Development of fault diagnosis methods based on qualitative predictions of symptom evolution behaviors

Abstract

A SDG-based reasoning procedure is presented in this paper to qualitatively predict the evolution process of one or more fault propagating in a multi-loop process system. A set of IF-THEN rules are then constructed accordingly for diagnosis purpose. The resulting fuzzy inference system can be used to identify not only the locations of fault origins but also their magnitude levels. Numerical simulation studies have been carried out to verify the feasibility of the proposed approach.