This article deals with the multi objective optimization of square hybrid tubes (metal-composite) under axial impact load. Maximum crushing load and absorbed energy are objective functions and fiber orientation angles of the composite layers are chosen as design parameters while the maximum crush load is limited. Back-propagation artificial neural networks (ANNs) are utilized to construct the mapping between the variables and the objectives. Non-dominated sorting Genetic algorithm–II (NSGAII) is applied to obtain the optimal solutions and the finite element commercial software LS-DYNA is used to generate the training and test sets for the ANNs. Optimum results are presented as a Pareto frontier.

This content is only available via PDF.
You do not currently have access to this content.