relation: https://khub.utp.edu.my/scholars/391/
title: Taguchi's method for optimized neural network based autoreclosure in extra high voltage lines
creator: Desta, Z.F.
creator: Rao, K.S.R.
description: This paper presents a method to discriminate the temporary faults from the permanent ones in an extra high voltage transmission line so that improper reclosing of the line into a fault is avoided. The fault identification prior to reclosing is based on optimized artificial neural network associated with Levenberg Marquardt algorithm to train the ANN and Taguchi's Method to find optimal parameters of the algorithm and number of hidden neurons. The algorithms are developed using MATLABTM software. A range of faults are simulated using SimPowerSytemsTM and the spectra of the fault data are analyzed using Fast Fourier Transform which facilitates extraction of distinct features of each fault type. For both training and testing purposes, the neural network is fed with the normalized energies of the DC component, the fundamental and the first four harmonics of the faulted voltages. The developed algorithm is verified with dedicated testing data. The results show that it is possible to effectively distinguish the type of fault and practically avoid reclosing into faults. ©2008 IEEE.
date: 2008
type: Conference or Workshop Item
type: PeerReviewed
identifier:   Desta, Z.F. and Rao, K.S.R.  (2008) Taguchi's method for optimized neural network based autoreclosure in extra high voltage lines.  In: UNSPECIFIED.     
relation: https://www.scopus.com/inward/record.uri?eid=2-s2.0-63049108927&doi=10.1109%2fPECON.2008.4762603&partnerID=40&md5=017ca117ee59727552b8bb7d74fc0280
relation: 10.1109/PECON.2008.4762603
identifier: 10.1109/PECON.2008.4762603