Título: A Comparative Study of the Application of Neural Networks and Decision Trees in the Classification of Incipient Faults in Power Transformers
Autores: Castanheira, Luciana G.; Vasconcelos, João A. de; Reis, Agnaldo J. Rocha; Magalhães, Paulo H. V.; Silva, Sávio A. L. da
Resumo: The power transformer is one of the most important equipment in an electric power system. If this equipment is out of order for some reason, the damage for both society and electric utilities are very significant. In this work, we present a comparative study of the application of Multi-Layer Perceptrons trained via Rprop algorithm and Decision Trees in the classification of incipient faults in power transformers. The proposed procedures have been applied to real databases derived from chromatographic tests of power transformers. The results obtained by both techniques are compared and fully described. The classifiers discussed here can be seen as a very important component in power transformer predictive maintenance activities.
Palavras-chave: Páginas: 8
Código DOI: 10.21528/CBIC2011-24.4
Artigo em pdf: st_24.4.pdf
Arquivo BibTex: st_24.4.bib