Power quality disturbances events recognition based on S-transform and probabilistic neural network

Abstract

Power quality (PQ) events recognition is the most important research area of power quality control. A novel high performance classification system based on S-transform and probabilistic neural network is proposed in this paper. Firstly, S-transform processes the original PQ signals into a complex matrix named S-matrix. The time and frequency features of disturbances signal are extracted from the S-matrix. Then, the selected subset of features is used as the input vector of the classifier. Finally, the probabilistic neural network classifier is trained and tested by the simulated simples. The simulation results show the effectiveness of the new approach. © 2010 Springer-Verlag.