LEARNING DYNAMIC FAULT MODELS BASED ON A FUZZY SET COVERING METHOD

The synthesis of a real-time diagnostic expert system to monitor plant performance and identify faults in the event of process failure as we ll as signal potential failures is described. The crucial features whi ch have been included are system reliability, use of dynamic trends in data and parameters to identify problem as well as the ability to han dle complex knowledge. The emphasis here is on how a dynamic simulator is used to incorporate a learning algorithm based on a fuzzy set cove ring method for formulating a knowledge model of the operational chara cteristics, which enables debugging and testing of the system to be ca rried out continuously. The procedure is illustrated by reference to t he operation of refinery crude oil distillation columns. (C) 1997 Else vier Science Ltd.