No CrossRef data available.
Article contents
High-flexibility reconstruction of small-scale motions in wall turbulence using a generalized zero-shot learning
Published online by Cambridge University Press: 14 August 2024
Abstract
This study proposes a novel super-resolution (or SR) framework for generating high-resolution turbulent boundary layer (TBL) flow from low-resolution inputs. The framework combines a super-resolution generative adversarial neural network (SRGAN) with down-sampling modules (DMs), integrating the residual of the continuity equation into the loss function. The DMs selectively filter out components with excessive energy dissipation in low-resolution fields prior to the super-resolution process. The framework iteratively applies the SRGAN and DM procedure to fully capture the energy cascade of multi-scale flow structures, collectively termed the SRGAN-based energy cascade reconstruction framework (EC-SRGAN). Despite being trained solely on turbulent channel flow data (via ‘zero-shot transfer’), EC-SRGAN exhibits remarkable generalization in predicting TBL small-scale velocity fields, accurately reproducing wavenumber spectra compared to direct numerical simulation (DNS) results. Furthermore, a super-resolution core is trained at a specific super-resolution ratio. By leveraging this pretrained super-resolution core, EC-SRGAN efficiently reconstructs TBL fields at multiple super-resolution ratios from various levels of low-resolution inputs, showcasing strong flexibility. By learning turbulent scale invariance, EC-SRGAN demonstrates robustness across different TBL datasets. These results underscore the potential of EC-SRGAN for generating and predicting wall turbulence with high flexibility, offering promising applications in addressing diverse TBL-related challenges.
- Type
- JFM Rapids
- Information
- Copyright
- © The Author(s), 2024. Published by Cambridge University Press
References
Cao, Y., Tamura, T., Zhou, D., Bao, Y. & Han, Z. 2022 Topological description of near-wall flows around a surface-mounted square cylinder at high Reynolds numbers. J. Fluid Mech. 933, A39.CrossRefGoogle Scholar
Fukami, K., Fukagata, K. & Taira, K. 2021 Machine learning-based spatio-temporal super resolution reconstruction of turbulent flows. J. Fluid Mech. 909, A9.CrossRefGoogle Scholar
Fukami, K., Goto, S. & Taira, K. 2024 Data-driven nonlinear turbulent flow scaling with Buckingham Pi variables. J. Fluid Mech. 984, R4.CrossRefGoogle Scholar
Guastoni, L., Güemes, A., Ianiro, A., Discetti, S., Schlatter, P., Azizpour, H. & Vinuesa, R. 2021 Convolutional-network models to predict wall-bounded turbulence from wall quantities. J. Fluid Mech. 928, A27.CrossRefGoogle Scholar
Güemes, A., Discetti, S., Ianiro, A., Sirmacek, B., Azizpour, H. & Vinuesa, R. 2021 From coarse wall measurements to turbulent velocity fields through deep learning. Phys. Fluids 33, 075121.CrossRefGoogle Scholar
He, K., Zhang, X., Ren, S. & Sun, J. 2016 Deep residual learning for image recognition. In IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, pp. 770–778. IEEE.CrossRefGoogle Scholar
Lee, J. & Zaki, T.A. 2018 Detection algorithm for turbulent interfaces and large-scale structures in intermittent flows. Comput. Fluids 175, 142–158.CrossRefGoogle Scholar
Lee, M., Malaya, N. & Moser, R.D. 2013 Petascale direct numerical simulation of turbulent channel flow on up to 786 K cores. In The International Conference on High Performance Computing, Denver, CO, USA, pp. 1–11. IEEE.CrossRefGoogle Scholar
Mi, J., Jin, X. & Li, H. 2023 Cascade-Net for predicting cylinder wake at Reynolds numbers ranging from subcritical to supercritical regime. Phys. Fluids 35, 075132.CrossRefGoogle Scholar
Obiols-Sales, O., Vishnu, A. & Malaya, N.P. 2021 SURFNet: super-resolution of turbulent flows with transfer learning using small datasets. In IEEE 30th International Conference on Parallel Architectures and Compilation Techniques (PACT), Atlanta, USA, pp. 331–344. IEEE.CrossRefGoogle Scholar
Shevkar, P.P., Mohanan, S.K. & Puthenveettil, B.A. 2023 Effect of shear on local boundary layers in turbulent convection. J. Fluid Mech. 962, A41.CrossRefGoogle Scholar
Stengel, K., Glaws, A., Hettinger, D. & King, R.N. 2020 Adversarial super-resolution of climatological wind and solar data. PNAS 117 (29), 201918964.CrossRefGoogle ScholarPubMed
Towne, A., et al. 2023 A database for reduced-complexity modeling of fluid flows. AIAA J. 61, 7.CrossRefGoogle Scholar
Vinuesa, R. & Brunton, S.L. 2022 Enhancing computational fluid dynamics with machine learning. Nat. Comput. Sci. 2, 358–366.CrossRefGoogle ScholarPubMed
Wang, H., Wu, W., Su, Y., Duan, Y. & Wang, P. 2019 Image super-resolution using a improved generative adversarial network. In IEEE 9th International Conference on Electronics Information and Emergency Communication, Beijing, China, pp. 312–315. IEEE.CrossRefGoogle Scholar
Wu, H., Chen, Y., Xie, P., Zhou, D., Tamura, T., Zhang, K., Cao, S. & Cao, Y. 2023 Sparse-measurement-based peak wind pressure evaluation by super-resolution convolutional neural networks. J. Wind Engng Ind. Aerod. 242, 105574.CrossRefGoogle Scholar
Xian, Y., Lampert, C.H., Schiele, B. & Akata, Z. 2017 Zero-shot learning – a comprehensive evaluation of the good, the bad and the ugly. IEEE T. Pattern Anal. 41, 2251–2265.CrossRefGoogle Scholar
Yousif, M.Z., Yu, L. & Lim, H.C. 2021 High-fidelity reconstruction of turbulent flow from spatially limited data using enhanced super-resolution generative adversarial network. Phys. Fluids 33 (12), 125119.CrossRefGoogle Scholar
Yousif, M.Z., Zhang, M., Yu, L., Vinuesa, R. & Lim, H.C. 2023 A transformer-based synthetic-inflow generator for spatially developing turbulent boundary layers. J. Fluid Mech. 957, A6.CrossRefGoogle Scholar