Title :
Determination of neural-network topology for partial discharge pulse pattern recognition
Author :
Salama, M.M.A. ; Bartnikas, R.
Author_Institution :
Dept. of Electr. & Comput. Eng., Waterloo Univ., Ont., Canada
fDate :
3/1/2002 12:00:00 AM
Abstract :
A time-series approach has been employed to devise neural-network topologies for time dependent partial discharge pulse pattern recognition applications. The cascaded output neural-network structure was found to provide the highest success rate in differentiating between two different partial discharge patterns. This was accomplished by utilizing the indexed feature of the first stage output as one of the inputs into the second stage of the cascaded neural network
Keywords :
network topology; neural nets; partial discharges; pattern recognition; time series; cascaded output neural-network; cavity size classification; network topology; neural-network topologies; partial discharge pulse; partial discharges; pattern recognition; time dependent; time series; Dielectrics and electrical insulation; Fault location; Gas insulation; Geometry; Multi-layer neural network; Network topology; Neural networks; Partial discharges; Pattern recognition; Thermal stresses;
Journal_Title :
Neural Networks, IEEE Transactions on
