Inverse design is an efficient and powerful design tool in the aircraft industry, however, most of the methods require physically meaningful pressure distributions as an input which deeply relies on designer expertise. In this paper, it was proposed to reduce the two-dimensional coordinate value data and pressure distribution data of the airfoil through the variational autoencoder. The model maps high-dimensional data to low-dimensional space, and extracted the low-dimensional manifold structure of high-dimensional data. Test cases of a low-speed airfoil and a transonic airfoil were used for pressure distribution prediction. The result shows that the VAE can achieve high accuracy for pressure distribution prediction. A framework for inverse design of airfoils was also established, and the objective function was the difference between the target pressure and the design pressure. Using a global optimization algorithm to optimization in the low-dimensional space, and a physically meaningful aerodynamic shape and pressure distribution was obtained by the trained model. The VAE model acted like a surrogate model, and the hidden space dimension is low, so the global optimal solution can be efficiently found when the number of populations and iteration steps are small. In the method, the target pressure distribution was defined without a strong dependence on the designer’s experience, achieving a rapid inverse design at the minute level.
Inverse Design Method of Pressure Distribution Using Variational Autoencoder
Lect. Notes Electrical Eng.
Asia-Pacific International Symposium on Aerospace Technology ; 2023 ; Lingshui, China October 16, 2023 - October 18, 2023
2023 Asia-Pacific International Symposium on Aerospace Technology (APISAT 2023) Proceedings ; Chapter : 124 ; 1595-1610
2024-07-05
16 pages
Article/Chapter (Book)
Electronic Resource
English
Springer Verlag | 2021
|Springer Verlag | 2025
|