Selection of proper artificial neural networks for fault classification on single circuit transmission line

Simple item page
dc.contributor.authorBunjongjit, Sulee
dc.contributor.authorNgaopitakkul, Atthapol
dc.date.accessioned2026-08-06T10:03:58Z
dc.date.available2026-08-06T10:03:58Z
dc.date.issued2012-01-01
dc.description.abstractThis paper proposes a new technique using discrete wavelet transform (DWT) and artificial neural networks for fault classification on single circuit transmission line. Simulation and the training process for the artificial neural networks are performed using ATP/EMTP and MATLAB respectively. The mother wavelet daubechies4 (db4) is employed to decompose high frequency component from these current signals. Positive sequence current signals are employed in faults detection decision algorithm. The variations of first scale high frequency component detecting faults are employed as an input for the training process. Back-propagation (BP) neural network, Radial basis function (RBF) neural network and Probabilistic neural network (PNN) are compared in this paper. The results are shown that average accuracy values obtained from PNN give satisfactory results with less training time. © 2012 ICIC International.
dc.identifier.citationInternational Journal of Innovative Computing Information and Control, 8(1 A), 361-374, 2012
dc.identifier.issn13494198
dc.identifier.other2-s2.0-84856950586
dc.identifier.urihttps://dspace.kmitl.ac.th/handle/123456789/4106
dc.sourceInternational Journal of Innovative Computing Information and Control
dc.subjectFault classification
dc.subjectNeural networks
dc.subjectTransmission line
dc.subjectWavelet transform
dc.titleSelection of proper artificial neural networks for fault classification on single circuit transmission line
dc.typeArticle

Files

Collections

Research