Data-driven reduced-order models via regularised Operator Inference for a single-injector combustion process
Abstract
This paper derives predictive reduced-order models for rocket engine combustion dynamics via Operator Inference, a scientific machine learning approach that blends data-driven learning with physics-based modelling. The non-intrusive nature of the approach enables variable transformations that expose system structure. The specific contribution of this paper is to advance the formulation robustness and algorithmic scalability of the Operator Inference approach. Regularisation is introduced to the formulation to avoid over-fitting. The task of determining an optimal regularisation is posed as an optimisation problem that balances training error and stability of long-time integration dynamics. A scalable algorithm and open-source implementation are presented, then demonstrated for a single-injector rocket combustion example. This example exhibits rich dynamics that are difficult to capture with state-of-the-art reduced models. With appropriate regularisation and an informed selection of learning variables, the reduced-order models exhibit high accuracy in re-predicting the training regime and acceptable accuracy in predicting future dynamics, while achieving close to a million times speedup in computational cost. When compared to a state-of-the-art model reduction method, the Operator Inference models provide the same or better accuracy at approximately one thousandth of the computational cost.
- Authors:
-
- Oden Institute for Computational Engineering and Sciences, University of Texas at Austin, Austin, TX, USA
- Department of Aerospace Engineering, University of Michigan, Ann Arbor, MI, USA
- Publication Date:
- Research Org.:
- Univ. of Texas, Austin, TX (United States). Oden Institute for Computational Engineering and Sciences
- Sponsoring Org.:
- USDOE Office of Science (SC); US Air Force Office of Scientific Research (AFOSR)
- OSTI Identifier:
- 2325428
- Alternate Identifier(s):
- OSTI ID: 1782859
- Grant/Contract Number:
- SC0019303; FA9550-17-1-0195
- Resource Type:
- Published Article
- Journal Name:
- Journal of the Royal Society of New Zealand
- Additional Journal Information:
- Journal Name: Journal of the Royal Society of New Zealand Journal Volume: 51 Journal Issue: 2; Journal ID: ISSN 0303-6758
- Publisher:
- Informa UK Limited
- Country of Publication:
- New Zealand
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING; model reduction; operator inference; scientific machine learning; combustion; data-driven model
Citation Formats
McQuarrie, Shane A., Huang, Cheng, and Willcox, Karen E. Data-driven reduced-order models via regularised Operator Inference for a single-injector combustion process. New Zealand: N. p., 2021.
Web. doi:10.1080/03036758.2020.1863237.
McQuarrie, Shane A., Huang, Cheng, & Willcox, Karen E. Data-driven reduced-order models via regularised Operator Inference for a single-injector combustion process. New Zealand. https://doi.org/10.1080/03036758.2020.1863237
McQuarrie, Shane A., Huang, Cheng, and Willcox, Karen E. Sun .
"Data-driven reduced-order models via regularised Operator Inference for a single-injector combustion process". New Zealand. https://doi.org/10.1080/03036758.2020.1863237.
@article{osti_2325428,
title = {Data-driven reduced-order models via regularised Operator Inference for a single-injector combustion process},
author = {McQuarrie, Shane A. and Huang, Cheng and Willcox, Karen E.},
abstractNote = {This paper derives predictive reduced-order models for rocket engine combustion dynamics via Operator Inference, a scientific machine learning approach that blends data-driven learning with physics-based modelling. The non-intrusive nature of the approach enables variable transformations that expose system structure. The specific contribution of this paper is to advance the formulation robustness and algorithmic scalability of the Operator Inference approach. Regularisation is introduced to the formulation to avoid over-fitting. The task of determining an optimal regularisation is posed as an optimisation problem that balances training error and stability of long-time integration dynamics. A scalable algorithm and open-source implementation are presented, then demonstrated for a single-injector rocket combustion example. This example exhibits rich dynamics that are difficult to capture with state-of-the-art reduced models. With appropriate regularisation and an informed selection of learning variables, the reduced-order models exhibit high accuracy in re-predicting the training regime and acceptable accuracy in predicting future dynamics, while achieving close to a million times speedup in computational cost. When compared to a state-of-the-art model reduction method, the Operator Inference models provide the same or better accuracy at approximately one thousandth of the computational cost.},
doi = {10.1080/03036758.2020.1863237},
journal = {Journal of the Royal Society of New Zealand},
number = 2,
volume = 51,
place = {New Zealand},
year = {Sun Jan 31 00:00:00 EST 2021},
month = {Sun Jan 31 00:00:00 EST 2021}
}
https://doi.org/10.1080/03036758.2020.1863237
Works referenced in this record:
SciPy 1.0: fundamental algorithms for scientific computing in Python
journal, February 2020
- Virtanen, Pauli; Gommers, Ralf; Oliphant, Travis E.
- Nature Methods
Approximation of Large-Scale Dynamical Systems
book, January 2005
- Antoulas, Athanasios C.
- Advances in Design and Control
Missing Point Estimation in Models Described by Proper Orthogonal Decomposition
journal, November 2008
- Astrid, Patricia; Weiland, Siep; Willcox, Karen
- IEEE Transactions on Automatic Control, Vol. 53, Issue 10
The GNAT method for nonlinear model reduction: Effective implementation and application to computational fluid dynamics and turbulent flows
journal, June 2013
- Carlberg, Kevin; Farhat, Charbel; Cortial, Julien
- Journal of Computational Physics, Vol. 242
Lift & Learn: Physics-informed machine learning for large-scale nonlinear dynamical systems
journal, May 2020
- Qian, Elizabeth; Kramer, Boris; Peherstorfer, Benjamin
- Physica D: Nonlinear Phenomena, Vol. 406
Certified real-time solution of the parametrized steady incompressible Navier-Stokes equations: rigorous reduced-basisa posteriori error bounds
journal, January 2005
- Veroy, K.; Patera, A. T.
- International Journal for Numerical Methods in Fluids, Vol. 47, Issue 8-9
Finding Structure with Randomness: Probabilistic Algorithms for Constructing Approximate Matrix Decompositions
journal, January 2011
- Halko, N.; Martinsson, P. G.; Tropp, J. A.
- SIAM Review, Vol. 53, Issue 2
Applied Numerical Linear Algebra
book, January 1997
- Demmel, James W.
- Society for Industrial and Applied Mathematics
Stabilization of projection-based reduced order models for linear time-invariant systems via optimization-based eigenvalue reassignment
journal, April 2014
- Kalashnikova, Irina; van Bloemen Waanders, Bart; Arunajatesan, Srinivasan
- Computer Methods in Applied Mechanics and Engineering, Vol. 272
Data-driven operator inference for nonintrusive projection-based model reduction
journal, July 2016
- Peherstorfer, Benjamin; Willcox, Karen
- Computer Methods in Applied Mechanics and Engineering, Vol. 306
An ‘empirical interpolation’ method: application to efficient reduced-basis discretization of partial differential equations
journal, November 2004
- Barrault, Maxime; Maday, Yvon; Nguyen, Ngoc Cuong
- Comptes Rendus Mathematique, Vol. 339, Issue 9
Reduced Basis Approximation and a Posteriori Error Estimation for Affinely Parametrized Elliptic Coercive Partial Differential Equations: Application to Transport and Continuum Mechanics
journal, May 2008
- Rozza, G.; Huynh, D. B. P.; Patera, A. T.
- Archives of Computational Methods in Engineering, Vol. 15, Issue 3
Krylov subspace techniques for reduced-order modeling of large-scale dynamical systems
journal, October 2002
- Bai, Zhaojun
- Applied Numerical Mathematics, Vol. 43, Issue 1-2
Simplified Reaction Mechanisms for the Oxidation of Hydrocarbon Fuels in Flames
journal, December 1981
- Westbrook, Charles K.; Dryer, Frederick L.
- Combustion Science and Technology, Vol. 27, Issue 1-2
Discovering governing equations from data by sparse identification of nonlinear dynamical systems
journal, March 2016
- Brunton, Steven L.; Proctor, Joshua L.; Kutz, J. Nathan
- Proceedings of the National Academy of Sciences, Vol. 113, Issue 15
Model reduction methods based on Krylov subspaces
journal, May 2003
- Freund, Roland W.
- Acta Numerica, Vol. 12
Sampling Low-Dimensional Markovian Dynamics for Preasymptotically Recovering Reduced Models from Data with Operator Inference
journal, January 2020
- Peherstorfer, Benjamin
- SIAM Journal on Scientific Computing, Vol. 42, Issue 5
Simulation of pulmonary air flow with a subject-specific boundary condition
journal, August 2010
- Yin, Youbing; Choi, Jiwoong; Hoffman, Eric A.
- Journal of Biomechanics, Vol. 43, Issue 11
M ODELING OF F LUID -S TRUCTURE I NTERACTION
journal, January 2001
- Dowell, Earl H.; Hall, Kenneth C.
- Annual Review of Fluid Mechanics, Vol. 33, Issue 1
On the role and challenges of CFD in the aerospace industry
journal, January 2016
- Spalart, P. R.; Venkatakrishnan, V.
- The Aeronautical Journal, Vol. 120, Issue 1223
Workshop Report on Basic Research Needs for Scientific Machine Learning: Core Technologies for Artificial Intelligence
report, February 2019
- Baker, Nathan; Alexander, Frank; Bremer, Timo
The Proper Orthogonal Decomposition in the Analysis of Turbulent Flows
journal, January 1993
- Berkooz, G.; Holmes, P.; Lumley, J. L.
- Annual Review of Fluid Mechanics, Vol. 25, Issue 1
Investigations and Improvement of Robustness of Reduced-Order Models of Reacting Flow
journal, December 2019
- Huang, Cheng; Duraisamy, Karthik; Merkle, Charles L.
- AIAA Journal, Vol. 57, Issue 12
Low‐dimensional models for complex geometry flows: Application to grooved channels and circular cylinders
journal, October 1991
- Deane, A. E.; Kevrekidis, I. G.; Karniadakis, G. E.
- Physics of Fluids A: Fluid Dynamics, Vol. 3, Issue 10
A Simplex Method for Function Minimization
journal, January 1965
- Nelder, J. A.; Mead, R.
- The Computer Journal, Vol. 7, Issue 4
Coupling between hydrodynamics, acoustics, and heat release in a self-excited unstable combustor
journal, April 2015
- Harvazinski, Matthew E.; Huang, Cheng; Sankaran, Venkateswaran
- Physics of Fluids, Vol. 27, Issue 4
Bayesian calibration of a large-scale geothermal reservoir model by a new adaptive delayed acceptance Metropolis Hastings algorithm: ADAPTIVE DELAYED ACCEPTANCE METROPOLIS-HASTINGS ALGORITHM
journal, October 2011
- Cui, T.; Fox, C.; O'Sullivan, M. J.
- Water Resources Research, Vol. 47, Issue 10
Conservative model reduction for finite-volume models
journal, October 2018
- Carlberg, Kevin; Choi, Youngsoo; Sargsyan, Syuzanna
- Journal of Computational Physics, Vol. 371
Fluid-solid coupling for the investigation of diastolic and systolic human left ventricular function
journal, August 2010
- Nordsletten, D.; McCormick, M.; Kilner, P. J.
- International Journal for Numerical Methods in Biomedical Engineering, Vol. 27, Issue 7
A Survey of Projection-Based Model Reduction Methods for Parametric Dynamical Systems
journal, January 2015
- Benner, Peter; Gugercin, Serkan; Willcox, Karen
- SIAM Review, Vol. 57, Issue 4
Turbulence and the dynamics of coherent structures. I. Coherent structures
journal, January 1987
- Sirovich, Lawrence
- Quarterly of Applied Mathematics, Vol. 45, Issue 3
The NumPy Array: A Structure for Efficient Numerical Computation
journal, March 2011
- van der Walt, Stéfan; Colbert, S. Chris; Varoquaux, Gaël
- Computing in Science & Engineering, Vol. 13, Issue 2
Nonlinear Model Order Reduction via Lifting Transformations and Proper Orthogonal Decomposition
journal, June 2019
- Kramer, Boris; Willcox, Karen E.
- AIAA Journal, Vol. 57, Issue 6
A hybrid stabilization approach for reduced‐order models of compressible flows with shock‐vortex interaction
journal, December 2019
- Rezaian, Elnaz; Wei, Mingjun
- International Journal for Numerical Methods in Engineering, Vol. 121, Issue 8
Nonlinear Model Reduction via Discrete Empirical Interpolation
journal, January 2010
- Chaturantabut, Saifon; Sorensen, Danny C.
- SIAM Journal on Scientific Computing, Vol. 32, Issue 5
A posteriori error bounds for reduced-basis approximations of parametrized parabolic partial differential equations
journal, January 2005
- Grepl, Martin A.; Patera, Anthony T.
- ESAIM: Mathematical Modelling and Numerical Analysis, Vol. 39, Issue 1
State of the art of geothermal reservoir simulation
journal, August 2001
- O'Sullivan, Michael J.; Pruess, Karsten; Lippmann, Marcelo J.
- Geothermics, Vol. 30, Issue 4
Learning Physics-Based Reduced-Order Models for a Single-Injector Combustion Process
journal, June 2020
- Swischuk, Renee; Kramer, Boris; Huang, Cheng
- AIAA Journal, Vol. 58, Issue 6