Pattern recognition of partial discharge with fractal analysis to characteristic spectrum

Author

Li Jian ; Ju, Tang ; Caixin, Sun ; Xin, Li ; Du Lin

Author_Institution

Chongqing Univ., China

Volume

2

fYear

2000

fDate

2000

Firstpage

720

Abstract

While partial discharge (PD) pattern recognition is widely considered as an important method to test insulation degradation, the major problem encountered is the extraction of PD pattern features. Using the analysis of the three-dimensional statistical spectrum, this paper adopts fractal theory to extract PD pattern features. From designed model tests and fraction calculation results, it is shown that the method is effective in extracting PD pattern features which are helpful in PD pattern recognition based on three-dimensional statistical spectrs

Keywords

backpropagation; feature extraction; fractals; image recognition; insulation testing; partial discharge measurement; power engineering computing; spectral analysis; BPNN training; PD pattern feature extraction; backpropagation neural network; fractal analysis; insulation degradation testing; partial discharge pattern recognition; three-dimensional statistical spectrum; Character recognition; Degradation; Feature extraction; Fractals; Geometry; Insulation testing; Partial discharges; Pattern analysis; Pattern recognition; Sun;

fLanguage

English

Publisher

ieee

Conference_Titel

Properties and Applications of Dielectric Materials, 2000. Proceedings of the 6th International Conference on

Conference_Location

Xi´an

Print_ISBN

0-7803-5459-1

Type

conf

DOI

10.1109/ICPADM.2000.876126

Filename

876126