Data-based approach for wing shape design optimization

Aircraft design is a trade-off among different objectives and constraints, so multiple design rounds are usually required. Aerodynamic shape optimization based on high-fidelity computational fluid dynamics is consequently expensive, especially for wing design in the transonic regime. To address the interactive demand in aircraft design, we present a data-based approach to real-time high-fidelity wing shape optimization. Accurate and fast data-based models are constructed to perform aerodynamic analyses in lieu of costly computational fluid dynamic simulations. For the versatility of the data-based models, 135,108 training data that cover wing samples of different aerodynamic shapes, flight speeds, and flight altitudes are used. The verification on 47,967 wings shows that mean relative errors of C_L, C_D, and C_M compared to computational fluid dynamic simulations are all within 0.4%. The models are further verified in multiple single-point, multi-point, and multi-objective wing design optimization problems. The optimized wings have similar shapes to those obtained by computational-fluid-dynamics-based optimization, and the differences in C_D are merely one∼two counts. These results demonstrate the effectiveness of the data-based approach to fast and high-fidelity wing design. This work showcases a real-time high-fidelity optimization approach to high-dimensional nonlinear engineering problems using data-based models. © 2021 Elsevier Masson SAS.