DEVELOPMENT OF AN ONLINE FUZZY EXPERT-SYSTEM FOR INTEGRATED ALARM PROCESSING IN NUCLEAR-POWER-PLANTS

An on-line fuzzy expert system, called alarm filtering and diagnostic system (AFDS), was developed to provide the operator with clean alarm pictures and system-wide failure information during abnormal states th rough alarm filtering and diagnosis, In addition, it carries out alarm prognosis to warn the operator of process abnormalities. Clean alarm pictures that have no information overlapping are generated from multi ple activated alarms at the alarm filtering stage. The meta rules for dynamic filtering were established on the basis of the alarm relations hip network. In the case of alarm diagnosis, the relations between ala rms and abnormal states are represented by means of fuzzy relations, a nd the compositional inference rule of fuzzy logic is utilized to infe r abnormal states from the fuzzy relations. The AFDS offers the operat or related operating procedures as well as diagnostic results, At the stage of alarm prognosis, the future values of some important critical safety parameters are predicted by means of Levinson algorithm select ed from the comparative experiments, and the global trends of these pa rameters are estimated using data smoothing and fuzzy membership. This information enables early failure detection and is also used to suppl ement diagnostic symptoms. The AFDS has been validated and demonstrate d using the full-scope simulator for Yonggwang Units 1, 2. From the va lidation results, it can be concluded that the AFDS is able to aid the operator to terminate early and mitigate plant abnormalities.