CHEMICAL-PLANT FAULT-DIAGNOSIS THROUGH A HYBRID SYMBOLIC-CONNECTIONIST MACHINE LEARNING APPROACH

A novel hybrid symbolic-connectionist approach to machine learning is introduced and applied to fault diagnosis of a hydrocarbon chlorinatio n plant. The learning algorithm addresses the knowledge acquisition pr oblem by developing and maintaining the knowledge base through instanc e based inductive learning. The performance of the learning system is discussed in terms of the knowledge extracted from example cases and i ts classification accuracy on the test cases. Results indicate that th e introduced system is a promising alternative to neural networks for fault diagnosis and a complement to expert systems. (C) 1997 Elsevier Science Ltd.