ONLINE FAULT-DIAGNOSIS OF POWER SUBSTATION USING CONNECTIONIST EXPERT-SYSTEM

This paper proposes a new connectionist (or neural network) expert sys tem for on-line fault diagnosis of a power substation. The Connectioni st Expert Diagnosis System has similar profile of an expert system, bu t can be constructed much more easily from elemental samples. These sa mples associate the faults with their protective relays and breakers a s well as the bus voltages and feeder currents. Through an elaborately designed structure, alarm signals are processed by different connecti onist models. The output of the connectionist models is then integrate d to provide the final conclusion with a confidence level. The propose d approach has been practically verified by testing on a typical Taiwa n Power (Taipower) secondary substation. The test results show that ra pid and exactly correct diagnosis is obtained even for the fault condi tions involving multiple faults or failure operation of protective rel ay and circuit breaker. Moreover, the system can be transplanted into various substations with little additional implementation effort.