期刊
COMPOSITE STRUCTURES
卷 98, 期 -, 页码 15-23出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.compstruct.2012.11.015
关键词
Structural optimization; Discrete variable stiffness; Sandwich plate; Genetic Algorithm; Artificial neural network
资金
- European Social Fund within the project Support for the implementation of doctoral studies at Riga Technical University
A new optimization technique of composite plates with discrete varying stiffness is proposed. It consists of three main steps. Analysis of optimal continuous varying bending and shear stiffness of plate is done in the first step by minimizing structural compliance and stress field differences. Size optimization of discrete domains is done in the second step by solving minimization problem with a Genetic Algorithm. Dimension optimization of plates internal structure is done by previously trained feed-forward artificial neural network in the third step. A simply supported rectangular plate with uniformly distributed load and multispan plate with concentrated loads are optimized by the using of proposed method. The deflection of optimized plate could be reduced up to 50%, and average increase of strength to mass ratio is about 20%. (c) 2012 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据