https://orcid.org/0000-0003-3578-6085
Abstract
In this work, we consider the problem of learning a reduced-order model of a high-dimensional stochastic nonlinear system with control inputs from noisy data. In particular, we develop a hybrid parametric/nonparametric model that learns the “average” linear dynamics in the data using dynamic mode decomposition with control (DMDc) and the nonlinearities and model uncertainties using Gaussian process (GP) regression and compare it with total least-squares dynamic mode decomposition (tlsDMD), extended here to systems with control inputs (tlsDMDc). The proposed approach is also compared with existing methods, such as DMDc-only and GP-only models, in two tasks: controlling the stochastic nonlinear Stuart–Landau equation and predicting the flowfield induced by a jet-like body force field in a turbulent boundary layer using data from large-scale numerical simulations.
References
1.
Lumey
,
J. L.
, 1970
, Stochastic Tools in Turbulence
,
Elsevier Science
, New York
.2.
Sirovich
,
L.
, 1987
, “
Turbulence and the Dynamics of Coherent Structures. I. Coherent Structures
,” Q. Appl. Math.
,
45
(3
), pp. 561
–571
.10.1090/qam/9104623.
Willcox
,
K.
, and
Peraire
,
J.
, 2002
, “
Balanced Model Reduction Via the Proper Orthogonal Decomposition
,” AIAA J.
,
40
(11
), pp. 2323
–2330
.10.2514/2.15704.
Rowley
,
C. W.
,
Mezić
,
I.
,
Bagheri
,
S.
,
Schlatter
,
P.
, and
Henningson
,
D. S.
, 2009
, “
Spectral Analysis of Nonlinear Flows
,” J. Fluid Mech.
,
641
, pp. 115
–127
.10.1017/S00221120099920595.
Schmid
,
P. J.
, 2010
, “
Dynamic Mode Decomposition of Numerical and Experimental Data
,” J. Fluid Mech.
,
656
, pp. 5
–28
.10.1017/S00221120100012176.
Proctor
,
J. L.
,
Brunton
,
S. L.
, and
Kutz
,
J. N.
, 2016
, “
Dynamic Mode Decomposition With Control
,” SIAM J. Appl. Dyn. Sys
t.,
15
(1
), pp. 142
–161
.10.1137/15M10138577.
Tsolovikos
,
A.
,
Bakolas
,
E.
,
Suryanarayanan
,
S.
, and
Goldstein
,
D.
, 2021
, “
Estimation and Control of Fluid Flows Using Sparsity-Promoting Dynamic Mode Decomposition
,” IEEE Control Syst. Lett.
,
5
(4
), pp. 1145
–1150
.10.1109/LCSYS.2020.30157768.
Hemati
,
M. S.
,
Rowley
,
C. W.
,
Deem
,
E. A.
, and
Cattafesta
,
L. N.
, 2017
, “
De-Biasing the Dynamic Mode Decomposition for Applied Koopman Spectral Analysis of Noisy Datasets
,” Theor. Comput. Fluid Dyn.
,
31
(4
), pp. 349
–368
.10.1007/s00162-017-0432-29.
Dawson
,
S.
,
Hemati
,
M. S.
,
Williams
,
M. O.
, and
Rowley
,
C. W.
, 2016
, “
Characterizing and Correcting for the Effect of Sensor Noise in the Dynamic Mode Decomposition
,” Exp. Fluids
,
57
(3
), pp. 1
–19
.10.1007/s00348-016-2127-710.
Jovanović
,
M. R.
,
Schmid
,
P. J.
, and
Nichols
,
J. W.
, 2014
, “
Sparsity-Promoting Dynamic Mode Decomposition
,” Phys. Fluids
,
26
(2
), p. 024103
.10.1063/1.486367011.
Mezić
,
I.
, 2013
, “
Analysis of Fluid Flows Via Spectral Properties of the Koopman Operator
,” Annu. Rev. Fluid Mech.
,
45
, pp. 357
–378
.10.1146/annurev-fluid-011212-14065212.
Korda
,
M.
, and
Mezić
,
I.
, 2018
, “
Linear Predictors for Nonlinear Dynamical Systems: Koopman Operator Meets Model Predictive Control
,” Automatica
,
93
, pp. 149
–160
.10.1016/j.automatica.2018.03.04613.
Abraham
,
I.
, and
Murphey
,
T. D.
, 2019
, “
Active Learning of Dynamics for Data-Driven Control Using Koopman Operators
,” IEEE Trans. Rob.
,
35
(5
), pp. 1071
–1083
.10.1109/TRO.2019.292388014.
Williams
,
M. O.
,
Hemati
,
M. S.
,
Dawson
,
S. T.
,
Kevrekidis
,
I. G.
, and
Rowley
,
C. W.
, 2016
, “
Extending Data-Driven Koopman Analysis to Actuated Systems
,” IFAC-PapersOnLine
,
49
(18
), pp. 704
–709
.10.1016/j.ifacol.2016.10.24815.
Li
,
Q.
,
Dietrich
,
F.
,
Bollt
,
E. M.
, and
Kevrekidis
,
I. G.
, 2017
, “
Extended Dynamic Mode Decomposition With Dictionary Learning: A Data-Driven Adaptive Spectral Decomposition of the Koopman Operator
,” Chaos: Interdiscip. J. Nonlinear Sci.
,
27
(10
), p. 103111
.10.1063/1.499385416.
Williams
,
M. O.
,
Rowley
,
C. W.
, and
Kevrekidis
,
I. G.
, 2015
, “
A Kernel-Based Approach to Data-Driven Koopman Spectral Analysis
,” J. Comput. Nonlinear Dyn.
, 2(2), pp. 247
–252
.10.3934/jcd.201500517.
Lusch
,
B.
,
Kutz
,
J. N.
, and
Brunton
,
S. L.
, 2018
, “
Deep Learning for Universal Linear Embeddings of Nonlinear Dynamics
,” Nat. Commun.
,
9
(1
), pp. 1
–10
.10.1038/s41467-018-07210-018.
Yeung
,
E.
,
Kundu
,
S.
, and
Hodas
,
N.
, 2019
, “
Learning Deep Neural Network Representations for Koopman Operators of Nonlinear Dynamical Systems
,” 2019 American Control Conference
, Philadelphia, PA, July 10–12
, pp. 4832
–4839
.10.23919/ACC.2019.881533919.
Brunton
,
S. L.
,
Proctor
,
J. L.
, and
Kutz
,
J. N.
, 2016
, “
Discovering Governing Equations From Data by Sparse Identification of Nonlinear Dynamical Systems
,” Proc. Natl. Acad. Sci.
,
113
(15
), pp. 3932
–3937
.10.1073/pnas.151738411320.
Benner
,
P.
,
Goyal
,
P.
,
Kramer
,
B.
,
Peherstorfer
,
B.
, and
Willcox
,
K.
, 2020
, “
Operator Inference for Non-Intrusive Model Reduction of Systems With Non-Polynomial Nonlinear Terms
,” Comput. Methods Appl. Mech. Eng.
,
372
, p. 113433
.10.1016/j.cma.2020.11343321.
Rasmussen
,
C. E.
, Williams
, C. K. I.
, 2006
, “
Gaussian Processes for Machine Learning
,” The MIT Press
, Cambridge, MA
.22.
Quinonero-Candela
,
J.
, and
Rasmussen
,
C. E.
, 2005
, “
A Unifying View of Sparse Approximate Gaussian Process Regression
,” J. Mach. Learn. Res.
,
6
, pp. 1939
–1959
.10.5555/1046920.119490923.
Titsias
,
M.
, 2009
, “
Variational Learning of Inducing Variables in Sparse Gaussian Processes
,” Artificial Intelligence and Statistics
, Clearwater Beach, FL, Apr. 16–18, pp. 567
–574
.https://proceedings.mlr.press/v5/titsias09a.html24.
Hoffman
,
M. D.
,
Blei
,
D. M.
,
Wang
,
C.
, and
Paisley
,
J.
, 2013
, “
Stochastic Variational Inference
,” J. Mach. Learn. Res.
,
14
(5
), 1303
–1347
.10.48550/arXiv.1206.705125.
Hensman
,
J.
,
Fusi
,
N.
, and
Lawrence
,
N. D.
, 2013
, “
Gaussian Processes for Big Data
,” Proceedings of the Twenty-Ninth Conference on Uncertainty in Artificial Intelligence
, Bellevue, WA, Aug. 11–15, pp. 282
–290
.https://auai.org/uai2013/prints/papers/244.pdf26.
Grimes
,
D. B.
,
Chalodhorn
,
R.
, and
Rao
,
R. P.
, 2006
, “
Dynamic Imitation in a Humanoid Robot Through Nonparametric Probabilistic Inference
,” Robotics: Science and Systems
,
Philadelphia, PA
, Aug. 16–19, pp. 199
–206
.10.15607/RSS.2006.II.02627.
Ko
,
J.
,
Klein
,
D. J.
,
Fox
,
D.
, and
Haehnel
,
D.
, 2007
, “
Gaussian Processes and Reinforcement Learning for Identification and Control of an Autonomous Blimp
,” Proceedings 2007 IEEE International Conference on Robotics and Automation
, Rome, Italy, Apr. 10–14, pp. 742
–747
.10.1109/ROBOT.2007.36307528.
Pan
,
Y.
, and
Theodorou
,
E. A.
, 2015
, “
Data-Driven Differential Dynamic Programming Using Gaussian Processes
,” 2015 American Control Conference (ACC)
, Chicago, IL, July 1–3, pp. 4467
–4472
.29.
Hewing
,
L.
,
Kabzan
,
J.
, and
Zeilinger
,
M. N.
, 2020
, “
Cautious Model Predictive Control Using Gaussian Process Regression
,” IEEE Trans. Control Syst. Technol.
,
28
(6
), pp. 2736
–2743
.10.1109/TCST.2019.294975730.
Tsolovikos
,
A.
, and
Bakolas
,
E.
, 2021
, “
Cautious Nonlinear Covariance Steering Using Variational Gaussian Process Predictive Models
,” IFAC-PapersOnLine
,
54
(20
), pp. 59
–64
.10.1016/j.ifacol.2021.11.15331.
Xiao
,
M.
,
Breitkopf
,
P.
,
Filomeno Coelho
,
R.
,
Knopf-Lenoir
,
C.
,
Sidorkiewicz
,
M.
, and
Villon
,
P.
, 2010
, “
Model Reduction by CPOD and Kriging
,” Struct. Multidiscip. Optim.
,
41
(4
), pp. 555
–574
.10.1007/s00158-009-0434-932.
Guo
,
M.
, and
Hesthaven
,
J. S.
, 2018
, “
Reduced Order Modeling for Nonlinear Structural Analysis Using Gaussian Process Regression
,” Comput. Methods Appl. Mech. Eng.
,
341
, pp. 807
–826
.10.1016/j.cma.2018.07.01733.
Chang
,
Y.-H.
,
Zhang
,
L.
,
Wang
,
X.
,
Yeh
,
S.-T.
,
Mak
,
S.
,
Sung
,
C.-L.
,
Jeff Wu
,
C.
, and
Yang
,
V.
, 2019
, “
Kernel-Smoothed Proper Orthogonal Decomposition-Based Emulation for Spatiotemporally Evolving Flow Dynamics Prediction
,” AIAA J.
,
57
(12
), pp. 5269
–5280
.10.2514/1.J05780334.
Ortali
,
G.
,
Demo
,
N.
, and
Rozza
,
G.
, 2022
, “
A Gaussian Process Regression Approach Within a Data-Driven POD Framework for Engineering Problems in Fluid Dynamics
,” Math. Eng.
,
4
(3
), pp. 1
–16
.10.3934/mine.202202135.
Masuda
,
A.
,
Susuki
,
Y.
,
Martínez-Ramón
,
M.
,
Mammoli
,
A.
, and
Ishigame
,
A.
, 2019
, “
Application of Gaussian Process Regression to Koopman Mode Decomposition for Noisy Dynamic Data
,” e-print arXiv:1911.01143
.10.48550/arXiv.1911.0114336.
Maulik
,
R.
,
Botsas
,
T.
,
Ramachandra
,
N.
,
Mason
,
L. R.
, and
Pan
,
I.
, 2021
, “
Latent-Space Time Evolution of Non-Intrusive Reduced-Order Models Using Gaussian Process Emulation
,” Phys. D: Nonlinear Phenom.
,
416
, p. 132797
.10.1016/j.physd.2020.13279737.
Bonilla
,
E. V.
,
Chai
,
K.
, and
Williams
,
C.
, 2007
, “
Multi-Task Gaussian Process Prediction
,” Advances in Neural Information Processing Systems
, Vancouver, BC, Dec. 3–4.https://papers.nips.cc/paper_files/paper/2007/file/66368270ffd51418ec58bd793f2d9b1b-Paper.pdf38.
Noack
,
B. R.
,
Afanasiev
,
K.
,
Morzyński
,
M.
,
Tadmor
,
G.
, and
Thiele
,
F.
, 2003
, “
A Hierarchy of Low-Dimensional Models for the Transient and Post-Transient Cylinder Wake
,” J. Fluid Mech.
,
497
, pp. 335
–363
.10.1017/S002211200300669439.
Borrelli
,
F.
,
Bemporad
,
A.
, and
Morari
,
M.
, 2017
, Predictive Control for Linear and Hybrid Systems
,
Cambridge University Press
, Cambridge, UK
.40.
Tsolovikos
,
A.
,
Suryanarayanan
,
S.
,
Bakolas
,
E.
, and
Goldstein
,
D.
, 2021
, “
Model Predictive Control of Material Volumes With Application to Vortical Structures
,” AIAA J.
,
59
(10
), pp. 4057
–4070
.10.2514/1.J06041341.
Tsolovikos
,
A.
,
Jariwala
,
A.
,
Suryanarayanan
,
S.
,
Bakolas
,
E.
, and
Goldstein
,
D.
, 2023
, “
Separation Delay in Turbulent Boundary Layers Via Model Predictive Control of Large-Scale Motions
,” Phys. Fluids
,
35
(11
), p. 115118
.10.1063/5.0169138
