Title :
Genetic Optimization of a PD Diagnostic System for Cable Accessories
Author :
Rizzi, Antonello ; Mascioli, Fabio Massimo Frattale ; Baldini, Francesco ; Mazzetti, Carlo ; Bartnikas, R.
Author_Institution :
Univ. of Rome La Sapienza, Rome
fDate :
7/1/2009 12:00:00 AM
Abstract :
An automatic procedure, based on a genetic algorithm capable of optimizing a diagnostic system for the recognition and identification of partial-discharge (PD) pulse patterns in the terminations and joints of solid dielectric extruded power distribution cables, is described. The core of the diagnostic system is a fuzzy neural network, namely a Min-Max classifier. The genetic optimization is capable for reducing the system complexity, while enhancing its diagnostic performance. The developed procedure is sufficiently general to be applied to PD source identification in the cables themselves as well as other electric power apparatus.
Keywords :
fuzzy neural networks; genetic algorithms; partial discharges; pattern recognition; power cables; power engineering computing; Min-Max classifier; PD diagnostic system; cable accessories; diagnostic system; electric power apparatus; fuzzy neural network; genetic algorithm; genetic optimization; partial-discharge pulse pattern identification; partial-discharge pulse pattern recognition; solid dielectric extruded power distribution cables; Cable shielding; Fault location; Fuzzy neural networks; Genetic algorithms; Insulation; Neural networks; Partial discharges; Pattern recognition; Polymers; Power cables; Automatic feature selection; XLPE; cable accessories; fuzzy neural networks; genetic algorithms (GAs); partial-discharge (PD) patterns classification;
Journal_Title :
Power Delivery, IEEE Transactions on
DOI :
10.1109/TPWRD.2009.2016826
