On-line fault detection and diagnosis based on a coupled system

An on-line fault detection and diagnosis system, which has been designed to cope with transient behaviours of the process, is described in this paper. The system consists of a knowledge based approach coupled with a hierarchical structure of fuzzy neural networks. Fault detection is performed through the knowledge based system. The hierarchical structure of fuzzy neural networks performs the fault diagnosis task. The aim of this approach is to diagnose multiple simultaneous faults from only single fault symptoms. A chemical process has been used as a test bed of the current approach.