SURVEY OF ARTIFICIAL-INTELLIGENCE METHODS FOR DETECTION AND IDENTIFICATION OF COMPONENT FAULTS IN NUCLEAR-POWER-PLANTS

A comprehensive survey of computer-based systems that apply artificial intelligence methods to detect and identify component faults in nucle ar power plants is presented. Classification criteria are established that categorize artificial intelligence diagnostic systems according t o the types of computing approaches used (e.g., computing tools, compu ter languages, and shell and simulation programs), the types of method ologies employed (e.g., types of knowledge, reasoning and inference me chanisms, and diagnostic approach), and the scope of the system. The m ajor issues of process diagnostics and computer-based diagnostic syste ms are identified and cross-correlated with the various categories use d for classification. Ninety-five publications are reviewed.