A Hybrid Shared/Distributed Memory Parallel Genetic Algorithm for Optimization of Laminate Composites

Abstract

This work presents a genetic algorithm combining two types of computational parallelization methods,resulting in a hybrid shared/distributed memory algorithm based on the island model using both Open-MP and MPI libraries. In order to take further advantage of the island configuration, different geneticparameters are used in each one, allowing the consideration of multiple evolution environments concur-rently. To specifically treat composite structures, a three-chromosome variable encoding and special lam-inate operators are used. The resulting gains in execution time due to the parallel implementation allowthe use of high fidelity analysis procedures based on the Finite Element Method in the optimization ofcomposite laminate plates and shells. Two numerical examples are presented in order to assess the per-formance and reliability of the proposed algorithm.