High-flexibility reconstruction of small-scale motions in wall turbulence using a generalized zero-shot learning

• Published in: Journal of fluid mechanics Vol. 990
• Main Authors: Wu, Haokai, Zhang, Kai, Zhou, Dai, Chen, Wen-Li, Han, Zhaolong, Cao, Yong
• Format: Journal Article
• Language: English
• Published: Cambridge, UK Cambridge University Press 14.08.2024
• Subjects: Boundary layers; Cascade flow; Channel flow; Continuity equation; Datasets; Direct numerical simulation; Energy; Energy dissipation; Energy exchange; Flexibility; Flow structures; Flow velocity; Fluid dynamics; JFM Rapids; Mathematical models; Neural networks; Physics; Reconstruction; Residual energy; Scale invariance; Simulation; Turbulence; Turbulent boundary layer; Turbulent flow; Velocity distribution; Wavelengths; Zero-shot learning; turbulent boundary layers; boundary layer structure
• ISSN: 0022-1120; 1469-7645
• DOI: 10.1017/jfm.2024.521

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.