Using of Kriging Surrogate Model in the Multi-Objective Optimization of Complicated Structure

To solve the problem of too large calculating amount in the multi-objective optimization of complicated structure, a method based on Kriging surrogate model is proposed and being used in an aerospace assembly to verify its effectiveness. There are two objectives in the structural optimization of the assembly, min mass and max frequency. The method is based on the following steps, first get the sample point by the design of the experiment, and then create the Kriging surrogate model based on the sample points, and at last get the Pareto set by using multi-objective genetic algorithm method working on the established surrogate model to solve the multi-objective problem. The designer can choose the suitable Pareto solution to modify the structure. The method can save the design time and cost at the same time and can provide a reference for similar products.