Fault Detection and Repairing for Intelligent Connected Vehicles Based on Dynamic Bayesian Network Model

With the development of Internet of Things and intelligent transport system, the intelligent connected vehicle (ICV) represents the future direction of the vehicle industry. Due to the open wireless medium, high speed mobility and vulnerability to environmental impact, vehicle data faults are inevitable, which may lead to traffic jam or even accident threatening the life of the driver and passengers. At present, there are few studies for fault detection and repairing of ICV while using traditional methods directly for ICV has a low accuracy. In this paper, we propose a threshold-based fault detection and repairing scheme using a dynamic Bayesian network (DBN) model, which can obtain the temporal and spatial correlations of vehicle data for accurate real-time or history fault detection and repairing. In addition, we give an algorithm of how to select the threshold to achieve the best effect by history data before fault detection and repairing process. Finally, simulation results show that the proposed scheme possesses a good fault detection and repairing accuracy as well as a low false alarm rate compared to other available methods.