Multi-Modal Diagnostics for Vehicle Fault Detection

Abstract

On-board vehicle diagnostic systems must have low development and hardware costs in order to be viable. Model-based methods have shown promise since they use analytical redundancy to reduce costly physical redundancy. However, these methods must also be computationally efficient and function accurately even with simple, low-cost models. The approach presented in this paper uses multiple simple models to analyze dissimilar observable modes of a system. Residuals generated using the models are related and interpreted in a Bayesian network to determine fault probabilities and yield a diagnosis. The technique is demonstrated with a diagnostic system for automobile handling.