Partial discharge pattern recognition for four kinds of electrode systems

Author

Okamoto, Tatsuki ; Hozumi, Naohiro ; Imajo, Takahisa

Author_Institution

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

fYear

1992

fDate

7-10 Jun 1992

Firstpage

375

Lastpage

378

Abstract

The authors describe a method for recognizing partial discharge characteristics for four kinds of electrode systems. The method uses a neural network system with an input of φ-q-n distribution patterns. The θ-q-n distribution consists of the pulse count n versus the pulse height q and the phase angle φ. The learning characteristics and recognition characteristics of the neural network were investigated, and the recognition capability for a combined pattern signal input was shown. The effectiveness of the neural network system for partial discharge recognition is discussed

Keywords

backpropagation; electrical engineering computing; feedforward neural nets; image recognition; insulation testing; partial discharges; combined pattern signal input; error backpropagation method; learning characteristics; neural network system; partial discharge characteristics; pattern recognition; phase angle; pulse count; pulse height; recognition capability; Character recognition; Data processing; Electrodes; Neural networks; Partial discharge measurement; Partial discharges; Pattern recognition; Signal analysis; Signal processing; Voltage;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical Insulation, Conference Record of the 1992 IEEE International Symposium on

Conference_Location

Baltimore, MD

ISSN

1089-084X

Print_ISBN

0-7803-0649-X

Type

conf

DOI

10.1109/ELINSL.1992.246985

Filename

246985