Format: HTML | BibTeX | DC | EndNote | NLM | MARC | MARCXML
000000185 001__ 185
000000185 037__ $$aENY-ARTICLE-2008-146
000000185 041__ $$aeng
000000185 100__ $$aRebizant, W$$uWroclaw University of Technology, Poland
000000185 245__ $$aCurrent Transformer Saturation Detection with Genetically Optimized Neural Networks
000000185 260__ $$c2005-03-24
000000185 300__ $$a6p
000000185 500__ $$aProceedings of the 2005 IEEE PowerTech Conference, St. Petersburg, Russia, 27-30 June 2005, CD-ROM, paper 220
000000185 520__ $$aApplication of the genetic algorithm (GA) for optimization of artificial neural network (ANN) based CT saturation detector is presented. To determine the most suitable ANN topology for the CT state classifier the rules of evolutionary improvement of the characteristics of individuals by concurrence and heredity are used. The proposed genetic optimization principles were implemented in MATLAB programming code. The initial as well as further consecutive network populations were created, trained and graded in a closed loop until the selection criterion was fulfilled. Various aspects of genetic optimization have been studied, including ANN quality assessment, versions of genetic operations etc. The developed optimized neural CT saturation detector has been tested with EMTP-ATP generated signals, proving better performance than traditionally used algorithms and methods.
000000185 6531_ $$aprotective relaying
000000185 6531_ $$aCT saturation
000000185 6531_ $$aartificial intelligence
000000185 6531_ $$aneural networks
000000185 6531_ $$agenetic algorithms
000000185 6531_ $$atransient analysis
000000185 700__ $$aBejmert, D$$uWroclaw University of Technology, Poland
000000185 8560_ $$fzbigniew.leonowicz@pwr.wroc.pl
000000185 8564_ $$uhttp://zet10.ipee.pwr.wroc.pl/record/185/files/$$zAccess to Fulltext
000000185 909CO $$ooai:zet10.pwr.wroc.pl:185$$pglobal
000000185 980__ $$aARTICLE