Fault Diagnosis Strategy of Autonomous Steering System for Intelligent Vehicle Based on State Estimation

2022 6th CAA International Conference on Vehicular Control and Intelligence (CVCI)(2022)

引用 0|浏览0
This paper proposes a fault diagnosis strategy of autonomous steering system for intelligent vehicles based on state estimation. An autonomous steering controller with rack displacement signal as state input is designed to improve the performance of autonomous steering. Due to the importance of rack displacement signal and the harsh working environment of the displacement sensor, the fault diagnosis strategy composed of Bidirectional Long Short-Term Memory (Bi-LSTM) based rack displacement estimator and Sequential Probability Ratio Test (SPRT) based fault diagnosis flow is proposed to detect displacement sensor faults quickly and accurately. The estimator incorporates information of the vehicle and estimates the rack displacement. In addition, the residual sequence of rack displacement signals is analyzed to monitor the fault signal to further determine state of the sensor. Through simulation, the effectiveness of the proposed strategy is verified.
Autonomous steering system,Fault diagnosis strategy,Bidirectional Long Short-Term Memory (Bi-LSTM),Sequential Probability Ratio Test (SPRT)
AI 理解论文