Discrete wavelet transform and probabilistic neural network algorithm for classification of fault type in underground cable

Simple item page
dc.contributor.authorNgaopitakkul, A.
dc.contributor.authorSuttisinthong, N.
dc.date.accessioned2026-08-06T10:03:42Z
dc.date.available2026-08-06T10:03:42Z
dc.date.issued2012-01-01
dc.description.abstractThis paper proposes an algorithm based on a combination of discrete wavelet transform (DWT) and probabilistic neural network (PNN) for classifying fault types on underground cable. Simulations and the training process for the PNN are performed using ATPIEMTP and MATLAB. The mother wavelet daubechies4 (db4) is employed to decompose high frequency component from these signals. The maximum coefficients of DWT of phase A, B, C and zero sequence for post-fault current waveforms are used as an input for the training pattern. Various cases studies based on Thailand electricity distribution underground systems have been investigated so that the algorithm can be implemented. The coefficients of DWT are also compared with those of PNN in this paper. The results show that the proposed algorithm is capable of performing the fault classification with satisfactory accuracy. © 2012 IEEE.
dc.identifier.citationProceedings International Conference on Machine Learning and Cybernetics, 1, 360-366, 2012
dc.identifier.doi10.1109/ICMLC.2012.6358940
dc.identifier.issn2160133X
dc.identifier.other2-s2.0-84871664514
dc.identifier.urihttps://dspace.kmitl.ac.th/handle/123456789/4040
dc.sourceProceedings International Conference on Machine Learning and Cybernetics
dc.subjectFault classification
dc.subjectProbabilistic neural network
dc.subjectUnderground cable
dc.subjectWavelet transform
dc.titleDiscrete wavelet transform and probabilistic neural network algorithm for classification of fault type in underground cable
dc.typeConference Paper

Files

Collections

Research