A Study on Improving the Convergence of the Real-Coded Genetic Algorithm for Electromagnetic Inverse Scattering of Multiple Perfectly Conducting Cylinders

Anyong QING  Ching Kwang LEE  

IEICE TRANSACTIONS on Electronics   Vol.E85-C   No.7   pp.1460-1471
Publication Date: 2002/07/01
Online ISSN: 
Print ISSN: 0916-8516
Type of Manuscript: PAPER
Category: Electromagnetic Theory
real-coded genetic algorithm (RcGA),  penalty function,  closed cubic B-splines,  adaptive hybrid algorithm,  

Full Text: PDF(744.5KB)>>
Buy this Article

A study on improving the performance of the real-coded genetic algorithm for electromagnetic inverse scattering of two-dimensional perfectly conducting cylinders is presented. Three schemes, namely, the penalty function approach, the closed cubic B-splines local shape function approach and the adaptive hybrid algorithm approach are proposed to deal with the problem. These schemes can be used separately or be combined to improve the performance. Numerical examples validate the schemes.