Deep Learning Methods for Reynolds-Averaged Navier–Stokes Simulations of Airfoil Flows
By Nils Thuerey, Konstantin Weissenow, Lukas Prantl, Xiangyu Y. Hu. AIAA Journal, 2018
532 citations recorded by the source corpus.
This study investigates the accuracy of deep learning models for the inference of Reynolds-averaged Navier–Stokes (RANS) solutions. This study focuses on a modernized U-net architecture and evaluat...
Subfields: Aerospace Engineering, Computational Mechanics, Statistical and Nonlinear Physics
View Paper: https://www.semanticscholar.org/paper/70375d7005f32d3522e04212f9bf072fb818cd9d
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Aerospace Engineering
In Computational Mechanics
- Adrian Albert
- Alvaro Sanchez-Gonzalez
- L. Zampieri
- Peter W. Battaglia
- Mustafa Mustafa
- Tobias Pfaff
- Karthik Kashinath
- Meire Fortunato
In Statistical and Nonlinear Physics
- Adrian Albert
- Alvaro Sanchez-Gonzalez
- L. Zampieri
- Peter W. Battaglia
- Rose Yu
- Mustafa Mustafa
- Rui Wang
- Karthik Kashinath
Citations in the corpus
- Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers (2020, unknown): “Additionally, convolutional neural networks (CNNs) were studied for stochastic sub-grid modeling [60], airfoil flow problems [56, 67], and as part of generative networks to leverage the fast inference of pre-trained models [10, 66, 29].”
- Towards Physics-informed Deep Learning for Turbulent Flow Prediction (2019, background): “ed on the shape and the frequency of the motions. Baselines generate smooth predictions and miss the details of small scale motion. U-net is the best performing data-driven video prediction baseline. [23] also found the U-net architecture is quite effective in modeling dynamics flows. Nevertheless, ”
- Learning Mesh-Based Simulation with Graph Networks (2020, methodology): “[36], and found that on both datasets, MESHGRAPHNETS outperforms the UNet in terms of RMSE (Figure 5a).”
- Geometric Deep Learning for Volumetric Computational Fluid Dynamics (2019, methodology): “• The mean relative pointwise absolute error that we call l1rel metric: l1rel = ∑N i |yi − ŷi| ∑N i |yi| It is the metric used in the reference paper for the airfoils section [50].”