Metamodel Assisted Robust Optimization under Interval Uncertainly Based on Reverse Model

Previous deterministic robust optimization approaches based on sensitivity region information usually involve nested optimization, leading to a significant burden in computational time. In this paper, a strategy to improve the computational efficiency of the robust approach based on reverse model, metamodel assisted robust optimization, in which the nested optimization structure is reduced into a single loop optimization structure, is studied. A numerical example is used to demonstrate the applicability of the proposed metamodel assisted robust optimization.