Applying Energy-Equal Entropy of Wavelet Packet to Diagnose CircuitBreaker Faults

摘要

Aiming to better reflect features of machinery vibration signals of high-voltage (HV) circuit breaker (CB), anew method is proposed on the basis of energy-equal entropy of wavelet packet(WP). First of all, three-layer waveletpacket decomposes vibration signal, reconstructing 8 nodes of signals in the 3rd layer. Then, the vector is extracted withenergy-equal entropy of reconstructed signals. At last, the simple back-propagation (BP) neural network for fault diagnosiscontributes to classification of the characteristic parameter. This technology is the basis of a number of patents and patentspending, which is experimentally demonstrated by the significant improvement of diagnose faults.