Integrated model-based and data-driven fault detection and diagnosis approach for an automotive electric power steering system

Integrity of electric power steering system is vital to vehicle handling and driving performance. Advances in electric power steering (EPS) system have increased complexity in detecting and isolating faults. In this paper, we propose a hybrid model-based and data-driven approach to fault detection and diagnosis (FDD) in an EPS system. We develop a physics-based model of an EPS system, conduct fault injection experiments to derive fault-sensor measurement dependencies, and investigate various FDD schemes to detect and isolate the faults. Finally, we use an SVM regression technique to estimate the severity of faults.