H. Igarashi et al., DEVELOPMENT OF WATER CHEMISTRY DIAGNOSTIC SYSTEM FOR BWRS USING FUZZY-REASONING, Journal of Nuclear Science and Technology, 31(10), 1994, pp. 1023-1037
A diagnostic system for BWR water chemistry has been developed incorpo
rating high-speed fuzzy reasoning, holding in view preventive maintena
nce as principal objective. The system combines two expert systems-one
for detecting an anomaly in the plant operating condition and quickly
inferring its cause in a preliminary analysis, and the other performi
ng a detailed diagnosis of the detected anomaly. The system for anomal
y detection and quick preliminary diagnosis infers the occurrence of v
arious anomalies and their causes from the fuzzy relation existing bet
ween the fuzzy causes and symptoms, applying a high-speed method for s
olving the inverse problem of fuzzy correspondence. The system can be
run on a small size computer, and is thus conveniently adapted to prac
tical application at machine side. The system for detailed diagnosis i
ncorporates the expertise of water chemistry engineers, and outputs pe
rtinent information and data to guide operators. Trial application of
the system using data from actual plant operation conclusively demonst
rated its effectiveness as a practical preventive maintenance system f
or actual plants.