Design optimization of electromagnetic devices using artificial neural networks

Author

Mohammed, Osama A. ; Park, Dong C. ; Üler, Fuat G. ; Ziqiang, Chen

Author_Institution

Dept. of Electr. & Comput. Eng., Florida Int. Univ., Miami, FL, USA

Volume

28

Issue

5

fYear

1992

fDate

9/1/1992 12:00:00 AM

Firstpage

2805

Lastpage

2807

Abstract

A novel method for the optimal design of the electromagnetic devices is presented. The method utilizes artificial neural networks (ANNs) in a design environment which encompasses numerical computations and expert´s input for generating a variety of ANN training data. Results of two implementation examples are provided. The optimal design is obtained quickly (in a matter of milliseconds) once the ANNs are trained with a variety of geometrical topologies. The procedure explained can be used to provide good initial designs for use with iterative search techniques (currently used) to reduce searching time. This aspect is highly desirable in connection with increasing the effectiveness of the optimal design procedure

Keywords

CAD; electromagnetic devices; expert systems; neural nets; ANN training data; artificial neural networks; electromagnetic devices; expert´s input; geometrical topologies; iterative search techniques; numerical computations; Artificial neural networks; Backpropagation algorithms; Computer networks; Design optimization; Electromagnetic devices; Geometry; Multilayer perceptrons; Network topology; Neurons; Training data;

fLanguage

English

Journal_Title

Magnetics, IEEE Transactions on

Publisher

ieee

ISSN

0018-9464

Type

jour

DOI

10.1109/20.179633

Filename

179633