. As a key prediction model, the LSTM neural network is sensitive to time and can learn patterns and features in time series data. This makes LSTM have advantages in tasks such as time series prediction and signal processing. The power system model and the long short-term memory (LSTM) prediction model are used to construct a training set for predicting the center of mass sideslip angle and yaw rate. The LSTM method is used to predict the center of mass sideslip angle and yaw rate. If the system detects an abnormal state in a certain aspect, such as a large center of mass sideslip angle, the early warning mechanism will be triggered.

[0035] Specifically, first determine whether the yaw rate prediction value is greater than the preset yaw rate deviation instability threshold value, as shown in Table 3. This threshold value is pre-set based on factors such as the vehicle's driving speed and road adhesion conditions, and is used to distinguish between the vehicle's stable state and unstable state. If the yaw rate prediction value exceeds the threshold value, it indicates that the vehicle may be at risk of steering instability. At this time, the system will output the fault inducement, which may be slippery road surface, excessive speed or excessive steering angle. At the same time, the system will promptly remind the driver to pay attention to the vehicle's driving state through voice warnings, and take corresponding measures, such as slowing down and adjusting the steering angle, to avoid potential dangerous situations. If the yaw rate prediction value does not exceed the preset threshold value, the yaw rate prediction value is output normally for the driver's reference. This helps the driver understand the current steering state of the vehicle and make reasonable driving decisions in advance.

[0036] Next, determine whether the predicted value of the center of mass sideslip angle is within the preset stable zone. This stable zone is determined by the phase plane method, and two straight lines in the phase plane that are symmetrical and parallel to the origin are used as the boundaries of the stable domain. This phase plane method can intuitively represent the stable state of the vehicle. When the predicted value of the center of mass sideslip angle is within the stable zone, it indicates that the vehicle has good trajectory following characteristics and yaw stability, and the vehicle is stable. At this time, the system outputs the predicted value of the center of mass sideslip angle normally. If the predicted value of the center of mass sideslip angle is not within the preset stable zone, it indicates that the vehicle may be at risk of instability. At this time, the system also outputs the cause of the fault and issues a voice warning. These causes of faults may include uneven vehicle load, insufficient tire pressure, etc. Through timely warnings, the driver can quickly take measures to adjust the vehicle's driving state and ensure driving safety.

[0037] In this embodiment, the yaw rate and the sideslip angle of the center of mass are two important control targets. The two control quantities interfere with and couple with each other. Therefore, when studying the instability criticality of the steering stability of distributed electric vehicles, it is necessary to comprehensively consider the above two physical quantities. By adopting the control threshold method to control the sideslip angle of the center of mass and the yaw rate within a certain range, the parameters are identified, and the general expression and different parameters of the stability boundary are given. When using the sideslip angle of the center of mass to judge, the following formula is usually used as the constraint relationship: , , |, , where B1 and B2 are both stability boundary constants, corresponding to the following table 2 according to different road adhesion coefficients to find the corresponding constants, is the yaw rate predicted by the LSTM artificial neural network, K is the threshold value of the yaw rate deviation, and its value is related to the vehicle speed. is the center of mass sideslip angle predicted by the LSTM neural network, C is the center of mass sideslip angle instability prediction value, and D is the yaw rate instability prediction value.

[0038] Table 2 Plane stability boundary parameters

[0039] Table 3 Yaw angular velocity deviation instability threshold

[0040] See also Figure 6 In this embodiment, when the predicted sideslip angle of the center of mass is within the stable region of the phase plane, the vehicle has trajectory following characteristics and yaw stability, and the vehicle drives stably; when the predicted sideslip angle of the center of mass is outside the stable region of the phase plane, the phase trajectory of the sideslip angle of the center of mass diverges, and the vehicle eventually becomes unstable.

[0041] Specifically, in this embodiment, several distributed electric vehicle steering instability judgment criteria are provided, as shown in Table 4.

[0042] Table 4 Steering instability judgment table

[0043] If the predicted value of the center of mass slip angle instability is within the normal working range, the system will output the center of mass slip angle value normally without triggering an early warning; if the predicted value of the center of mass slip angle instability is ≥1, the fault type is judged as an abnormal center of mass slip angle instability fault, and the possible fault cause is analyzed according to the pre-trained model. The center of mass slip angle instability fault information is output and an early warning is issued to remind the driver to drive safely.

[0044] If the predicted yaw rate instability value is within the normal working range, the system outputs the yaw rate value normally and no warning is triggered; if the predicted yaw rate instability value is ≥1, the fault type is judged as yaw rate instability abnormal fault, and the possible fault cause is analyzed according to the pre-trained model. The yaw rate instability fault information is output and a warning is issued to remind the driver to drive safely.

[0045] In summary, the distributed electric vehicle steering stability warning method realizes real-time monitoring and high-precision prediction of the driving status of distributed electric vehicles through the combination of digital twin technology and deep learning algorithm; it not only improves the monitoring accuracy and real-time performance of steering faults, but also ensures the accuracy and reliability of data through multi-source data fusion and strict verification process. In addition, through timely warning processing, potential dangerous situations can be effectively avoided, the driving safety of vehicles can be improved, and strong technical support can be provided for the widespread application of electric vehicles.

[0046] See also Figure 7 The second embodiment of the present invention provides a distributed electric vehicle steering stability warning device, which includes: A virtual entity establishing unit 201 is used to obtain a perception data set collected by a sensor component configured on the electric vehicle, and establish a virtual entity corresponding to the electric vehicle based on the perception data set; A digital twin unit 202 is used to obtain a virtual data set of the virtual entity, and fuse the virtual data set with the perception data set based on the digital twin technology to generate a data twin simulation data set; The LSTM neural network unit 203 is used to calculate the data twin simulation data set using the LSTM neural network model to generate a distributed electric vehicle steering instability prediction value, wherein the distributed electric vehicle steering instability prediction value includes a center of mass sideslip angle prediction value and a yaw angular velocity prediction value; The early warning unit 204 is used to perform early warning processing on the distributed electric vehicle steering instability prediction value, generate an early warning result or output the distributed electric vehicle steering instability prediction value.

[0047] The third embodiment of the present invention provides a distributed electric vehicle steering stability warning device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the distributed electric vehicle steering stability warning method as described in any one of the above.

[0048] A fourth embodiment of the present invention provides a readable storage medium storing a computer program, wherein the computer program can be executed by a processor of a device where the storage medium is located to implement a distributed electric vehicle steering stability warning method as described in any one of the above.

[0049] Exemplarily, the above-mentioned devices and process steps can be implemented by a computer program. The computer program can be divided into one or more units. The one or more units are stored in the memory and executed by the processor to complete the present invention.

[0050] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0051] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the present invention by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0052] Wherein, if the electronic device or printer integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0053] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0054] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A distributed electric vehicle steering stability warning method, characterized in that: include: Acquire a perception data set collected by a sensor component configured on the electric vehicle, and establish a virtual entity corresponding to the electric vehicle based on the perception data set; Acquire a virtual data set of the virtual entity, and fuse the virtual data set with the perception data set based on digital twin technology to generate a data twin simulation data set; The data twin simulation data set is calculated using an LSTM neural network model to generate a distributed electric vehicle steering instability prediction value, wherein the distributed electric vehicle steering instability prediction value includes a center of mass sideslip angle prediction value and a yaw angular velocity prediction value; Perform early warning processing on the distributed electric vehicle steering instability prediction value, generate an early warning result or output the distributed electric vehicle steering instability prediction value.

2. The distributed electric vehicle steering stability early warning method according to claim 1 is characterized in that: Acquire a perception data set collected by a sensor component configured on the electric vehicle, and establish a virtual entity corresponding to the electric vehicle based on the perception data set, specifically: Acquire a perception data set collected by a sensor component configured on the electric vehicle, wherein the perception data set includes SOC data, wheel speed, torque, steering wheel angle, acceleration, and braking force; Establishing a Simulink simulation model based on the perception data set, wherein the Simulink simulation model includes a seven-degree-of-freedom dynamic model of longitudinal, lateral, yaw motion and four wheel rotation, an ideal two-degree-of-freedom model, a magic formula tire model and a longitudinal driver model; The Simulink simulation model and the Carsim vehicle model are fused to generate a virtual entity corresponding to the electric vehicle, wherein the vehicle parameters and the power source in the Carsim vehicle model are modified according to the Simulink simulation model.

3. The distributed electric vehicle steering stability early warning method according to claim 1 is characterized in that: Acquire a virtual data set of the virtual entity, fuse the virtual data set with the perception data set based on digital twin technology, and generate a data twin simulation data set, specifically: Acquiring a virtual data set of the virtual entity, the virtual data set comprising slip rate, vehicle speed, yaw angular velocity, vehicle sideslip angle, lateral acceleration, and yaw moment; Calculating the sensed data set and the virtual data set based on an MPC control algorithm; The data calculated by the MPC control algorithm is processed by HIL hardware-in-the-loop testing, and a data twin simulation data set is constructed based on the test results.

4. The distributed electric vehicle steering stability early warning method according to claim 1 is characterized in that: Performing early warning processing on the distributed electric vehicle steering instability prediction value, generating an early warning result or outputting the distributed electric vehicle steering instability prediction value, specifically: Determining whether the yaw rate prediction value is greater than a preset yaw rate deviation instability threshold value; If yes, output the fault cause and give a voice warning; If not, output the yaw rate prediction value.

5. The distributed electric vehicle steering stability early warning method according to claim 4 is characterized in that: Also includes: Determining whether the predicted value of the sideslip angle of the center of mass is within a preset stable region; If yes, output the predicted value of the center of mass sideslip angle; If not, the fault cause will be output and a voice warning will be given.

6. The distributed electric vehicle steering stability early warning method according to claim 5 is characterized in that: use The phase plane method determines the preset stable region, wherein two straight lines in the phase plane that are symmetrical and parallel to the origin serve as the boundaries of the stable region.

7. The distributed electric vehicle steering stability early warning method according to claim 6 is characterized in that: The constraint relationship condition for judging whether the predicted value of the center of mass sideslip angle is within the preset stable region is: , , |, , where B1 and B2 are stability boundary constants, is the yaw rate predicted by the LSTM artificial neural network, K is the threshold value of the yaw rate deviation, is the center of mass sideslip angle predicted by the LSTM neural network, C is the center of mass sideslip angle instability prediction value, and D is the yaw rate instability prediction value.

8. A distributed electric vehicle steering stability warning device, characterized in that: include: A virtual entity establishing unit, used to obtain a perception data set collected by a sensor component configured on the electric vehicle, and establish a virtual entity corresponding to the electric vehicle based on the perception data set; A digital twin unit, used to obtain a virtual data set of the virtual entity, fuse the virtual data set with the perception data set based on the digital twin technology, and generate a data twin simulation data set; An LSTM neural network unit is used to calculate the data twin simulation data set using an LSTM neural network model to generate a distributed electric vehicle steering instability prediction value, wherein the distributed electric vehicle steering instability prediction value includes a center of mass sideslip angle prediction value and a yaw angular velocity prediction value; The early warning unit is used to perform early warning processing on the distributed electric vehicle steering instability prediction value, generate an early warning result or output the distributed electric vehicle steering instability prediction value.

9. A distributed electric vehicle steering stability warning device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the distributed electric vehicle steering stability warning method as described in any one of claims 1 to 7 is implemented.

10. A readable storage medium, characterized in that: A computer program is stored, and the computer program can be executed by a processor of the device where the storage medium is located to implement the distributed electric vehicle steering stability warning method as described in any one of claims 1 to 7.

Images