Title :
Toward automatic classification of partial discharge sources with neural networks
Author :
Hirata, Akimasa ; Nakata, Syou ; Kawasaki, Zen-Ichiro
Author_Institution :
Nagoya Inst. of Technol., Japan
Abstract :
In this letter, we propose an automatic classification scheme of discharge sources on the basis of Fourier spectrum for received electromagnetic (EM) pulses. Confirming the reproducibility of EM pulses from each source validates this scheme. The recognition rate for six discharge sources is 80% or better. The feature of our system is time efficient and to treat hundreds of pulses.
Keywords :
Fourier analysis; neural nets; partial discharge measurement; power apparatus; power engineering computing; signal classification; Fourier spectrum; neural networks; partial discharge sources automatic classification; received electromagnetic pulses; Dielectrics and electrical insulation; Fault location; Multiple signal classification; Neural networks; Partial discharges; Power system reliability; Pulse power systems; Remote sensing; Reproducibility of results; Sensor arrays; Digital systems; fault diagnosis; neural-network applications; partial discharges;
Journal_Title :
Power Delivery, IEEE Transactions on
DOI :
10.1109/TPWRD.2005.848439
