Fault diagnosis of vacuum circuit breaker based on coil current of release

Abstract

The release is the key component of operation mechanism of circuit breaker. Its current waveform contains many information. The fault diagnosis of circuit breaker can be realized by analyzing the current waveform of coil. Firstly, the combination method of wavelet analysis and seeking extreme points in region extremum is proposed to obtain the feature values of coil current of circuit breakers. Then, a novel intelligent particle swarm optimization (PSO) algorithm was adopted to search the optimal parameters of support vector machine (SVM). Finally, a high-performance SVM with optimal parameters is constructed for fault diagnosis. The experimental results show that the method can achieve a high fault diagnosis accuracy.