A New Variable-Fidelity Optimization Framework Based on Model Fusion and Objective-Oriented Sequential Sampling

Abstract

Computational models with variable fidelity have been widely used in engineering design. To alleviate the computational burden, surrogate models are used for optimization without directly invoking expensive high-fidelity simulations. In this work, a model fusion technique based on the Bayesian–Gaussian process modeling is employed to construct cheap surrogate models to integrate information from both low-fidelity and high-fidelity models, while the interpolation uncertainty of the surrogate model due to the lack of sufficient high-fidelity simulations is quantified. In contrast to space filling, the sequential sampling of a high-fidelity simulation model in our proposed framework is objective-oriented, aiming for improving a design objective. Strategy based on periodical switching criteria is studied, which is shown to be effective in guiding the sequential sampling of a high-fidelity model toward improving a design objective as well as reducing the interpolation uncertainty. A design confidence metric is proposed as the stopping criterion to facilitate design decision making against the interpolation uncertainty. Examples are provided to illustrate the key ideas and features of model fusion, sequential sampling, and design confidence—the three key elements in the proposed variable-fidelity optimization framework.