Fault diagnosis of a train door system based on semantic knowledge representation

Recent developments in defining ontologies for a domain provide significant potential in model design, able to encapsulate the essence of the diagnostic semantic into concepts and to describe the key relationships between the components of the system being diagnosed. In this paper, a framework based on the knowledge space of the system is developed to guide the fault detection process and better automated knowledge discovery to improve diagnostics. The approach is applied to the domain of a pneumatic door system of a rolling stock vehicle. This article describes the diagnostic capabilities of the proposed ontology-based approach, illustrating these concepts using measurements taken from a door system placed in a test rig, and reports diagnostic results in the situation where the door system is not faulty, but showing symptomatic behaviour. The results presented here are considered as advisory information to assist the maintenance engineer in order to recover from the fault.