A Multi-Objective Robust Aircraft Wing Shape Optimization Approach

Abstract

A robust aerodynamic shape optimization problem is one of the most challenging processes due to the high number of design parameters. The consideration of uncertainties causes a considerable computational burden. Therefore, the reduction of the number of required design variables has a significant impact on computational efficiency. In this study, Proper Orthogonal Decomposition (POD) method is utilized to extract the essential feature of the design variables for an aircraft wing geometry. The design exploration is conducted with the reduced-order parametric model constructed with POD rather than using the more complex or high-dimensional system. The Radial Basis Function (RBF) interpolation technique is implemented to estimate the unknown field available in the design space. Model-form uncertainties originating from the turbulence model required for the CFD analyses are determined using the eigenspace perturbation methodology. Robust solutions that satisfy the design requirements are obtained while taking uncertainties into account using Inductive Design Exploration Method (IDEM). The results of the case study show that geometric filtration using POD-RBF based IDEM computation approach is an alternative multi-objective robust optimization framework. © 2021, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.