Wavelet ANN based transformer fault diagnosis using gas-in-oil analysis

Author

Honglei, Li ; Dengming, Xiao ; Yazhu, Chen

Author_Institution

Shanghai Jiaotong Univ., China

Volume

1

fYear

2000

fDate

2000

Firstpage

147

Abstract

This paper describes a wavelet artificial neural network (ANN) for signal classification, and applies it for transformer Fault Detection with dissolved gas analysis (DGA). The weights of the network are replaced by wavelet functions and are corrected by conjugate gradient method in the training iteration. Preliminary simulation results show wavelet ANN for DGA can get a 95% correct diagnosis rate, superior then BP ANN. Besides, precondition techniques of input data is studied, a suitable precondition algorithm play an important role in ANN

Keywords

conjugate gradient methods; fault diagnosis; insulation testing; neural nets; power transformer insulation; power transformer testing; signal classification; transformer oil; wavelet transforms; conjugate gradient method; dissolved gas analysis; fault diagnosis; gas-in-oil analysis; power transformer insulation; precondition algorithm; signal classification; wavelet artificial neural network; Artificial neural networks; Dissolved gas analysis; Fault detection; Fault diagnosis; Gases; Oil insulation; Pattern classification; Power transformer insulation; Power transformers; Wavelet analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Properties and Applications of Dielectric Materials, 2000. Proceedings of the 6th International Conference on

Conference_Location

Xi´an

Print_ISBN

0-7803-5459-1

Type

conf

DOI

10.1109/ICPADM.2000.875651

Filename

875651