Automatic Classification of hybrid Power Quality Disturbances using Wavelet Norm Entropy and Neural Network

摘要

The classification of single and multiple power quality (PQ) disturbances is a very important task for the detection and monitoring of various faults and events in electrical power network. This paper presents an automatic classification algorithm for PQ disturbances based on wavelet norm entropy (WNE) features & probabilistic neural network (PNN) as an effective pattern classifier. The discrete wavelet transform (DWT) based multiresolution analysis (MRA) technique is proposed to extract the most important and constructive features of power quality disturbances at various resolution levels. The distinctive norm entropy features of the PQ disturbances are extracted and are employed as inputs to the PNN. Various other architectures of neural networks such as multilayer perceptron (MLP) and radial basis function (RBF) are also employed for comparison. The PNN is found the most suitable classification tool for the classification of the PQ disturbances. The simulation results obtained show that the proposed approach can detect and classify the disturbances effectively and can be applied successfully in real-time electrical power distribution networks.