Skip to main content
SpringerLink
Log in

Development of Artificial Neural Networks with Integrated Conditional Random Fields Capable of Predicting Non-linear Dynamics of the Flow Around Cylinders

  • Conference paper
  • First Online:
New Results in Numerical and Experimental Fluid Mechanics XII (DGLR 2018)

Part of the book series: Notes on Numerical Fluid Mechanics and Multidisciplinary Design ((NNFM,volume 142))

Included in the following conference series:

  • 2458 Accesses

Abstract

This paper presents a new approach intended to predict flow dynamics based on observed data. The approach uses artificial neural networks extended by an adapted conditional random field. This artificial neural network is trained end-to-end and the embedded conditional random field memorizes previous events and uses this memory for flow predictions. The prediction capability of the proposed method is demonstrated for flows around cylinders which are computed with a Lattice Boltzmann method in order to train the artificial neural network.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 169.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 219.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 219.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Abebe, A.J., Solomatine, D.P., Venneker, R.G.W.: Application of adaptive fuzzy rule-based models for reconstruction of missing precipitation events. Hydrol. Sci. J. 45(3), 425–436 (2000)

    Article  Google Scholar 

  2. Box, G.E.P., Jenkins, G.: Time Series Analysis, Forecasting and Control. Holden-Day Inc., San Francisco (1990)

    MATH  Google Scholar 

  3. Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous systems. Software available from tensorflow.org (2015)

  4. Faller, W.E., Schreck, S.J.: Neural networks: applications and opportunities in aeronautics. Prog. Aerosp. Sci. 32(5), 433–456 (1996)

    Article  Google Scholar 

  5. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)

    Google Scholar 

  6. Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006)

    Article  MathSciNet  Google Scholar 

  7. Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)

  8. Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Sytems, vol. 25, pp. 1097–1105. Curran Associates, Inc. (2012)

    Google Scholar 

  9. Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of 18th International Conference on Machine Learning, pp. 282–289 (2001)

    Google Scholar 

  10. Latt, J.: Palabos, parallel Lattice Boltzmann solver (2009)

    Google Scholar 

  11. Lee, H., Grosse, R., Ranganath, R., Ng, A.Y.: Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. In: Proceedings of the 26th Annual International Conference on Machine Learning, pp. 609–616. ACM (2009)

    Google Scholar 

  12. Mannarino, A., Mantegazza, P.: Nonlinear aeroelastic reduced order modeling by recurrent neural networks. J. Fluid Struct. 48, 103–121 (2014)

    Article  Google Scholar 

  13. Takens, F.: Detecting strange attractors in turbulence. In: Dynamical Systems and Turbulence, Warwick 1980, pp. 366–381. Springer (1981)

    Google Scholar 

  14. van Rossum, G., Drake, F.L.: The Python Language Reference Manual. Network Theory Ltd., Bristol (2011)

    Google Scholar 

  15. Vemuri, V.: Artificial neural networks: theoretical concepts. In: Computer Society Press Technology, Neural Networks. Computer Society Press of the IEEE (1988)

    Google Scholar 

  16. Winter, M., Breitsamter, C.: Neurofuzzy-model-based unsteady aerodynamic computations across varying freestream conditions. AIAA J. 54, 2705–2720 (2016)

    Article  Google Scholar 

  17. Zhang, W., Wang, B., Ye, Z., Quan, J.: Efficient method for limit cycle flutter analysis based on nonlinear aerodynamic reduced-order models. AIAA J. 50(5), 1019–1028 (2012)

    Article  Google Scholar 

Download references

Acknowledgment

We thank Annika Köhne for the valuable corrections of this manuscript and Axel Dannhauer for fruitful discussions and continuous support.

Author information

Authors and Affiliations

  1. German Aerospace Center (DLR), Institute of Aerodynamics and Flow Technology, Bunsenstr. 10, 37073, Göttingen, Germany

    Sebastian Herzog & Claus Wagner

  2. Max Planck Institute for Dynamics and Self-Organization, Am Faßberg 17, 37077, Göttingen, Germany

    Sebastian Herzog

  3. Third Institute of Physics, University of Göttingen, Friedrich-Hund-Platz 1, 37077, Göttingen, Germany

    Sebastian Herzog

  4. Institute of Thermodynamics and Fluid Mechanics, Technische Universität Ilmenau, Helmholtzring 1, 98693, Ilmenau, Germany

    Claus Wagner

Authors
  1. Sebastian Herzog
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Claus Wagner
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Sebastian Herzog .

Editor information

Editors and Affiliations

  1. Deutsches Zentrum für Luft- und Raumfahrt, Institut für Aerodynamik und Strömungstechnik, Göttingen, Niedersachsen, Germany

    Andreas Dillmann

  2. Airbus Operations GmbH, Bremen, Bremen, Germany

    Gerd Heller

  3. Institut für Aerodynamik und Gasdynamik, Universität Stuttgart, Stuttgart, Baden-Württemberg, Germany

    Ewald Krämer

  4. Deutsches Zentrum für Luft- und Raumfahrt, Institut für Aerodynamik und Strömungstechnik, Göttingen, Niedersachsen, Germany

    Claus Wagner

  5. Fachgebiet Strömungslehre und Aerodynamik, Technische Universität Darmstadt, Darmstadt, Hessen, Germany

    Cameron Tropea

  6. Fachgebiet Strömungslehre und Aerodynamik, Technische Universität Darmstadt, Darmstadt, Hessen, Germany

    Suad Jakirlić

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Herzog, S., Wagner, C. (2020). Development of Artificial Neural Networks with Integrated Conditional Random Fields Capable of Predicting Non-linear Dynamics of the Flow Around Cylinders. In: Dillmann, A., Heller, G., Krämer, E., Wagner, C., Tropea, C., Jakirlić, S. (eds) New Results in Numerical and Experimental Fluid Mechanics XII. DGLR 2018. Notes on Numerical Fluid Mechanics and Multidisciplinary Design, vol 142. Springer, Cham. https://doi.org/10.1007/978-3-030-25253-3_7

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-25253-3_7

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-25252-6

  • Online ISBN: 978-3-030-25253-3

  • eBook Packages: EngineeringEngineering (R0)

Publish with us

Policies and ethics

Search

Navigation