Unsupervised Deep Learning of Turbulent Heat Transfer via Generative Adversarial Networks

Nicholas J. Ward

Abstract


Machine learning and deep learning can be useful in providing insight to near-wall turbulence. The research question that this study seeks to answer is how to effectively predict the turbulent heat transfer of a 2D channel flow using a generative adversarial network (GAN). The first objective of this study is to predict the heat transfer using the wall variables p, du/dy, and dw/dy only. The second objective is to extrapolate the trained GAN model to temperature gradients at higher Reynolds numbers. Direct numerical simulations (DNS) were performed to determine the training data, and machine learning algorithm was developed to effectively capture the flow physics in a turbulent channel flow. The predictions from the proposed GAN correlated well with the DNS data at Re_tau= 180. The predictions were effectively captured within 2% of the DNS training data. The temperature was not required to measure the temperature gradients using the GAN model proposed in this study. Additionally, the GAN was also able to capture the flow physics for the test data at higher Reynolds numbers. To accomplish this, an appropriate normalization technique was required for the predictions. This work will be useful in future work to be applied to other problems in fluid mechanics, such as drag reduction, capturing near-wall flow physics, and super-resolution.

Keywords


turbulent channel flow; turbulent heat transfer; artificial intelligence; deep learning; generative adversarial network (GAN)

Full Text:

PDF

References


L. Deng and X. Li, “Machine learning paradigms for speech recognition: An overview,” IEEE Transac-tions on Audio, Speech and Language Processing, vol. 21, no. 5, pp. 1060–1089, 2013.

J. Padmanabhan, M. Jose and J. Premkumar, “Machine learning in automatic speech recognition: A survey,” IETE Technical Review, vol. 32, no. 4, pp. 240–251, 2015.

C. M. Bishop and N. M. Nasrabadi, Pattern Recogni-tion and Machine Learning. New York, NY, USA: Springer, 2006.

D. Melati, Y. Grinberg, M. K. Dezfouli, S. Janz, P. Cheben, J. H. Schmid, A. Sanchez-Postigo and D. X. Xu, “Mapping the global design space of nanopho-tonic components using machine learning pattern recognition,” Nature Communications, vol. 10, no. 1, pp. 1–9, Oct. 2019.

T. Dao, A. Gu, A. J. Ratner, V. Smith, C. De Sa and C. Re, “A kernel theory of modern data augmentation,” in Proc. International Conference on Machine Learn-ing, 2019.

S. Dabetwar, S. Ekwaro-Osire and J. P. Dias, “Fatigue damage diagnostics of composites using data fusion and data augmentation with deep neural networks,” Journal of Nondestructive Evaluation, Diagnostics and Prognostics of Engineering Systems, vol. 5, no. 2, 2022.

B. S. Kusumo, A. Heryana, O. Mahendra and H. F. Pardede, “Machine learning-based automatic detec-tion of corn-plant diseases using image processing,” in Proc. 2018 International Conference on Computer, Control, Informatics and its Applications (IC3INA), pp. 93–97, 2019.

H. Zerouaoui and A. Idri, “Reviewing machine learn-ing and image processing-based decision-making systems for breast cancer imaging,” Journal of Medi-cal Systems, vol. 45, no. 1, pp. 1–20, Jan. 2021.

S. L. Brunton, B. R. Noack and P. Koumoutsakos, “Machine learning for fluid mechanics,” Annual Re-view of Fluid Mechanics, vol. 52, pp. 477–508, 2020.

J. Kim, P. Moin and R. Moser, “Turbulence statistics in fully developed channel flow at low Reynolds number,” Journal of Fluid Mechanics, vol. 177, pp. 133–166, 1987.

J. Jimenez and P. Moin, “The minimal flow unit in near-wall turbulence,” Journal of Fluid Mechanics, vol. 225, pp. 213–240, 1991.

M. Lee and R. D. Moser, “Direct numerical simula-tion of turbulent channel flow up to Re? ? 5200,” Journal of Fluid Mechanics, vol. 774, pp. 395–415, 2015.

R. A. Antonia, L. V. Krishnamoorthy and L. Fulachi-er, “Correlation between the longitudinal velocity fluctuation and temperature fluctuation in the near-wall region of a turbulent boundary layer,” Interna-tional Journal of Heat and Mass Transfer, vol. 31, no. 4, pp. 723–730, Apr. 1988.

J. Jeong and F. Hussain, “On the identification of a vortex,” Journal of Fluid Mechanics, vol. 285, pp. 69–94, 1995.

J. Jeong, F. Hussain, W. Schoppa and J. Kim, “Coher-ent structures near the wall in a turbulent channel flow,” Journal of Fluid Mechanics, vol. 332, pp. 185–214, 1997.

L. Agostini and M. Leschziner, “Spectral analysis of near-wall turbulence in channel flow at Re? = 4200 with emphasis on the attached-eddy hypothesis,” 2017.

W. Schoppa and F. Hussain, “Coherent structure generation in near-wall turbulence,” Journal of Fluid Mechanics, vol. 453, pp. 57–108, 2002.

N. Hutchins and I. Marusic, “Large-scale influences in near-wall turbulence,” Philosophical Transactions of the Royal Society A, vol. 365, no. 1852, pp. 647–664, Mar. 2007.

A. Lozano-Duran, N. C. Constantinou, M.-A. Niko-laidis and M. Karp, “Cause-and-effect of linear mechanisms sustaining wall turbulence,” Journal of Fluid Mechanics, 2020.

H. Choi, P. Moin and J. Kim, “Active turbulence con-trol for drag reduction in wall-bounded flows,” Jour-nal of Fluid Mechanics, vol. 262, pp. 75–110, 1994.

D. Babcock, C. Lee, B. Gupta, J. Kim and R. Good-man, “Active drag reduction using neural networks,” in Proc. International Workshop on Neural Networks for Identification, Control, Robotics, and Sig-nal/Image Processing, 1996, pp. 279–287.

C. Lee, J. Kim, D. Babcock and R. Goodman, “Appli-cation of neural networks to turbulence control for drag reduction,” Physics of Fluids, vol. 9, no. 6, pp. 1740–1747, 1997.

H. J. Bae and P. Koumoutsakos, “Scientific multia-gent reinforcement learning for wall-models of tur-bulent flows,” arXiv preprint arXiv:2106.11144, 2021.

K. Fukami, Y. Nabae, K. Kawai and K. Fukagata, “Synthetic turbulent inflow generator using machine learning,” Physical Review Fluids, vol. 4, p. 064603, 2019.

M. Z. Yousif, L. Yu and H.-C. Lim, “High-fidelity reconstruction of turbulent flow from spatially lim-ited data using enhanced super-resolution generative adversarial network,” arXiv preprint arXiv:2109.04250, 2021.

H. Wang, Z. Yang, B. Li and S. Wang, “Predicting the near-wall velocity of wall turbulence using a neural network for particle image velocimetry,” Physics of Fluids, vol. 32, no. 11, p. 115105, 2020.

K. Ezhilsabareesh, C. Atkinson, A. Lozano-Duran, P. J. Schmid, J. Jimenez and J. Soria, “Effect of limited near-wall inlet data on the direct numerical simula-tion of turbulent channel flow,” Journal of Physics: Conference Series, vol. 1522, p. 012019, 2020.

J. Kim and C. Lee, “Prediction of turbulent heat transfer using convolutional neural networks,” Jour-nal of Fluid Mechanics, vol. 882, p. A18, 2020.

H. Kim, J. Kim and C. Lee, “Interpretable deep learn-ing for prediction of Prandtl number effect in turbu-lent heat transfer,” Journal of Fluid Mechanics, vol. 955, 2023.

S. Cai, Z. Wang, S. Wang, P. Perdikaris and G. E. Karniadakis, “Physics-informed neural networks for heat transfer problems,” Journal of Heat Transfer, vol. 143, no. 6, Jun. 2021.

J. Kim and P. Moin, “Transport of passive scalars in a turbulent channel flow,” Turbulent Shear Flows, vol. 6, pp. 85–96, 1989.

A. Radford, L. Metz and S. Chintala, “Unsupervised representation learning with deep convolutional gen-erative adversarial networks,” arXiv preprint arXiv:1511.06434, 2016.

P. Isola, J.-Y. Zhu, T. Zhou and A. A. Efros, “Image-to-image translation with conditional adversarial networks,” arXiv preprint arXiv:1611.07004, 2016.

J. Henry, T. Natalie and D. Madsen, “Pix2Pix GAN for image-to-image translation,” 2021.

J.-L. Wu, K. Kashinath, A. Albert, D. Chirila and H. Xiao, “Enforcing statistical constraints in generative adversarial networks for modeling chaotic dynamical systems,” Journal of Computational Physics, vol. 406, p. 109209, 2020.

V. Nagarajan and J. Z. Kolter, “Gradient descent GAN optimization is locally stable,” in Proc. Neural Information Processing Systems (NeurIPS), 2017.

T. Tieleman and G. Hinton, “RMSProp: Divide the gradient by a running average of its recent magni-tude,” COURSERA: Neural Networks for Machine Learning, 2012.

D. P. Kingma and J. Ba, “Adam: A method for sto-chastic optimization,” in Proc. International Confer-ence on Learning Representations, 2015.

S. J. Reddi, S. Kale and S. Kumar, “On the conver-gence of Adam and beyond,” in Proc. International Conference on Learning Representations, 2018.

S. Ioffe and C. Szegedy, “Batch normalization: Ac-celerating deep network training by reducing internal covariate shift,” in Proc. International Conference on Machine Learning, 2015.

H. Noh, S. Hong and B. Han, “Learning deconvolu-tion network for semantic segmentation,” in Proc. IEEE International Conference on Computer Vision, 2015.

N. Srivastava, G. Hinton, A. Krizhevsky and R. Sala-khutdinov, “Dropout: A simple way to prevent neural networks from overfitting,” Journal of Machine Learning Research, vol. 15, pp. 1929–1958, 2014.

O. Ronneberger, P. Fischer and T. Brox, “U-Net: Convolutional networks for biomedical image seg-mentation,” in Proc. MICCAI, 2015.

Z. Zhou, M. M. R. Siddiquee, N. Tajbakhsh and J. Liang, “UNet++: A nested U-Net architecture for medical image segmentation,” in Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, 2018.

H. Abe, H. Kawamura and Y. Matsuo, “Surface heat-flux fluctuations in a turbulent channel flow up to Re? = 1020 with Pr = 0.025 and 0.71,” International Journal of Heat and Fluid Flow, vol. 25, no. 3, pp. 404–419, Jun. 2004.

H. Kawamura, K. Ohsaka, H. Abe and K. Yamamoto, “DNS of turbulent heat transfer in channel flow with low to medium-high Prandtl number fluid,” Interna-tional Journal of Heat and Fluid Flow, vol. 19, no. 5, pp. 482–491, Oct. 1998.

H. Kawamura, H. Abe and Y. Matsuo, “DNS of turbu-lent heat transfer in channel flow with respect to Reynolds and Prandtl number effects,” International Journal of Heat and Fluid Flow, vol. 20, no. 3, pp. 196–207, Jun. 1999.




DOI (PDF): https://doi.org/10.20508/ijrer.v16i1.15250.g9170

Refbacks

  • There are currently no refbacks.


Online ISSN: 1309-0127

Publisher: Gazi University

IJRER is indexed in EI Compendex, SCOPUS, EBSCO, WEB of SCIENCE (Clarivate Analytics)and CrossRef.

IJRER has been indexed in Emerging Sources Citation Index from 2016 in web of science.

WEB of SCIENCE in 2025; 

h=35,

Average citation per item=6.59

Last three Years Impact Factor=(1947+1753+1586)/(146+201+78)=5286/425=12.43

Category Quartile:Q4