Title :
Diagnosis of DGA based on fuzzy and ANN methods
Author :
Gao, N. ; Zhang, G.J. ; Qian, Z. ; Yan, Z. ; Zhu, D.H.
Author_Institution :
Dept. of Electr. Eng., Tsinghua Univ., Beijing, China
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
Keywords :
ART neural nets; fuzzy neural nets; insulating oils; insulation testing; principal component analysis; ANN; DGA; FART network; artificial neural network; dissolved gas analysis; fuzzy adaptive resonance theory; membership function; oil-immersed insulation diagnosis; principal component analysis; statistical analysis; Artificial neural networks; Dissolved gas analysis; Fault diagnosis; Gas insulation; Gases; Oil insulation; Power engineering and energy; Power transformer insulation; Statistical analysis; Subspace constraints;
Conference_Titel :
Electrical Insulating Materials, 1998. Proceedings of 1998 International Symposium on
Conference_Location :
Toyohashi
Print_ISBN :
4-88686-050-8
DOI :
10.1109/ISEIM.1998.741860
