- Physical Review Journals
All JournalsPhysics Magazine
Access Provided by Xinjiang University

Physical Review Fluids

Export citation

Export citation

Choose format for download:

Download Citation
  • Access by Xinjiang University

Progressive, extrapolative machine learning for near-wall turbulence modeling

Yuanwei Bin1,2, Lihua Chen3, George Huang4,*, and Xiang I. A. Yang1,†

  • 1Department of Mechanical Engineering, Pennsylvania State University, State College, Pennsylvania 16802, USA
  • 2State Key Laboratory for Turbulence and Complex Systems, Peking University, Beijing 100871, China
  • 3Department of Engineering Mechanics, Zhejiang University, Hangzhou 310027, China
  • 4Department of Mechanical and Materials Engineering, Wright State University, Dayton, Ohio 45435, USA

  • *george.huang@wright.edu
  • †xzy48@psu.edu
PDF

Phys. Rev. Fluids 7, 084610 – Published 26 August, 2022

DOI: https://doi.org/10.1103/PhysRevFluids.7.084610

Abstract

Conventional empirical turbulence modeling is progressive: one begins by modeling simple flows and progressively works towards more complex ones. The outcome is a series of nested models, with the next, more complex model accounting for some additional physics relative to the previous, less complex model. The above, however, is not the philosophy of data-enabled turbulence modeling. Data-enabled modeling is one stop: one trains against a group of data, which contains simple and complex flows. The resulting model is the best fit of the training data but does not closely reproduce any particular flow. The differences between the two modeling approaches have left data-enabled models open to criticism: machine learned models do not fully preserve, e.g., the law of the wall (among other empirical facts), and they do not generalize to, e.g., high Reynolds numbers (among other conditions). The purpose of this paper is to respond to and resolve some of these criticisms: we intend to show that the conventional progressive modeling is compatible with data-enabled modeling. The paper hinges on the extrapolation theorem and the neutral neural network theorem. The extrapolation theorem allows us to control a network's behavior when extrapolating and the neutral neural network theorem allows us to augment a network without “catastrophic forgetting.” For demonstration purposes, we successively model the flow in the constant stress layer, which is simple; the flow in a channel and a boundary layer, which is more complex; and wall-bounded flow with system rotation, which is even more complex. We show that the more complex models respect the less complex models, and that the models preserve the known empiricism.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (39)

  1. P. Spalart, Comments on the feasibility of LES for wings, and on hybrid RANS/LES approach: Advances in DNS/LES, in Proceedings of the First AFOSR International Conference on DNS/LES, 1997.
  2. H. Choi and P. Moin, Grid-point requirements for large eddy simulation: Chapman's estimates revisited, Phys. Fluids 24, 011702 (2012).
  3. X. I. A. Yang and K. P. Griffin, Grid-point and time-step requirements for direct numerical simulation and large-eddy simulation, Phys. Fluids 33, 015108 (2021).
  4. C. Meneveau and J. Katz, Scale-invariance and turbulence models for large-eddy simulation, Annu. Rev. Fluid Mech. 32, 1 (2000).
  5. S. T. Bose and G. I. Park, Wall-modeled large-eddy simulation for complex turbulent flows, Annu. Rev. Fluid Mech. 50, 535 (2018).
  6. P. A. Durbin, Some recent developments in turbulence closure modeling, Annu. Rev. Fluid Mech. 50, 77 (2018).
  7. X. I. A. Yang, J. Sadique, R. Mittal, and C. Meneveau, Integral wall model for large eddy simulations of wall-bounded turbulent flows, Phys. Fluids 27, 025112 (2015).
  8. X. I. A. Yang, J. Sadique, R. Mittal, and C. Meneveau, Exponential roughness layer and analytical model for turbulent boundary layer flow over rectangular-prism roughness elements, J. Fluid Mech. 789, 127 (2016).
  9. K. Duraisamy, G. Iaccarino, and H. Xiao, Turbulence modeling in the age of data, Annu. Rev. Fluid Mech. 51, 357 (2019).
  10. S. L. Brunton, B. R. Noack, and P. Koumoutsakos, Machine learning for fluid mechanics, Annu. Rev. Fluid Mech. 52, 477 (2020).
  11. X. I. A. Yang, S. Zafar, J.-X. Wang, and H. Xiao, Predictive large-eddy-simulation wall modeling via physics-informed neural networks, Phys. Rev. Fluids 4, 034602 (2019).
  12. X. L. Huang, X. I. Yang, and R. F. Kunz, Wall-modeled large-eddy simulations of spanwise rotating turbulent channels-comparing a physics-based approach and a data-based approach, Phys. Fluids 31, 125105 (2019).
  13. S. B. Pope and S. B. Pope, Turbulent Flows (Cambridge University, New York, 2000).
  14. C. Teo, K. Lim, G. Hong, and M. Yeo, A neural net approach in analyzing photograph in PIV, in Conference Proceedings 1991: IEEE International Conference on Systems, Man, and Cybernetics (IEEE, New York, 1991), pp. 1535–1538.
  15. M. Milano and P. Koumoutsakos, Neural network modeling for near wall turbulent flow, J. Comput. Phys. 182, 1 (2002).
  16. L. Prandtl, Bericht über untersuchungen zur ausgebildeten turbulenz, Z. Angew. Math. Mech. 5, 136 (1925).
  17. B. Launder and D. Spalding, The numerical computation of turbulent flows, Comput. Methods Appl. Mech. Eng. 3, 269 (1974).
  18. F. H. Clauser, The turbulent boundary layer, in Advances in Applied Mechanics (Elsevier, Amsterdam, 1956), Vol. 4, pp. 1–51.
  19. X. I. A. Yang, Z.-H. Xia, J. Lee, Y. Lv, and J. Yuan, Mean flow scaling in a spanwise rotating channel, Phys. Rev. Fluids 5, 074603 (2020).
  20. B. Tracey, K. Duraisamy, and J. Alonso, Application of supervised learning to quantify uncertainties in turbulence and combustion modeling, in Proceedings of the 51st AIAA Aerospace Sciences Meeting (AIAA, 2013), p. 259.
  21. J. Ling, R. Jones, and J. Templeton, Machine learning strategies for systems with invariance properties, J. Comput. Phys. 318, 22 (2016).
  22. J. Weatheritt and R. Sandberg, A novel evolutionary algorithm applied to algebraic modifications of the RANS stress–strain relationship, J. Comput. Phys. 325, 22 (2016).
  23. J.-L. Wu, H. Xiao, and E. Paterson, Physics-informed machine learning approach for augmenting turbulence models: A comprehensive framework, Phys. Rev. Fluids 3, 074602 (2018).
  24. S. Beetham, R. O. Fox, and J. Capecelatro, Sparse identification of multiphase turbulence closures for coupled fluid-particle flows, J. Fluid Mech. 914, A11 (2021).
  25. J. Sirignano, J. F. MacArt, and J. B. Freund, A deep learning PDE augmentation method with application to large-eddy simulation, J. Comput. Phys. 423, 109811 (2020).
  26. J. R. Holland, J. D. Baeder, and K. Duraisamy, Field inversion and machine learning with embedded neural networks: Physics-consistent neural network training, in AIAA Aviation, p. 3200, 2019.
  27. H. J. Bae and P. Koumoutsakos, Scientific multi-agent reinforcement learning for wall-models of turbulent flows, Nat. Commun. 13, 1443 (2022).
  28. T.-R. Xiang, X. Yang, and Y.-P. Shi, Neuroevolution-enabled adaptation of the Jacobi method for Poisson's equation with density discontinuities, Theoretical and Applied Mechanics Letters 11, 100252 (2021).
  29. H. D. Akolekar, Y. Zhao, R. D. Sandberg, and R. Pacciani, Integration of machine learning and computational fluid dynamics to develop turbulence models for improved low-pressure turbine wake mixing prediction, Journal of Turbomachinery 143, 121001 (2021).
  30. P. M. Milani, J. Ling, G. Saez-Mischlich, J. Bodart, and J. K. Eaton, A machine learning approach for determining the turbulent diffusivity in film cooling flows, Journal of Turbomachinery 140, 021006 (2018).
  31. J. Ling, A. Kurzawski, and J. Templeton, Reynolds averaged turbulence modelling using deep neural networks with embedded invariance, J. Fluid Mech. 807, 155 (2016).
  32. P. Spalart, Comments on machine learning models, in Model Consistent Data Driven Turbulence Modeling (Symposium, Virtual, 2021).
  33. J. Graham, K. Kanov, X. I. A. Yang, M. Lee, N. Malaya, C. C. Lalescu, R. Burns, G. Eyink, A. Szalay, R. D. Moser, and C. Meneveau, A web services accessible database of turbulent channel flow and its use for testing a new integral wall model for les, J. Turbul. 17, 181 (2016).
  34. M. Lee and R. D. Moser, Direct numerical simulation of turbulent channel flow up to Reτ≈5200, J. Fluid Mech. 774, 395 (2015).
  35. P. Schlatter and R. Örlü, Assessment of direct numerical simulation data of turbulent boundary layers, J. Fluid Mech. 659, 116 (2010).
  36. X. L. Huang and X. I. Yang, A Bayesian approach to the mean flow in a channel with small but arbitrarily directional system rotation, Phys. Fluids 33, 015103 (2021).
  37. R. M. French, Catastrophic forgetting in connectionist networks, Trends Cognit. Sci. 3, 128 (1999).
  38. G. M. Van de Ven and A. S. Tolias, Three scenarios for continual learning, arXiv:1904.07734.
  39. C. Huang, S. Li, J. Wang, B. Yang, and F. Zhang, Global uncertainty analysis for the rrkm/master equation modeling of a typical multi-well and multi-channel reaction system, Combust. Flame 216, 62 (2020).

Outline

Information

Phys. Rev. Fluids 7, 084610– Published 26 August, 2022
  • Received 15 March 2022
  • Accepted 15 August 2022
Crossmark - Check for updates button

©2022 American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation