Aging recognition of partial discharge patterns using neural network and semi-fractal dimension

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.