Classification of power quality disturbances using quantum neural network and DS evidence fusion

Abstract

SUMMARY A novel classifier based on Quantum Neural Network (QNN) and Dempster-Shafer (DS) evidence theory to recognize the types of power quality (PQ) disturbances is presented. According to the Discrete Wavelet Transform (DWT), Wavelet Packet Transform (WPT) and S-transform (ST) algorithms, three kinds of feature vectors extracted from the original signals are used to train three different quantum neural networks, then DS evidence theory is used for global fusion at the decision level to gain a unified classification result from the outputs of QNNs. Ten types of disturbances are considered for the classification problem. Simulation results indicate that the classification performance of QNN is better than back propagation neural network (BPNN). The recognition capability of the QNN-DS classifier is compared with BPNN-DS, probabilistic neural network with voting rules (PNN-VR) at the decision level, and only one QNN with information fusion at the feature level. It shows that the proposed classifier has good performance on recognizing single and multiple disturbances under different situations and can achieve a highest accuracy of all. Copyright © 2011 John Wiley & Sons, Ltd.