New approach for partial discharge recognition on transformers on-site by means of genetic algorithms

authored by

D. Wenzel, H. Borsi, Ernst Gockenbach

Abstract

In this paper, the application of genetic algorithms for Partial Discharge (PD) recognition on transformers on-site is introduced. First, a short description of genetic algorithms is given. Afterwards, the separation of PD from noise signals as one of the main problems for a sensitive PD-measurement on-site is explained. It is shown, that the use of genetic algorithms for the optimization of neural networks allows a sufficient separation of PD from the pulse shaped noises. Furthermore, the use of genetic algorithms for localizing PD origins in transformers is of great promise, if reference signals are available. Here, the application of genetic algorithms is demonstrated on signals measured at the coil of a distribution transformer in laboratory. The limits of the used methods are shown by superposing synthetically generated noises to the measured pulses.

Organisation(s)

High Voltage Engineering and Asset Management Section (Schering Institute)

Type

Conference article

Journal

Conference Record of IEEE International Symposium on Electrical Insulation

Volume

1

Pages

57-60

No. of pages

4

ISSN

0164-2006

Publication date

1996

Publication status

Published

Peer reviewed

Yes

ASJC Scopus subject areas

Electrical and Electronic Engineering, Building and Construction