Fault Diagnosis for High Voltage Circuit Breakers With Improved Characteristic Entropy of Wavelet Packet

Based on the introduction of wavelet packet and characteristic entropy,a new method to diagnosis fault for high voltage circuit breakers is presented,and its steps and analysis are also introduced. The method combines the strongpoint of wavelet packet and characteristic entropy. Firstly,vibration after clearing up noise is wp-decomposed at the third level,and the eight signals of each junction at the third level are reconstructed; Secondly,the vector is extracted with the segmental energy of reconstructed signals based on the theory of entropy; and lastly the classification of characteristic parameter is realized with simple BP neural network for fault diagnosis. The experimentation without loads indicates the method can easily and accurately diagnose breaker faults,and exploit a new road for fault diagnosis of HV circuit breakers.