UTILIZING HOPFIELD NEURAL NETWORKS AND AN IMPROVED SIMULATED ANNEALING PROCEDURE FOR DESIGN OPTIMIZATION OF ELECTROMAGNETIC DEVICES

Authors
MOHAMMED OA MERCHANT RS ULER FG
Citation
Oa. Mohammed et al., UTILIZING HOPFIELD NEURAL NETWORKS AND AN IMPROVED SIMULATED ANNEALING PROCEDURE FOR DESIGN OPTIMIZATION OF ELECTROMAGNETIC DEVICES, IEEE transactions on magnetics, 29(6), 1993, pp. 2404-2406
Citations number
10
Categorie Soggetti
Engineering, Eletrical & Electronic","Physics, Applied
Journal title
IEEE transactions on magnetics → ACNP
ISSN journal
00189464
Volume
29
Issue
6
Year of publication
1993
Part
1
Pages
2404 - 2406
Database
ISI
SICI code
0018-9464(1993)29:6<2404:UHNNAA>2.0.ZU;2-U
Abstract
A new method for the design optimization of electromagnetic devices is presented. Improved Simulated Annealing (SA) is used along with the H opfield neural network (HN) to optimize a solution obtained from a tra ined multilayered perceptron (MLP). This results in an overall increas e in the speed of optimization. Results are presented for two examples which show the effectiveness of the proposed method in obtaining a ne ar optimal solution.