Format: HTML | BibTeX | DC | EndNote | NLM | MARC | MARCXML
000000300 001__ 300
000000300 037__ $$aENY-ARTICLE-2009-239
000000300 041__ $$aeng
000000300 100__ $$aJanik, P$$uWroclaw University of Technology, Poland
000000300 245__ $$aAutomated Classification of Power Quality Disturbances using SVM and RBF Networks
000000300 260__ $$c2005-10-19
000000300 300__ $$a7p
000000300 500__ $$a12th International Conference on Harmonics and Quality of Power, Cascais, Portugal, 1-5 Oct 2006, paper No. 3A.1
000000300 520__ $$aThe authors propose a new method of power quality classification using SVM (Support Vector Machine) neural networks. Classifier based on RBF networks (Radial Basis Function) was in parallel applied to enable proper performance comparison. Both, RBF and SVM networks are introduced and considered an appropriate tool for classification problems. Space phasor is used for feature extraction from three-phase signals, to build distinguished patterns for classifiers. In order to create training and testing vectors different disturbance classes were simulated (e.g. sags, voltage fluctuations, transients) in Matlab. Finally, the investigation results of the novel approach are shown and interpreted.
000000300 6531_ $$aPower Quality
000000300 6531_ $$aDisturbance Classification,
000000300 6531_ $$aNeural Networks
000000300 6531_ $$aSpace Phasor
000000300 6531_ $$aSupport Vector Machines
000000300 700__ $$aLobos, T$$uWroclaw University of Technology, Poland
000000300 8560_ $$fleon99@pwr.wroc.pl
000000300 8564_ $$uhttp://zet10.ipee.pwr.wroc.pl/record/300/files/$$zAccess to Fulltext
000000300 909CO $$ooai:zet10.pwr.wroc.pl:300$$pglobal
000000300 980__ $$aARTICLE