Competitive genetic algorithms with application to reliability optimal design

Competition is introduced among the populations of a number of genetic algorithms (GAs) having different sets of parameters. The aim is to calibrate the population size of the GAs by altering the resources of the system, i.e. the allocated computing time. The co-evolution of the different population...

Full description

Saved in:
Bibliographic Details
Published in:Advances in engineering software (1992) 2003-12, Vol.34 (11), p.773-785
Main Authors: Dimou, C.K., Koumousis, V.K.
Format: Article
Language:English
Subjects:
Competition
Genetic algorithms
Population dynamics
Reliability analysis
Structural optimization
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Competition is introduced among the populations of a number of genetic algorithms (GAs) having different sets of parameters. The aim is to calibrate the population size of the GAs by altering the resources of the system, i.e. the allocated computing time. The co-evolution of the different populations is controlled at the level of the union of populations, i.e. the metapopulation, on the basis of statistics and trends of the evolution of every population. Evolution dynamics improve the capacity of the optimization algorithm to find optimum solutions and results in statistically better designs as compared to the standard GA with any of the fixed parameters considered. The method is applied to the reliability based optimal design of simple trusses. Numerical results are presented and the robustness of the proposed algorithm is discussed.
ISSN:0965-9978
DOI:10.1016/S0965-9978(03)00101-7