Title: Well, how accurate is it? A Study of Deep Learning Methods for Reynolds-Averaged Navier-Stokes Simulations

Nils Thuerey, TUM
K. Weissenow, TUM
H. Mehrotra, TUM
N. Mainali, TUM
L. Prantl, TUM
Xiangyu Hu, TUM

With this study we investigate the accuracy of deep learning models for the inference of Reynolds-Averaged Navier-Stokes turbulence simulations. We focus on a modernized U-net architecture, and evaluate a large number of trained neural networks with respect to their accuracy for the calculation of pressure and velocity fields. In particular, we illustrate how training data size and the number of weights in the networks interact. With our best models we arrive at a mean relative pressure and velocity error of less than 3% across a range of previously unseen airfoil shapes. In addition all source code is publicly available in order to ensure reproducibility and to provide a starting point for researchers interested in deep learning methods for physics problems. While this work focuses on RANS solutions, the neural network architecture and learning setup are very generic, and applicable to a wide range of PDE problems with field data.

Preprint (arXiv)

Fig. 1: Overview of the network architecture (a U-net) and the input / output data.