Robust design optimization based on multi-objective particle swarm optimization

Abstract

For real world problems, there are inevitably perturbations in the design parameters or (and) variables. If an optimal solution is sensitive to the small perturbations of design parameters or variables, it may be inappropriate or risk for practical use. Robust design optimization can find solutions which are good in optimality and good in robustness simultaneously. Traditional robust optimization searched for robust solution by converting the original problem into a single-objective optimization problem. But only one solution can be obtained from one run of optimization using these methods. This paper applied a multi-objective optimization approach to get the robust optimal solutions. A novel robustness measurement is proposed and is compared with other methods of estimating robustness. The theoretical and experimental results verify that the proposed method outperforms the conventional methodologies. In solving the converted multi-objective optimization problems, a more efficient multi-objective particle swarm optimization is used. The test functions proved that the proposed method is more efficient than the conventional ones.