Partial discharge pattern recognition for three kinds of model electrodes with a neural network

Author

Okamoto, T. ; Tanaka, T.

Author_Institution

Central Res. Inst. of Electr. Power Ind., Yokosuka, Japan

Volume

142

Issue

1

fYear

1995

fDate

1/1/1995 12:00:00 AM

Firstpage

75

Lastpage

84

Abstract

The paper describes a method of recognising partial discharge characteristics for three kinds of electrode systems. The method uses a neural network system with input signal of φ-q-n distribution patterns. The φ-q-n distribution consists of the pulse count [n] versus pulse height [q] and phase angle [φ]. The learning characteristics and recognition characteristics of the neural network were investigated. The basic characteristics of recognition capability for combined pattern signal input was shown. The effectiveness of the neural network system for partial discharge recognition was shown

Keywords

electrodes; high-voltage techniques; impulse testing; learning (artificial intelligence); neural nets; partial discharges; pattern recognition; power engineering computing; statistical analysis; φ-q-n distribution patterns; combined pattern signal input; effectiveness; learning characteristics; model electrodes; neural network; partial discharge pattern recognition; phase angle; pulse count; pulse height; recognition characteristics;

fLanguage

English

Journal_Title

Science, Measurement and Technology, IEE Proceedings -

Publisher

iet

ISSN

1350-2344

Type

jour

DOI

10.1049/ip-smt:19951430

Filename

370769