CNNFOIL: convolutional encoder decoder modeling for pressure fields around airfoils
- PDF / 3,070,983 Bytes
- 15 Pages / 595.276 x 790.866 pts Page_size
- 93 Downloads / 170 Views
(0123456789().,-volV)(0123456789().,-volV)
ORIGINAL ARTICLE
CNNFOIL: convolutional encoder decoder modeling for pressure fields around airfoils Cihat Duru1
•
Hande Alemdar2 • O¨zgu¨r Ug˘ras¸ Baran1
Received: 3 June 2020 / Accepted: 26 October 2020 Ó Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract In this study, we propose an encoder–decoder convolutional neural network-based approach for estimating the pressure field around an airfoil. The developed tool is one of the early steps of a machine-learning-based aerodynamic performance prediction tool. Network training and evaluation are performed from a set of computational fluid dynamics (CFD)-based solutions of the 2-D flow field around a group of known airfoils involving symmetrical, cambered, thick and thin airfoils. Reynolds averaged Navier Stokes-based CFD simulations are performed at a selected single Mach number and for an angle of attack condition. The calculated pressure field, which is the main parameter for lift and drag calculations, is fed to the neural network training algorithm. Pressure data are calculated using CFD methods on high-quality structured computational grids. For the better shape learning, a distance map is generated from airfoil shape and provided to the algorithm at data locations of the pressure points relative to the airfoil shape. Experiments are conducted with unseen airfoil shapes to evaluate the predictive capability of our model. Performance analysis for airfoils with different thicknesses and cambers is conducted. We also investigated the effect of the shock on the performance of our model. Overall, our model achieves 88% accuracy for unseen airfoil shapes and shows promise to capture the overall flow pattern accurately. Also, significant speedup is achieved compared to time-consuming CFD simulations. We achieve almost four orders of speed-up with a much cheaper computational resource. Keywords Computational fluid dynamics Machine learning Convolutional neural network Aerodynamics
1 Introduction Prediction of airfoil performance constitutes a crucial step in aircraft design. The initial design stage involves experimenting with many different airfoil sections and often results in a custom airfoil profile at the final design. Figure 1 shows an airfoil geometry with the essential
& Cihat Duru [email protected] Hande Alemdar [email protected] ¨ zgu¨r Ug˘ras¸ Baran O [email protected] 1
Department of Mechanical Engineering, Middle East Technical University, Ankara, Turkey
2
Department of Computer Engineering, Middle East Technical University, Ankara, Turkey
geometrical characteristics which affect the flow around the airfoil. A lifting surface of an aircraft geometry is defined by a number of parameters requested by flight regime, maneuvering requirements, flight altitude, structural limits, and other constraints. In general, initial airfoil profile of a lifting surface is selected from a particular family of airfoil sections, based on the mission requirements. These requirements include but not
Data Loading...
