Skip to main content
SpringerLink
Log in

ENHANCEMENT OF RANS MODELS BY MEANS OF THE TENSOR BASIS RANDOM FOREST FOR TURBULENT FLOWS IN TWO-DIMENSIONAL CHANNELS WITH BUMPS

  • Published:
Journal of Applied Mechanics and Technical Physics Aims and scope

Abstract

DNS and RANS computation results for flows in two-dimensional channels with bumps are processed to generate input and output data for a machine learning method aimed to enhance the Reynolds stress anisotropy model and, thus, improve the RANS approach accuracy. The tensor basis random forest method is chosen as a machine learning tool. The prediction of the new model for the Reynolds stress anisotropy tensor is in better agreement with DNS data for two channel flow geometries than those obtained by the conventional linear eddy viscosity model.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2

REFERENCES

  1. P. Durbin, “Some Recent Developments in Turbulence Closure Modeling," Annual Rev. Fluid Mech. 50, 77–103 (2018).

    Article  ADS  MathSciNet  MATH  Google Scholar 

  2. S. N. Yakovenko and K. C. Chang, “Computational Studies of Near-Wall Behaviors of Low-Reynolds-Number Reynolds-Stress Models," AIAA J. 51, 279–296 (2019).

    Article  ADS  Google Scholar 

  3. K. Duraisamy, G. Iaccarino, and H. Xiao, “Turbulence Modeling in the Age of Data," Annual Rev. Fluid Mech. 51, 357–377 (2019).

    Article  ADS  MathSciNet  MATH  Google Scholar 

  4. S. L. Brunton, B. R. Noack, and P. Koumoutsakos, “Machine Learning for Fluid Mechanics," Annual Rev. Fluid Mech. 52, 477–508 (2020).

    Article  ADS  MathSciNet  MATH  Google Scholar 

  5. J. Ling, A. Kurzawski, and J. Templeton, “Reynolds Averaged Turbulence Modelling using Deep Neural Networks with Embedded Invariance," J. Fluid Mech. 807, 155–166 (2016).

    Article  ADS  MathSciNet  MATH  Google Scholar 

  6. M. Kaandorp, “Machine Learning for Data-Driven RANS Turbulence Modelling: Master Thesis," (Delft: Delft Univ. of Technol., 2018).

  7. M. Kaandorp and R. P. Dwight, “Data-Driven Modelling of the Reynolds Stress Tensor using Random Forests with Invariance," Comput. Fluids 202, 104497 (2020).

    Article  MathSciNet  MATH  Google Scholar 

  8. R. McConkey, E. Yee, and F. S. Lien, “A Curated Dataset for Data-Driven Turbulence Modelling," Scientific Data 8, 255 (2021).

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Novosibirsk State University, Novosibirsk, Russia

    A. Bernard

  2. Khristianovich Institute of Theoretical and Applied Mechanics, Siberian Branch, Russian Academy of Sciences, Novosibirsk, Russia

    S. N. Yakovenko

Authors
  1. A. Bernard
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. S. N. Yakovenko
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to S. N. Yakovenko.

Additional information

Translated from Prikladnaya Mekhanika i Tekhnicheskaya Fizika, 2023, Vol. 64, No. 3, pp. 89-94. https://doi.org/10.15372/PMTF20230309.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Bernard, A., Yakovenko, S.N. ENHANCEMENT OF RANS MODELS BY MEANS OF THE TENSOR BASIS RANDOM FOREST FOR TURBULENT FLOWS IN TWO-DIMENSIONAL CHANNELS WITH BUMPS. J Appl Mech Tech Phy 64, 437–441 (2023). https://doi.org/10.1134/S0021894423030094

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1134/S0021894423030094

Keywords

Search

Navigation