Hybrid Modeling Technique for Large Eddy Simulations

  • F. Sarghini
  • S. Santini
Conference paper


In this paper a multilayer feed-forward neural network, previously offline trained, is used in substitution of a Bardina’ scale similar model- (BFR) [1] Sub-Grid Scale (SGS) model in Large Eddy Simulation of a channel flow at Re τ = 180. Results show the ability of neural networks to identify and reproduce the highly non-linear behavior of turbulent flows.


Large Eddy Simulation Reynolds Average Navier Stokes Reynolds Average Navier Stokes Subgrid Scale Turbulent Viscosity Coefficient 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bardina J., Ferziger J.H., Reynolds W.C. (1980) Improved subgrid scale models for large eddy simulation. AIAA Paper No. 80, 1357Google Scholar
  2. 2.
    Germano M., Piomelli U., Moin P., Cabot W.H. (1991) A dynamic subgrid-scale eddy viscosity model. Phys. Fluids A. 3, 1760CrossRefGoogle Scholar
  3. 3.
    Germano M. (1992) Turbulence: the filtering approach. J. Fluid Mech. 238, 325CrossRefGoogle Scholar
  4. 4.
    Sarghini F., Piomelli U., Balaras E. (1999) Scale-Similar models for Large Eddy simulations. Phys. Fluids. 6, 1596CrossRefGoogle Scholar
  5. 5.
    Smagorinsky J. (1963) General circulation experiments with the primitive equations. I. The basic experiment. Mon. Weather Rev. 91, 99CrossRefGoogle Scholar
  6. 6.
    Chen S., Cowan C. F. N., Grant P. M. (1991) Orthogonal least squares algorithms for radial basis function networks. IEEE Trans. Neur. Networks. 2, 302–309CrossRefGoogle Scholar
  7. 7.
    Cybenko G. (1989) Approximation by superposition of a sigmoidal function. Mathematics Contr., Signals, and Syst. 2, 303–314CrossRefGoogle Scholar
  8. 8.
    Funahashi K. (1989) On the approximate realization of continous mappings by using neural networks. Neural Networks. 2, 183–192CrossRefGoogle Scholar
  9. 9.
    Hornik K., Stinchcombe M., White H. (1989) Multi-layer feedforward networks are universal approximators. Neural Networks. 2, 359–366CrossRefGoogle Scholar
  10. 10.
    Hornik K., Stinchombe M., White H. (1989) Multilayer feedforward networks are universal approximators. Neural Networks. 2, 359–366 neural networks to identify and reproduce the highly non-linear behavior of turbulent flows.Google Scholar
  11. 11.
    Wang Z.,Tham M., Morris T. (1992) Multilayer Feedforward Neural Networks: A Canonical Form Approximation of Nonlinearity. Int. Journal Control. 56, 655Google Scholar
  12. 12.
    Wang W., Lin C. (1998) Runge-Kutta Neural Networks for Identification of Dynamical Systems in High Accuracy. IEEE Trans, on Neural Networks. 9, 294–307CrossRefGoogle Scholar
  13. 13.
    Glielmo L., Santini S., Milano M. (2000) A Machine Learning Approach to Modeling and Identification of Automotive Three-Way Catalytic Converters. IEEE/ASME Transaction on Mechatronics. 2, 132–141CrossRefGoogle Scholar
  14. 14.
    Narendra K., Parthasarathy K. (1990) Identification and Control of Dynamic Systems using Neural Networks. IEEE Transaction on Neural Networks. 1, 4–27CrossRefGoogle Scholar
  15. 15.
    Ploemen I. H. J., van de Molengraft M. J. G. (1999) Hybrid Modeling for Mechanical Systems: Methodologies and Applications. Journal of Dynamical Systems Measurements and Control. 121, 270–277CrossRefGoogle Scholar
  16. 16.
    Lee C., Kim J., Babcock D., Goodman R. (1997) Application of neural network to turbulence control for drag reduction. Phys. Fluids. 9, 1740CrossRefGoogle Scholar
  17. 17.
    Giralt F., Arenas A., Ferre-Gine J., Rallo R., Kopp G.A. (2000) The simulation and interpretation of free turbulence with a cognitive neural system. Phys. Fluids. 12, 1826CrossRefGoogle Scholar
  18. 18.
    Haykin S. (1994) Neural Networks. McMillan, NYGoogle Scholar
  19. 19.
    Barron A.R. (1992) Neural net approximation. Proc. of the 7th Yale Workshop on Adaptive and Learning Syst. 68–72Google Scholar
  20. 20.
    Barron A. R. (1993) Universal approximation bounds for superpositions of a sigmoidal function. IEEE Trans. Inform. Theory. 39, 930–945CrossRefGoogle Scholar
  21. 21.
    Werbos P. (1988) Backpropagation: Past and future. Proceedings of the IEEE International Conference on Neural Networks. IEEE Press, 343–353Google Scholar

Copyright information

© Springer-Verlag Italia, Milan 2002

Authors and Affiliations

  • F. Sarghini
    • 1
  • S. Santini
    • 2
  1. 1.Departimento di Energetica. Termo-Fluidodinamica Applicata e Condizionamenti AmbientaliUniversità di Napoli “Federico II”NapoliItalia
  2. 2.Dipartimento di Informatica e SistemisticaUniversità di Napoli “Federico II”NapoliItalia

Personalised recommendations