CNNFOIL: convolutional encoder decoder modeling for pressure fields around airfoils

• Published in: Neural computing & applications Vol. 33; no. 12; pp. 6835 - 6849
• Main Authors: Duru, Cihat, Alemdar, Hande, Baran, Özgür Uğraş
• Format: Journal Article
• Language: English
• Published: London Springer London 01.06.2021; Springer Nature B.V
• Subjects: Aerodynamics; Algorithms; Angle of attack; Artificial Intelligence; Artificial neural networks; Cambering; Coders; Computational Biology/Bioinformatics; Computational fluid dynamics; Computational grids; Computational Science and Engineering; Computer Science; Computer simulation; Data Mining and Knowledge Discovery; Flow distribution; Image Processing and Computer Vision; Mach number; Machine learning; Mathematical models; Model accuracy; Neural networks; Original Article; Performance prediction; Probability and Statistics in Computer Science; Reynolds averaged Navier-Stokes method; Thin airfoils; Two dimensional flow; Aerodynamics; Computational fluid dynamics; Convolutional neural network; Machine learning
• DOI: 10.1007/s00521-020-05461-x
• ISSN: 0941-0643

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 speed-up is achieved compared to time-consuming CFD simulations. We achieve almost four orders of speed-up with a much cheaper computational resource.