Non-Myopic Multifidelity Method for Multi-regime Constrained Aerodynamic Optimization

The exploration and trade-off analysis of different aerodynamic design configurations requires solving optimization problems. The major bottleneck to asses the optimal design is the large number of time-consuming evaluations of high-fidelity computational fluid dynamics (CFD) models, necessary to capture the non-linear phenomena and discontinuities that occurs at higher Mach number regimes. To address this limitation, we propose an original non-myopic multifidelity Bayesian framework aimed at including expensive high-fidelity CFD simulations for the optimization of the aerodynamic design. Our scheme comes with a two-step lookahead policy to maximize the improvement of the solution quality considering the rewards of future steps, and an active learning scheme informed by the fluid dynamic regime and the information extracted from data, to wisely select the aerodynamic model to interrogate. We validate the proposed algorithm for the case of a constrained drag coefficient optimization problem of a NACA 0012 airfoil, and compare the results to other popular multifidelity and single-fidelity optimization frameworks. The results suggest that our strategy outperforms the other approaches, allowing to significantly reduce the drag coefficient through a principled selection of limited evaluations of the high-fidelity CFD model.