Adaptive fault diagnosis of HVCBs based on P-SVDD and P-KFCM

High voltage circuit breakers (HVCBs) are among most important pieces of equipment in the power system, and thus its fault diagnosis is quite essential for efficient operation. Most related research can only diagnose the known fault. However, the diagnosis may fail to work when an unknown fault occurs. Aimed to address the lack of new knowledge acquisition and real-time model classification updating, a novel method based on particle swarm optimization-support vector domain description (P-SVDD) and particle swarm optimization-kernel-based fuzzy c-means (P-KFCM) is proposed for adaptive fault diagnosis of HVCBs in this paper. In the proposed method, P-SVDD can detect the unknown fault sample by particle swarm optimization (PSO) parameter optimization while P-KFCM is used in known sample category recognition and its modified partition coefficient (MPC) cluster validity is used in unknown fault category search. The proposed method's operation process is introduced in detail, and the principles underlying the adaptive fault diagnosis model are discussed as well. In engineering application of an online monitoring system with fault diagnosis, the simulation results based on the measured HVCB closing coil current show that the proposed adaptive model can acquire new knowledge and update model classification in real-time with a higher diagnostic accuracy, compared with the existing algorithms.