Access the full text.
Sign up today, get DeepDyve free for 14 days.
D. Rumelhart, Geoffrey Hinton, Ronald Williams (1986)
Learning representations by back-propagating errorsNature, 323
Haecheon Choi, W. Jeon, Jinsung Kim (2008)
CONTROL OF FLOW OVER A BLUFF BODYProceeding of Fifth International Symposium on Turbulence and Shear Flow Phenomena
Yann LeCun, L. Bottou, Yoshua Bengio, P. Haffner (1998)
Gradient-based learning applied to document recognitionProc. IEEE, 86
F. Pino, Lorenzo Schena, J. Rabault, M. Mendez (2022)
Comparative analysis of machine learning methods for active flow controlJournal of Fluid Mechanics, 958
Kai Fukami, K. Fukagata, K. Taira (2023)
Super-resolution analysis via machine learning: a survey for fluid flowsTheoretical and Computational Fluid Dynamics, 37
R. Schoephoerster, M. Moreno, James Moore, T. Schneider (2007)
A Linear Systems Approach to Flow Control
D. Park, D. Ladd, E. Hendricks (1994)
Feedback control of von Kármán vortex shedding behind a circular cylinder at low Reynolds numbersPhysics of Fluids, 6
John Kim (2003)
Control of turbulent boundary layersPhysics of Fluids, 15
H. Choi, W.-P. Jeon, J. Kim (2008)
Control of flow over a bluff bodyAnnual Review of Fluid Mechanics, 40
Hosnieh Kor, Mehdi Ghomizad, K. Fukagata (2017)
A unified interpolation stencil for ghost-cell immersed boundary method for flow around complex geometriesJournal of Fluid Science and Technology, 12
P. Ricco, M. Skote, M. Leschziner (2021)
A review of turbulent skin-friction drag reduction by near-wall transverse forcingProgress in Aerospace Sciences, 123
Kemin Zhou, P. Khargonekar (1988)
An algebraic Riccati equation approach to H ∞ optimizationSystems & Control Letters, 11
S. Brunton, B. Noack (2015)
Closed-Loop Turbulence Control: Progress and ChallengesApplied Mechanics Reviews, 67
J.C. Doyle, K. Glover, P.P. Khargonekar, B.A. Francis (1989)
Statespace solutions to standard H2 and H∞ control problemsIEEE Transactions on Automatic Control, 34
J. Doyle, K. Glover, P. Khargonekar, B. Francis (1989)
State-space solutions to standard H/sub 2/ and H/sub infinity / control problemsIEEE Transactions on Automatic Control, 34
O. San, R. Maulik (2018)
Extreme learning machine for reduced order modeling of turbulent geophysical flows.Physical review. E, 97 4-1
M. Milano, P. Koumoutsakos (2002)
Neural network modeling for near wall turbulent flowJournal of Computational Physics, 182
J. Rabault, M. Kuchta, A. Jensen, U. Réglade, Nicolas Cerardi (2018)
Artificial neural networks trained through deep reinforcement learning discover control strategies for active flow controlJournal of Fluid Mechanics, 865
V. Kornilov (2015)
Current state and prospects of researches on the control of turbulent boundary layer by air blowingProgress in Aerospace Sciences, 76
R. Castellanos, G. Maceda, I. Fuente, B. Noack, A. Ianiro, S. Discetti (2022)
Machine-learning flow control with few sensor feedback and measurement noisePhysics of Fluids
Romain Lopez, Pierre Boyeau, N. Yosef, Michael Jordan, J. Regier (2020)
AUTO-ENCODING VARIATIONAL BAYES
K. Fukagata, K. Iwamoto, Y. Hasegawa (2023)
Turbulent Drag Reduction by Streamwise Traveling Waves of Wall-Normal ForcingAnnual Review of Fluid Mechanics
K. Roussopoulos (1993)
Feedback control of vortex shedding at low Reynolds numbersJournal of Fluid Mechanics, 248
T. Bewley (2001)
Flow control: new challenges for a new RenaissanceProgress in Aerospace Sciences, 37
Kai Fukami, K. Fukagata, K. Taira (2020)
Assessment of supervised machine learning methods for fluid flowsTheoretical and Computational Fluid Dynamics, 34
G.E. Hinton, R.R. Salakhutdinov (2006)
Reducing the dimensionality of data with neural networksScience, 313
M. Farazmand, A. Saibaba (2022)
Tensor-based flow reconstruction from optimally located sensor measurementsJournal of Fluid Mechanics, 962
N. Kasagi, Yuji Suzuki, K. Fukagata (2009)
Microelectromechanical Systems–Based Feedback Control of Turbulence for Skin Friction ReductionAnnual Review of Fluid Mechanics, 41
Taichi Nakamura, Kai Fukami, K. Hasegawa, Yusuke Nabae, K. Fukagata (2020)
Convolutional neural network and long short-term memory based reduced order surrogate for minimal turbulent channel flowPhysics of Fluids
(2023)
Flow control by a hybrid use of machine learning and control theory
Wenwen Tong, Shizhao Wang, Yue Yang (2022)
Estimating forces from cross-sectional data in the wake of flows past a plate using theoretical and data-driven modelsPhysics of Fluids
Geoffrey Hinton, R. Salakhutdinov (2006)
Supporting Online Material for Reducing the Dimensionality of Data with Neural Networks
Chang Hou, Nan Deng, Bernd Noack (2023)
Dynamics-augmented cluster-based network modelJournal of Fluid Mechanics
M. Pastoor, L. Henning, B. Noack, R. King, G. Tadmor (2008)
Feedback shear layer control for bluff body drag reductionJournal of Fluid Mechanics, 608
S. Brunton (2021)
Applying machine learning to study fluid mechanicsActa Mechanica Sinica, 37
A. Güemes, C. Vila, S. Discetti (2022)
Super-resolution generative adversarial networks of randomly-seeded fieldsNature Machine Intelligence, 4
(1967)
“The structure of inhomogeneous turbulent flows
I. Higgins, L. Matthey, Arka Pal, Christopher Burgess, Xavier Glorot, M. Botvinick, S. Mohamed, Alexander Lerchner (2016)
beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework
R. Vinuesa, S. Brunton (2021)
Enhancing computational fluid dynamics with machine learningNature Computational Science, 2
Feng Ren, Chenglei Wang, Hui Tang (2019)
Active control of vortex-induced vibration of a circular cylinder using machine learningPhysics of Fluids
Kai Fukami, Takaaki Murata, Kai Zhang, K. Fukagata (2020)
Sparse identification of nonlinear dynamics with low-dimensionalized flow representationsJournal of Fluid Mechanics, 926
Takaaki Murata, Kai Fukami, K. Fukagata (2019)
Nonlinear mode decomposition with convolutional neural networks for fluid dynamicsJournal of Fluid Mechanics, 882
K. Taira, Maziar Hemati, S. Brunton, Yiyang Sun, K. Duraisamy, S. Bagheri, Scott Dawson, C. Yeh (2019)
Modal Analysis of Fluid Flows: Applications and OutlookAIAA Journal
S. Brunton, B. Noack, P. Koumoutsakos (2019)
Machine Learning for Fluid MechanicsArXiv, abs/1905.11075
G. Karniadakis, K. Choi (2003)
MECHANISMS ON TRANSVERSE MOTIONS IN TURBULENT WALL FLOWSAnnual Review of Fluid Mechanics, 35
John Kim, T. Bewley (2007)
A Linear Systems Approach to Flow ControlAnnual Review of Fluid Mechanics, 39
R. Vinuesa, S. Brunton, B. McKeon (2023)
The transformative potential of machine learning for experiments in fluid mechanicsNature Reviews Physics, 5
S. Brunton, Maziar Hemati, K. Taira (2020)
Special issue on machine learning and data-driven methods in fluid dynamicsTheoretical and Computational Fluid Dynamics, 34
L. Guastoni, A. Güemes, A. Ianiro, S. Discetti, P. Schlatter, H. Azizpour, R. Vinuesa (2020)
Convolutional-network models to predict wall-bounded turbulence from wall quantitiesJournal of Fluid Mechanics, 928
J.L. Lumley (1967)
The Structure of Inhomogeneous Turbulent Flows Atmospheric Turbulence and Radio Wave Propagation
Haecheon Choi, P. Moin, John Kim (1994)
Active turbulence control for drag reduction in wall-bounded flowsJournal of Fluid Mechanics, 262
K. Hasegawa, Kai Fukami, Takaaki Murata, K. Fukagata (2020)
CNN-LSTM based reduced order modeling of two-dimensional unsteady flows around a circular cylinder at different Reynolds numbersFluid Dynamics Research, 52
Yuning Wang, Alberto Solera-Rico, C. Vila, R. Vinuesa (2024)
Towards optimal β-variational autoencoders combined with transformers for reduced-order modelling of turbulent flowsInternational Journal of Heat and Fluid Flow
A. Racca, N. Doan, L. Magri (2023)
Predicting turbulent dynamics with the convolutional autoencoder echo state networkJournal of Fluid Mechanics, 975
Kai Fukami, Yusuke Nabae, K. Kawai, K. Fukagata (2018)
Synthetic turbulent inflow generator using machine learningPhysical Review Fluids
K. Fukagata (2023)
Reduced order modeling of fluid flows using convolutional neural networksJournal of Fluid Science and Technology
K. Duraisamy, G. Iaccarino, Heng Xiao (2018)
Turbulence Modeling in the Age of DataAnnual Review of Fluid Mechanics
S. Illingworth, H. Naito, K. Fukagata (2014)
Active control of vortex shedding: an explanation of the gain window.Physical review. E, Statistical, nonlinear, and soft matter physics, 90 4
B. McKeon, Ati Sharma (2010)
A critical-layer framework for turbulent pipe flowJournal of Fluid Mechanics, 658
M. Brenner, J. Eldredge, J. Freund (2019)
Perspective on machine learning for advancing fluid mechanicsPhysical Review Fluids
C. Rowley, David Williams (2006)
Dynamics and control of high-reynolds-number flow over open cavitiesAnnual Review of Fluid Mechanics, 38
F. Abergel, R. Temam (1990)
On some control problems in fluid mechanicsTheoretical and Computational Fluid Dynamics, 1
Dmitrii Kochkov, Jamie Smith, Ayya Alieva, Qing Wang, M. Brenner, Stephan Hoyer (2021)
Machine learning–accelerated computational fluid dynamicsProceedings of the National Academy of Sciences of the United States of America, 118
B.D.O. Anderson, J.B. Moore (2014)
Optimal Control: Linear Quadratic Methods
S. Brunton, J. Proctor, J. Kutz (2015)
Discovering governing equations from data by sparse identification of nonlinear dynamical systemsProceedings of the National Academy of Sciences, 113
K. Fukami, K. Fukagata, K. Taira (2020)
Assessment of supervised machine learning for fluid flowsTheoretical and Computational Fluid Dynamics, 34
Flow control has a great potential to contribute to a sustainable society through mitigation of environmental burden. However, the high dimensional and nonlinear nature of fluid flows poses challenges in designing efficient control laws using the control theory. This paper aims to propose a hybrid method (i.e. machine learning and control theory) for feedback control of fluid flows, by which the flow is mapped to the latent space in such a way that the linear control theory can be applied therein.Design/methodology/approachThe authors propose a partially nonlinear linear system extraction autoencoder (pn-LEAE), which consists of convolutional neural networks-based autoencoder (CNN-AE) and a custom layer to extract low-dimensional latent dynamics from fluid velocity field data. This pn-LEAE is designed to extract a linear dynamical system so that the modern control theory can easily be applied, while a nonlinear compression is done with the autoencoder (AE) part so that the latent dynamics conform to that linear system. The key technique is to train this pn-LEAE with the ground truths at two consecutive time instants, whereby the AE part retains its capability as the AE, and the weights in the linear dynamical system are trained simultaneously.FindingsThe authors demonstrate the effectiveness of the linear system extracted by the pn-LEAE, as well as the designed control law’s effectiveness for a flow around a circular cylinder at the Reynolds number of ReD = 100. When the control law derived in the latent space was applied to the direct numerical simulation, the lift fluctuations were suppressed over 50%.Originality/valueTo the best of the authors’ knowledge, this is the first attempt using CNN-AE for linearization of fluid flows involving transient development to design a feedback control law.
International Journal of Numerical Methods for Heat and Fluid Flow – Emerald Publishing
Published: Sep 2, 2024
Keywords: Machine learning; Autoencoder; Linear system extraction; Reduced order modeling; Flow control
Read and print from thousands of top scholarly journals.
Already have an account? Log in
Bookmark this article. You can see your Bookmarks on your DeepDyve Library.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Copy and paste the desired citation format or use the link below to download a file formatted for EndNote
Access the full text.
Sign up today, get DeepDyve free for 14 days.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.