Comparison of the ANN with SVRM method on determining the magnetic characteristics of the E-core Transverse Flux Machine

Author

Gundogan Turker, C. ; Erfan Kuyumcu, F. ; Turker Tokan, N.

Author_Institution

Dept. of Electr. Eng., Kocaeli Univ., Kocaeli, Turkey

fYear

2013

fDate

25-28 Feb. 2013

Firstpage

278

Lastpage

283

Abstract

The E-core Transverse Flux Machine (ETFM) is combined of transverse flux and reluctance principle. An accurate ETFM model needs a good knowledge of the magnetic characteristics to know its electrical and mechanical behaviors. This paper proposed Support Vector Regression Machine (SVRM) and Artificial Neural Network (ANN) methods for determining of the magnetic characteristics of the ETFM. The data for the training and testing is obtained by experimental measurement methods. To reveal the accuracy of the nonlinear learning methods, the SVRM performance is compared with ANN´s.

Keywords

electric machine analysis computing; neural nets; regression analysis; reluctance machines; support vector machines; ANN method; E-core transverse flux machine; ETFM model; SVRM method; artificial neural network; electrical behaviors; magnetic characteristics; mechanical behaviors; nonlinear learning methods; support vector regression machine; switched reluctance machine; Artificial neural networks; Magnetic flux; Rotors; Stator windings; Torque; Training; Artificial Neural Networks; E-Core Transverse Flux Machine; Support Vector Machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Industrial Technology (ICIT), 2013 IEEE International Conference on

Conference_Location

Cape Town

Print_ISBN

978-1-4673-4567-5

Electronic_ISBN

978-1-4673-4568-2

Type

conf

DOI

10.1109/ICIT.2013.6505685

Filename

6505685