Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Super-resolution Reconstruction of Transitional Boundary Layers Using a Deep Neural Network

Super-resolution Reconstruction of Transitional Boundary Layers Using a Deep Neural Network Numerical simulations of turbulent flow require excessive computational resources due to the multi scale characteristics of turbulence. Thus, a technique to reconstruct a high-resolution flow field from a coarse flow data can be helpful. For this purpose, various artificial neural-network-based super-resolution methods have been developed in recent years. Although previous studies reported that the super-resolution methods show remarkable performance for turbulent channel flow and homogeneous isotropic turbulence, its application for spatially developing flow with laminar, transitional, and turbulent characteristics has not been reported. In the present study, a super-resolution reconstruction method applicable for spatially developing laminar-transition-turbulent flow is developed by training the network for boundary layer flow with bypass transition. In addition, the generalization of the network for boundary layer flow with natural transition and for fully turbulent boundary layer flow is attempted. A super-resolution method based on a generative adversarial network (GAN) is employed for the study as it shows the best performance among tested network models. It is found that the developed method successfully reconstructs flow structures in transitional and early turbulent regions. In addition, statistics such as the mean velocity and the power spectral density of velocity from recovered fields show good agreement to those of DNS. Notably, the GAN model which is only trained for the bypass transition is also found to be applicable to boundary layer flow with K-type natural transition and fully developed turbulent boundary layers. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png International Journal of Aeronautical and Space Sciences Springer Journals

Super-resolution Reconstruction of Transitional Boundary Layers Using a Deep Neural Network

Download PDF
17 pages

Loading next page...
 
/lp/springer-journals/super-resolution-reconstruction-of-transitional-boundary-layers-using-rVm8MLiYZo
Publisher
Springer Journals
Copyright
Copyright © The Author(s), under exclusive licence to The Korean Society for Aeronautical & Space Sciences 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
ISSN
2093-274X
eISSN
2093-2480
DOI
10.1007/s42405-023-00598-0
Publisher site
See Article on Publisher Site

Abstract

Numerical simulations of turbulent flow require excessive computational resources due to the multi scale characteristics of turbulence. Thus, a technique to reconstruct a high-resolution flow field from a coarse flow data can be helpful. For this purpose, various artificial neural-network-based super-resolution methods have been developed in recent years. Although previous studies reported that the super-resolution methods show remarkable performance for turbulent channel flow and homogeneous isotropic turbulence, its application for spatially developing flow with laminar, transitional, and turbulent characteristics has not been reported. In the present study, a super-resolution reconstruction method applicable for spatially developing laminar-transition-turbulent flow is developed by training the network for boundary layer flow with bypass transition. In addition, the generalization of the network for boundary layer flow with natural transition and for fully turbulent boundary layer flow is attempted. A super-resolution method based on a generative adversarial network (GAN) is employed for the study as it shows the best performance among tested network models. It is found that the developed method successfully reconstructs flow structures in transitional and early turbulent regions. In addition, statistics such as the mean velocity and the power spectral density of velocity from recovered fields show good agreement to those of DNS. Notably, the GAN model which is only trained for the bypass transition is also found to be applicable to boundary layer flow with K-type natural transition and fully developed turbulent boundary layers.

Journal

International Journal of Aeronautical and Space Sciences – Springer Journals

Published: May 23, 2023

Keywords: Super-resolution reconstruction; Transitional boundary layer; Turbulent boundary layer; Deep neural network; Generative adversarial network

References

  • Unsupervised deep learning for super-resolution reconstruction of turbulence
    Kim, H; Kim, J; Won, S; Lee, C
  • Super-resolution reconstruction of turbulent velocity fields using a generative adversarial network-based artificial intelligence framework
    Deng, Z; He, C; Liu, Y; Kim, KC
  • Data-driven prediction of unsteady flow over a circular cylinder using deep learning
    Lee, S; You, D
  • Analysis of a convolutional neural network for predicting unsteady volume wake flow fields
    Lee, S; You, D
  • Reynolds averaged turbulence modelling using deep neural networks with embedded invariance
    Ling, J; Kurzawski, A; Templeton, J
  • Modeling subgrid-scale force and divergence of heat flux of compressible isotropic turbulence by artificial neural network
    Xie, C; Li, K; Ma, C; Wang, J
  • Toward neural-network-based large eddy simulation: application to turbulent channel flow
    Park, J; Choi, H
  • Prediction of molten steel flow in a tundish with water model data using a generative neural network with different clip sizes
    Choi, B; Lee, S; You, D
  • Prediction of a typhoon track using a generative adversarial network and satellite images
    Rüttgers, M; Lee, S; Jeon, S; You, D
  • Prediction of typhoon track and intensity using a generative adversarial network with observational and meteorological data
    Rüttgers, M; Jeon, S; Lee, S; You, D
  • Deep learning methods for super-resolution reconstruction of turbulent flows
    Liu, B; Tang, J; Huang, H; Lu, XY
  • Machine-learning-based spatio-temporal super resolution reconstruction of turbulent flows
    Fukami, K; Fukagata, K; Taira, K
  • From coarse wall measurements to turbulent velocity fields through deep learning
    Güemes, A; Discetti, S; Ianiro, A; Sirmacek, B; Azizpour, H; Vinuesa, R
  • On bypass transition in separation bubbles: a review
    Yang, Z
  • Transitional–turbulent spots and turbulent–turbulent spots in boundary layers
    Wu, X; Moin, P; Wallace, JM; Skarda, J; Lozano-Durán, A; Hickey, JP
  • A dynamic global-coefficient subgrid-scale eddy-viscosity model for large-eddy simulation in complex geometries
    You, D; Moin, P
  • Application of a fractional-step method to incompressible Navier-Stokes equations
    Kim, J; Moin, P
  • Progress-variable approach for large-eddy simulation of non-premixed turbulent combustion
    Pierce, CD; Moin, P
  • Image super-resolution using deep convolutional networks
    Dong, C; Loy, CC; He, K; Tang, X
  • Imagenet classification with deep convolutional neural networks
    Krizhevsky, A; Sutskever, I; Hinton, GE
  • Transitional and turbulent boundary layer with heat transfer
    Wu, X; Moin, P
  • A multi-GPU method for ADI-based fractional-step integration of incompressible Navier-Stokes equations
    Ha, S; Park, J; You, D
  • Generation of turbulent inflow data for spatially-developing boundary layer simulations
    Lund, TS; Wu, X; Squires, KD
  • On the unsteady Reynolds-averaged Navier-Stokes capability of simulating turbulent boundary layers under unsteady adverse pressure gradients
    Park, J; Ha, S; You, D
  • Direct numerical simulation of turbulence in a nominally zero-pressure-gradient flat-plate boundary layer
    Wu, X; Moin, P