QES-Shell: An Expert System for Nuclear Power Plant Operator's Training

Abstract

Decision making in complex systems such as nuclear power plants is a difficult task at best. The nuclear power plant operators are susceptible to various operational mistakes causing the high risk accidents and safety issues. Therefore, the role of expert systems in the offline training program for the operators is ever increasing. In this paper, we describe the development of an Expert System Shell, "QES_SHELL", to assist, off-line, QNPP operators and plant personnel in a better familiarization to infer the anticipated and foreseen malfunctions from the observed symptoms. The "QES_SHELL" has been implemented in the Turbo Prolog language. Its inferencing mechanism is of the "Rule-based" type and it adopts the "Depth First" technique to search the knowledge base. The performance of the QES_SHELL on "LOCA Diagnostics" at QNPP has been found satisfactory through Turing test.