Title :
PD pattern recognition for stator bar models with six kinds of characteristic vectors using BP network
Author :
Gao, Kai ; Tan, Kexiong ; Li, Fuqi ; Wu, Chengqi
Author_Institution :
Dept. of Electr. Eng., Tsinghua Univ., Beijing, China
fDate :
6/1/2002 12:00:00 AM
Abstract :
The application of six different kinds of characteristic vectors to recognize PD sources is studied. Four kinds of model bars are used to simulate typical partial discharges in generator stator winding. The PD signals were measured by using a computer aided digital sampling system. The sampling results are processed by six kinds of feature extraction methods and different characteristic vectors are obtained. Then these vectors are used as input patterns for BP network. Recognition results using all six kinds of vectors are reasonable. Further analysis shows that vectors formed by moment features or fractal dimensions possess fairly good abilities of pattern identification and data compression
Keywords :
backpropagation; data compression; feature extraction; fractals; insulation testing; partial discharges; pattern recognition; stators; backpropagation etwork; characteristic vector; computer aided digital sampling system; data compression; feature extraction; fractal dimension; generator winding; insulation testing; partial discharge; pattern recognition; stator bar model; Application software; Bars; Character recognition; Computational modeling; Feature extraction; Partial discharges; Pattern analysis; Pattern recognition; Signal sampling; Stator windings;
Journal_Title :
Dielectrics and Electrical Insulation, IEEE Transactions on
DOI :
10.1109/TDEI.2002.1007700
