PD characterization using short duration Fourier transform of acoustic emission signals

Author

Tian, Y. ; Lewin, P.L. ; Sutton, S.J. ; Swingler, S.G.

Author_Institution

Dept. of Electron. & Comput. Sci., Southampton Univ., UK

Volume

2

fYear

2004

Firstpage

695

Abstract

The frequency spectrum of acoustic emission signals obtained using short duration Fourier transform as the artificial neural network input parameter has been investigated. The acoustic spectrum is not significantly influenced by applied electric stresses compared with (φ-q-n patterns or statistical operators such as skewness and kurtosis. A feed forward neural network using the back propagation algorithm was initially applied to characterize acoustic emission signals produced from different shapes of void within a polyethylene dielectric. It was then used to discriminate between the background noise and acoustic emission signals produced by void discharges or treeing discharges. The obtained identification results for the different experimental arrangements are encouraging.

Keywords

Fourier transforms; acoustic emission; acoustic noise; acoustic signal processing; backpropagation; dielectric materials; feedforward neural nets; partial discharges; polymers; trees (electrical); PD characterization; acoustic emission signal; acoustic spectrum; applied electric stresses; artificial neural network input parameter; background noise; backpropagation algorithm; feed forward neural network; frequency spectrum; polyethylene dielectric; short duration Fourier transform; treeing discharges; void discharges; Acoustic emission; Acoustic propagation; Artificial neural networks; Feedforward neural networks; Feeds; Fourier transforms; Frequency; Neural networks; Partial discharges; Stress;

fLanguage

English

Publisher

ieee

Conference_Titel

Solid Dielectrics, 2004. ICSD 2004. Proceedings of the 2004 IEEE International Conference on

Print_ISBN

0-7803-8348-6

Type

conf

DOI

10.1109/ICSD.2004.1350526

Filename

1350526