By Topic

A novel feature extraction and optimisation method for neural network-based fault classification in TCSC-compensated lines

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Cheong, W.J. ; Dept. of Electron. & Electr. Eng., Univ. of Bath, UK ; Aggarwal, R.K.

The suitability of fault classifiers introduced hitherto to operate correctly under a real TCSC transmission system remains a challenge since the computations are determined based on a number of postulations. This paper describes an alternative approach to fault classification in TCSC tines using artificial neural networks (ANNs). Special emphasis is placed on illustrating a combined wavelet transform and selforganising map (SOM) methodology to extract, validate and optimise the key characteristics of the fault transient phenomena in a TCSC line such that the input features to the ANNs are near optimal. As a result, it is shown that the fault classification proposed provides the ability to accurately classify the fault type, obviating the need for any predefined assumptions. Extensive simulation studies have been made to verify that the proposed method is both powerful and appropriate for fault classification.

Published in:

Power Engineering Society Summer Meeting, 2002 IEEE  (Volume:2 )

Date of Conference:

25-25 July 2002