Evaluation of a Neural Network-Based Closure for the Unresolved Stresses in Turbulent Premixed V-Flames

Abstract

Data-driven modelling in fluid mechanics is a promising alternative given the continuous increase of computational power and data-storage capabilities. Highly non-linear flows which include turbulence and reaction are challenging to model, and accurate algebraic closures for the unresolved terms in large eddy simulations of such flows are difficult to obtain. In this study, an artificial neural network is developed in order to directly model an important unclosed term namely the unresolved stress tensor. The performance of this approach is evaluated a priori using direct numerical simulation data of a highly demanding flow configuration, a turbulent premixed V-flame, and compared against the predictions of eight other classic models in the literature which include both static and dynamic formulations.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

References

  1. Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M., Levenberg, J., Mané, D., Monga, R., Moore, S., Murray, D., Olah, C., Schuster, M., Shlens, J., Steiner, B., Sutskever, I., Talwar, K., Tucker, P., Vanhoucke, V., V., Vijay, V., Fernanda, V., Oriol, W., Pete, W., Martin, W., Martin, Y., Yu., Z.X.: TensorFlow: Large-scale machine learning on heterogeneous systems (2015). http://tensorflow.org/

  2. Anderson, B.W., Domaradzki, J.A.: A subgrid-scale model for large-eddy simulation based on the physics of interscale energy transfer in turbulence. Phys. Fluids 24, 1–35 (2012)

    Google Scholar 

  3. Aspden, A., Day, M., Bell, J.: Three-dimensional direct numerical simulation of turbulent lean premixed methane combustion with detailed kinetics. Combust. Flame 166, 266–283 (2016)

    Google Scholar 

  4. Bardina, J., Ferziger, J.H., Reynolds, W.C.: Improved turbulence models based on Large Eddy simulation of homogeneous, incompressible, turbulent flows. Technical Report no. TF-19, Dep. Mech. Eng. Stanford University (1983)

  5. Bray, K.N.C., Libby, P.A., Masuya, G., Moss, J.B.: Turbulence production in premixed turbulent flames. Combust. Sci. Technol. 25, 127–140 (1981)

    Google Scholar 

  6. Chatzopoulos, A.K., Rigopoulos, S.: A chemistry tabulation approach via rate-controlled constrained equilibrium (RCCE) and artificial neural networks (ANNs), with application to turbulent non-premixed \({CH}_4/{H}_2/{N}_2\) flames. Proc. Combust. Inst. 34, 1465–1473 (2013)

    Google Scholar 

  7. Chomiak, J., Nisbet, J.: Modelling variable density effects in turbulent flames-some basic considerations. Combust. Flame 102, 371–386 (1995)

    Google Scholar 

  8. Clark, R.A.: Evaluation of sub-grid scalar models using an accurately simulated turbulent flow. J. Fluid Mech. 91, 1–16 (1979)

    Google Scholar 

  9. Gamahara, M., Hattori, Y.: Searching for turbulence models by artificial neural network. Phys. Rev. Fluids 2, 054604 (2017)

    Google Scholar 

  10. Germano, M., Piomelli, U., Moin, P., Cabot, W.H.: A dynamic sub-grid scale eddy viscosity model. Phys. Fluids 3, 1760–1765 (1991)

    MATH  Google Scholar 

  11. Gicquel, L.Y.M., Staffelbach, G., Poinsot, T.: Large eddy simulations of gaseous flames in gas turbine combustion chambers. Prog. En. Combust. Sc. 38, 782–817 (2012)

    Google Scholar 

  12. Gutheil, E., Balakrishnan, G., Williams, F.A.: Structure and extinction of hydrogen-air diffusion flames. In: Peters, N., Rogg, B. (eds.) Lecture Notes in Physics: Reduced Kinetic Mechanisms for Applications in Combustion Systems, pp. 177–195. Springer, New York (1993)

    Google Scholar 

  13. Hornik, K.: Approximation capabilities of multi-layer feedforward networks. Neural Netw. 4, 251–257 (1991)

    Google Scholar 

  14. Ihme, M., Schmitt, C., Pitsch, H.: Optimal artificial neural networks and tabulation methods for chemistry representation in LES of a bluff-body swirl-stabilized flame. Proc. Combust. Inst. 32, 1527–1535 (2009)

    Google Scholar 

  15. Kanov, K., Burns, R., Lalescu, C., Eyink, G.: The John hopkins turbulence databases: an open simulation laboratory for turbulence research. Comput. Sci. Eng. 17, 10–17 (2015)

    Google Scholar 

  16. Kee, R.J., Dixon-Lewis, G., Warnatz, J., Coltrin, M.E., Miller, J.A.: A Fortran computer code package for the evaluation of gas-phase multicomponent transport properties. Report No. SAND86-8246, Sandia National Laboratories, Livermore, CA, USA (1986)

  17. Kee, R.J., Rupley, F.M., Miller, J.A.: Chemkin-II: A Fortran chemical kinetics package for the analysis of gas phase chemical kinetics. Report No. SAND89-8009B, Sandia National Laboratories, Livermore, CA, USA (1989)

  18. Khan, J., Wei, J.S., Ringer, M., Saal, L.H., Ladanyi, M., Westermann, F., Berthold, F., Schwab, M., Antonescu, C.R., Peterson, C., Meltzer, P.S.: Classification and diagnostic prediction of cancers using gene expression profiling and artificial neural networks. Nature 7, 673–679 (2001)

    Google Scholar 

  19. Klein, M., Kasten, C., Gao, Y., Chakraborty, N.: A priori direct numerical simulation assessment of sub-grid scale stress tensor closures for turbulent premixed combustion. Comput. Fluids 122, 1–1 (2015)

    MathSciNet  MATH  Google Scholar 

  20. Kravchenko, A.G., Moin, P.: Numerical studies of flow over a circular cylinder at \(re_d=\)3900. Phys. Fluids 12, 403–417 (2000)

    Google Scholar 

  21. Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks. Proc. Adv. Neural Inf. Process. Syst. 25, 1090–1098 (2012)

    Google Scholar 

  22. Kutz, J.N.: Deep learning in fluid dynamics. J. Fluid Mech. 814, 1–4 (2017)

    MATH  Google Scholar 

  23. Lapeyre, C.J., Misdariis, A., Cazard, N., Veynante, D., Poinsot, T.: Training convolutional neural networks to estimate turbulent sub-grid scale reaction rates. Combust. Flame 203, 255–264 (2019)

    Google Scholar 

  24. Lilly, D.K.: A proposed modification of the Germano subgrid-scale closure method. Phys. Fluids 4, 633–635 (1992)

    Google Scholar 

  25. Ling, J., Kurawski, A., Templeton, J.: Reynolds averaged turbulence modelling using deep neural networks with embedded invariance. J. Fluid Mech. 807, 155–166 (2016)

    MathSciNet  MATH  Google Scholar 

  26. Lodato, G., Vervisch, L., Domingo, P.: A compressible wall-adapting similarity mixed model for large-eddy simulation of the impinging round jet. Phys. Fluids 21, 1–21 (2009)

    MATH  Google Scholar 

  27. Ma, M., Lu, J., Tryggvason, G.: Using statistical learning to close two- fluid multiphase flow equations for a simple bubbly system. Phys. Fluids 27, 092101 (2015)

    Google Scholar 

  28. Maulik, R., San, O.: A neural network approach for the blind deconvolution of turbulent flows. J. Fluid Mech. 831, 151–181 (2017)

    MathSciNet  MATH  Google Scholar 

  29. Meneveau, C., Katz, J.: Scale invariance and turbulence models for Large-Eddy simulation. Ann. Rev. Fluid. Mech. 32, 1–32 (2000)

    MathSciNet  MATH  Google Scholar 

  30. Milano, M., Koumoutsakos, P.: Neural network modelling for near wall turbulent flow. J. Comput. Phys. 182, 1–26 (2002)

    MATH  Google Scholar 

  31. Minamoto, Y., Fukushima, N., Tanahashi, M., Miyauchi, T., Dunstan, T.: Effect of flow geometry on turbulence-scalar interaction in premixed flames. Phys. Fluids 23, 1–18 (2011)

    Google Scholar 

  32. Minamoto, Y., Aoki, K., Tanahashi, M., Swaminathan, N.: Dns of swirling hydrogen-air premixed flames. Int. J. Hydrog. Energy 40, 13604–13620 (2015)

    Google Scholar 

  33. Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A.A., Veness, J., Bellemare, M.G., Graves, A., Riedmiller, M., Fidjeland, A.K., Ostrovski, G., Petersen, S., Beattie, C., Sadik, A., Antonoglou, I., King, H., Kumaran, D., Wierstra, D., Legg, S., Hassabis, D.: Human-level control through deep reinforcement learning. Nature 518, 529–533 (2015)

    Google Scholar 

  34. Moin, P., Squires, K., Cabot, W., Lee, S.: A dynamic sub-grid scale model for compressible turbulence and scalar transport. J. Fluid Mech. 3, 2746–2757 (1991)

    MATH  Google Scholar 

  35. Moreau, A., Teytaud, O., Bertoglio, J.P.: Optimal estimation for large-eddy simulation of turbulence and application to the analysis of subgrid models. Phys. Fluids 18, 105101 (2006)

    MathSciNet  MATH  Google Scholar 

  36. Nicoud, F., Ducros, F.: Sub-grid scale stress modelling based on the square of the velocity gradient tensor. Flow Turbul. Combust. 62, 183–200 (1999)

    MATH  Google Scholar 

  37. Nikolaou, Z.M., Chrysostomou, C., Vervisch, L., Cant, S.: Modelling turbulent premixed flames using convolutional neural networks: application to sub-grid scale variance and filtered reaction rate, pp. 1–19 (2018a). arXiv:1810.07944 [physics.flu-dyn]

  38. Nikolaou, Z.M., Swaminathan, N.: Evaluation of a reduced mechanism for turbulent premixed combustion. Combust. Flame 161, 3085–3099 (2014)

    Google Scholar 

  39. Nikolaou, Z.M., Swaminathan, N.: Direct numerical simulation of complex fuel combustion with detailed chemistry: physical insight and mean reaction rate modelling. Combust. Sci. Technol. 187, 1759–1789 (2015)

    Google Scholar 

  40. Nikolaou, Z.M., Swaminathan, N.: Assessment of FSD and SDR closures for turbulent flames of alternative fuels. Flow Turbul. Combust. 101, 759–774 (2018)

    Google Scholar 

  41. Nikolaou, Z.M., Vervisch, L.: A priori assessment of an iterative deconvolution method for LES sub-grid scale variance modelling. Flow Turbul. Combust. 101, 33–53 (2018)

    Google Scholar 

  42. Nikolaou, Z.M., Vervisch, L., Cant, R.S.: Scalar flux modelling in turbulent flames using iterative deconvolution. Phys. Rev. Fluids 3, 043201 (2018b)

    Google Scholar 

  43. Nikolaou, Z.M., Chrysostomou, C., Vervisch, L., Cant, S.: Progress variable variance and filtered rate modelling using convolutional neural networks and flamelet methods. Flow Turbul. Combust. 103, 485–501 (2019)

    Google Scholar 

  44. Perez, F.H., Mukhadiyev, N., Xu, X., Sow, A., Li, B., Sankaran, R., Im, H.: Direct numerical simulation of reacting flows with detailed chemistry using many-core CPU acceleration. Comput. Fluids 173, 73–79 (2018)

    MathSciNet  MATH  Google Scholar 

  45. Pfandler, P., Beyrau, F., Dinkelacker, F., Leipertz, A.: A prior testing of an eddy viscosity model for the density-weighted sub-grid scale stress tensor in turbulent premixed flames. Exp. Fluids 49, 839–851 (2010)

    Google Scholar 

  46. Pitsch, H.: Large eddy simulation of turbulent combustion. Ann. Rev. Fluid Mech. 38, 453–482 (2006)

    MathSciNet  MATH  Google Scholar 

  47. Prasad, A., Williamson, C.H.K.: The instability of the separated shear layer from a bluff body. Phys. Fluids 8, 1347–1349 (1996)

    Google Scholar 

  48. Prasad, A., Williamson, C.H.K.: The instability of the shear layer separating from a bluff body. J. Fluid Mech. 333, 375–402 (1997)

    Google Scholar 

  49. Sagaut, P.: Large Eddy Simulation for Incompressible Flows: An Introduction. Springer, Berlin (2001)

    Google Scholar 

  50. Salvetti, M.V.: A priori tests of a new dynamic sub-grid scale model for finite difference large eddy simulations. Phys. Fluids 7, 2831–2847 (1994)

    MATH  Google Scholar 

  51. Sarghini, F., de Felice, G., Santini, S.: Neural networks based subgrid scale modeling in large eddy simulations. Comput. Fluids 97–108, 32 (2003)

    MATH  Google Scholar 

  52. Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85–117 (2015)

    Google Scholar 

  53. Schmitt, F.G.: About boussinesq’s turbulent viscosity hypothesis: historical remarks and a direct evaluation of its validity. C. R. Mech. 335, 617–627 (2007)

    MATH  Google Scholar 

  54. Schoepplein, M., Weatheritt, J., Sandberg, R., Talei, M., Klein, M.: Application of an evolutionary algorithm to LES modelling of turbulent transport in premixed flames. J. Comput. Phys. 374, 1166–1179 (2018)

    MathSciNet  MATH  Google Scholar 

  55. Seltz, A., Domingo, P., Vervisch, L., Nikolaou, Z.: Direct mapping from LES resolved scales to filtered-flame generated manifolds using convolutional neural networks. Combust. Flame 210, 71–82 (2019)

    Google Scholar 

  56. Sen, B.A., Menon, S.: Turbulent premixed flame modeling using artificial neural networks based chemical kinetics. Proc. Combust. Inst. 32, 1605–1611 (2009)

    Google Scholar 

  57. Sen, B.A., Hawkes, E.R., Menon, S.: Large eddy simulation of extinction and reignition with artificial neural networks based chemical kinetics. Combust. Flame 157, 566–578 (2010)

    Google Scholar 

  58. Shimura, M., Yamawaki, K., Fukushima, N., Shim, Y., Nada, Y., Tanahashi, M., Miyauchi, T.: Flame and eddy structures in hydrogen-air turbulent jet premixed flame. J. Turbul. 13, N42 (2012)

    MathSciNet  MATH  Google Scholar 

  59. Silver, D.: Mastering the game of go with deep neural networks and tree search. Nature 529, 484–489 (2016)

    Google Scholar 

  60. Singh, A.P., Melida, S., Duraisamy, K.: Machine-learning-augmented predictive modeling of turbulent separated flows over airfoils. AIAA 55, 2215–2227 (2017)

    Google Scholar 

  61. Smagorinsky, J.: General circulation experiments with the primitive equations. Mon. Weath. Rev. 91, 99–164 (1963)

    Google Scholar 

  62. Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. Proc. Adv. Neural Inf. Process. Syst. 27, 3104–3112 (2014)

    Google Scholar 

  63. Tanahashi, M., Fujimura, M., Miyauchi, T.: Coherent fine-scale eddies in turbulent premixed flames. Proc. Combust. Inst. 28, 529–535 (2000)

    Google Scholar 

  64. Tao, B., Katz, J., Meneveau, C.: Geometry and scale relationships in high Reynolds number turbulence determined from three-dimensional holographic velocimetry. Phys. Fluids 12, 941–944 (2000)

    MATH  Google Scholar 

  65. Tao, B., Katz, J., Meneveau, C.: Statistical geometry of subgrid-scale stresses determined from holographic velocimetry measurements. J. Fluid Mech. 457, 35–78 (2002)

    MathSciNet  MATH  Google Scholar 

  66. Tracy, B., Duraisamy, K., Alonson, J.J.: A machine learning stratety to assist turbulence model development. In: 53rd AIAA Aerospace Sciences Meeting, AIAA SciTech Forum, pp. 1–22 (2015)

  67. Treichler, S., Bauer, M., Bhagatwala, A., Borghesi, G., Sankaran, R., Kolla, P.M.H., Slaughter, E., Lee, W., Aiken, A., Chen, J.: S3D-Legion: an exascale software for direct numerical simulation of turbulent combustion with complex multicomponent chemistry. Exascale Sci. Appl. 12, 257–258 (2017)

    MATH  Google Scholar 

  68. Vreman, B., Geurts, B., Kuerten, H.: Large eddy simulation of the temporal mixing layer using the Clark model. Theor. Comput. Fluid Dyn. 8, 309–324 (1996)

    MATH  Google Scholar 

  69. Vreman, B., Geurts, B., Kuerten, H.: Large-eddy simulation of the temporal mixing layer. J. Fluid Mech. 339, 357–390 (1997)

    MathSciNet  MATH  Google Scholar 

  70. Wang, H., Hawkes, E., Chen, J., Zhou, B.: Direct numerical simulations of a high Karlovitz number laboratory premixed jet flame-an analysis of flame stretch and flame thickening. J. Fluid Mech. 815, 511–536 (2017a)

    Google Scholar 

  71. Wang, J., Wu, J., Xiao, H.: Physics-informed machine learning approach for reconstructing reynolds stress modelling discrepancies based on DNS data. Phys. Rev. Fluids 2, 034603 (2017b)

    Google Scholar 

  72. Wang, Z., Luo, K., Li, D., Tan, J., Fan, J.: Investigations of data-driven closure for subgrid-scale stress in large-eddy simulation. Phys. Fluids 30, 125101 (2018)

    Google Scholar 

  73. Williamson, C.H.K.: Vortex dynamics in the cylinder wake. Ann. Rev. Fluid Mech. 12, 477–539 (1996)

    MathSciNet  Google Scholar 

  74. Wincelmans, G.S., Wray, A.A., Vasilyev, O.V., Jeanmart, H.: Explicit-filtering large-eddy simulation using the tensor-diffusivity model supplemented by a dynamic smagorinsky term. Phys. Fluids 13, 1385–1403 (2001)

    MATH  Google Scholar 

  75. Yenerdag, B., Minamoto, Y., Naka, Y., Shimura, M., Tanahashi, M.: Flame propagation and heat transfer characteristics of a hydrogen-air premixed flame in a constant volume vessel. Int. J. Hydrog. Energy 41, 9679–9689 (2016)

    Google Scholar 

  76. Yenerdag, B., Minamoto, Y., Aoki, K., Shimura, M., Nada, Y., Tanahashi, M.: Flame-wall interactions of lean premixed flames under elevated, rising pressure conditions. Fuel 189, 8–14 (2017)

    Google Scholar 

  77. Yoshizawa, A.: Statistical theory for compressible turbulent shear flows, with the application to sub-grid modelling. Phys. Fluids 29, 2152–2164 (1986)

    MATH  Google Scholar 

  78. Zhang, Y., Street, R.L., Koseff, J.R.: A dynamic mixed subgrid-scale model and its application to turbulent recirculating flows. Phys. Fluids 5, 3186–3196 (1993)

    MATH  Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Z. M. Nikolaou.

Ethics declarations

Conflict of interest

The authors declare they have no conflict of interest.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Nikolaou, Z.M., Chrysostomou, C., Minamoto, Y. et al. Evaluation of a Neural Network-Based Closure for the Unresolved Stresses in Turbulent Premixed V-Flames. Flow Turbulence Combust 106, 331–356 (2021). https://doi.org/10.1007/s10494-020-00170-w

Download citation

Keywords

  • Direct numerical simulation
  • Large eddy simulation
  • Machine-learning
  • Sub-grid scale modelling
  • Artificial neural networks
  • Reynolds stresses