Data augmented turbulence modeling for three-dimensional separation flows

Abstract

Field inversion and machine learning are implemented in this study to describe three-dimensional (3-D) separation flow around an axisymmetric hill and augment the Spart-Allmaras (SA) model. The discrete adjoint method is used to solve the field inversion problem, and an artificial neural network is used as the machine learning model. A validation process for field inversion is proposed to adjust the hyperparameters and obtain a physically acceptable solution. The field inversion result shows that the non-equilibrium turbulence effects in the boundary layer upstream of the mean separation line and in the separating shear layer dominate the flow structure in the 3-D separating flow, which agrees with prior physical knowledge. However, the effect of turbulence anisotropy on the mean flow appears to be limited. Two approaches are proposed and implemented in the machine learning stage to overcome the problem of sample imbalance while reducing the computational cost during training. The results are all satisfactory, which proves the effectiveness of the proposed approaches.

On the benefits and limitations of Echo State Networks for turbulent flow prediction

“…This is why in the past years, such algorithms have gained popularity in the fluid mechanics community. Recent ML applications in this field cover turbulence modeling [6][7][8][9][10], indirect determination of fluid properties from flow data [11], flow control [12][13][14], production of super-resolved small-scale features of complex flows [15,16], as well as turbulent flow prediction [17]. The latter, poses a challenge, as turbulent flows are inherently chaotic, so that predictions, starting from a certain flow state will quickly diverge from the true trajectory over time.…”