Title :
PD classification by a modular neural network based on task decomposition
Author :
Hong, T. ; Fang, M.T.C. ; Hilder, D.
Author_Institution :
Dept. of Electr. Eng. & Electron., Liverpool Univ., UK
fDate :
4/1/1996 12:00:00 AM
Abstract :
The use of modular neural network (MNN) for the recognition of partial discharge (PD) sources has been investigated. Three phase related quantities, the PD pulse counts, the average and maximum discharge magnitudes form the feature vector of a discharge signal. The MNN consists of 5 sub-networks with identical structure and a maximum selector. Each subnetwork is assigned the task to recognize a particular PD source. Compared with a single neural network which is trained to recognize all PD sources, the MNN has a higher training ability, faster rate of convergence and better recognition rate
Keywords :
neural nets; partial discharges; pattern classification; PD classification; convergence; modular neural network; partial discharges; recognition; task decomposition; training; Artificial intelligence; Convergence; Fault location; Laboratories; Manufacturing; Multi-layer neural network; Neural networks; Partial discharges; Quality assurance; Testing;
Journal_Title :
Dielectrics and Electrical Insulation, IEEE Transactions on
