The Case for a Hybrid Approach to Diagnosis: A Railway Switch

Behavioral models are at the core of FaultDetection and Isolation (FDI) and Model-Based Diagnosis (MBD) methods. In some practical applications, however, building and validating such models may not always be possible, or only partially validated models can be obtained. In this paper we present a diagnosis solution when only a partially validated model is available. The solution uses a fault-augmented physics-based model to extract meaningful behavioral features corresponding to the normal and abnormal behavior. These features together with experimental training data are used to build a data-driven statistical model used for classifying the behavior of the system based on observations. We apply this approach for a railway switch diagnosis problem.