An evolutionary computation based fuzzy fault diagnosis system for a power transformer

Author

Huang, Yann-Chang ; Yang, Hong-Tzer ; Huang, Ching-Lien

Author_Institution

Dept. of Electr. Eng., Nat. Cheng Kung Univ., Tainan, Taiwan

fYear

1996

fDate

11-14 Dec 1996

Firstpage

218

Lastpage

223

Abstract

To improve the diagnosis accuracy of conventional dissolved gas analysis (DGA) approaches, this paper proposes an evolutionary programming (EP) based fuzzy system development technique to identify the incipient faults of the power transformers. In comparison to results of the conventional DGA and artificial neural network (ANN) classification methods, the proposed method has been verified to possess superior performance both in developing the diagnosis system and in identifying the practical transformer fault cases

Keywords

fault diagnosis; fuzzy set theory; fuzzy systems; genetic algorithms; neural nets; performance evaluation; power engineering computing; power transformers; artificial neural network; classification methods; dissolved gas analysis; evolutionary computation; evolutionary programming; fuzzy fault diagnosis system; fuzzy system development technique; performance; power transformer; Artificial neural networks; Dissolved gas analysis; Evolutionary computation; Fault diagnosis; Fuzzy systems; Genetic programming; Oil insulation; Petroleum; Power transformer insulation; Power transformers;

fLanguage

English

Publisher

ieee

Conference_Titel

Fuzzy Systems Symposium, 1996. Soft Computing in Intelligent Systems and Information Processing., Proceedings of the 1996 Asian

Conference_Location

Kenting

Print_ISBN

0-7803-3687-9

Type

conf

DOI

10.1109/AFSS.1996.583594

Filename

583594