Neural network approach compared to sensitivity analysis based on finite element technique for optimization of permanent magnet generators

Authors
Tsekouras, G Kiartzis, S Kladas, AG Tegopoulos, JA
Citation
G. Tsekouras et al., Neural network approach compared to sensitivity analysis based on finite element technique for optimization of permanent magnet generators, IEEE MAGNET, 37(5), 2001, pp. 3618-3621
Citations number
10
Categorie Soggetti
Apllied Physucs/Condensed Matter/Materiales Science
Journal title
IEEE TRANSACTIONS ON MAGNETICS
ISSN journal
00189464 → ACNP
Volume
37
Issue
5
Year of publication
2001
Part
1
Pages
3618 - 3621
Database
ISI
SICI code
0018-9464(200109)37:5<3618:NNACTS>2.0.ZU;2-E
Abstract
The paper presents the optimization procedure of a permanent magnet generat or for a 20 kW wind turbine prototype. "Peripheral" Neodymium alloy magnet rotor structure has been considered to perform the optimal shape design. A fully connected four layer feedforward neural network has been introduced a nd compared to a technique based on the finite element method and sensitivi ty analysis. The considered methods are in very good agreement.