Title | ||
---|---|---|
Deep unsupervised learning of turbulence for inflow generation at various Reynolds numbers. |
Abstract | ||
---|---|---|
•We applied an unsupervised deep learning algorithm to inflow generation of turbulent channel flows.•We combined GAN and RNN to generate 2D time-varying turbulent flows.•The trained network could generate the flows at various Reynolds numbers, outside of trained one.•We could achieve high statistical accuracy compared to DNS. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1016/j.jcp.2019.109216 | Journal of Computational Physics |
Keywords | Field | DocType |
Inflow generation,Synthetic generation method,Deep learning,Unsupervised learning,Generative adversarial networks,Recurrent neural networks | Direct numerical simulation,Boundary value problem,Reynolds number,Mathematical analysis,Turbulence,Unsupervised learning,Mechanics,Boundary layer,Flow conditioning,Inflow,Mathematics | Journal |
Volume | ISSN | Citations |
406 | 0021-9991 | 2 |
PageRank | References | Authors |
0.37 | 12 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Junhyuk Kim | 1 | 2 | 0.37 |
Changhoon Lee | 2 | 123 | 15.40 |