Please use this identifier to cite or link to this item: https://hdl.handle.net/11499/9357
Full metadata record
DC FieldValueLanguage
dc.contributor.authorKöroğlu, Selim-
dc.contributor.authorDemirçali, Akif-
dc.date.accessioned2019-08-16T13:00:10Z
dc.date.available2019-08-16T13:00:10Z
dc.date.issued2016-
dc.identifier.issn1532-5008-
dc.identifier.urihttps://hdl.handle.net/11499/9357-
dc.identifier.urihttps://doi.org/10.1080/15325008.2016.1219427-
dc.description.abstractThis article presents an intelligent diagnosis and classification method for power transformer fault classification based on dissolved gas analysis: the support vector machine. It is a powerful algorithm for classification of faults that needs a limited set of small sampling data, a case of applications with non-linear behavior, and a high number of parameters; however, appropriate model parameters must be determined carefully. The selection of parameters has a direct effect on the machine's classification accuracy. In this study, a multi-layer support vector machine classifier is optimized by a grid search method and three heuristic approaches: (1) genetic, (2) differential evolution, and (3) particle swarm optimization algorithms. The performance analysis of the support vector machine hybridized with these optimization methods is demonstrated using the same classification set. The employed structure has five support vector machine layers, each of which uses a Gaussian kernel function due to its advantages of needing one parameter for optimization and providing excellent classification ability for non-linear data. The proposed approach gives highly accurate performance for diagnosis of power transformers. The support vector machine optimized with the particle swarm optimization algorithm has the best accuracy and requires less computational time compared to the other methods. © 2016, Copyright © Taylor & Francis Group, LLC.en_US
dc.language.isoenen_US
dc.publisherTaylor and Francis Inc.en_US
dc.relation.ispartofElectric Power Components and Systemsen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectdifferential evolution algorithmen_US
dc.subjectdissolved gas analysisen_US
dc.subjectgenetic algorithmen_US
dc.subjectgrid searchen_US
dc.subjectparticle swarm optimizationen_US
dc.subjectsupport vector machineen_US
dc.subjecttransformer fault diagnosisen_US
dc.subjectComputer aided diagnosisen_US
dc.subjectEvolutionary algorithmsen_US
dc.subjectFace recognitionen_US
dc.subjectFault detectionen_US
dc.subjectGenetic algorithmsen_US
dc.subjectHeuristic algorithmsen_US
dc.subjectHeuristic methodsen_US
dc.subjectParticle swarm optimization (PSO)en_US
dc.subjectPower transformersen_US
dc.subjectSupport vector machinesen_US
dc.subjectVectorsen_US
dc.subjectClassification accuracyen_US
dc.subjectDifferential evolution algorithmsen_US
dc.subjectDissolved gas analysisen_US
dc.subjectGaussian kernel functionsen_US
dc.subjectGrid searchen_US
dc.subjectParticle swarm optimization algorithmen_US
dc.subjectSupport vector machine classifiersen_US
dc.subjectTransformer fault diagnosisen_US
dc.subjectOptimizationen_US
dc.titleDiagnosis of power transformer faults based on multi-layer support vector machine hybridized with optimization methodsen_US
dc.typeArticleen_US
dc.identifier.volume44en_US
dc.identifier.issue19en_US
dc.identifier.startpage2172
dc.identifier.startpage2172en_US
dc.identifier.endpage2184en_US
dc.authorid0000-0001-8178-3227-
dc.authorid0000-0001-9030-7775-
dc.identifier.doi10.1080/15325008.2016.1219427-
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.identifier.scopus2-s2.0-84994145011en_US
dc.identifier.wosWOS:000387800200004en_US
dc.identifier.scopusqualityQ2-
dc.ownerPamukkale University-
item.fulltextNo Fulltext-
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.cerifentitytypePublications-
item.languageiso639-1en-
item.grantfulltextnone-
item.openairetypeArticle-
crisitem.author.dept10.04. Electrical-Electronics Engineering-
crisitem.author.dept10.04. Electrical-Electronics Engineering-
Appears in Collections:Mühendislik Fakültesi Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection
Show simple item record



CORE Recommender

SCOPUSTM   
Citations

17
checked on Nov 16, 2024

WEB OF SCIENCETM
Citations

12
checked on Nov 21, 2024

Page view(s)

46
checked on Aug 24, 2024

Google ScholarTM

Check




Altmetric


Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.