In this paper, we present two deep learning-based hybrid data-driven reduced-order models for prediction of unsteady fluid flows. These hybrid models rely on recurrent neural networks (RNNs) to evolve low-dimensional states of unsteady fluid flow. The first model projects the high-fidelity time series data from a finite element Navier–Stokes solver to a low-dimensional subspace via proper orthogonal decomposition (POD). The time-dependent coefficients in the POD subspace are propagated by the recurrent net (closed-loop encoder–decoder updates) and mapped to a high-dimensional state via the mean flow field and the POD basis vectors. This model is referred to as POD-RNN. The second model, referred to as the convolution recurrent autoencoder network (CRAN), employs convolutional neural networks (instead of POD) as layers of linear kernels with nonlinear activations, to extract low-dimensional features from flow field snapshots. The flattened features are advanced using a recurrent (closed-loop manner) net and up-sampled (transpose convoluted) gradually to high-dimensional snapshots. Two benchmark problems of the flow past a cylinder and the flow past side-by-side cylinders are selected as the unsteady flow problems to assess the efficacy of these models. For the problem of the flow past a single cylinder, the performance of both the models is satisfactory and the CRAN model is found to be overkill. However, the CRAN model completely outperforms the POD-RNN model for a more complicated problem of the flow past side-by-side cylinders involving the complex effects of vortex-to-vortex and gap flow interactions. Owing to the scalability of the CRAN model, we introduce an observer-corrector method for calculation of integrated pressure force coefficients on the fluid–solid boundary on a reference grid. This reference grid, typically a structured and uniform grid, is used to interpolate scattered high-dimensional field data as snapshot images. These input images are convenient in training the CRAN model, which motivates us to further explore the application of the CRAN-based models for prediction of fluid flows.
REFERENCES
1.
G.
Berkooz
, P.
Holmes
, and J. L.
Lumley
, “The proper orthogonal decomposition in the analysis of turbulent flows
,” Annu. Rev. Fluid Mech.
25
(1
), 539
–575
(1993
).2.
J.
Burkardt
, M.
Gunzburger
, and H.-C.
Lee
, “POD and CVT-based reduced-order modeling of Navier–Stokes flows
,” Comput. Methods Appl. Mech. Eng.
196
(1-3
), 337
–355
(2006
).3.
W.
Yao
and R. K.
Jaiman
, “Model reduction and mechanism for the vortex-induced vibrations of bluff bodies
,” J. Fluid Mech.
827
, 357
–393
(2017
).4.
S.
Bukka
, A.
Magee
, and R.
Jaiman
, “Stability analysis of passive suppression for vortex-induced vibration
,” J. Fluid Mech.
886
, A12
(2020
).5.
S. B.
Reddy
, A. R.
Magee
, and R. K.
Jaiman
, “A data-driven approach for the stability analysis of vortex-induced vibration
,” in ASME 2018 37th International Conference on Ocean, Offshore and Arctic Engineering
(American Society of Mechanical Engineers
, 2018
), p. V002T08A004
.6.
K.
Duraisamy
, Z. J.
Zhang
, and A. P.
Singh
, “New approaches in turbulence and transition modeling using data-driven techniques
,” in 53rd AIAA Aerospace Sciences Meeting
(AIAA
, 2015
), p. 1284
.7.
T.
Miyanawala
and R.
Jaiman
, “An efficient deep learning technique for the Navier-Stokes equations: Application to unsteady wake flow dynamics
,” arXiv:1710.09099 (2017
).8.
J.-X.
Wang
, J.-L.
Wu
, and H.
Xiao
, “Physics-informed machine learning approach for reconstructing Reynolds stress modeling discrepancies based on DNS data
,” Phys. Rev. Fluids
2
(3
), 034603
.9.
Y.
LeCun
, Y.
Bengio
, and G.
Hinton
, “Deep learning
,” Nature
521
(7553
), 436
(2015
).10.
A. T.
Mohan
and D. V.
Gaitonde
, “A deep learning based approach to reduced order modeling for turbulent flow control using LSTM neural networks
,” arXiv:1804.09269 (2018
).11.
Z.
Wang
, D.
Xiao
, F.
Fang
, R.
Govindan
, C. C.
Pain
, and Y.
Guo
, “Model identification of reduced order fluid dynamics systems using deep learning
,” Int. J. Numer. Methods Fluids
86
(4
), 255
–268
(2018
).12.
T. P.
Miyanawala
and R. K.
Jaiman
, “Decomposition of wake dynamics in fluid–structure interaction via low-dimensional models
,” J. Fluid Mech.
867
, 723
–764
(2019
).13.
T.
Murata
, K.
Fukami
, and K.
Fukagata
, “Nonlinear mode decomposition with convolutional neural networks for fluid dynamics
,” J. Fluid Mech.
882
, A13
(2020
).14.
S. L.
Brunton
, J. L.
Proctor
, and J. N.
Kutz
, “Discovering governing equations from data by sparse identification of nonlinear dynamical systems
,” Proc. Natl. Acad. Sci. U. S. A.
113
(15
), 3932
–3937
(2016
).15.
S.
Rudy
, A.
Alla
, S. L.
Brunton
, and J. N.
Kutz
, “Data-driven identification of parametric partial differential equations
,” SIAM J. Appl. Dyn. Syst.
18
(2
), 643
–660
(2019
).16.
M.
Raissi
, Z.
Wang
, M. S.
Triantafyllou
, and G. E.
Karniadakis
, “Deep learning of vortex-induced vibrations
,” J. Fluid Mech.
861
, 119
–137
(2019
).17.
K.
Champion
, B.
Lusch
, J. N.
Kutz
, and S. L.
Brunton
, “Data-driven discovery of coordinates and governing equations
,” Proc. Natl. Acad. Sci. U. S. A.
116
(45
), 22445
–22451
(2019
).18.
P.
Choudhury
, R.
Allen
, and M.
Endres
, “Developing theory using machine learning methods
,” available at: SSRN 3251077, 2018
.19.
Z.
Long
, Y.
Lu
, and B.
Dong
, “PDE-Net 2.0: Learning PDEs from data with a numeric-symbolic hybrid deep network
,” J. Comput. Phys.
399
, 108925
(2019
).20.
S.
Pan
and K.
Duraisamy
, “Data-driven discovery of closure models
,” SIAM J. Appl. Dyn. Syst.
17
(4
), 2381
–2413
(2018
).21.
T. Q.
Chen
, Y.
Rubanova
, J.
Bettencourt
, and D. K.
Duvenaud
, “Neural ordinary differential equations
,” in Advances in Neural Information Processing Systems
(Curran Associates
, 2018
), pp. 6571
–6583
.22.
R.
Maulik
, A.
Mohan
, B.
Lusch
, S.
Madireddy
, and P.
Balaprakash
, “Time-series learning of latent-space dynamics for reduced-order model closure
,” Phys. D: Nonlinear Phenom.
405
, 132368
(2020
).23.
S.
Jeong
, B.
Solenthaler
, M.
Pollefeys
, M.
Gross
et al, “Data-driven fluid simulations using regression forests
,” ACM Trans. Graphics
34
(6
), 199
(2015
).24.
K.
Um
, X.
Hu
, and N.
Thuerey
, “Liquid splash modeling with neural networks
,” in Computer Graphics Forum
(Wiley Online Library
, 2018
), Vol. 37, pp. 171
–182
.25.
S.
Wiewel
, M.
Becher
, and N.
Thuerey
, “Latent space physics: Towards learning the temporal evolution of fluid flow
,” in Computer Graphics Forum
(Wiley Online Library
, 2019
), Vol. 38, pp. 71
–82
.26.
Y.
Xie
, E.
Franz
, M.
Chu
, and N.
Thuerey
, “tempoGAN: A temporally coherent, volumetric GAN for super-resolution fluid flow
,” ACM Trans. Graphics
37
(4
), 95
(2018
).27.
B.
Kim
, V. C.
Azevedo
, N.
Thuerey
, T.
Kim
, M.
Gross
, and B.
Solenthaler
, “Deep fluids: A generative network for parameterized fluid simulations
,” in Computer Graphics Forum
(Wiley Online Library
, 2019
), Vol. 38, pp. 59
–70
.28.
B.
Bonev
, L.
Prantl
, and N.
Thuerey
, “Pre-computed liquid spaces with generative neural networks and optical flow
,” arXiv:1704.078543 (2017
).29.
N.
Thuerey
, K.
Weißenow
, L.
Prantl
, and X.
Hu
, “Deep learning methods for Reynolds-averaged Navier-Stokes simulations of airfoil flows
” AIAA J.
58
(1
), 25
–36
(2020
).30.
S.
Bhatnagar
, Y.
Afshar
, S.
Pan
, K.
Duraisamy
, and S.
Kaushik
, “Prediction of aerodynamic flow fields using convolutional neural networks
,” Comput. Mech.
64
, 525
(2019
).31.
K. T.
Carlberg
, A.
Jameson
, M. J.
Kochenderfer
, J.
Morton
, L.
Peng
, and F. D.
Witherden
, “Recovering missing CFD data for high-order discretizations using deep neural networks and dynamics learning
,” J. Comput. Phys.
395
, 105
(2019
).32.
M.
Korda
and I.
Mezić
, “Linear predictors for nonlinear dynamical systems: Koopman operator meets model predictive control
,” Automatica
93
, 149
–160
(2018
).33.
S.
Peitz
and S.
Klus
, “Koopman operator-based model reduction for switched-system control of PDEs
,” Automatica
106
, 184
–191
(2019
).34.
Z.
Liu
, S.
Kundu
, L.
Chen
, and E.
Yeung
, “Decomposition of nonlinear dynamical systems using Koopman Gramians
,” in 2018 Annual American Control Conference (ACC)
(IEEE
, 2018
), pp. 4811
–4818
.35.
I.
Mezić
, “Analysis of fluid flows via spectral properties of the Koopman operator
,” Annu. Rev. Fluid Mech.
45
, 357
–378
(2013
).36.
M.
Korda
and I.
Mezić
, “On convergence of extended dynamic mode decomposition to the Koopman operator
,” J. Nonlinear Sci.
28
(2
), 687
–710
(2018
).37.
M.
Budisic
, M.
Ryan
, and I.
Mezić
, “Applied Koopmanism
,” Chaos
22
(4
), 047510
(2012
).38.
S.
Pan
and K.
Duraisamy
, “Long-time predictive modeling of nonlinear dynamical systems using neural networks
,” Complexity
2018
, 4801012
.39.
S.
Pan
and K.
Duraisamy
, “Physics-informed probabilistic learning of linear embeddings of non-linear dynamics with guaranteed stability
,” SIAM J. Appl. Dyn. Syst.
19
(1
), 480
–509
(2020
).40.
K.
Yeo
and I.
Melnyk
, “Deep learning algorithm for data-driven simulation of noisy dynamical system
,” J. Comput. Phys.
376
, 1212
–1231
(2019
).41.
S. E.
Otto
and C. W.
Rowley
, “Linearly recurrent autoencoder networks for learning dynamics
,” SIAM J. Appl. Dyn. Syst.
18
(1
), 558
–593
(2019
).42.
B.
Lusch
, J. N.
Kutz
, and S. L.
Brunton
, “Deep learning for universal linear embeddings of nonlinear dynamics
,” Nat. Commun.
9
(1
), 4950
(2018
).43.
T.
Miyanawala
and R.
Jaiman
, “A hybrid data-driven deep learning technique for fluid-structure interaction
,” in International Conference on Offshore Mechanics and Arctic Engineering (ASME, 2019), Vol. 58776, p. V002T08A004.44.
K.
Lee
and K. T.
Carlberg
, “Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders
,” J. Comput. Phys.
404
, 108973
(2020
).45.
N. B.
Erichson
, M.
Muehlebach
, and M. W.
Mahoney
, “Physics-informed autoencoders for Lyapunov-stable fluid flow prediction
,” arXiv:1905.10866 (2019
).46.
F. J.
Gonzalez
and M.
Balajewicz
, “Deep convolutional recurrent autoencoders for learning low-dimensional feature dynamics of fluid systems
,” arXiv:1808.01346 (2018
).47.
B.
Liu
and R. K.
Jaiman
, “Interaction dynamics of gap flow with vortex-induced vibration in side-by-side cylinder arrangement
,” Phys. Fluids
28
(12
), 127103
(2016
).48.
J. E.
D’Souza
, R. K.
Jaiman
, and C. K.
Mak
, “Dynamics of tandem cylinders in the vicinity of a plane moving wall
,” Comput. Fluids
124
, 117
–135
(2016
).49.
B.
Liu
and R.
Jaiman
, “Dynamics of gap flow interference in a vibrating side-by-side arrangement of two circular cylinders at moderate Reynolds number
,” arXiv:1801.05109 (2018
).50.
R. C.
Mysa
, A.
Kaboudian
, and R. K.
Jaiman
, “On the origin of wake-induced vibration in two tandem circular cylinders at low Reynolds number
,” J. Fluids Struct.
61
, 76
–98
(2016
).51.
R. K.
Jaiman
, M. Z.
Guan
, and T. P.
Miyanawala
, “Partitioned iterative and dynamic subgrid-scale methods for freely vibrating square-section structures at subcritical Reynolds number
,” Comput. Fluids
133
, 68
–89
(2016
).52.
R. K.
Jaiman
, N. R.
Pillalamarri
, and M. Z.
Guan
, “A stable second-order partitioned iterative scheme for freely vibrating low-mass bluff bodies in a uniform flow
,” Comput. Methods Appl. Mech. Eng.
301
, 187
–215
(2016
).53.
J.
Liu
, R. K.
Jaiman
, and P. S.
Gurugubelli
, “A stable second-order scheme for fluid-structure interaction with strong added-mass effects
,” J. Comput. Phys.
270
, 687
–710
(2014
).54.
R.
Jaiman
, P.
Geubelle
, E.
Loth
, and X.
Jiao
, “Transient fluid–structure interaction with non-matching spatial and temporal discretizations
,” Comput. Fluids
50
(1
), 120
–135
(2011
).55.
SciPy reference guide, release 1.4.1, https://docs.scipy.org/doc/scipy-1.4.1/scipy-ref-1.4.1.pdf,
2019
.56.
J. N.
Kani
and A. H.
Elsheikh
, “Dr-rnn: A deep residual recurrent neural network for model reduction
,” arXiv:1709.00939 (2017
).57.
O.
Ogunmolu
, X.
Gu
, S.
Jiang
, and N.
Gans
, “Nonlinear systems identification using deep dynamic neural networks
,” arXiv:1610.01439 (2016
).58.
K.
Yeo
, “Model-free prediction of noisy chaotic time series by deep learning
,” arXiv:1710.01693 (2017
).59.
C.
Olah
, “Understanding Lstm networks,” available at https://colah.github.io/posts/2015-08-Understanding-LSTMs/.60.
Q.
Li
, F.
Dietrich
, E. M.
Bollt
, and I. G.
Kevrekidis
, “Extended dynamic mode decomposition with dictionary learning: A data-driven adaptive spectral decomposition of the Koopman operator
,” Chaos
27
(10
), 103111
(2017
).61.
62.
R.
Mojgani
and M.
Balajewicz
, “Physics-aware registration based auto-encoder for convection dominated PDEs
,” arXiv:2006.15655 (2020
).63.
T.
Taddei
, “A registration method for model order reduction: Data compression and geometry reduction
,” SIAM J. Sci. Comput.
42
(2
), A997
–A1027
(2020
).64.
S. R.
Bukka
, “Data-driven computing for the stability analysis and prediction of fluid-structure interaction
,” Ph.D. thesis, National University of Singapore
, 2019
.65.
S. R.
Bukka
, A. R.
Magee
, and R. K.
Jaiman
, “Deep convolutional recurrent autoencoders for flow field prediction
,” arXiv:2003.12147 (2020
).66.
S. B.
Reddy
, A. R.
Magee
, and R. K.
Jaiman
, “Reduced order model for unsteady fluid flows via recurrent neural networks
,” in ASME 2019 38th International Conference on Ocean, Offshore and Arctic Engineering
(American Society of Mechanical Engineers
, 2019
).© 2021 Author(s).
2021
Author(s)
You do not currently have access to this content.