Partial discharge pattern recognition using fractal dimension.
|
Accession number;02A0423808
|
| Title;Partial discharge pattern recognition using fractal dimension. |
| Author;
LI J
(Chongqing Univ., Chongqing, Chn)
SUN C
(Chongqing Univ., Chongqing, Chn)
LI X
(Chongqing Univ., Chongqing, Chn)
DU L
(Chongqing Univ., Chongqing, Chn)
ZHOU Q
(Chongqing Univ., Chongqing, Chn)
|
Journal Title;Proceedings of the Symposium on Electrical and Electronic Insulating Materials and Applications in Systems
|
Journal Code:G0398B
|
ISSN:
|
|
VOL.33rd;NO.;PAGE.137-140(2001)
|
| Figure&Table&Reference;FIG.4, TBL.2, REF.12 |
| Pub. Country;Japan |
| Language;English |
| Abstract;This paper brings forward a modified differential box-counting(MDBC) method to evaluate the fractal dimension(FD). And on the base of the new method, this paper proposes and studies the FD and the 2nd order generalized dimension of partial discharge(PD) gray intensity image as two kinds of PD pattern features. Furthermore, high gray intensity image is constructed for extraction of FD as a new PD pattern feature. A PD image is divided into two equal parts according to power frequency phase angle and then we extract 6 fractal features for recognition to a PD image. Large quantities of PD samples are acquired by PD models test and used for testifying the proposed method. Using with fractal features and designed back-propagation neural network, we acquire satisfactory recognition results for discharge model samples. (author abst.) |
|
|
|
Related Articles;
|
|
