Localization of winding shorts using fuzzified neural networks

Author

El-Sharkawi, M.A. ; Marks, R.J., II ; Oh, Seho ; Huang, S.J. ; Kerszenbaum, Isidor ; Rodriguez, Alonso

Author_Institution

Dept. of Electr. Eng., Washington Univ., Seattle, WA, USA

Volume

10

Issue

1

fYear

1995

fDate

3/1/1995 12:00:00 AM

Firstpage

140

Lastpage

146

Abstract

Shorted turns in field winding of large turbogenerators are difficult to detect and localize. We propose a technique whereby shorts are detected and localized using an artificial neural network with a fuzzified output. The method is based on injecting two simultaneous and identical waveform signals at both ends of the field winding. Selected features of the received signals are used to train the neural network. Once trained, the neural network can detect and localize short turns in the field winding. The proposed method is verified by a field test on 60 MVA turbogenerator. The results show that the proposed method is quite accurate and efficient

Keywords

electric machine analysis computing; fault location; fuzzy neural nets; learning (artificial intelligence); machine testing; machine windings; short-circuit currents; synchronous generators; turbogenerators; 60 MVA; artificial neural network; fuzzified neural networks; fuzzified output; neural network training; synchronous generators; turbogenerators; waveform signals injection; winding shorts detection; winding shorts localisation; Artificial neural networks; Boring; Circuit faults; Coils; Conductors; Copper; Neural networks; Testing; Turbogenerators; Voltage;

fLanguage

English

Journal_Title

Energy Conversion, IEEE Transactions on

Publisher

ieee

ISSN

0885-8969

Type

jour

DOI

10.1109/60.372579

Filename

372579