More Web Proxy on the site http://driver.im/

research-article

Reconstructing Three-Dimensional Bluff Body Wake from Sectional Flow Fields with Convolutional Neural Networks

Authors:

Mitsuaki Matsuo,

Taichi Nakamura,

Masaki Morimoto,

Koji FukagataAuthors Info & Claims

SN Computer Science, Volume 5, Issue 3

https://doi.org/10.1007/s42979-024-02602-0

Published: 07 March 2024 Publication History

Abstract

The recent development of high-performance computing enables us to generate spatio-temporal high-resolution data of nonlinear dynamical systems and to analyze them for a deeper understanding of their complex nature. This trend can be found in a wide range of science and engineering, which suggests that detailed investigations on efficient data handling in physical science must be required in the future. This study considers the use of convolutional neural networks (CNNs) to achieve efficient data storage and estimation of scientific big data derived from nonlinear dynamical systems. The CNN is used to reconstruct three-dimensional data from a few numbers of two-dimensional sections in a computationally friendly manner. The present model is a combination of two- and three-dimensional CNNs, which allows users to save only some of the two-dimensional sections to reconstruct the volumetric data. As examples, we consider a flow around a square cylinder at the diameter-based Reynolds number

R e_{D} = 300

. We demonstrate that volumetric fluid flow data can be reconstructed with the present method from as few as five sections. Furthermore, we propose a combination of the present CNN-based reconstruction with an adaptive sampling-based super-resolution analysis to augment the data compressibility. Our report can serve as a bridge toward practical data handling for not only fluid mechanics but also a broad range of physical sciences.

References

[1]

Moore GE Cramming more components onto integrated circuits Electronics. 1965 38 1-4

[2]

Kajishima T, Taira K. Computational fluid dynamics. Cham: Springer International Publishing, 2017;(1).

[3]

Brunton SL, Noack BR, and Koumoutsakos P Machine learning for fluid mechanics Ann Rev Fluid Mech. 2020 52 477-508

[4]

Kutz JN Deep learning in fluid dynamics J Fluid Mech. 2017 814 1-4

[5]

Brunton SL, Hemati MS, and Taira K Special issue on machine learning and data-driven methods in fluid dynamics Theor Comput Fluid Dyn. 2020 34 4 333-337

[6]

Hinton GE and Salakhutdinov RR Reducing the dimensionality of data with neural networks Science. 2006 313 5786 504-507

[7]

Taira K, Hemati MS, Brunton SL, Sun Y, Duraisamy K, Bagheri S, Dawson S, and Yeh C-A Modal analysis of fluid flows: applications and outlook AIAA J. 2020 58 3 998-1022

[8]

Nóvoa A and Magri L Real-time thermoacoustic data assimilation J Fluid Mech. 2022 948 A35

[9]

Milano M and Koumoutsakos P Neural network modeling for near wall turbulent flow J Comput Phys. 2002 182 1-26

Digital Library

[10]

Glaws A, King R, and Sprague M Deep learning for in situ data compression of large turbulent flow simulations Phys Rev Fluids. 2020 5 114602

[11]

Morimoto M, Fukami K, Zhang K, Nair AG, and Fukagata K Convolutional neural networks for fluid flow analysis: toward effective metamodeling and low-dimensionalization Theor Comput Fluid Dyn. 2021 35 5 633-658

[12]

Eivazi H, Le Clainche S, Hoyas S, and Vinuesa R Towards extraction of orthogonal and parsimonious non-linear modes from turbulent flows Expert Syst Appl. 2022 202 117038

Digital Library

[13]

Le Clainche S, Ferrer E, Gibson S, Cross E, Parente A, and Vinuesa R Improving aircraft performance using machine learning: a review Aerosp Sci Technol. 2023 138

[14]

Yousif MZ, Yu L, Lim H-C. Physics-guided deep learning for generating turbulent inflow conditions. J. Fluid Mech., 2022;936

[15]

Doan NAK, Polifke W, Magri L. Auto-encoded reservoir computing for turbulence learning. In International Conference on Computational Science, 2021;344–351. Springer.

[16]

Omata N and Shirayama S A novel method of low-dimensional representation for temporal behavior of flow fields using deep autoencoder AIP Adv. 2019 9 1 015006

[17]

Hasegawa K, Fukami K, Murata T, and Fukagata K Machine-learning-based reduced-order modeling for unsteady flows around bluff bodies of various shapes Theor Comput Fluid Dyn. 2020 34 4 367-383

[18]

Hasegawa K, Fukami K, Murata T, Fukagata K. Data-driven reduced order modeling of flows around two-dimensional bluff bodies of various shapes. ASME-JSME-KSME Joint Fluids Engineering Conference, San Francisco, USA, (Paper 5079), 2019.

[19]

Maulik R, Lusch B, and Balaprakash P Reduced-order modeling of advection-dominated systems with recurrent neural networks and convolutional autoencoders Phys Fluids. 2021 33 3 037106

[20]

Hasegawa K, Fukami K, Murata T, and Fukagata K CNN-LSTM based reduced order modeling of two-dimensional unsteady flows around a circular cylinder at different Reynolds numbers Fluid Dyn Res. 2020 52 065501

[21]

Nakamura T, Fukami K, Hasegawa K, Nabae Y, and Fukagata K Convolutional neural network and long short-term memory based reduced order surrogate for minimal turbulent channel flow Phys Fluids. 2021 33 025116

[22]

Fukami K, Murata T, Zhang K, and Fukagata K Sparse identification of nonlinear dynamics with low-dimensionalized flow representations J Fluid Mech. 2021 926 A10

[23]

Lusch B, Kutz JN, and Brunton SL Deep learning for universal linear embeddings of nonlinear dynamics Nat Commu. 2018 9 1 4950

[24]

Murata T, Fukami K, and Fukagata K Nonlinear mode decomposition with convolutional neural networks for fluid dynamics J Fluid Mech. 2020 882 A13

[25]

Xu J and Duraisamy K Multi-level convolutional autoencoder networks for parametric prediction of spatio-temporal dynamics Comput Meth Appl Mech Eng. 2020 372 113379

[26]

Liu Y, Ponce C, Brunton SL, and Kutz JN Multiresolution convolutional autoencoders J Comput Phys. 2023 474

Digital Library

[27]

Muehlebach M, Erichson NB, Mahoney M. Physics-informed autoencoders for lyapunov-stable fluid flow prediction. In Machine Learning and the Physical Sciences Workshop, Conference on Neural Information Processing Systems, 2019.

[28]

Fukami K, Nakamura T, and Fukagata K Convolutional neural network based hierarchical autoencoder for nonlinear mode decomposition of fluid field data Phys Fluids. 2020 32 095110

[29]

Brenner MP, Eldredge JD, and Freund JB Perspective on machine learning for advancing fluid mechanics Phys Rev Fluids. 2019 4 100501

[30]

Erichson NB, Mathelin L, Yao Z, Brunton SL, Mahoney MW, and Kutz JN Shallow neural networks for fluid flow reconstruction with limited sensors Proc R Soc A. 2020 476 2238 20200097

[31]

Fukami K, Fukagata K, and Taira K Assessment of supervised machine learning for fluid flows Theor Comput Fluid Dyn. 2020 34 4 497-519

[32]

Everson R and Sirovich L Karhunen–loeve procedure for gappy data J Opt Soc Am. 1995 12 8 1657-1664

[33]

Nakamura T, Fukami K, and Fukagata K Identifying key differences between linear stochastic estimation and neural networks for fluid flow regressions Sci Rep. 2022 12 3726

[34]

Nair NJ and Goza A Leveraging reduced-order models for state estimation using deep learning J Fluid Mech. 2020 897 R1

[35]

Fukami K, Maulik R, Ramachandra N, Fukagata K, and Taira K Global field reconstruction from sparse sensors with Voronoi tessellation-assisted deep learning Nat Mach Intell. 2021 3 945-951

[36]

Fukami K, Fukagata K, and Taira K Super-resolution reconstruction of turbulent flows with machine learning J Fluid Mech. 2019 870 106-120

[37]

Fukami K, Fukagata K, Taira K. Super-resolution analysis with machine learning for low-resolution flow data. In 11th International Symposium on Turbulence and Shear Flow Phenomena (TSFP11), Southampton, UK, number 208, 2019.

[38]

Maulik R and San O Resolution and energy dissipation characteristics of implicit LES and explicit filtering models for compressible turbulence Fluids 2017 2 2 14

[39]

Liu B, Tang J, Huang H, and Lu X-Y Deep learning methods for super-resolution reconstruction of turbulent flows Phys Fluids 2020 32 025105

[40]

Kim H, Kim J, Won S, and Lee C Unsupervised deep learning for super-resolution reconstruction of turbulence J Fluid Mech. 2021 910 A29

[41]

Fukami K, Fukagata K, and Taira K Machine-learning-based spatio-temporal super resolution reconstruction of turbulent flows J Fluid Mech. 2021 909 A9

[42]

Yousif MZ, Yu L, and Lim H-C High-fidelity reconstruction of turbulent flow from spatially limited data using enhanced super-resolution generative adversarial network Phys Fluids 2021 33 12 125119

[43]

Yousif MZ, Yu L, and Lim H-C Super-resolution reconstruction of turbulent flow fields at various reynolds numbers based on generative adversarial networks Phys Fluids. 2022 34 1 015130

[44]

Yousif MZ, Zhang M, Yu L, Vinuesa R, and Lim H-C A transformer-based synthetic-inflow generator for spatially-developing turbulent boundary layers J Fluid Mech. 2023 957 A6

[45]

Deng Z, He C, Liu Y, and Kim KC Super-resolution reconstruction of turbulent velocity fields using a generative adversarial network-based artificial intelligence framework Phys Fluids. 2019 31 125111

[46]

Morimoto M, Fukami K, and Fukagata K Experimental velocity data estimation for imperfect particle images using machine learning Phys Fluids. 2021 33 8 087121

[47]

Cai S, Zhou S, Xu C, and Gao Q Dense motion estimation of particle images via a convolutional neural network Exp Fluids. 2019 60 60-73

[48]

Yousif MZ, Yu L, Hoyas S, Vinuesa R, and Lim H-C A deep-learning approach for reconstructing 3D turbulent flows from 2D observation data Sci Rep. 2023 13 2529

[49]

Huang J, Liu H, and Cai W Online in situ prediction of 3-D flame evolution from its history 2-D projections via deep learning J Fluid Mech. 2019 875 R2

[50]

Kench S and Cooper SJ Generating three-dimensional structures from a two-dimensional slice with generative adversarial network-based dimensionality expansion Nat Mach Intell. 2021 3 299-305

[51]

Bai H and Alam MdM Dependence of square cylinder wake on Reynolds number Phys Fluids 2018 30 015102

[52]

Caltagirone JP Sur l’interaction fluide-milieu poreux: application au calcul des efforts excerses sur un obstacle par un fluide visqueux C R Acad Sci Paris 1994 318 571-577

[53]

LeCun Y, Bottou L, Bengio Y, and Haffner P Gradient-based learning applied to document recognition Proc IEEE 1998 86 11 2278-2324

[54]

LeCun Y, Bengio Y, and Hinton G Deep learning Nature 2015 521 436-444

[55]

Fukami K, Nabae Y, Kawai K, and Fukagata K Synthetic turbulent inflow generator using machine learning Phys Rev Fluids. 2019 4 064603

[56]

Champion K, Lusch B, Kutz JN, and Brunton SL Data-driven discovery of coordinates and governing equations Proc Natl Acad Sci USA 2019 45 116 22445-22451

[57]

Kim J and Lee C Prediction of turbulent heat transfer using convolutional neural networks J Fluid Mech. 2020 882 A18

[58]

Fukami K, An B, Nohmi M, Obuchi M, and Taira K Machine-learning-based reconstruction of turbulent vortices from sparse pressure sensors in a pump sump J Fluids Eng. 2022 144 12 121501

[59]

He K, Zhang X, Ren S, and Sun J Deep residual learning for image recognition Proc IEEE. 2016 1 770-778

[60]

Glaws A, King R, and Sprague M Deep learning for in situ data compression of large turbulent flow simulations Phys Rev Fluids. 2020 5 11 114602

[61]

Momenifar M, Diao E, Tarokh V, and Bragg AD Dimension reduced turbulent flow data from deep vector quantisers J Turbul. 2022 23 4–5 232-264

[62]

Nair V, Hinton GE. Rectified linear units improve restricted boltzmann machines. Proc. Int. Conf. Mach. Learn., 2010;807–814.

[63]

Bergstra J, Yamins D, Cox D. Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures. In International Conference on Machine Learning, 2013;28:115–123. PMLR.

[64]

Maulik R, Mohan A, Lusch B, Madireddy S, Balaprakash P, and Livescu D Time-series learning of latent-space dynamics for reduced-order model closure Phys D. 2020 405 132368

[65]

Prechelt L Automatic early stopping using cross validation: quantifying the criteria Neural Netw. 1998 11 4 761-767

Digital Library

[66]

Brunton SL, Kutz JN. Data-Driven Science and Engineering: Machine Learning, Dynamical Systems, and Control. Cambridge University Press, pages ISBN, 1108422098, 2019.

[67]

Jeong J and Hussain F On the identification of a vortex J Fluid Mech. 1995 285 69-94

[68]

Pérez JM, Clainche SL, and Vega JM Reconstruction of three-dimensional flow fields from two-dimensional data J Comput Phys. 2020 407 109239

Digital Library

[69]

Morimoto M, Fukami K, Zhang K, and Fukagata K Generalization techniques of neural networks for fluid flow estimation Neural Comput Appl. 2022 34 3647-3669

Digital Library

[70]

Nakamura T and Fukagata K Robust training approach of neural networks for fluid flow state estimations Int J Heat Fluid Flow. 2022 96 108997

[71]

Keys R Cubic convolution interpolation for digital image processing IEEE Trans Acoustics Speech Signal Process. 1981 29 6 1153-1160

[72]

Robinson AH and Cherry C Results of a prototype television bandwidth compression scheme Proc IEEE 1967 55 3 356-364

[73]

Fukami K, Hasegawa K, Nakamura T, Morimoto M, and Fukagata K Model order reduction with neural networks: application to laminar and turbulent flows SN Comput Sci. 2021 2 467

Digital Library

[74]

Ogoke F, Meidani K, Hashemi A, Farimani AB. Graph convolutional networks applied to unstructured flow field data. Mach. Learn.: Sci. Technol., 2021;2:045020.

[75]

Kashefi A, Rempe D, and Guibas LJ A point-cloud deep learning framework for prediction of fluid flow fields on irregular geometries Phys Fluids. 2021 33 027104

[76]

Gao H, Sun L, and Wang J-X PhyGeoNet: physics-informed geometry-adaptive convolutional neural networks for solving parameterized steady-state PDEs on irregular domain J Comput Phys. 2021 428 110079

[77]

Maulik R, Fukami K, Ramachandra N, Fukagata K, and Taira K Probabilistic neural networks for fluid flow surrogate modeling and data recovery Phys Rev Fluids. 2020 5 104401

[78]

Morimoto M, Fukami K, Maulik R, Vinuesa R, and Fukagata K Assessments of epistemic uncertainty using gaussian stochastic weight averaging for fluid-flow regression Phys D. 2022 440 133454

Cited By

Puri ROnishi JRüttgers MSarma RTsubokura MLintermann A(2024)On the choice of physical constraints in artificial neural networks for predicting flow fieldsFuture Generation Computer Systems10.1016/j.future.2024.07.009161:C(361-375)Online publication date: 1-Dec-2024
https://dl.acm.org/doi/10.1016/j.future.2024.07.009

Recommendations

Visualization of Three-Dimensional Flow Structures in the Wake of an Inclined Circular Cylinder

In the previous measurements of the aerodynamic sound generated from an inclined circular cylinder, it is reported that the sound pressure level (SPL) changes with the aspect ratio and the inclined angle. Therefore, we have investigated the changes in ...
Flow visualization behind a streamwise oscillating cylinder and a stationary cylinder in tandem arrangement

Interference is investigated between a stationary cylinder wake and that of a downstream streamwise oscillating cylinder. Experiments were carried out in a water tunnel. A laser-induced fluorescence technique was used to visualize the flow structure behind ...
Vortex Methods for Direct Numerical Simulation of Three-Dimensional Bluff Body Flows

Recent contributions to the 3-D vortex methods are presented. Following Cottet, the particles strength exchange (PSE) scheme for diffusion is modified in the vicinity of solid boundaries to avoid a spurious vorticity flux and to enforce a zero-normal ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image SN Computer Science

SN Computer Science Volume 5, Issue 3

Mar 2024

750 pages

EISSN:2661-8907

Issue’s Table of Contents

© The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2024. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Publisher

Springer-Verlag

Berlin, Heidelberg

Publication History

Published: 07 March 2024

Accepted: 28 December 2023

Received: 31 October 2022

Author Tags

Qualifiers

Research-article

Funding Sources

Japan Society for the Promotion of Science

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 21 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Puri ROnishi JRüttgers MSarma RTsubokura MLintermann A(2024)On the choice of physical constraints in artificial neural networks for predicting flow fieldsFuture Generation Computer Systems10.1016/j.future.2024.07.009161:C(361-375)Online publication date: 1-Dec-2024
https://dl.acm.org/doi/10.1016/j.future.2024.07.009

View Options

View options

Media

Figures

Other

Tables

View Issue’s Table of Contents