A Bayesian-Based Approach to Multifidelity Multidisciplinary Design Optimization
Douglas Allaire, Karen E. Willcox, Olivier Toupet · 13th AIAA/ISSMO Multidisciplinary Analysis Optimization Conference · 2010
Design processes for complex systems often begin with low-fidelity models and progressively incorporate higher fidelity tools. Existing multifidelity optimization approaches generally attempt to calibrate low-fidelity models or replace low-fidelity analysis results using data from higher fidelity analyses. This paper proposes a fundamentally dierent approach that uses the tools of estimation theory to fuse together information from multifidelity analyses. This approach is combined with maximum entropy characterizations of model inadequacy and global sensitivity analysis for fidelity management, resulting in a Bayesian-based approach to mitigating risk in multifidelity multidisciplinary design optimization. The method is demonstrated on a wing-sizing problem for a high altitude, long endurance vehicle.