Abstract
We propose a method to construct a reduced order model with machine learning for unsteady flows. The present machine-learned reduced order model (ML-ROM) is constructed by combining a convolutional neural network autoencoder (CNN-AE) and a long short-term memory (LSTM), which are trained in a sequential manner. First, the CNN-AE is trained using direct numerical simulation (DNS) data so as to map the high-dimensional flow data into low-dimensional latent space. Then, the LSTM is utilized to establish a temporal prediction system for the low-dimensionalized vectors obtained by CNN-AE. As a test case, we consider flows around a bluff body whose shape is defined using a combination of trigonometric functions with random amplitudes. The present ML-ROMs are trained on a set of 80 bluff body shapes and tested on a different set of 20 bluff body shapes not used for training, with both training and test shapes chosen from the same random distribution. The flow fields are confirmed to be well reproduced by the present ML-ROM in terms of various statistics. We also focus on the influence of two main parameters: (1) the latent vector size in the CNN-AE, and (2) the time step size between the mapped vectors used for the LSTM. The present results show that the ML-ROM works well even for unseen shapes of bluff bodies when these parameters are properly chosen, which implies great potential for the present type of ML-ROM to be applied to more complex flows.
Similar content being viewed by others
References
Taira, K., Brunton, S.L., Dawson, S., Rowley, C.W., Colonius, T., McKeon, B.J., Schmidt, O.T., Gordeyev, S., Theofilis, V., Ukeiley, L.S.: Modal analysis of fluid flows: an overview. AIAA J. 55(12), 4013–4041 (2017)
Lumley, J.L.: The structure of inhomogeneous turbulent flows. In: Yaglom, A.M., Tatarski, V.I. (eds.) Atmospheric Turbulence and Wave Propagation, pp. 166–178. Nauka, Moscow (1967)
Schmid, P.: Dynamic mode decomposition of numerical and experimental data. J. Fluid Mech. 656, 5–28 (2010)
Bakewell, H.P., Lumley, J.L.: Viscous sublayer and adjacent wall region in turbulent pipe flow. Phys. Fluids 10, 1880 (1967)
Gómez, F., Blackburn, H.M.: Data-driven approach to design of passive flow control strategies. Phys. Rev. Fluids 2, 021901 (2017)
Alfonsi, G., Primavera, L.: The structure of turbulent boundary layers in the wall region of plane channel flow. Proc. R. Soc. A 463(2078), 593–612 (2007)
Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Nature 313, 504–507 (2006)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436–444 (2015)
Kutz, N.: Deep learning in fluid dynamics. J. Fluid Mech. 814, 1–4 (2017)
Brunton, S.L., Noack, B.R., Koumoutsakos, P.: Machine learning for fluid mechanics. Annu. Rev. Fluid Mech. 52, 477–508 (2019)
Taira, K., Hemati, M.S., Brunton, S.L., Sun, Y., Duraisamy, K., Bagheri, S., Dawson, S.T.M., Yeh, C.-A.: Modal analysis of fluid flows: applications and outlook. AIAA J. 58(3), 998–1022 (2020)
Brenner, M.P., Eldredge, J.D., Freund, J.B.: Perspective on machine learning for advancing fluid mechanics. Phys. Rev. Fluids 4, 100501 (2019)
Fukami, K., Fukagata, K., Taira, K.: Assessment of supervised machine learning methods for fluid flows. Theor. Comput. Fluid Dyn. (2020). https://doi.org/10.1007/s00162-020-00518-y
Ling, J., Kurzawski, A., Templeton, J.: Reynolds averaged turbulence modelling using deep neural networks with embedded invariance. J. Fluid Mech. 807, 155–166 (2016)
Fukami, K., Fukagata, K., Taira, K.: Super-resolution reconstruction of turbulent flows with machine learning. J. Fluid Mech. 870, 106–120 (2019)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Xiaowei, J., Peng, C., Wen-Li, C., Hui, L.: Prediction model of velocity field around circular cylinder over various Reynolds numbers by fusion convolutional neural networks based on pressure on the cylinder. Phys. Fluids 30, 047105 (2018)
Viquerata, J., Hachema, E.: A supervised neural network for drag prediction of arbitrary 2D shapes in low Reynolds number flows, arXiv preprint, arXiv:1907.05090 [physics.comp-ph] (2019)
San, O., Maulik, R.: Extreme learning machine for reduced order modeling of turbulent geophysical flows. Phys. Rev. E 97, 04322 (2018)
Srinivasan, P.A., Guastoni, L., Azizpour, H., Schlatter, P., Vinuesa, R.: Predictions of turbulent shear flows using deep neural networks. Phys. Rev. Fluids 4, 054603 (2019)
Murata, T., Fukami, K., Fukagata, K.: Nonlinear mode decomposition with convolutional neural networks for fluid dynamics. J. Fluid Mech. 882, A13 (2020)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9, 1735–1780 (1997)
Anzai, Y., Fukagata, K., Meliga, P., Boujo, E., Gallaire, F.: Numerical simulation and sensitivity analysis of a low-Reynolds-number flow around a square cylinder controlled using plasma actuators. Phys. Rev. Fluids 2, 043901 (2017)
Kor, H., Ghomizad, M.B., Fukagata, K.: A unified interpolation stencil for ghost-cell immersed boundary method for flow around complex geometries. J. Fluid. Sci. Technol. 12, JFST0011 (2017)
Amsden, A.A., Harlow, F.H.: The SMAC method, Los Alamos Scientific Lab. Report., No. LA-4370 (1970)
Spalart, P.R., Moser, R.D., Rogers, M.M.: Spectral methods for the Navier–Stokes equations with one infinite and two periodic directions. J. Comput. Phys. 96, 297–324 (1991)
Mitsuishi, A., Fukagata, K., Kasagi, N.: Near-field development of large-scale vortical structures in a controlled confined coaxial jet. J. Turbul. 8(23), 1–27 (2007)
Fukami, K., Nabae, Y., Kawai, K., Fukagata, K.: Synthetic turbulent inflow generator using machine learning. Phys. Rev. Fluids 4, 064603 (2019)
Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313, 504–507 (2006)
Du, X., Qu, X., He, Y., Guo, D.: Single image super-resolution based on multi-scale competitive convolutional neural network. Sensors 18(789), 1–17 (2018)
Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: The 32nd International Conference on Machine Learning. Lille, France (2015)
Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines, In: Proc. 27th International Conference on Machine Learning (2010)
Mathieu, M., Couprie, C., LeCun, Y.: Deep multi-scale video prediction beyond mean square error, arXiv preprint, arXiv:1511.05440v6 [cs.LG] (2016)
Lee, S., You, D.: Data-driven prediction of unsteady flow over a circular cylinder using deep learning. J. Fluid Mech. 879, 217–254 (2019)
Kingma, D., Ba, J.: A method for stochastic optimization, arXiv preprint, arXiv:1412.6980 [cs.LG] (2014)
Brunton, S.L., Kutz, J.N.: Data-driven Science and Engineering: Machine Learning, Dynamical Systems, and Control. Cambridge University Press, Cambridge (2019)
Prechelt, L.: Automatic early stopping using cross validation: quantifying the criteria. Neural Netw 11(4), 761–767 (1998)
Graves, A., Jaitly, N., Mohamed, A.: Hybrid speech recognition with deep bidirectional LSTM, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, Olomouc, Czech, Dec. 8-12 (2013)
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014)
Williams, R.J., Zipser, D.: A learning algorithm for continually running fully recurrent neural networks. Neural Comput. 1, 270–280 (1989)
Ehlert, A., Nayeri, C.N., Morzynski, M., Noack, B.R.: Locally linear embedding for transient cylinder wakes, arXiv preprint, arXiv:1906.07822 [physics.flu-dyn] (2019)
Acknowledgements
Authors are grateful to Dr. S. Obi, Dr. K. Ando, Mr. M. Morimoto, and Mr. T. Nakamura (Keio University) for fruitful discussions. This work was supported through JSPS KAKENHI Grant Number 18H03758 by Japan Society for the Promotion of Science.
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by Kunihiko Taira.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Hasegawa, K., Fukami, K., Murata, T. et al. Machine-learning-based reduced-order modeling for unsteady flows around bluff bodies of various shapes. Theor. Comput. Fluid Dyn. 34, 367–383 (2020). https://doi.org/10.1007/s00162-020-00528-w
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00162-020-00528-w