Abstract
Many reduced-order models are neither robust with respect to parameter changes nor cost-effective enough for handling the nonlinear dependence of complex dynamical systems. In this study, we put forth a robust machine learning framework for projection-based reduced-order modeling of such nonlinear and nonstationary systems. As a demonstration, we focus on a nonlinear advection-diffusion system given by the viscous Burgers equation, which is a prototypical setting of more realistic fluid dynamics applications due to its quadratic nonlinearity. In our proposed methodology the effects of truncated modes are modeled using a single layer feed-forward neural network architecture. The neural network architecture is trained by utilizing both the Bayesian regularization and extreme learning machine approaches, where the latter one is found to be more computationally efficient. A significant emphasis is laid on the selection of basis functions through the use of both Fourier bases and proper orthogonal decomposition. It is shown that the proposed model yields significant improvements in accuracy over the standard Galerkin projection methodology with a negligibly small computational overhead and provide reliable predictions with respect to parameter changes.
Similar content being viewed by others
References
Akhtar, I., Borggaard, J., Burns, J.A., Imtiaz, H., Zietsman, L.: Using functional gains for effective sensor location in flow control: a reduced-order modelling approach. J. Fluid Mech. 781, 622–656 (2015)
Akhtar, I., Wang, Z., Borggaard, J., Iliescu, T.: A new closure strategy for proper orthogonal decomposition reduced-order models. J. Comput. Nonlinear Dyn. 7(3), 034,503 (2012)
Amsallem, D., Farhat, C.: Interpolation method for adapting reduced-order models and application to aeroelasticity. AIAA J. 46(7), 1803–1813 (2008)
Amsallem, D., Farhat, C.: Stabilization of projection-based reduced-order models. Int. J. Numer. Methods Eng. 91(4), 358–377 (2012)
Antoulas, A.C.: Approximation of Large-Scale Dynamical Systems. SIAM, Philadelphia (2005)
Aubry, N., Holmes, P., Lumley, J.L., Stone, E.: The dynamics of coherent structures in the wall region of a turbulent boundary layer. J. Fluid Mech. 192(1), 115–173 (1988)
Balajewicz, M., Dowell, E.H.: Stabilization of projection-based reduced order models of the Navier–Stokes. Nonlinear Dyn. 70(2), 1619–1632 (2012)
Banyay, G.A., Ahmadpoor, M., Brigham, J.C.: Proper orthogonal decomposition based reduced order modeling of the very high temperature reactor lower plenum hydrodynamics. In: ASME 2014 4th Joint US-European Fluids Engineering Division Summer Meeting Collocated with the ASME 2014 12th International Conference on Nanochannels, Microchannels, and Minichannels, pp. V01DT27A013–V01DT27A013. American Society of Mechanical Engineers (2014)
Benner, P., Gugercin, S., Willcox, K.: A survey of projection-based model reduction methods for parametric dynamical systems. SIAM Rev. 57, 483–531 (2015)
Benosman, M., Borggaard, J., San, O., Kramer, B.: Learning-based robust stabilization for reduced-order models of 2D and 3D Boussinesq equations. Appl. Math. Model. 49, 162–181 (2017)
Benosman, M., Kramer, B., Boufounos, P.T., Grover, P.: Learning-based reduced order model stabilization for partial differential equations: application to the coupled Burgers’ equation. In: American Control Conference (ACC), 2016, pp. 1673–1678. IEEE (2016)
Bergmann, M., Bruneau, C.H., Iollo, A.: Improvement of reduced order modeling based on POD. Computational Fluid Dynamics 2008, 779–784 (2009)
Borggaard, J., Hay, A., Pelletier, D.: Interval-based reduced order models for unsteady fluid flow. Int. J. Numer. Anal. Model. 4(3-4), 353–367 (2007)
Borggaard, J., Iliescu, T., Wang, Z.: Artificial viscosity proper orthogonal decomposition. Math. Comput. Model. 53(1), 269–279 (2011)
Borggaard, J., Wang, Z., Zietsman, L.: A goal-oriented reduced-order modeling approach for nonlinear systems. Comput. Math. Appl. 71(11), 2155–2169 (2016)
Buffoni, M., Camarri, S., Iollo, A., Salvetti, M.V.: Low-dimensional modelling of a confined three-dimensional wake flow. J. Fluid Mech. 569, 141–150 (2006)
Bui-Thanh, T., Willcox, K., Ghattas, O., van Bloemen Waanders, B.: Goal-oriented, model-constrained optimization for reduction of large-scale systems. J. Comput. Phys. 224(2), 880–896 (2007)
Carlberg, K., Farhat, C.: A low-cost, goal-oriented ‘compact proper orthogonal decomposition’ basis for model reduction of static systems. Int. J. Numer. Methods Eng. 86(3), 381–402 (2011)
Cazemier, W.: Proper Orthogonal Decomposition and Low Dimensional Models for Turbulent Flows. Groningen (1997)
Cazemier, W., Verstappen, R., Veldman, A.: Proper orthogonal decomposition and low-dimensional models for driven cavity flows. Phys. Fluids (1994-present) 10 (7), 1685–1699 (1998)
Cordier, L., Majd, E., Abou, B., Favier, J.: Calibration of POD reduced-order models using Tikhonov regularization. Int. J. Numer. Methods Fluids 63(2), 269–296 (2010)
Dawson, C.W., Wilby, R.: An artificial neural network approach to rainfall-runoff modelling. Hydrol. Sci. J. 43(1), 47–66 (1998)
Demuth, H.B., Beale, M.H., De Jess, O., Hagan, M.T.: Neural Network Design. Martin Hagan (2014)
Dyke, S., Spencer, B. Jr, Sain, M., Carlson, J.: Modeling and control of magnetorheological dampers for seismic response reduction. Smart Mater. Struct. 5 (5), 565 (1996)
Efe, M., Debiasi, M., Yan, P., Ozbay, H., Samimy, M.: Control of subsonic cavity flows by neural networks-analytical models and experimental validation. In: 43rd AIAA Aerospace Sciences Meeting and Exhibit, p. 294 (2005)
Efe, M.O., Debiasi, M., Ozbay, H., Samimy, M.: Modeling of subsonic cavity flows by neural networks. In: Proceedings of the IEEE International Conference on Mechatronics, 2004. ICM’04, pp. 560–565. IEEE (2004)
El Majd, B.A., Cordier, L.: New regularization method for calibrated POD reduced-order models. Math. Model. Anal. 21(1), 47–62 (2016)
Faller, W.E., Schreck, S.J.: Unsteady fluid mechanics applications of neural networks. J. Aircr. 34(1), 48–55 (1997)
Fang, F., Pain, C., Navon, I., Gorman, G., Piggott, M., Allison, P., Farrell, P., Goddard, A.: A POD reduced order unstructured mesh ocean modelling method for moderate Reynolds number flows. Ocean Model. 28(1), 127–136 (2009)
Foresee, F.D., Hagan, M.T.: Gauss-Newton approximation to Bayesian learning. In: International Conference on Neural Networks, 1997, vol. 3, pp. 1930–1935. IEEE (1997)
Fortuna, L., Nunnari, G., Gallo, A.: Model Order Reduction Techniques with Applications in Electrical Engineering. Springer Science & Business Media, Berlin (2012)
Freund, R.W.: Reduced-order modeling techniques based on Krylov subspaces and their use in circuit simulation. In: Applied and Computational Ccontrol, Signals, and Circuits, pp. 435–498. Springer (1999)
Gaspard, P.: Chaos, Scattering and Statistical Mechanics, vol. 9. Cambridge University Press, Cambridge (2005)
Gillies, E.: Low-dimensional characterization and control of non-linear wake flows. Ph.D. thesis, PhD. Dissertation, University of Glasgow, Scotland (1995)
Gillies, E.: Low-dimensional control of the circular cylinder wake. J. Fluid Mech. 371, 157–178 (1998)
Gillies, E.: Multiple sensor control of vortex shedding. AIAA J. 39(4), 748–750 (2001)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT press, Cambridge (2016)
Hagan, M.T., Menhaj, M.B.: Training feedforward networks with the Marquardt algorithm. IEEE Trans. Neural Netw. 5(6), 989–993 (1994)
Haykin, S.S., Haykin, S.S., Haykin, S.S., Haykin, S.S.: Neural Networks and Learning Machines, vol. 3. Pearson, Upper Saddle River (2009)
Hocevar, M., Sirok, B., Grabec, I.: Experimental turbulent field modeling by visualization and neural networks. J. Fluids Eng. 126, 316–322 (2004)
Holmes, P., Lumley, J.L., Berkooz, G.: Turbulence, Coherent Structures, Dynamical Systems and Symmetry. Cambridge University Press, Cambridge (1998)
Hotelling, H.: Analysis of a complex of statistical variables into principal components. J. Educ. Psychol. 24(6), 417 (1933)
Huang, G.B., Zhu, Q.Y., Siew, C.K.: Extreme learning machine: theory and applications. Neurocomputing 70(1), 489–501 (2006)
Imtiaz, H., Akhtar, I.: Closure modeling in reduced-order model of Burgers’ equation for control applications. J. Aerosp. Eng. 231(4), 642–656 (2017)
Iollo, A., Lanteri, S., Désidéri, J.A.: Stability properties of POD–Galerkin approximations for the compressible Navier–Stokes equations. Theor. Comput. Fluid Dyn. 13(6), 377–396 (2000)
Kazantzis, N., Kravaris, C., Syrou, L.: A new model reduction method for nonlinear dynamical systems. Nonlinear Dyn. 59(1), 183–194 (2010)
Khibnik, A., Narayanan, S., Jacobson, C., Lust, K.: Analysis of low dimensional dynamics of flow separation. In: Continuation Methods in Fluid Dynamics, vol. 74, pp. 167–178. Vieweg (2000)
Kim, T.W., Valdés, J.B.: Nonlinear model for drought forecasting based on a conjunction of wavelet transforms and neural networks. J. Hydrol. Eng. 8(6), 319–328 (2003)
Kunisch, K., Volkwein, S.: Control of the Burgers equation by a reduced-order approach using proper orthogonal decomposition. J. Optim. Theory Appl. 102(2), 345–371 (1999)
Kunisch, K., Volkwein, S.: Galerkin proper orthogonal decomposition methods for parabolic problems. Numer. Math. 90(1), 117–148 (2001)
Kunisch, K., Volkwein, S.: Optimal snapshot location for computing POD basis functions. ESAIM: Mathematical Modelling and Numerical Analysis 44(3), 509–529 (2010)
Lassila, T., Manzoni, A., Quarteroni, A., Rozza, G.: Model order reduction in fluid dynamics: challenges and perspectives. In: Quarteroni, A., Rozza, G. (eds.) Reduced Order Methods for Modeling and Computational Reduction. Springer, Milano (2013)
Lee, C., Kim, J., Babcock, D., Goodman, R.: Application of neural networks to turbulence control for drag reduction. Phys. Fluids 9(6), 1740–1747 (1997)
Levenberg, K.: A method for the solution of certain non-linear problems in least squares. Q. Appl. Math. 2(2), 164–168 (1944)
Ling, J., Kurzawski, A., Templeton, J.: Reynolds averaged turbulence modelling using deep neural networks with embedded invariance. J. Fluid Mech. 807, 155–166 (2016)
Loève, M.: Probability Theory; Foundations, Random Sequences. D. Van Nostrand Company, New York (1955)
Lorenz, E.N.: Empirical orthogonal functions and statistical weather prediction. Massachusetts Institute of Technology, Department of Meteorology, Cambridge (1956)
Lucia, D.J., Beran, P.S., Silva, W.A.: Reduced-order modeling: new approaches for computational physics. Prog. Aerosp. Sci. 40(1), 51–117 (2004)
Lumley, J.: The structures of inhomogeneous turbulent flow. In: Yaglom, A., Tatarski, V. (eds.) Atmospheric Turbulence and Radio Wave Propagation, pp. 160–178 (1967)
MacKay, D.J.: Bayesian interpolation. Neural Comput. 4(3), 415–447 (1992)
Maleewong, M., Sirisup, S.: On-line and off-line POD assisted projective integral for non-linear problems: a case study with Burgers’ equation. International Journal of Mathematical, Computational, Physical, Electrical and Computer Engineering 5(7), 984–992 (2011)
Marquardt, D.W.: An algorithm for least-squares estimation of nonlinear parameters. J. Soc. Ind. Appl. Math. 11(2), 431–441 (1963)
Maulik, R., San, O.: Explicit and implicit LES closures for Burgers turbulence. J. Comput. Appl. Math. 327, 12–40 (2018)
Moin, P.: Fundamentals of Engineering Numerical Analysis. Cambridge University Press, Cambridge (2010)
Moosavi, A., Stefanescu, R., Sandu, A.: Efficient construction of local parametric reduced order models using machine learning techniques. arXiv:1511.02909 (2015)
Moosavi, A., Stefanescu, R., Sandu, A.: Multivariate predictions of local reduced-order-model errors and dimensions. arXiv:1701.03720 (2017)
Narayanan, S., Khibnik, A., Jacobson, C., Kevrekedis, Y., Rico-Martinez, R., Lust, K.: Low-dimensional models for active control of flow separation. In: Proceedings of the 1999 IEEE International Conference on Control Applications, 1999, vol. 2, pp. 1151–1156. IEEE (1999)
Nguyen, D., Widrow, B.: Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights. In: 1990 IJCNN International Joint Conference on Neural Networks, 1990, pp. 21–26. IEEE (1990)
Noack, B., Papas, P., Monkewitz, P.: Low-dimensional Galerkin model of a laminar shear-layer. Tech. rep., Tech. Rep. 2002-01. Laboratoire De Mecanique des Fluides, Departement de Genie Mecanique, Ecole Polytechnique Fédérale de Lausanne, Switzerland (2002)
Noack, B.R., Afanasiev, K., Morzyński, M., Tadmor, G., Thiele, F.: A hierarchy of low-dimensional models for the transient and post-transient cylinder wake. J. Fluid Mech. 497, 335–363 (2003)
Noack, B.R., Morzynski, M., Tadmor, G.: Reduced-Order Modelling for Flow Control, vol. 528. Springer, Berlin (2011)
Pinnau, R.: Model reduction via proper orthogonal decomposition. Model Order Reduction: Theory, Research Aspects and Applications 13, 95–109 (2008)
Raissi, M., Perdikaris, P., Karniadakis, G.E.: Physics informed deep learning (Part I): data-driven discovery of nonlinear partial differential equations. arXiv:1711.10561 (2017)
Raissi, M., Perdikaris, P., Karniadakis, G.E.: Physics informed deep learning (Part II): data-driven discovery of nonlinear partial differential equations. arXiv:1711.10566 (2017)
Ravindran, S.S.: A reduced-order approach for optimal control of fluids using proper orthogonal decomposition. Int. J. Numer. Methods Fluids 34(5), 425–448 (2000)
Rowley, C.W.: Model reduction for fluids, using balanced proper orthogonal decomposition. Int. J. Bifurc. Chaos 15(03), 997–1013 (2005)
Rowley, C.W., Dawson, S.T.: Model reduction for flow analysis and control. Annu. Rev. Fluid Mech. 49, 387–417 (2017)
Roychowdhury, J.: Reduced-order modeling of time-varying systems. IEEE Trans. Circuits Syst. II, Analog Digit. Signal Process. 46(10), 1273–1288 (1999)
Sahan, R., Koc-Sahan, N., Albin, D., Liakopoulos, A.: Artificial neural network-based modeling and intelligent control of transitional flows. In: Proceedings of the 1997 IEEE International Conference on Control Applications, 1997, pp. 359–364. IEEE (1997)
San, O., Iliescu, T.: Proper orthogonal decomposition closure models for fluid flows: Burgers equation. Int. J. Numer. Anal. Model. 5, 217–237 (2014)
San, O., Iliescu, T.: A stabilized proper orthogonal decomposition reduced-order model for large scale quasigeostrophic ocean circulation. Adv. Comput. Math. 41(5), 1289–1319 (2015)
Schmid, P.J.: Dynamic mode decomposition of numerical and experimental data. J. Fluid Mech. 656, 5–28 (2010)
Serre, D.: Matrices: Theory and Applications. Springer, New York (2002)
Silveira, L.M., Kamon, M., White, J.: Efficient reduced-order modeling of frequency-dependent coupling inductances associated with 3-D interconnect structures. IEEE Transactions on Components, Packaging, and Manufacturing Technology: Part B 19(2), 283–288 (1996)
Sirisup, S., Karniadakis, G.E.: A spectral viscosity method for correcting the long-term behavior of POD models. J. Comput. Phys. 194(1), 92–116 (2004)
Sirovich, L.: Turbulence and the dynamics of coherent structures. I-Coherent structures. II-symmetries and transformations. III-dynamics and scaling. Q. Appl. Math. 45, 561–571 (1987)
Taira, K., Brunton, S.L., Dawson, S., Rowley, C.W., Colonius, T., McKeon, B.J., Schmidt, O.T., Gordeyev, S., Theofilis, V., Ukeiley, L.S.: Modal analysis of fluid flows: an overview. AIAA J. 55(12), 4013–4041 (2017)
Ullmann, S., Lang, J.: A POD-Galerkin reduced model with updated coefficients for Smagorinsky LES. In: V European Conference on Computational Fluid Dynamics, ECCOMAS CFD, p. 2010 (2010)
Wang, Z.: Reduced-order modeling of complex engineering and geophysical flows: analysis and computations. Ph.D. thesis, Virginia Tech (2012)
Wang, Z., Akhtar, I., Borggaard, J., Iliescu, T.: Two-level discretizations of nonlinear closure models for proper orthogonal decomposition. J. Comput. Phys. 230(1), 126–146 (2011)
Wang, Z., Akhtar, I., Borggaard, J., Iliescu, T.: Proper orthogonal decomposition closure models for turbulent flows: a numerical comparison. Comput. Methods Appl. Mech. Eng. 237, 10–26 (2012)
Weller, J., Lombardi, E., Bergmann, M., Iollo, A.: Numerical methods for low-order modeling of fluid flows based on POD. Int. J. Numer. Methods Fluids 63(2), 249–268 (2010)
Wells, D., Wang, Z., Xie, X., Iliescu, T.: An evolve-then-filter regularized reduced order model for convection-dominated flows. Int. J. Numer. Methods Fluids 84, 598–615 (2017)
Widrow, B., Rumelhart, D.E., Lehr, M.A.: Neural networks: applications in industry, business and science. Commun. ACM 37(3), 93–106 (1994)
Xie, X., Mohebujjaman, M., Rebholz, L., Iliescu, T.: Data-driven filtered reduced order modeling of fluid flows. arXiv:1709.04362 (2017)
Xie, X., Wells, D., Wang, Z., Iliescu, T.: Approximate deconvolution reduced order modeling. Comput. Methods Appl. Mech. Eng. 313, 512–534 (2017)
Zhang, G., Patuwo, B.E., Hu, M.Y.: Forecasting with artificial neural networks: the state of the art. Int. J. Forecast. 14(1), 35–62 (1998)
Acknowledgments
The computing for this project was performed by using resources from the High Performance Computing Center (HPCC) at Oklahoma State University.
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by: Peter Benner
Rights and permissions
About this article
Cite this article
San, O., Maulik, R. Neural network closures for nonlinear model order reduction. Adv Comput Math 44, 1717–1750 (2018). https://doi.org/10.1007/s10444-018-9590-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10444-018-9590-z
Keywords
- Machine learning
- Neural networks
- Extreme learning machine
- Model order reduction
- Projection methods
- Burgers equation