PD pattern recognition with neural networks using the multilayer perceptron technique

Author

Mazroua, Amira A. ; Salama, M.M.A. ; Bartnikas, R.

Author_Institution

Dept. of Electr. & Comput. Eng., Waterloo Univ., Ont., Canada

Volume

28

Issue

6

fYear

1993

fDate

12/1/1993 12:00:00 AM

Firstpage

1082

Lastpage

1089

Abstract

The partial discharge (PD) pattern recognition capability of a neural network, employing the multilayer perceptron technique with data input based on five discharge pulse form parameters, is examined. Simple discharge sources, consisting of artificially created cylindrical cavities with metallic and dielectric electrodes, are employed. The PD pattern discrimination capability is tested using cavities of equal depth but with different electrodes, and cavities of varying depths but with similar electrodes. Preliminary test results are positive

Keywords

charge measurement; feedforward neural nets; insulation testing; partial discharges; pattern recognition; 2D feature patterns; artificially created cylindrical cavities; backpropagation training algorithm; dielectric electrodes; discharge pulse form parameters; learning curves; metallic electrodes; multilayer perceptron; neural networks; partial discharge; pattern discrimination capability; pattern recognition; Artificial neural networks; Dielectrics; Electrodes; Fault location; Multi-layer neural network; Multilayer perceptrons; Neural networks; Partial discharges; Pattern recognition; Testing;

fLanguage

English

Journal_Title

Electrical Insulation, IEEE Transactions on

Publisher

ieee

ISSN

0018-9367

Type

jour

DOI

10.1109/14.249382

Filename

249382