Optimal design of laminated composite structures using coarse-grain parallel genetic algorithms

Abstract

A new coarse-grain parallel architecture for genetic algorithms, called island injection genetic algorithms, is implemented for the optimal design of laminated composite structures. This approach represents the design at various levels of refinement in subpopulations on separate computational nodes, then seeks good designs at each level of resolution and injects these good solutions into a population (node) with higher resolution to “fine-tune” the design. Numerical results are presented for the optimal design of a laminated composite beam to maximize its capacity to absorb mechanical energy without fracture. It is shown that super linear speedup can be achieved by using the injection algorithm.