Application of FBOLES—a prototype expert system for fault diagnosis in nuclear power plants

Abstract

Abstract The basic concept of a frequency-based on-line expert system (FBOLES) approach for the on-line fault diagnoses of nuclear power plants has been previously presented in our companion papers. This paper reports on the status of the protoype software development and the real time on-line experiment results. The main steam and feedwater condensate system (MSFCS, namely, the secondary loop) of a nuclear power plant (950 MW, three loops) simulated by the Tsinghua simulator has been selected as a target system at the present stage of development. The knowledge bases for MSFCS have been initially constructed. A total of 62 signals from the simulator have been selected as the on-line evidence for diagnosis. Thirty-three fault experiments were performed in which 21 were detected accurately (only one candidate) by FBOLES immediately after the first abnormal signals were received and the other 12 were detected accurately within 0·5 to 3 min as the development of abnormality. These experiments include not only the failures of pumps, valves, pipes, etc., of MSFCS itself, but also the failures outside MSFCS. Three of them involve non-initiating events. As a software package, FBOLES can perform either the on-line diagnosis where the signals are input from the simulator directly or the off-line diagnosis that either repeats the on-line diagnosis in a selectable time scale by using the data received on-line and stored on disk or allows users to input signals from a keyboard. Also, the integrated information base, including the modular mini knowledge bases and other necessary data, can be edited and assembled by users easily and compiled by FBOLES into coded format.