Redes Bayesianas aplicadas ao Diagnóstico de Falhas Incipientes em Transformadores de Potência (Bayesian Networks applied to Failure Diagnosis in Power Transformer)

Angel Javier Quispe Carita (anngelc@gmail.com)1, Luciana Cambraia Leite (luciana@del.ufms.br)1, Aarão Pedro Pires Medeiros (aaraojr@gmail.com)1, Ruben Barros (ruben@batlab.ufms.br)2, leandro Sauer (leandrosauer@uol.com.br)2


1Universidade Federal de Mato Grosso do Sul / UFMS
2UFMS

This paper appears in: Revista IEEE América Latina

Publication Date: June 2013
Volume: 11,   Issue: 4 
ISSN: 1548-0992


Abstract:
This work describes the structure, learning and application of Bayesian Network to diagnosis of faults in power transformer through the dissolved gases analysis (DGA) in oil. The Bayesian Network uses the concentration ratios of gases methane/hydrogen (CH4/H2), ethane/methane (C2H6/CH4), ethylene/ethane (C2H4/C2H6) and acetylene/ethylene (C2H2/C2H4), as elements that activate the network diagnosis: normal deterioration, electrical failure and thermal failure. The learning was performed from historical database, and the Bayesian Network presented a high degree of reliability and consistency. The simulations suggest good results when compared to some existing in the literature.

Index Terms:
Bayesian Network, Transformer Failures , Bayesian Learning, DGA.   


Documents that cite this document
This function is not implemented yet.


[PDF Full-Text (1038)]