PD Pattern Classification for dc System Based on Fractal Dimensions Combined with Statistical Features

Author

Du, B.X. ; Zhang, Q. ; Lu, Yuhang ; Zhang, Xiangjin

Author_Institution

Sch. of Electr. Eng. & Autom., Tianjin Univ.

fYear

2006

fDate

38869

Firstpage

427

Lastpage

430

Abstract

For the purpose of identifying the defects within the insulation at DC system, a 3-dimensional image of partial discharge (PD), which is based on the theory of wavelet analysis and different from the traditional phi-q-n image, is proposed in this paper. Its three parameters are the frequency, the time and the amplitude. Then the fractal dimensions combined with the lacunarity that is a measure of denseness of the fractal surface in the point of probability are computed. In succession the back-propagation neural network (BPNN) is used for the classification. With acoustic PD signals gathered in artificial defect experiments, the final results of the BPNN show that the method performs effectively in recognizing the PD patterns

Keywords

acoustic signal detection; backpropagation; fractals; image classification; insulating materials; insulator testing; neural nets; partial discharge measurement; power engineering computing; probability; wavelet transforms; 3-dimensional image; BPNN; DC system; acoustic PD signal detection; back-propagation neural network; fractal dimensions; insulation material defects; lacunarity measure; partial discharge; pattern classification; pattern recognition; probability; wavelet analysis; Acoustic measurements; Fractals; Frequency; Image analysis; Insulation; Partial discharge measurement; Partial discharges; Pattern classification; Surface acoustic waves; Wavelet analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Properties and applications of Dielectric Materials, 2006. 8th International Conference on

Conference_Location

Bali

Print_ISBN

1-4244-0189-5

Electronic_ISBN

1-4244-0190-9

Type

conf

DOI

10.1109/ICPADM.2006.284206

Filename

4062695