Comparison of different neural networks algorithms used in the diagnosis and thermal ageing prediction of transformer oil

Author

Mokhnache, L. ; Boubakeur, A. ; Said, N. Nait

Author_Institution

Fac. of Eng., Univ. of Batna, Algeria

Volume

6

fYear

2002

fDate

6-9 Oct. 2002

Abstract

In this paper supervised and unsupervised neural networks are applied. To help the inexperienced transformer oil analyst to make good diagnosis, a Levenberg-Marquardt net and a Bayesian network are applied in the diagnosis of the transformer oil. The last net presents the best generalization. A Kohonen net is applied also to classify the diagnosis. An RBFG (Radial Basis Function Gaussian) net is used to predict thermal ageing of the same oil.

Keywords

belief networks; fault diagnosis; generalisation (artificial intelligence); learning (artificial intelligence); power engineering computing; radial basis function networks; self-organising feature maps; transformer oil; Bayesian network; Kohonen net; Levenberg-Marquardt net; RBFG net; Radial Basis Function Gaussian network; generalization; supervised neural networks; thermal ageing prediction; transformer oil diagnosis; unsupervised neural networks; Aging; Cooling; IEC standards; Intelligent networks; Laboratories; Neural networks; Oil insulation; Petroleum; Power transformer insulation; Thermal engineering;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man and Cybernetics, 2002 IEEE International Conference on

ISSN

1062-922X

Print_ISBN

0-7803-7437-1

Type

conf

DOI

10.1109/ICSMC.2002.1175643

Filename

1175643