Multi-Fidelity Constrained Bayesian Optimization with Application to Aircraft Wing Design

Aircraft design relies heavily on solving challenging and computationally expensive Multidisciplinary Design Optimization (MDO) problems. In this context, there has been growing interest in multi-fidelity models for Bayesian Optimization to improve the MDO process by balancing computational cost and accuracy through the combination of high- and low-fidelity simulation models, enabling efficient exploration of the design process at a minimal computational effort. In the existing literature, fidelity selection focuses only on the objective function to decide how to integrate multiple fidelity levels, balancing precision and computational cost using variance reduction criteria. In this work, we propose novel multi-fidelity selection strategies. Specifically, we demonstrate how incorporating information from both the objective and the constraints can further reduce computational costs without compromising the optimality of the solution. We validate the proposed multi-fidelity optimization strategy by applying it to three analytical test cases, showcasing its effectiveness. The proposed method is used to solve efficiently a challenging aircraft wing design problem. The proposed setting uses a linear Vortex Lattice Method (VLM) as a low-fidelity model and a Reynolds-averaged Navier-Stokes coupled VLM as a high-fidelity model. We show that employing our proposed multi-fidelity approach can reduce the required computational budget for convergence by up to 65% when compared to a mono-fidelity approach.