DocumentCode :
3481746
Title :
Current transformer saturation detection with genetically optimized neural networks
Author :
Rebizant, Waldemar ; Bejmert, Daniel
Author_Institution :
Wroclaw Univ. of Technol., Warsaw
fYear :
2005
fDate :
27-30 June 2005
Firstpage :
1
Lastpage :
6
Abstract :
Application of the genetic algorithm (GA) for optimization of artificial neural network (ANN) based CT saturation detector is presented. To determine the most suitable ANN topology for the CT state classifier the rules of evolutionary improvement of the characteristics of individuals by concurrence and heredity are used. The proposed genetic optimization principles were implemented in MATLAB programming code. The initial as well as further consecutive network populations were created, trained and graded in a closed loop until the selection criterion was fulfilled. Various aspects of genetic optimization have been studied, including ANN quality assessment, versions of genetic operations etc. The developed optimized neural CT saturation detector has been tested with EMTP-ATP generated signals, proving better performance than traditionally used algorithms and methods.
Keywords :
current transformers; genetic algorithms; neural nets; power engineering computing; CT state classifier; EMTP-ATP generated signals; MATLAB; artificial neural network; current transformer saturation detection; genetic algorithm; genetically optimized neural networks; selection criterion; Artificial neural networks; Circuit faults; Current transformers; Detectors; Fault currents; Genetic algorithms; MATLAB; Network topology; Neural networks; Quality assessment; CT saturation; artificial intelligence; genetic algorithms; neural networks; protective relaying; transient analysis;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Power Tech, 2005 IEEE Russia
Conference_Location :
St. Petersburg
Print_ISBN :
978-5-93208-034-4
Electronic_ISBN :
978-5-93208-034-4
Type :
conf
DOI :
10.1109/PTC.2005.4524417
Filename :
4524417
Link To Document :
بازگشت