Skip to Main Content
With the proliferation of nonlinear loads, power quality problems have been paid more attention to. In order to mitigate the influence, various power quality disturbances must be classified before an appropriate action can be taken. Wavelet packet is developed on wavelet transform, which can provide more plenteous time-frequency information. This paper selects energy and entropy of terminal nodes through wavelet packet decomposition as feature vector respectively, using Bayes classifier to classify the disturbances, which are simulated and analyzed. The simulation results indicate that the entropy acted as feature vector has higher recognition accurate ratio.