A KNOWLEDGE-BASED EXPERT SYSTEM FOR FAULT DIAGNOSIS IN CHEMICAL PROCESSES

This paper develops a real-time expert system CPFD for fault diagnosis in chemical processes.Thissystem consists of dynamic database,knowledge base with editor,inference engine and man-machine in-terface.Knowledge base is composed of a series of production rules with certainty factor.Inference engineuses reasoning with uncertainty,"optimal depth first"control strategy and bidirectional search algorithm.The proposed system has been successfully applied to a large production scale catalytic cracker.