Journal
COMPOSITES SCIENCE AND TECHNOLOGY
Volume 68, Issue 2, Pages 537-550Publisher
ELSEVIER SCI LTD
DOI: 10.1016/j.compscitech.2007.06.031
Keywords
composites; laminated plate; natural frequency; optimisation; genetic algorithm; artificial neural network
Categories
Ask authors/readers for more resources
In this study the layer optimisation was carried out for maximum fundamental frequency of laminated composite plates under any combination of the three classical edge conditions. The optimal stacking sequences of laminated composite plates were searched by means of Genetic Algorithm. The first natural frequencies of the laminated composite plates with various stacking sequences were calculated using the finite element method. Genetic Algorithm maximizes the first natural frequency of the laminated composite plate defined as a fitness function (objective function). However, the finite element method needs a certain calculation time of the first natural frequency for each new lay-up sequence and plate edge condition. In order to reduce the searching time of the optimal lay-up sequence an artificial neural network model was proposed and trained with small training and testing data composed of the natural frequencies of the composite plates calculated for random lay-up sequences, layer number, edge conditions and plate length/width ratios using the finite element method. The outer layers of the composite plate had a stiffness increasing effect, and as the clamped plate edges were increased both stiffness and natural frequency of the plate increased. In addition the Genetic Algorithm predicted successfully the optimal layer sequences without yielding a local optimum on the contrary the Ritz-based layerwise optimisation method [Y. Narita, Layerwise optimization for the maximum fundamental frequency of laminated composite plates. J Sound Vib 2003;263:1005-16]. (C) 2007 Elsevier Ltd. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available