Application of deep learning method to Reynolds stress models of channel flow based on reduced-order modeling of DNS data

  • Zhen Zhang
  • Xu-dong Song
  • Shu-ran Ye
  • Yi-wei WangEmail author
  • Chen-guang Huang
  • Yi-ran An
  • Yao-song Chen


Recently, the methodology of deep learning is used to improve the calculation accuracy of the Reynolds-averaged Navier-Stokes (RANS) model. In this paper, a neural network is designed to predict the Reynolds stress of a channel flow of different Reynolds numbers. The rationality and the high efficiency of the neural network is validated by comparing with the results of the direct numerical simulation (DNS), the large eddy simulation (LES), and the deep neural network (DNN) of other studies. To further enhance the prediction accuracy, three methods are developed by using several algorithms and simplified models in the neural network. In the method 1, the regularization is introduced and it is found that the oscillation and the overfitting of the results are effectively prevented. In the method 2, y+ is embedded in the input variable while the combination of the invariants is simplified in the method 3. From the predicted results, it can be seen that by using the first two methods, the errors are reduced. Moreover, the method 3 shows considerable advantages in the DNS trend and the smoothness of a curve. Consequently, it is concluded that the DNNs can predict effectively the anisotropic Reynolds stress and is a promising technique of the computational fluid dynamics.

Key words

Deep neural network channel flow turbulence model Reynolds stress 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Vandriest E. R. On turbulent flow near a wall [J]. Journal of the Aeronautical Sciences, 1956, 23(11): 1007–1011.CrossRefGoogle Scholar
  2. [2]
    Feiereisen W. J. Numerical simulation of a compressible homogeneous, turbulent shear flow [D]. Doctoral Thesis, Stanford, USA: Stanford University, 1981.Google Scholar
  3. [3]
    Benzi R., Patarnello S., Santangelo P. On the statistical properties of two-dimensional decaying turbulence [J]. Europhysics Letters, 1987, 3(7): 811–818.CrossRefGoogle Scholar
  4. [4]
    Brachet M. E., Meneguzzi M., Sulem P. L. Small-scale dynamics of high-reynolds-number two-dimensional turbulence [J]. Physical Review Letters, 1986, 57(6): 683–686.CrossRefGoogle Scholar
  5. [5]
    Gilbert A. D. Spiral structures and spectra in two-dimensional turbulence [J]. Journal of Fluid Mechanics, 1988, 193: 475–497.MathSciNetCrossRefzbMATHGoogle Scholar
  6. [6]
    Pope S. B. Turbulent flows [M]. Cambridge, UK: Cambridge University Press, 2001.CrossRefGoogle Scholar
  7. [7]
    Rodi W. On the simulation of turbulent flow past bluff bodies [J]. Journal of Wind Engineering and Industrial Aerodynamics, 1993, 46-47: 3–19.CrossRefGoogle Scholar
  8. [8]
    Speziale C. G. A review of Reynolds stress models for turbulent shear flows [C]. 20th Symposium on Naval Hydrodynamics, Washington DC, USA, 1995.Google Scholar
  9. [9]
    Spalart P. R. Philosophies and fallacies in turbulence modeling [J]. Progress in Aerospace Sciences, 2015, 74: 1–15.CrossRefGoogle Scholar
  10. [10]
    Dutta R., Xing T. Five-equation and robust three-equation method for solution verification of large eddy simulations [J]. Journal of Hydrodynamics, 2018, 30(1): 23–33.CrossRefGoogle Scholar
  11. [11]
    Cheng H. Y., Long X. P., Liang Y. Z. et al. URANS simulations of the tip-leakage cavitating flow with verification and validation procedures [J]. Journal of Hydrodynamics, 2018, 30(3): 531–534.CrossRefGoogle Scholar
  12. [12]
    Wang C. C., Huang B., Wang G. Y. et al. Numerical simulation of transient turbulent cavitating flows with special emphasis on shock wave dynamics considering the water/vapor compressibility [J]. Journal of Hydrodynamics, 2018, 30(4): 573–591.CrossRefGoogle Scholar
  13. [13]
    Hinton G., Salakhutdinov R. Reducing the dimensionality of data with neural networks [J]. Science, 2006, 313(5786): 504–507.MathSciNetCrossRefzbMATHGoogle Scholar
  14. [14]
    Tracey B., Duraisamy K., Alonso J. Application of supervised learning to quantify uncertainties in turbulence and combustion modeling [C]. 51st AIAA Aerospace Sciences Meeting Including the New Horizons Forum and Aerospace Exposition, Texas, USA, 2013, 2013–0259.Google Scholar
  15. [15]
    Ling J., Ruiz A., Lacaze G. et al. Uncertainty analysis and data-driven model advances for a jet-in-crossflow [J]. Journal of Turbomachinery, 2016, 139(2): 021008.CrossRefGoogle Scholar
  16. [16]
    Ling J., Kurzawski A., Templeton J. Reynolds averaged turbulence modelling using deep neural networks with embedded invariance [J]. Journal of Fluid Mechanics, 2016, 807: 155–166.MathSciNetCrossRefzbMATHGoogle Scholar
  17. [17]
    Kutz J. N. Deep earning in fluid dynamics [J]. Journal of Fluid Mechanics, 2017, 814: 1–4.CrossRefzbMATHGoogle Scholar
  18. [18]
    Wang J. X., Wu J. L., Xiao H. Physics-informed machine learning approach for reconstructing Reynolds stress modeling discrepancies based on DNS data [J]. Physical Review Fluids, 2017, 2(3): 1–22.Google Scholar
  19. [19]
    Xiao H., Wu J. L., Wang J. X. et al. Quantifying and reducing model-form uncertainties in Reynolds-averaged Navier-Stokes simulations: A data-driven, physics-informed Bayesian approach [J]. Journal of Computational Physics, 2016, 324(C): 115–136.MathSciNetCrossRefzbMATHGoogle Scholar
  20. [20]
    Lecun Y., Bengio Y., Hinton G. Deep learning [J]. Nature, 2015, 521(7553): 436.CrossRefGoogle Scholar
  21. [21]
    Jarrett K., Kavukcuoglu K., Ranzato M. et al. What is the best multi-stage architecture for object recognition? [C]. International Conference on Computer Vision (ICCV), Kyoto, Japan, 2009, 2146–2153.Google Scholar
  22. [22]
    Krizhevsky A., Sutskever I., Hinton G. E. ImageNet classification with deep convolutional neural networks [C]. 25th International Conference on Neural Information Processing Systems, Nevada, USA, 2012, 1097–1105.Google Scholar
  23. [23]
    He K., Zhang X., Ren S. et al. Deep residual learning for image recognition [C]. International Conference on Computer Vision (ICCV), Santiago, Chile, 2015, 1026–1034.Google Scholar
  24. [24]
    Maas A. L., Hannun A. Y., Ng A. Y. Rectifier nonlinearities improve neural network acoustic models [C]. International Conference on Machine Learning (ICML), Atlanta, USA, 2013.Google Scholar
  25. [25]
    Pope S. B. A more general effective-viscosity hypothesis [J]. Journal of Fluid Mechanics Digital Archive, 1975, 72(2): 331–340.CrossRefzbMATHGoogle Scholar
  26. [26]
    Jones R., Templeton J., Ling J. Machine learning strategies for systems with invariance properties [J]. Journal of Computational Physics, 2016, 318(8): 22–35.MathSciNetzbMATHGoogle Scholar
  27. [27]
    Moser R. D., Kim J., Mansour N. N. Direct numerical simulation of turbulent channel flow up to Re = 590 ? [J]. Physics of Fluids, 1999, 11(4): 943–945.CrossRefzbMATHGoogle Scholar
  28. [28]
    Krogh A., Hertz J. A. A simple weight decay can improve generalization [C]. International Conference on Neural Information Processing Systems. San Mateo, California, USA, 1992, 950–957.Google Scholar

Copyright information

© China Ship Scientific Research Center 2018

Authors and Affiliations

  • Zhen Zhang
    • 1
    • 2
  • Xu-dong Song
    • 3
  • Shu-ran Ye
    • 1
    • 2
  • Yi-wei Wang
    • 1
    • 2
    Email author
  • Chen-guang Huang
    • 1
    • 2
  • Yi-ran An
    • 3
  • Yao-song Chen
    • 3
  1. 1.Key Laboratory for Mechanics in Fluid Solid Coupling Systems, Institute of MechanicsChinese Academy of SciencesBeijingChina
  2. 2.College of Engineering ScienceUniversity of Chinese Academy of SciencesBeijingChina
  3. 3.College of EngineeringPeking UniversityBeijingChina

Personalised recommendations