Artificial intelligence combined with hybrid FEM-BE techniques for global transformer optimization

Amoiralis, EI; Georgilakis, PS; Kefalas, TD; Tsili, MA; Kladas, AG

dc.contributor.author	Amoiralis, EI	en
dc.contributor.author	Georgilakis, PS	en
dc.contributor.author	Kefalas, TD	en
dc.contributor.author	Tsili, MA	en
dc.contributor.author	Kladas, AG	en
dc.date.accessioned	2014-03-01T02:44:28Z
dc.date.available	2014-03-01T02:44:28Z
dc.date.issued	2007	en
dc.identifier.issn	0018-9464	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/31842
dc.subject	Adaptive training	en
dc.subject	Artificial intelligence (AI)	en
dc.subject	Artificial neural networks	en
dc.subject	Decision trees (DTs)	en
dc.subject	Finite-element method-boundary-element (FEM-BE) techniques	en
dc.subject	Transformer design optimization	en
dc.subject	Transformer winding	en
dc.subject.classification	Engineering, Electrical & Electronic	en
dc.subject.classification	Physics, Applied	en
dc.subject.other	Boundary element method	en
dc.subject.other	Computer simulation	en
dc.subject.other	Decision trees	en
dc.subject.other	Finite element method	en
dc.subject.other	Global optimization	en
dc.subject.other	Neural networks	en
dc.subject.other	Power transformers	en
dc.subject.other	Transformer windings	en
dc.subject.other	Adaptive training	en
dc.subject.other	Hybrid numerical model	en
dc.subject.other	Material classification	en
dc.subject.other	Transformer design optimization	en
dc.subject.other	Artificial intelligence	en
dc.title	Artificial intelligence combined with hybrid FEM-BE techniques for global transformer optimization	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/TMAG.2006.892258	en
heal.identifier.secondary	http://dx.doi.org/10.1109/TMAG.2006.892258	en
heal.language	English	en
heal.publicationDate	2007	en
heal.abstract	The aim of the transformer design optimization is to define the dimensions of all the parts of the transformer, based on the given specification, using available materials economically in order to achieve lower cost, lower weight, reduced size, and better operating performance. In this paper, a hybrid artificial intelligence/numerical technique is proposed for the selection of winding material in power transformers. The technique uses decision trees and artificial neural networks for winding material classification, along with finite-element/boundary element modeling of the transformer for the calculation of the performance characteristics of each considered design. The efficiency and accuracy provided by the hybrid numerical model render it particularly suitable for use with optimization algorithms. The accuracy of this method is 96% (classification success rate for the winding material on an unknown test set), which makes it very efficient for industrial use. © 2007 IEEE.	en
heal.publisher	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC	en
heal.journalName	IEEE Transactions on Magnetics	en
dc.identifier.doi	10.1109/TMAG.2006.892258	en
dc.identifier.isi	ISI:000245327200122	en
dc.identifier.volume	43	en
dc.identifier.issue	4	en
dc.identifier.spage	1633	en
dc.identifier.epage	1636	en