A comparison between 2D DeepCFD, 2D CFD simulations and 2D/2C PIV measurements of NACA 0012 and NACA 6412 airfoils

In this study, fluid flow predictions using three different methods were compared: DeepCFD, an artificial intelligence code; computational fluid dynamics (CFD) using Ansys Fluent and OpenFOAM; and two-dimensional, two-component particle image velocimetry (PIV) measurements. The airfoils under investigation were the NACA 0012 with a 10 degrees degrees angle of attack and the NACA 6412 with a 0 degrees degrees angle of attack. To train DeepCFD, 763, 2585, and 6283 OpenFOAM simulations based on primitives were utilized. The investigation was conducted at a free stream velocity of 10 m/s and a Reynolds number of 82000. Results show that once the DeepCFD network is trained, prediction times are negligible, enabling real-time optimization of airfoils. The mean absolute error between CFD and DeepCFD, with 6283 trained primitives, for NACA 0012 predictions resulted in velocity components Ux x = 1.08 m/s, Uy y = 0.43 m/s, and static pressure p = 4.57 Pa. For NACA 6412, the corresponding mean absolute errors are Ux x = 0.81 m/s, Uy y = 0.59 m/s, and p = 7.5 Pa. Qualitative agreement was observed between PIV measurements, DeepCFD, and CFD. Results are promising that artificial intelligence has the potential for realtime fluid flow optimization of NACA airfoils in the future. The main goal was not just to train a network specifically for airfoils, but also for variant shapes. Airfoils are used since they are highly sophisticated in fluid dynamics and experimental data was available.