FAULT ISOLATION USING FUZZY MODEL-BASED OBSERVERS

Abstract

Model-based fault detection and isolation is an approach with increasing attention in the academic and industrial fields, due to economical and safety related matters. However, in practice it is very difficult to achieve accurate models for complex nonlinear plants. The inherent characteristics of fuzzy logic theory makes it suitable for Fault Detection and Isolation (FDI). This paper proposes a regularity criterion to determine the structure of fuzzy models and a fuzzy decision making approach to isolate faults. An industrial valve simulator is used to detect and isolate several abrupt and incipient faults.