Computational & Technology Resources
an online resource for computational,
engineering & technology publications |
|
Civil-Comp Proceedings
ISSN 1759-3433 CCP: 34
DEVELOPMENTS IN NEURAL NETWORKS AND EVOLUTIONARY COMPUTING FOR CIVIL AND STRUCTURAL ENGINEERING Edited by: B.H.V. Topping
Paper VII.3
An Integrated Shape Optimization Approach using Genetic Algorithms and Fuzzy Rule-Based System J.P. Yang and C.K. Soh
School of Civil and Structural Engineering, Nanyang Technological University, Singapore J.P. Yang, C.K. Soh, "An Integrated Shape Optimization Approach using Genetic Algorithms and Fuzzy Rule-Based System", in B.H.V. Topping, (Editor), "Developments in Neural Networks and Evolutionary Computing for Civil and Structural Engineering", Civil-Comp Press, Edinburgh, UK, pp 171-177, 1995. doi:10.4203/ccp.34.7.3
Abstract
Structural optimization, in the classic sense, is the
minimization of mass by varying or determining the
different design variables. Shape optimization,
however, is to maximize the use of materials under the
allowable design performances. It plays a significant
part in the preliminary design stage and has been
considered as the most challenging and economically
the most rewarding task in structural design. During the
past few years, genetic-based optimization approaches
have been applied to many structural design problems
with great success. In this paper, a new approach
integrating genetic algorithms with fuzzy rule-based
system for structural shape optimization is investigated.
An automated optimization procedure based upon the
proposed approach is developed and used in the least-weight shape design of truss structures, which
include
their geometry as a design variable to be optimized.
The approach uses a fuzzy control strategy to guide the
genetic algorithm based search to get the maximum
optimization improvement in as few search steps as
possible. A representative example is presented to
verify the applicability and effectiveness of the
proposed approach to structural shape optimization.
purchase the full-text of this paper (price £20)
go to the previous paper |
|