Hostname: page-component-848d4c4894-4rdrl Total loading time: 0 Render date: 2024-06-16T13:10:12.319Z Has data issue: false hasContentIssue false
  • English
  • Français

Artificial-neural-network-based nonlinear algebraic models for large-eddy simulation of compressible wall-bounded turbulence

Published online by Cambridge University Press:  29 March 2023

Dehao Xu Open the ORCID record for Dehao Xu [Opens in a new window] ,
Jianchun Wang Open the ORCID record for Jianchun Wang [Opens in a new window] ,
Changping Yu Open the ORCID record for Changping Yu [Opens in a new window]  and
Shiyi Chen
Dehao Xu
Affiliation:
State Key Laboratory of Turbulence and Complex Systems, College of Engineering, Peking University, Beijing 100871, PR China
Jianchun Wang*
Affiliation:
Department of Mechanics and Aerospace Engineering, Southern University of Science and Technology, Shenzhen 518055, PR China
Changping Yu
Affiliation:
Laboratory of High Temperature Gas Dynamics, Institute of Mechanics, Chinese Academy of Sciences, Beijing 100190, PR China
Shiyi Chen*
Affiliation:
State Key Laboratory of Turbulence and Complex Systems, College of Engineering, Peking University, Beijing 100871, PR China Department of Mechanics and Aerospace Engineering, Southern University of Science and Technology, Shenzhen 518055, PR China Eastern Institute for Advanced Study, Ningbo 315200, PR China
*
†Email addresses for correspondence: wangjc@sustech.edu.cn, chensy@sustech.edu.cn
†Email addresses for correspondence: wangjc@sustech.edu.cn, chensy@sustech.edu.cn
Get access Rights & Permissions [Opens in a new window]

Abstract

In this paper, we propose artificial-neural-network-based (ANN-based) nonlinear algebraic models for the large-eddy simulation (LES) of compressible wall-bounded turbulence. An innovative modification is applied to the invariants and the tensor bases of the nonlinear algebraic models through using the local grid widths along each direction to normalise the corresponding gradients of the flow variables. Furthermore, the dimensionless model coefficients are determined by the ANN method. The modified ANN-based nonlinear algebraic model (MANA model) has much higher correlation coefficients and much lower relative errors than the dynamic Smagorinsky model (DSM), Vreman model and wall-adapting local eddy-viscosity model in the a priori test. The significantly more accurate estimations of the mean subgrid-scale (SGS) fluxes of the kinetic energy and temperature variance are also obtained by the MANA models in the a priori test. Furthermore, in the a posteriori test, the MANA model can give much more accurate predictions of the flow statistics and the mean SGS fluxes of the kinetic energy and the temperature variance than other traditional eddy-viscosity models in compressible turbulent channel flows with untrained Reynolds numbers, Mach numbers and grid resolutions. The MANA model has a better performance in predicting the flow statistics in supersonic turbulent boundary layer. The MANA model can well predict both direct and inverse transfer of the kinetic energy and temperature variance, which overcomes the inherent shortcoming that the traditional eddy-viscosity models cannot predict the inverse energy transfer. Moreover, the MANA model is computationally more efficient than the DSM.

JFM classification

Mathematical Foundations: Machine learning Turbulent Flows: Turbulence modelling
Type
JFM Papers
Information
Journal of Fluid Mechanics , Volume 960 , 10 April 2023 , A4
Check for updates
Copyright
© The Author(s), 2023. Published by Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Aluie, H. 2013 Scale decomposition in compressible turbulence. Physica D 247, 54–65.CrossRefGoogle Scholar
Aluie, H. & Eyink, G.L. 2009 Localness of energy cascade in hydrodynamic turbulence. II. Sharp spectral filter. Phys. Fluids 21, 115108.CrossRefGoogle Scholar
Anderson, R. & Meneveau, C. 1999 Effects of the similarity model in finite-difference LES of isotropic turbulence using a Lagrangian dynamic mixed model. Flow Turbul. Combust. 62, 201–225.CrossRefGoogle Scholar
Beck, A., Flad, D. & Munz, C.-D. 2019 Deep neural networks for data-driven LES closure models. J. Comput. Phys. 398, 108910.CrossRefGoogle Scholar
Bonett, D.G. & Wright, T.A. 2000 Sample size requirements for estimating Pearson, Kendall and Spearman correlations. Psychometrika 65, 23–28.CrossRefGoogle Scholar
Chamecki, M., Meneveau, C. & Parlange, M.B. 2007 The local structure of atmospheric turbulence and its effect on the smagorinsky model for large eddy simulation. J. Atmos. Sci. 64, 1941–1958.CrossRefGoogle Scholar
Clark, R.A. 1979 Evaluation of sub-grid scalar models using an accurately simulated turbulent flow. J. Fluid Mech. 91, 1–16.CrossRefGoogle Scholar
Clevert, D., Unterthiner, T. & Hochreiter, S. 2015 Fast and accurate deep network learning by exponential linear units (ELUS). arXiv:1511.07289.Google Scholar
Coleman, G.N., Kim, J. & Moser, R.D. 1995 A numerical study of turbulent supersonic isothermal-wall channel flow. J. Fluid Mech. 305, 159–183.CrossRefGoogle Scholar
Da Silva, C.B. & Métais, O. 2002 On the influence of coherent structures upon interscale interactions in turbulent plane jets. J. Fluid Mech. 473, 103–145.CrossRefGoogle Scholar
Deardorff, J.W. 1970 A numerical study of three-dimensional turbulent channel flow at large Reynolds numbers. J. Fluid Mech. 41, 453–480.CrossRefGoogle Scholar
Duan, L., Beekman, I. & Martin, M.P. 2010 Direct numerical simulation of hypersonic turbulent boundary layers. Part 2. Effect of wall temperature. J. Fluid Mech. 655, 419–445.CrossRefGoogle Scholar
Dubois, T., Domaradzki, J.A. & Honein, A. 2002 The subgrid scale estimation model applied to large eddy simulations of compressible turbulence. Phys. Fluids 14, 1781–1801.CrossRefGoogle Scholar
Duchi, J., Hazan, E. & Singer, Y. 2011 Adaptive subgradient methods for online learning and stochastic optimization. J. Machine Learning Res. 12, 2121–2159.Google Scholar
Durbin, P.A. 2018 Some recent developments in turbulence closure modeling. Annu. Rev. Fluid Mech. 50, 77–103.CrossRefGoogle Scholar
Eyink, G.L. 2005 Locality of turbulent cascades. Physica D 207, 91–116.CrossRefGoogle Scholar
Eyink, G.L. & Aluie, H. 2009 Localness of energy cascade in hydrodynamic turbulence. I. Smooth coarse graining. Phys. Fluids 21, 115107.CrossRefGoogle Scholar
Frezat, H., Balarac, G., Le Sommer, J., Fablet, R. & Lguensat, R. 2021 Physical invariance in neural networks for subgrid-scale scalar flux modeling. Phys. Rev. Fluids 6, 024607.CrossRefGoogle Scholar
Gamahara, M. & Hattori, Y. 2017 Searching for turbulence models by artificial neural network. Phys. Rev. Fluids 2, 054604.CrossRefGoogle Scholar
Garnier, E., Adams, N. & Sagaut, P. 2009 Large Eddy Simulation for Compressible Flows. Springer.CrossRefGoogle Scholar
Germano, M., Piomelli, U., Moin, P. & Cabot, W.H. 1991 A dynamic subgrid-scale eddy viscosity model. Phys. Fluids A 3, 1760–1765.CrossRefGoogle Scholar
Ghosal, S., Lund, T.S., Moin, P. & Akselvoll, K. 1995 A dynamic localization model for large-eddy simulation of turbulent flows. J. Fluid Mech. 286, 229–255.CrossRefGoogle Scholar
Glorot, X. & Bengio, Y. 2010 Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, Proceedings of Machine Learning Research (ed. Y.W. Teh & M. Titterington), vol. 9, pp. 249–256. PMLR.Google Scholar
Goodfellow, I., Bengio, Y. & Courville, A. 2016 Deep Learning. MIT Press.Google Scholar
Hunt, J.C.R., Wray, A.A. & Moin, P. 1988 Eddies, streams, and convergence zones in turbulent flows. In Studying Turbulence Using Numerical Simulation Databases, 2, pp. 193–208. Center for Turbulence Research, Ames Research Center.Google Scholar
Jiang, Z., Xiao, Z., Shi, Y. & Chen, S. 2013 Constrained large-eddy simulation of wall-bounded compressible turbulent flows. Phys. Fluids 25, 106102.CrossRefGoogle Scholar
Jiménez, C., Ducros, F., Cuenot, B. & Béedat, B. 2001 Subgrid scale variance and dissipation of a scalar field in large eddy simulations. Phys. Fluids 13, 1748–1754.CrossRefGoogle Scholar
Kawai, S. & Larsson, J. 2013 Dynamic non-equilibrium wall-modeling for large eddy simulation at high Reynolds numbers. Phys. Fluids 25, 015105.CrossRefGoogle Scholar
Kingma, D.P. & Ba, J. 2014 Adam: a method for stochastic optimization. arXiv:1412.6980.Google Scholar
Lagha, M., Kim, J., Eldredge, J.D. & Zhong, X. 2011 A numerical study of compressible turbulent boundary layers. Phys. Fluids 23, 015106.CrossRefGoogle Scholar
Lesieur, M. & Metais, O. 1996 New trends in large-eddy simulations of turbulence. Annu. Rev. Fluid Mech. 28, 45–82.CrossRefGoogle Scholar
Lilly, D.K. 1992 A proposed modification of the germano subgrid-scale closure method. Phys. Fluids A 238, 633–635.CrossRefGoogle Scholar
Ling, J., Kurzawski, A. & Templeton, J.P. 2016 Reynolds averaged turbulence modelling using deep neural networks with embedded invariance. J. Fluid Mech. 807, 155–166.CrossRefGoogle Scholar
Lu, L., Shin, Y., Su, Y. & Karniadakis, G. 2020 Dying relu and initialization: theory and numerical examples. Commun. Comput. Phys. 28, 1671–1706.Google Scholar
Lund, T.S. & Novikov, E.A. 1992 Parameterization of Subgrid-Scale Stress By the Velocity Gradient Tensor. Center for Turbulent Research, Stanford University, NASA.Google Scholar
Maeder, T., Adams, N.A. & Kleiser, L. 2001 Direct simulation of turbulent supersonic boundary layers by an extended temporal approach. J. Fluid Mech. 429, 187–216.CrossRefGoogle Scholar
Martin, M.P., Piomelli, U. & Candler, G. 2000 Subgrid-scale models for compressible large-eddy simulations. J. Theor. Comput. Fluid Dyn. 13, 361–376.CrossRefGoogle Scholar
Maulik, R., San, O., Rasheed, A. & Vedula, P. 2019 Subgrid modelling for two-dimensional turbulence using neural networks. J. Fluid Mech. 858, 122–144.CrossRefGoogle Scholar
Meneveau, C. & Katz, J. 2000 Scale-invariance and turbulence models for large-eddy simulation. Annu. Rev. Fluid Mech. 32, 1–32.CrossRefGoogle Scholar
Meneveau, C., Lund, T.S. & Cabot, W.H. 1996 A lagrangian dynamic subgrid-scale model of turbulence. J. Fluid Mech. 319, 353–385.CrossRefGoogle Scholar
Moin, P., Squires, K., Cabot, W. & Lee, S. 1991 A dynamic subgrid-scale model for compressible turbulence and scalar transport. Phys. Fluids A 3, 2746.CrossRefGoogle Scholar
Moser, R.D., Haering, S.W. & Yalla, G.R. 2021 Statistical properties of subgrid-scale turbulence models. Annu. Rev. Fluid Mech. 53, 255–286.CrossRefGoogle Scholar
Nicoud, F. & Ducros, F. 1999 Subgrid-scale stress modelling based on the square of the velocity gradient tensor. Flow Turbul. Combust. 63, 183–200.CrossRefGoogle Scholar
Noll, W. 1967 Representations of certain isotropic tensor functions. Arch. Math. 21, 87–90.CrossRefGoogle Scholar
Park, J. & Choi, H. 2021 Toward neural-network-based large eddy simulation: application to turbulent channel flow. J. Fluid Mech. 914, A16.CrossRefGoogle Scholar
Piomelli, U. 1993 High Reynolds number calculations using the dynamic subgrid-scale stress model. Phys. Fluids A 5, 1484–1490.CrossRefGoogle Scholar
Piomelli, U. 1999 Large-eddy simulation: achievements and challenges. Prog. Aerosp. Sci. 35, 335–362.CrossRefGoogle Scholar
Pirozzoli, S. & Bernardini, M. 2011 Turbulence in supersonic boundary layers at moderate Reynolds number. J. Fluid Mech. 688, 120–168.CrossRefGoogle Scholar
Pirozzoli, S., Bernardini, M. & Grasso, F. 2008 Characterization of coherent vortical structures in a supersonic turbulent boundary layer. J. Fluid Mech. 613, 205–231.CrossRefGoogle Scholar
Pirozzoli, S., Bernardini, M. & Grasso, F. 2010 On the dynamical relevance of coherent vortical structures in turbulent boundary layers. J. Fluid Mech. 648, 325–349.CrossRefGoogle Scholar
Pirozzoli, S., Grasso, F. & Gatski, T.B. 2004 Direct numerical simulation and analysis of a spatially evolving supersonic turbulent boundary layer at $M=2.25$. Phys. Fluids 16, 530–545.CrossRefGoogle Scholar
Pope, S.B. 1975 A more general effective-viscosity hypothesis. J. Fluid Mech. 72, 331–340.CrossRefGoogle Scholar
Ragab, S.A., Sheen, S.C. & Sreedhar, M. 1992 An investigation of finite-difference methods for large-eddy simulation of a mixing layer. AIAA Paper 92-0554.Google Scholar
Sagaut, P. 2006 Large Eddy Simulation for Incompressible Flows. Springer.Google Scholar
Sayadi, T. & Moin, P. 2012 large eddy simulation of controlled transition to turbulence. Phys. Fluids 24, 114103.CrossRefGoogle Scholar
Shu, C.-W. & Osher, S. 1988 Efficient implementation of essentially non-oscillatory shock-capturing schemes. J. Comput. Phys. 77 (2), 439–471.Google Scholar
Smagorinsky, J. 1963 General circulation experiments with the primitive equations: I. The basic experiment. Mon. Weath. Rev. 91, 99–164.2.3.CO;2>CrossRefGoogle Scholar
Vollant, V., Balarac, G. & Corre, C. 2017 Subgrid-scale scalar flux modelling based on optimal estimation theory and machine-learning procedures. J. Turbul. 18, 854–878.CrossRefGoogle Scholar
Vreman, A.W. 2004 An eddy-viscosity subgrid-scale model for turbulent shear flow: algebraic theory and applications. Phys. Fluids 16, 3670–3681.CrossRefGoogle Scholar
Wang, Z., Luo, K., Li, D., Tan, J. & Fan, J. 2018 b Investigations of data-driven closure for subgrid-scale stress in large-eddy simulation. Phys. Fluids 30, 125101.CrossRefGoogle Scholar
Wang, J., Wan, M., Chen, S. & Chen, S. 2018 a Kinetic energy transfer in compressible isotropic turbulence. J. Fluid Mech. 841, 581–613.CrossRefGoogle Scholar
Wang, B.C., Yin, J., Yee, E. & Bergstrom, D.J. 2007 A complete and irreducible dynamic SGS heat-flux modelling based on the strain rate tensor for large-eddy simulation of thermal convection. Intl J. Heat Fluid Flow 28, 1227–1243.CrossRefGoogle Scholar
Wang, Y., Yuan, Z., Xie, C. & Wang, J. 2021 a Artificial neural network-based spatial gradient models for large-eddy simulation of turbulence. AIP Adv. 11, 055216.CrossRefGoogle Scholar
Wang, Y., Yuan, Z., Xie, C. & Wang, J. 2021 b A dynamic spatial gradient model for the subgrid closure in large-eddy simulation of turbulence. Phys. Fluids 33, 075119.CrossRefGoogle Scholar
Xie, C., Li, K., Ma, C. & Wang, J. 2019 a Modeling subgrid-scale force and divergence of heat flux of compressible isotropic turbulence by artificial neural network. Phys. Rev. Fluids 4, 104605.CrossRefGoogle Scholar
Xie, C., Wang, J., Li, K. & Ma, C. 2019 c Artificial neural network approach to large-eddy simulation of compressible isotropic turbulence. Phys. Rev. E 99, 053113.CrossRefGoogle ScholarPubMed
Xie, C., Wang, J., Li, H., Wan, M. & Chen, S. 2019 b Artificial neural network mixed model for large eddy simulation of compressible isotropic turbulence. Phys. Fluids 31, 085112.Google Scholar
Xie, C., Wang, J. & Weinan, E. 2020 a Modeling subgrid-scale forces by spatial artificial neural networks in large eddy simulation of turbulence. Phys. Rev. Fluids 5, 054606.CrossRefGoogle Scholar
Xie, C., Yuan, Z. & Wang, J. 2020 b Artificial neural network-based nonlinear algebraic models for large eddy simulation of turbulence. Phys. Fluids 32, 115101.CrossRefGoogle Scholar
Xu, D., Wang, J. & Chen, S. 2022 a Skin-friction and heat-transfer decompositions in hypersonic transitional and turbulent boundary layers. J. Fluid Mech. 941, A4.CrossRefGoogle Scholar
Xu, B., Wang, N., Chen, T. & Li, M. 2015 Empirical evaluation of rectified activations in convolutional network. arXiv:1505.00853.Google Scholar
Xu, D., Wang, J., Wan, M., Yu, C., Li, X. & Chen, S. 2021 a Compressibility effect in hypersonic boundary layer with isothermal wall condition. Phys. Rev. Fluids 6, 054609.CrossRefGoogle Scholar
Xu, D., Wang, J., Wan, M., Yu, C., Li, X. & Chen, S. 2021 b Effect of wall temperature on the kinetic energy transfer in hypersonic turbulent boundary layer. J. Fluid Mech. 929, A33.CrossRefGoogle Scholar
Xu, D., Wang, J., Yu, C., Li, X. & Chen, S. 2022 b Contribution of flow topology to the kinetic energy flux in hypersonic turbulent boundary layer. Phys. Fluids 34, 046103.CrossRefGoogle Scholar
Xu, D., Wang, J., Yu, C., Li, X. & Chen, S. 2022 c Effect of compressibility on the small-scale structures in hypersonic turbulent boundary layer. Phys. Fluids 34, 055121.CrossRefGoogle Scholar
Yang, X., Zafar, S., Wang, J. & Xiao, H. 2019 Predictive large-eddy-simulation wall modeling via physics-informed neural networks. Phys. Rev. Fluids 4, 034602.CrossRefGoogle Scholar
Yu, C., Yuan, Z., Qi, H., Wang, J., Li, X. & Chen, S. 2022 Kinetic-energy-flux-constrained model using an artificial neural network for large-eddy simulation of compressible wall-bounded turbulence. J. Fluid Mech. 932, A23.CrossRefGoogle Scholar
Yuan, Z., Wang, Y., Xie, C. & Wang, J. 2022 Dynamic nonlinear algebraic models with scale-similarity dynamic procedure for large-eddy simulation of turbulence. Adv. Aerodyn. 4, 16.CrossRefGoogle Scholar
Yuan, Z., Xie, C. & Wang, J. 2020 Deconvolutional artificial neural network models for large eddy simulation of turbulence. Phys. Fluids 32, 115106.CrossRefGoogle Scholar
Zang, Y., Street, R.L. & Koseff, J.R. 1993 A dynamic mixed subgrid-scale model and its application to turbulent recirculating flows. Phys. Fluids A 5, 3186–3196.CrossRefGoogle Scholar
Zeiler, M.D. 2012 Adadelta: an adaptive learning rate method. arXiv:1212.5701.Google Scholar
Zhao, D. & Aluie, H. 2018 Inviscid criterion for decomposing scales. Phys. Rev. Fluids 3, 054603.CrossRefGoogle Scholar
Zhou, Z., He, G., Wang, S. & Jin, G. 2019 Subgrid-scale model for large-eddy simulation of isotropic turbulent flows using an artificial neural network. Comput. Fluids 195, 104319.CrossRefGoogle Scholar
Supplementary material: File

Xu et al. supplementary material

Xu et al. supplementary material

Download Xu et al. supplementary material(File)
File 38.4 KB