Search Menu
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information
Search Scholarly Publications

Title: An artificial neural network framework for reduced order modeling of transient flows

Abstract

Here, this paper proposes a supervised machine learning framework for the non-intrusive model order reduction of unsteady fluid flows to provide accurate predictions of non-stationary state variables when the control parameter values vary. Our approach utilizes a training process from full-order scale direct numerical simulation data projected on proper orthogonal decomposition (POD) modes to achieve an artificial neural network (ANN) model with reduced memory requirements. This data-driven ANN framework allows for a nonlinear time evolution of the modal coefficients without performing a Galerkin projection. Our POD-ANN framework can thus be considered an equation-free approach for latent space dynamics evolution of nonlinear transient systems and can be applied to a wide range of physical and engineering applications. Within this framework we introduce two architectures, namely sequential network (SN) and residual network (RN), to train the trajectory of modal coefficients. We perform a systematic analysis of the performance of the proposed reduced order modeling approaches on prediction of a nonlinear wave-propagation problem governed by the viscous Burgers equation, a simplified prototype setting for transient flows. We find that the POD-ANN-RN yields stable and accurate results for test problems assessed both within inside and outside of the database range and performs significantly bettermore » than the standard intrusive Galerkin projection model. Finally, our results show that the proposed framework provides a non-intrusive alternative to the evolution of transient physics in a POD basis spanned space, and can be used as a robust predictive model order reduction tool for nonlinear dynamical systems.« less

Authors:
ORCiD logo [1];  [1];  [1]
+ Show Author Affiliations
  1. Oklahoma State Univ., Stillwater, OK (United States)
Publication Date:
Research Org.:
Oklahoma State Univ., Stillwater, OK (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)
OSTI Identifier:
1593569
Alternate Identifier(s):
OSTI ID: 1547460
Grant/Contract Number:  
SC0019290
Resource Type:
Accepted Manuscript
Journal Name:
Communications in Nonlinear Science and Numerical Simulation
Additional Journal Information:
Journal Volume: 77; Journal Issue: C; Journal ID: ISSN 1007-5704
Publisher:
Elsevier
Country of Publication:
United States
Language:
English
Subject:
42 ENGINEERING; Artificial neural networks; Reduced order modeling; Proper orthogonal decomposition; Convective flows; Non-intrusive model order reduction

Citation Formats

San, Omer, Maulik, Romit, and Ahmed, Mansoor. An artificial neural network framework for reduced order modeling of transient flows. United States: N. p., 2019. Web. doi:10.1016/j.cnsns.2019.04.025.
Copy to clipboard
San, Omer, Maulik, Romit, & Ahmed, Mansoor. An artificial neural network framework for reduced order modeling of transient flows. United States. https://doi.org/10.1016/j.cnsns.2019.04.025
Copy to clipboard
San, Omer, Maulik, Romit, and Ahmed, Mansoor. Thu . "An artificial neural network framework for reduced order modeling of transient flows". United States. https://doi.org/10.1016/j.cnsns.2019.04.025. https://www.osti.gov/servlets/purl/1593569.
Copy to clipboard
@article{osti_1593569,
title = {An artificial neural network framework for reduced order modeling of transient flows},
author = {San, Omer and Maulik, Romit and Ahmed, Mansoor},
abstractNote = {Here, this paper proposes a supervised machine learning framework for the non-intrusive model order reduction of unsteady fluid flows to provide accurate predictions of non-stationary state variables when the control parameter values vary. Our approach utilizes a training process from full-order scale direct numerical simulation data projected on proper orthogonal decomposition (POD) modes to achieve an artificial neural network (ANN) model with reduced memory requirements. This data-driven ANN framework allows for a nonlinear time evolution of the modal coefficients without performing a Galerkin projection. Our POD-ANN framework can thus be considered an equation-free approach for latent space dynamics evolution of nonlinear transient systems and can be applied to a wide range of physical and engineering applications. Within this framework we introduce two architectures, namely sequential network (SN) and residual network (RN), to train the trajectory of modal coefficients. We perform a systematic analysis of the performance of the proposed reduced order modeling approaches on prediction of a nonlinear wave-propagation problem governed by the viscous Burgers equation, a simplified prototype setting for transient flows. We find that the POD-ANN-RN yields stable and accurate results for test problems assessed both within inside and outside of the database range and performs significantly better than the standard intrusive Galerkin projection model. Finally, our results show that the proposed framework provides a non-intrusive alternative to the evolution of transient physics in a POD basis spanned space, and can be used as a robust predictive model order reduction tool for nonlinear dynamical systems.},
doi = {10.1016/j.cnsns.2019.04.025},
journal = {Communications in Nonlinear Science and Numerical Simulation},
number = C,
volume = 77,
place = {United States},
year = {Thu Apr 25 00:00:00 EDT 2019},
month = {Thu Apr 25 00:00:00 EDT 2019}
}
Copy to clipboard
Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record
https://doi.org/10.1016/j.cnsns.2019.04.025
Copyright Statement
Other availability
Search WorldCat Search WorldCat to find libraries that may hold this journal
Citation Metrics:
Cited by: 82 works
Citation information provided by
Web of Science
Save / Share:
Export Metadata
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.

Works referenced in this record:

Stabilized principal interval decomposition method for model reduction of nonlinear convective systems with moving shocks
journal, September 2018

Using functional gains for effective sensor location in flow control: a reduced-order modelling approach
journal, September 2015

  • Akhtar, Imran; Borggaard, Jeff; Burns, John A.
  • Journal of Fluid Mechanics, Vol. 781
  • DOI: 10.1017/jfm.2015.509

Stabilization of projection-based reduced-order models: STABILIZATION OF PROJECTION-BASED REDUCED-ORDER MODELS
journal, February 2012

  • Amsallem, David; Farhat, Charbel
  • International Journal for Numerical Methods in Engineering, Vol. 91, Issue 4
  • DOI: 10.1002/nme.4274

The dynamics of coherent structures in the wall region of a turbulent boundary layer
journal, July 1988

Nonintrusive reduced-order modeling of parametrized time-dependent partial differential equations
journal, February 2013

  • Audouze, Christophe; De Vuyst, Florian; Nair, Prasanth B.
  • Numerical Methods for Partial Differential Equations, Vol. 29, Issue 5
  • DOI: 10.1002/num.21768

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
  • DOI: 10.1137/130932715

The Proper Orthogonal Decomposition in the Analysis of Turbulent Flows
journal, January 1993

An improved algorithm for the shallow water equations model reduction: Dynamic Mode Decomposition vs POD: AN IMPROVED ALGORITHM FOR DYNAMIC MODE DECOMPOSITION VS POD
journal, April 2015

  • Bistrian, D. A.; Navon, I. M.
  • International Journal for Numerical Methods in Fluids, Vol. 78, Issue 9
  • DOI: 10.1002/fld.4029

Randomized dynamic mode decomposition for nonintrusive reduced order modelling: RANDOMIZED DYNAMIC MODE DECOMPOSITION FOR NIROM
journal, February 2017

  • Bistrian, Diana Alina; Navon, Ionel Michael
  • International Journal for Numerical Methods in Engineering, Vol. 112, Issue 1
  • DOI: 10.1002/nme.5499

Artificial viscosity proper orthogonal decomposition
journal, January 2011

  • Borggaard, Jeff; Iliescu, Traian; Wang, Zhu
  • Mathematical and Computer Modelling, Vol. 53, Issue 1-2
  • DOI: 10.1016/j.mcm.2010.08.015

Compressive sensing based machine learning strategy for characterizing the flow around a cylinder with limited pressure measurements
journal, December 2013

  • Bright, Ido; Lin, Guang; Kutz, J. Nathan
  • Physics of Fluids, Vol. 25, Issue 12
  • DOI: 10.1063/1.4836815

Closed-Loop Turbulence Control: Progress and Challenges
journal, August 2015

  • Brunton, Steven L.; Noack, Bernd R.
  • Applied Mechanics Reviews, Vol. 67, Issue 5
  • DOI: 10.1115/1.4031175

Low-dimensional modelling of a confined three-dimensional wake flow
journal, November 2006

Goal-oriented, model-constrained optimization for reduction of large-scale systems
journal, June 2007

A low-cost, goal-oriented ‘compact proper orthogonal decomposition’ basis for model reduction of static systems
journal, December 2010

  • Carlberg, Kevin; Farhat, Charbel
  • International Journal for Numerical Methods in Engineering, Vol. 86, Issue 3
  • DOI: 10.1002/nme.3074

Stable and accurate boundary treatments for compact, high-order finite-difference schemes
journal, May 1993

Greedy Nonintrusive Reduced Order Model for Fluid Dynamics
journal, December 2018

  • Chen, Wang; Hesthaven, Jan S.; Junqiang, Bai
  • AIAA Journal, Vol. 56, Issue 12
  • DOI: 10.2514/1.J056161

Acceleration techniques for reduced-order models based on proper orthogonal decomposition
journal, August 2008

  • Cizmas, Paul G. A.; Richardson, Brian R.; Brenner, Thomas A.
  • Journal of Computational Physics, Vol. 227, Issue 16
  • DOI: 10.1016/j.jcp.2008.04.036

Identification strategies for model-based control
journal, July 2013

An artificial neural network approach to rainfall-runoff modelling
journal, February 1998

Modeling and control of magnetorheological dampers for seismic response reduction
journal, October 1996

New Regularization Method for Calibrated pod Reduced-Order Models
journal, January 2016

Unsteady Fluid Mechanics Applications of Neural Networks
journal, January 1997

  • Faller, William E.; Schreck, Scott J.
  • Journal of Aircraft, Vol. 34, Issue 1
  • DOI: 10.2514/2.2134

A POD reduced order unstructured mesh ocean modelling method for moderate Reynolds number flows
journal, January 2009

Closed-loop separation control using machine learning
journal, April 2015

  • Gautier, N.; Aider, J. -L.; Duriez, T.
  • Journal of Fluid Mechanics, Vol. 770
  • DOI: 10.1017/jfm.2015.95

Pricing and hedging derivative securities with neural networks: Bayesian regularization, early stopping, and bagging
journal, July 2001

  • Gencay, R.
  • IEEE Transactions on Neural Networks, Vol. 12, Issue 4
  • DOI: 10.1109/72.935086

Low-dimensional control of the circular cylinder wake
journal, September 1998

Multiple Sensor Control of Vortex Shedding
journal, April 2001

Total variation diminishing Runge-Kutta schemes
journal, January 1998

  • Gottlieb, Sigal; Shu, Chi-Wang
  • Mathematics of Computation of the American Mathematical Society, Vol. 67, Issue 221
  • DOI: 10.1090/S0025-5718-98-00913-2

Stable architectures for deep neural networks
journal, December 2017

Practical error bounds for a non-intrusive bi-fidelity approach to parametric/stochastic model reduction
journal, September 2018

  • Hampton, Jerrad; Fairbanks, Hillary R.; Narayan, Akil
  • Journal of Computational Physics, Vol. 368
  • DOI: 10.1016/j.jcp.2018.04.015

Non-intrusive reduced order modeling of nonlinear problems using neural networks
journal, June 2018

Experimental Turbulent Field Modeling by Visualization and Neural Networks
journal, May 2004

  • Hocˇevar, Marko; Sˇirok, Brane; Grabec, Igor
  • Journal of Fluids Engineering, Vol. 126, Issue 3
  • DOI: 10.1115/1.1760534

Analysis of a complex of statistical variables into principal components.
journal, January 1933

  • Hotelling, H.
  • Journal of Educational Psychology, Vol. 24, Issue 6
  • DOI: 10.1037/h0071325

Stability Properties of POD-Galerkin Approximations for the Compressible Navier-Stokes Equations
journal, March 2000

  • Iollo, A.; Lanteri, S.; Désidéri, J. -A.
  • Theoretical and Computational Fluid Dynamics, Vol. 13, Issue 6
  • DOI: 10.1007/s001620050119

The Method of Proper Orthogonal Decomposition for Dynamical Characterization and Order Reduction of Mechanical Systems: An Overview
journal, August 2005

  • Kerschen, Gaetan; Golinval, Jean-claude; Vakakis, Alexander F.
  • Nonlinear Dynamics, Vol. 41, Issue 1-3
  • DOI: 10.1007/s11071-005-2803-2

Nonlinear Model for Drought Forecasting Based on a Conjunction of Wavelet Transforms and Neural Networks
journal, November 2003

Sparse Sensing and DMD-Based Identification of Flow Regimes and Bifurcations in Complex Flows
journal, January 2017

  • Kramer, Boris; Grover, Piyush; Boufounos, Petros
  • SIAM Journal on Applied Dynamical Systems, Vol. 16, Issue 2
  • DOI: 10.1137/15M104565X

Galerkin Proper Orthogonal Decomposition Methods for a General Equation in Fluid Dynamics
journal, January 2002

Optimal snapshot location for computing POD basis functions
journal, February 2010

  • Kunisch, Karl; Volkwein, Stefan
  • ESAIM: Mathematical Modelling and Numerical Analysis, Vol. 44, Issue 3
  • DOI: 10.1051/m2an/2010011

Application of neural networks to turbulence control for drag reduction
journal, June 1997

  • Lee, Changhoon; Kim, John; Babcock, David
  • Physics of Fluids, Vol. 9, Issue 6
  • DOI: 10.1063/1.869290

Compact finite difference schemes with spectral-like resolution
journal, November 1992

A method for the solution of certain non-linear problems in least squares
journal, January 1944

  • Levenberg, Kenneth
  • Quarterly of Applied Mathematics, Vol. 2, Issue 2
  • DOI: 10.1090/qam/10666

Non-intrusive reduced order modelling with least squares fitting on a sparse grid: NON-INTRUSIVE REDUCED ORDER MODELLING WITH LEAST SQUARES FITTING
journal, July 2016

  • Lin, Z.; Xiao, D.; Fang, F.
  • International Journal for Numerical Methods in Fluids, Vol. 83, Issue 3
  • DOI: 10.1002/fld.4268

Machine learning strategies for systems with invariance properties
journal, August 2016

Reynolds averaged turbulence modelling using deep neural networks with embedded invariance
journal, October 2016

  • Ling, Julia; Kurzawski, Andrew; Templeton, Jeremy
  • Journal of Fluid Mechanics, Vol. 807
  • DOI: 10.1017/jfm.2016.615

Reduced-order modeling: new approaches for computational physics
journal, February 2004

Construction of reduced-order models for fluid flows using deep feedforward neural networks
journal, June 2019

Modeling and control of physical processes using proper orthogonal decomposition
journal, January 2001

A neural network approach for the blind deconvolution of turbulent flows
journal, October 2017

A review of indirect/non-intrusive reduced order modeling of nonlinear geometric structures
journal, May 2013

  • Mignolet, Marc P.; Przekop, Adam; Rizzi, Stephen A.
  • Journal of Sound and Vibration, Vol. 332, Issue 10
  • DOI: 10.1016/j.jsv.2012.10.017

Neural Network Modeling for Near Wall Turbulent Flow
journal, October 2002

  • Milano, Michele; Koumoutsakos, Petros
  • Journal of Computational Physics, Vol. 182, Issue 1
  • DOI: 10.1006/jcph.2002.7146

Energy balance and mass conservation in reduced order models of fluid flows
journal, October 2017

  • Mohebujjaman, Muhammad; Rebholz, Leo G.; Xie, Xuping
  • Journal of Computational Physics, Vol. 346
  • DOI: 10.1016/j.jcp.2017.06.019

On the need for a nonlinear subscale turbulence term in POD models as exemplified for a high-Reynolds-number flow over an Ahmed body
journal, April 2014

  • Östh, Jan; Noack, Bernd R.; Krajnović, Siniša
  • Journal of Fluid Mechanics, Vol. 747
  • DOI: 10.1017/jfm.2014.168

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
  • DOI: 10.1016/j.cma.2016.03.025

A reduced-order approach for optimal control of fluids using proper orthogonal decomposition
journal, January 2000

Leapfrogging and synoptic Leapfrogging: A new optimization approach
journal, May 2012

Model Reduction for Flow Analysis and Control
journal, January 2017

Reduced-order modeling of time-varying systems
journal, January 1999

  • Roychowdhury, J.
  • IEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing, Vol. 46, Issue 10
  • DOI: 10.1109/82.799678

Principal interval decomposition framework for POD reduced-order modeling of convective Boussinesq flows: PRINCIPAL INTERVAL DECOMPOSITION MODEL REDUCTION FRAMEWORK
journal, February 2015

  • San, O.; Borggaard, J.
  • International Journal for Numerical Methods in Fluids, Vol. 78, Issue 1
  • DOI: 10.1002/fld.4006

A stabilized proper orthogonal decomposition reduced-order model for large scale quasigeostrophic ocean circulation
journal, May 2015

Extreme learning machine for reduced order modeling of turbulent geophysical flows
journal, April 2018

Machine learning closures for model order reduction of thermal fluids
journal, August 2018

Neural network closures for nonlinear model order reduction
journal, January 2018

Efficient reduced-order modeling of frequency-dependent coupling inductances associated with 3-D interconnect structures
journal, May 1996

  • Miguel Silveira, L.; Kamon, M.; White, J.
  • IEEE Transactions on Components, Packaging, and Manufacturing Technology: Part B, Vol. 19, Issue 2
  • DOI: 10.1109/96.496030

Using field inversion to quantify functional errors in turbulence closures
journal, April 2016

  • Singh, Anand Pratap; Duraisamy, Karthik
  • Physics of Fluids, Vol. 28, Issue 4
  • DOI: 10.1063/1.4947045

Turbulence and the dynamics of coherent structures. I. Coherent structures
journal, January 1987

  • Sirovich, Lawrence
  • Quarterly of Applied Mathematics, Vol. 45, Issue 3
  • DOI: 10.1090/qam/910462

Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous Spaces
journal, January 1997

  • Storn, Rainer; Price, Kenneth
  • Journal of Global Optimization, Vol. 11, Issue 4, p. 341-359
  • DOI: 10.1023/A:1008202821328

Optimal flow control using a POD-based reduced-order model
journal, June 2016

  • Tallet, Alexandra; Allery, Cyrille; Leblond, Cédric
  • Numerical Heat Transfer, Part B: Fundamentals, Vol. 70, Issue 1
  • DOI: 10.1080/10407790.2016.1173472

Data-assisted reduced-order modeling of extreme events in complex dynamical systems
journal, May 2018

Analysis of finite difference schemes for unsteady Navier-Stokes equations in vorticity formulation
journal, May 2002

Non-intrusive reduced order modeling of unsteady flows using artificial neural networks with application to a combustion problem
journal, May 2019

Two-level discretizations of nonlinear closure models for proper orthogonal decomposition
journal, January 2011

Proper orthogonal decomposition closure models for turbulent flows: A numerical comparison
journal, September 2012

  • Wang, Zhu; Akhtar, Imran; Borggaard, Jeff
  • Computer Methods in Applied Mechanics and Engineering, Vol. 237-240
  • DOI: 10.1016/j.cma.2012.04.015

Model identification of reduced order fluid dynamics systems using deep learning: Model identification in fluid dynamics using deep learning
journal, August 2017

  • Wang, Z.; Xiao, D.; Fang, F.
  • International Journal for Numerical Methods in Fluids, Vol. 86, Issue 4
  • DOI: 10.1002/fld.4416

An evolve-then-filter regularized reduced order model for convection-dominated flows: EVOLVE-THEN-FILTER REGULARIZED REDUCED ORDER MODEL
journal, February 2017

  • Wells, D.; Wang, Z.; Xie, X.
  • International Journal for Numerical Methods in Fluids, Vol. 84, Issue 10
  • DOI: 10.1002/fld.4363

Neural networks: applications in industry, business and science
journal, March 1994

  • Widrow, Bernard; Rumelhart, David E.; Lehr, Michael A.
  • Communications of the ACM, Vol. 37, Issue 3
  • DOI: 10.1145/175247.175257

Non-intrusive reduced order modelling of the Navier–Stokes equations
journal, August 2015

  • Xiao, D.; Fang, F.; Buchan, A. G.
  • Computer Methods in Applied Mechanics and Engineering, Vol. 293
  • DOI: 10.1016/j.cma.2015.05.015

A domain decomposition non-intrusive reduced order model for turbulent flows
journal, March 2019

Data-Driven Filtered Reduced Order Modeling of Fluid Flows
journal, January 2018

  • Xie, X.; Mohebujjaman, M.; Rebholz, L. G.
  • SIAM Journal on Scientific Computing, Vol. 40, Issue 3
  • DOI: 10.1137/17M1145136

Approximate deconvolution reduced order modeling
journal, January 2017

  • Xie, Xuping; Wells, David; Wang, Zhu
  • Computer Methods in Applied Mechanics and Engineering, Vol. 313
  • DOI: 10.1016/j.cma.2016.10.005

Numerical analysis of the Leray reduced order model
journal, January 2018

  • Xie, Xuping; Wells, David; Wang, Zhu
  • Journal of Computational and Applied Mathematics, Vol. 328
  • DOI: 10.1016/j.cam.2017.06.026

Forecasting with artificial neural networks:
journal, March 1998

    Sort by:
    [ × clear filter / sort ]

    Works referencing / citing this record:

    A deep learning enabler for nonintrusive reduced order modeling of fluid flows
    journal, August 2019

    • Pawar, S.; Rahman, S. M.; Vaddireddy, H.
    • Physics of Fluids, Vol. 31, Issue 8
    • DOI: 10.1063/1.5113494

    Nonintrusive reduced order modeling framework for quasigeostrophic turbulence
    journal, November 2019

    A deep learning enabler for non-intrusive reduced order modeling of fluid flows
    text, January 2019

      Sort by:
      [ × clear filter / sort ]

      Similar Records in DOE PAGES and OSTI.GOV collections: