Application of artificial neural network in noise mixed partial discharge recognition

Author

Zheng, Zhong ; Tan, Kexiong

Author_Institution

Dept. of Electr. Eng., Tsinghua Univ., Beijing, China

Volume

1

fYear

2001

fDate

2001

Firstpage

673

Abstract

To test partial discharge (PD) recognition ability under different noise conditions, systemic research is carried out. In a noise-screened high voltage lab and using a high speed, wide-band digital measuring system, different kinds of PD current waveforms are recorded. Noises of different types are investigated. Then the PD signals are immersed into different noises with certain signal-noise ratios (SNR). By applying the segmented time domain data compression method, the features vectors of mixed waveforms are extracted. Employing a backpropagation algorithm, a feedforward triple-layered artificial neural network (ANN) program is generated and optimized. The mixed waveforms are tested and influence of each noise types in different SNR conditions are studied

Keywords

automatic test software; backpropagation; data compression; feedforward neural nets; insulation testing; multilayer perceptrons; noise; partial discharge measurement; PD current waveforms; PD recognition ability; artificial neural network; backpropagation algorithm; features vectors; feedforward triple-layered artificial neural net; noise mixed partial discharge recognition; segmented time domain data compression method; signal-noise ratios; wide-band digital measuring system; Artificial neural networks; Current measurement; Noise measurement; Partial discharge measurement; Partial discharges; Signal to noise ratio; System testing; Velocity measurement; Voltage; Wideband;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical and Computer Engineering, 2001. Canadian Conference on

Conference_Location

Toronto, Ont.

ISSN

0840-7789

Print_ISBN

0-7803-6715-4

Type

conf

DOI

10.1109/CCECE.2001.933765

Filename

933765