Diagnosis of DGA based on fuzzy and ANN methods

N. Gao; G. J. Zhang; Z. Qian; Z. Yan; D. H. Zhu

Diagnosis of DGA based on fuzzy and ANN methods

N. Gao
, G. J. Zhang
, Z. Qian
, Z. Yan
, D. H. Zhu

Tsinghua University

Research output: Contribution to conference › Paper › peer-review

18 Scopus citations

Abstract

The accuracy of diagnosis with DGA (Dissolved Gas Analysis) is not satisfied though it is used widely in oil-immersed insulation. In this paper, the FART (Fuzzy Adaptive Resonance Theory) network is constructed to enhance the diagnostic accuracy of DGA method. Two input manners are discussed, one is the membership function of dissolved gases based on statistic method, another is the principal component analysis method. Finally, the practical examples had been given for checking the results of insulation diagnosis, it is shown that with the method introduced, the diagnosis will be more effective.

Original language	English
Pages	767-770
Number of pages	4
State	Published - 1998
Externally published	Yes
Event	Proceedings of the 1998 International Symposium on Electrical Insulating Materials - Toyohashi, Jpn Duration: 27 Sep 1998 → 30 Sep 1998

Conference

Conference	Proceedings of the 1998 International Symposium on Electrical Insulating Materials
City	Toyohashi, Jpn
Period	27/09/98 → 30/09/98

Cite this

@conference{b9228b1f6dee4624afe8926b92fdc611,

title = "Diagnosis of DGA based on fuzzy and ANN methods",

abstract = "The accuracy of diagnosis with DGA (Dissolved Gas Analysis) is not satisfied though it is used widely in oil-immersed insulation. In this paper, the FART (Fuzzy Adaptive Resonance Theory) network is constructed to enhance the diagnostic accuracy of DGA method. Two input manners are discussed, one is the membership function of dissolved gases based on statistic method, another is the principal component analysis method. Finally, the practical examples had been given for checking the results of insulation diagnosis, it is shown that with the method introduced, the diagnosis will be more effective.",

author = "N. Gao and Zhang, \{G. J.\} and Z. Qian and Z. Yan and Zhu, \{D. H.\}",

year = "1998",

language = "英语",

pages = "767--770",

note = "Proceedings of the 1998 International Symposium on Electrical Insulating Materials ; Conference date: 27-09-1998 Through 30-09-1998",

}

TY - CONF

T1 - Diagnosis of DGA based on fuzzy and ANN methods

AU - Gao, N.

AU - Zhang, G. J.

AU - Qian, Z.

AU - Yan, Z.

AU - Zhu, D. H.

PY - 1998

Y1 - 1998

N2 - The accuracy of diagnosis with DGA (Dissolved Gas Analysis) is not satisfied though it is used widely in oil-immersed insulation. In this paper, the FART (Fuzzy Adaptive Resonance Theory) network is constructed to enhance the diagnostic accuracy of DGA method. Two input manners are discussed, one is the membership function of dissolved gases based on statistic method, another is the principal component analysis method. Finally, the practical examples had been given for checking the results of insulation diagnosis, it is shown that with the method introduced, the diagnosis will be more effective.

AB - The accuracy of diagnosis with DGA (Dissolved Gas Analysis) is not satisfied though it is used widely in oil-immersed insulation. In this paper, the FART (Fuzzy Adaptive Resonance Theory) network is constructed to enhance the diagnostic accuracy of DGA method. Two input manners are discussed, one is the membership function of dissolved gases based on statistic method, another is the principal component analysis method. Finally, the practical examples had been given for checking the results of insulation diagnosis, it is shown that with the method introduced, the diagnosis will be more effective.

UR - https://www.scopus.com/pages/publications/0032321008

M3 - 论文

AN - SCOPUS:0032321008

SP - 767

EP - 770

T2 - Proceedings of the 1998 International Symposium on Electrical Insulating Materials

Y2 - 27 September 1998 through 30 September 1998

ER -

Diagnosis of DGA based on fuzzy and ANN methods

Abstract

Conference

Other files and links

Fingerprint

Cite this