Design optimization of a complex mechanical system using adaptive response surface method

摘要

Today's increasingly competitive industrial environment demands shorter product development lead-times, lower costs, and higher quality products. These requirements produce more complex design problems that are characterized by multiple design objectives as well as complex design objective and constraint relations. The optimization of these computationally intensive design problems leads to new technical challenges. This work applies a new global optimization search scheme, the Adaptive Response Surface Method (ARSM), to the optimal design of a complex mechanical system -- the radiator stack PEM fuel cell system. The design optimum manifests a significant increase in system performance and decrease in cost. The proposed method can also be applied to the solution of other complex design optimization problems.