Abstract
Swarm algorithms such as Particle Swarm Optimization (PSO) are non-gradient probabilistic optimization algorithms that have been successfully applied to obtain global optimal solutions for complex problems such as multi-peak problems. However these algorithms have not been applied to complicated structural and mechanical optimization problems since local optimization capability is still inferior to general numerical optimization methods. This paper discusses new swarm metaphors that incorporate design sensitivities concerning objective and constraint functions and are applicable to structural and mechanical design optimization problems. Single- and multiobjective optimization techniques using swarm algorithms are combined with a sequential linear programming (SLP) method. In the proposed techniques, swarm optimization algorithms and SLP are conducted simultaneously. Finally, truss structure design optimization problems are solved by the proposed hybrid method to verify the optimization efficiency.
