Separation of partial discharges from pulse-shaped noise signals with the help of neural networks

authored by

H. Borsi, Ernst Gockenbach, D. Wenzel

Abstract

A method to separate partial discharges (PD) from pulse-shaped noise signals using a neural network is described. The structure of neural networks and their ability for pattern recognition is presented. The adaptive resonance theory (ART) architectures, which are suitable for PD measurement, and the fast simulating algorithm ART 2-A, are explained. It is shown that the ART 2-A network is able to classify pulses in accordance with their origin for the distribution transformer. An examination of the signals measured on a power transformer under high voltage on-site is presented.

Organisation(s)

High Voltage Engineering and Asset Management Section (Schering Institute)

Type

Article

Journal

IEE Proceedings: Science, Measurement and Technology

Volume

142

Pages

69-74

No. of pages

6

ISSN

1350-2344

Publication date

01.1995

Publication status

Published

Peer reviewed

Yes

ASJC Scopus subject areas

Electrical and Electronic Engineering

Electronic version(s)

https://doi.org/10.1049/ip-smt:19951565 (Access: Closed)