A process fault detection and diagnosis system (PFD&D) is proposed for comp
lex chemical plants. The system combines an artificial neural network (ANN)
based supplement of a fuzzy system in a block-oriented configuration. A me
thodology for designing the system is described. As a motivating example, a
chemical plant with a recycle stream is considered. Faults in the supply o
f raw materials and in controllers are simulated. The performance of the sy
stem in handling simultaneous faults is also analysed. A comparison of the
proposed approach is made with a classification method (ANNs) and inference
methods (knowledge-based system). Results of system implementation in a fl
uidised bed coal gasifier at pilot plant scale are also shown. (C) 2001 Els
evier Science Ltd. All rights reserved.