Abstract—This paper presents an Artificial Neural Network (ANN) based approach for power system transient classification. Wavelet transform is applied to extract the features from the raw signal. An entropy based method is proposed to select the input features of the network. The entropy based method reduces the size of the input features without losing the characteristics of the signal. The selected features are given to a Radial Basis Function (RBF) neural network for further classification. The data required to develop the network are generated by simulating various faults in the test system. The simulation results show that the proposed method provides a robust and accurate method for power system transient classification.

Index Terms—Artificial Neural Networks, classification, Power system transients, disturbances, Wavelet Transform.

T.Jayasree is with the Electronics and Communication Engineering Department, Govt. Polytechnic College, Tuticorin, India (corresponding author to provide phone: 91 9486324974. Email: tjay_sree@yahoo.co.in)
D.Devaraj is with the Electrical and Electronics Engineering Department, Kalasalingam University, Srivilliputhur, India. (email:deva230@yahoo.com)
R.Sukanesh is with the Electronics and Communication Engineering Department, Thiagaraja College of Engineering, Madurai, India. (email: rshece@tce.edu)

Cite: T. Jayasree, D. Devaraj and R. Sukanesh, "Classification of Transients using Wavelet Based Entropy and Radial Basis Neural Networks," International Journal of Computer and Electrical Engineering vol. 1, no. 5, pp. 590-595, 2009.