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