An active learning variable-fidelity metamodeling approach for engineering design

Computational models with variable fidelity have been widely used in engineering design. To make a trade-off between high accuracy and low expense, variable fidelity (VF) metamodeling approaches that aim to integrate information from both low fidelity (LF) and high-fidelity (HF) models have gained increasing popularity. In this paper an active learning variable-fidelity (VF) metamodeling approach (ALVFM) based on a Kriging scaling function is proposed, in which the one-shot VF metamodeling process is transformed into an iterative process to utilize the already-acquired information of the difference characteristics between the high-fidelity (HF) models and low-fidelity (LF) models. An analytic nonlinear numerical case and a long cylinder pressure vessel optimization design problem verify the applicability of the proposed VF metamodeling approach.