Research on Digital Twin Vehicle Stability Monitoring System Based on Side Slip Angle

Focusing on the low efficiency of the current active safety control method with intelligent networked vehicles, which cannot warn potential dangers in advance, a digital twin vehicle stability monitoring system based on side slip angle is proposed. By analyzing the practical significance of digital twin technology in automobile field, the framework of vehicle stability monitoring system is proposed, which includes vehicle physical system, virtual vehicle model system, vehicle twin data platform and comprehensive monitoring system. Firstly, a virtual vehicle model is established, and its accuracy and real-time performance are verified by real vehicle test. The PSOLSTM (Particle Swarm Optimization Long and Short-Term Memory) algorithm relied on the improved LSTM (Long and Short-Term Memory) is designed in the cause of construct automobile side slip angle state estimator model, which has better accuracy and followability. Secondly, a simulation experiment platform and a real vehicle test platform are built based on the comprehensive monitoring system to verify the accuracy and real-time performance of the designed vehicle side slip angle state estimator model. The experiments show that the maximum estimation error of automobile side slip angle is only 0.634deg under four different working conditions. Finally, a digital twin vehicle stability monitoring platform based on side slip angle is designed. The new intelligent vehicle active safety control mode of “data-driven, virtual-real combination, accurate estimation, autonomous decision-making, shared autonomy” is realized under the drive of digital twin.

I. Introduction

With the continuous progress of conspiring to build a global ecological civilization, the development of green vehicles has become a significant way to attain the “double carbon”. The low-carbon development of automobile industry is of strategic significance to implement the “double carbon” strategy [1]. The intelligent and connected electric vehicle has become the mainstream direction of electric vehicle development [2], [3], [4]. The active safety technology of electric automobile is a vital factor in the system control of electric automobile [5]. At present, most of the vehicle controllers of electric vehicles overall monitor the parameters of various working conditions of electric vehicles and change the vehicle driving parameters according to them, so as to realize the control of electric vehicles. This method has low working efficiency, untimely control and cannot detect and warn some potential dangers in advance. It has a gap with the high standard control effect of intelligent and connected electric automobile. Therefore, it is urgent to propose an efficient and predictable vehicle active safety control system.