Title :
Aging recognition of partial discharge patterns using neural network and semi-fractal dimension
Author :
Jang-seob, Lim ; Young-sik, Park ; Cheol-su, Kim ; Myoung-rae, Jeong ; Woo-sung, Jung ; Tae-sung, Kim
Author_Institution :
Fac. of M.E.C. Eng., Mokpo Nat. Maritime Univ., Chonnam, South Korea
Abstract :
Aging diagnosis system using partial discharge (PD) is being highlighted as a research area for preventive diagnosis. But the application of PD for aging diagnosis requires complicated analysis method because of its complex progressing mechanism. In this paper, it has been developed new approach method to express the Semi-Fractal Dimension (SFD) of the tree pattern using image processing and the PD diagnosis system using Neural Network (NN). As a result after NN learning (SFD:1.2-1.3), the recognized rate of similar stress (SFD:1.2-1.4) was represented about 85%. In case of high stress (SFD:1.5-1.6), the safety area is possible to express the second output of NN in this experiments
Keywords :
ageing; fractals; insulation testing; neural nets; partial discharges; pattern recognition; trees (electrical); aging; diagnosis system; image processing; neural network; partial discharge; pattern recognition; safety area; semi-fractal dimension; tree; Aging; Electrodes; Fractals; Image processing; Life estimation; Needles; Neural networks; Partial discharges; Pattern recognition; Safety;
Conference_Titel :
Properties and Applications of Dielectric Materials, 1997., Proceedings of the 5th International Conference on
Conference_Location :
Seoul
Print_ISBN :
0-7803-2651-2
DOI :
10.1109/ICPADM.1997.617585
