Title :
PD pattern recognition using combined features
Author :
Li, Jian ; Sun, Caixin ; Wang, Youyuan ; Ji Yang ; Lin Du
Author_Institution :
Key Lab. of High Voltage Eng., Chongqing Univ., China
Abstract :
For the purpose of identifying the defects within the insulation, a suitable set of combined features is used as input of back-propagation neural network (BPNN). In this procedure, fractal dimensions and the 2nd generalized dimensions of original PD images and fractal dimensions of high gray intensity PD images are proposed and computed by modified differential box-counting (MDBC) method, and thereafter moments and correlative statistical parameters are studied for recognition of PD images. Therefore feature vector consists of altogether 17 parameters. Meanwhile quadtree partitioning fractal image compression (QPFIC) is used for PD data compression in purpose of improving rate of PD image communication. With PD data gathered in artificial defect experiments, the final analysis results shows the method by means of combined features and BPNN performs effectively in recognition after QPFIC compression of PD images.
Keywords :
backpropagation; data compression; fault location; feature extraction; image recognition; insulation testing; neural nets; partial discharge measurement; power apparatus; power engineering computing; quadtrees; HV apparatus; PD measurement; PD pattern recognition; back-propagation neural network; correlative statistical parameter; data compression; defect identification; feature vector; image communication; insulation; modified differential box-counting method; partial discharge measurement; quadtree partitioning fractal image compression; Data compression; Fractals; Image analysis; Image coding; Image communication; Image recognition; Insulation; Neural networks; Pattern recognition; Performance analysis;
Conference_Titel :
Electrical Insulation, 2004. Conference Record of the 2004 IEEE International Symposium on
Print_ISBN :
0-7803-8447-4
DOI :
10.1109/ELINSL.2004.1380490
