Title :
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.
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;
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
DOI :
10.1109/ICPADM.2006.284206
