Transformer fault diagnosis method based on rough set and Bayesian otimal classifier

Authors:
Hongsheng Su
Affiliations:
School of Automatic and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou, P.R.China
Venue:
CISST'09 Proceedings of the 3rd WSEAS international conference on Circuits, systems, signal and telecommunications
Year:
2009

Citing 2
Cited 0

Machine Learning

Machine Learning
Fuzzy neural classifier for transformer fault diagnosis based on EM learning

ICIC'06 Proceedings of the 2006 international conference on Intelligent computing: Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

According to intelligent complementary ideas, a new transformer fault diagnosis method is proposed based on rough set (RS) and Bayesian optimal classifier in this paper. Through RS reduction, the diagnostic decision table is simplified and fault symptoms information is compressed, and the minimal decision rules can be obtained. In light of the minimal decision rules, the complexity of Bayesian reasoning and difficulties of fault symptom acquisition are dramatically decreased. Moreover, probability reasoning may be realized by applying Bayesian optimal classifier, which can be used to describe the characteristics of fault information and investigate the fault reasons of transformer. In the end, a simulation example in transformer fault diagnosis indicates that the method is very effective and ubiquitous.