Combined Hilbert Transform-Neural Network Approach for Discrimination Between Inrush and Short-Circuit Currents

 

E. A. Feilat* and K. Al-Tallaq
Department of Electrical Power Engineering
Hijjawi Faculty for Engineering Technology
Yarmouk University 21163
Irbid, Jordan
*E-mail: eafeilat@yu.edu.jo

Abstract

This paper presents a new approach for digital protection of power transformers. The proposed technique is based on Hilbert transform (HT) combined with artificial neural network (ANN) for discrimination between the magnetizing inrush and internal short-circuit currents in power transformers. Hilbert transform is firstly applied as a pre-processing module to extract distinctive features from the transient current and voltage signals at the digital relay location. The features represent the instantaneous values of the apparent impedance seen by the relay during the first cycle of the transient period. Secondly, the features are fed into an ANN for classifying the transient phenomenon into either magnetizing inrush or short-circuit current. The results presented in this paper show that the proposed technique is very effective in discrimination between inrush and short-circuit currents power transformers.


To read the full article,
please log in:
If you haven't registered already,
you can do so for free:
 
© Copyright 2000-2004 Professor F.R. Hall & Dr I. Oraifige, University of Wolverhampton.
 
close this window