Dynamic data-driven model reduction: adapting reduced models from incomplete data

This work presents a data-driven online adaptive model reduction approach for systems that undergo dynamic changes. Classical model reduction constructs a reduced model of a large-scale system in an offline phase and then keeps the reduced model unchanged during the evaluations in an online phase; however, if the system changes online, the reduced model may fail to predict the behavior of the changed system. Rebuilding the reduced model from scratch is often too expensive in time-critical and real-time environments. We introduce a dynamic data-driven adaptation approach that adapts the reduced model from incomplete sensor data obtained from the system during the online computations. The updates to the reduced models are derived directly from the incomplete data, without recourse to the full model. Our adaptivity approach approximates the missing values in the incomplete sensor data with gappy proper orthogonal decomposition. These approximate data are then used to derive low-rank updates to the reduced basis and the reduced operators. In our numerical examples, incomplete data with 30–40 % known values are sufficient to recover the reduced model that would be obtained via rebuilding from scratch.

[1]  Steven L. Brunton,et al.  Nonlinear model reduction for dynamical systems using sparse sensor locations from learned libraries. , 2015, Physical review. E, Statistical, nonlinear, and soft matter physics.

[2]  Charbel Farhat,et al.  Progressive construction of a parametric reduced‐order model for PDE‐constrained optimization , 2014, ArXiv.

[3]  Sébastien Marmin.  Bayesian calibration of computer models with modern Gaussian process emulators , 2018 .

[4]  Karen Willcox,et al.  A surrogate modeling approach to support real-time structural assessment and decision-making , 2014 .

[5]  Karen Willcox,et al.  A Survey of Projection-Based Model Reduction Methods for Parametric Dynamical Systems , 2015, SIAM Rev..

[6]  F. Chinesta,et al.  A Short Review in Model Order Reduction Based on Proper Generalized Decomposition , 2018 .

[7]  Kevin Carlberg,et al.  Decreasing the temporal complexity for nonlinear, implicit reduced-order models by forecasting , 2012, 1209.5455.

[8]  Benjamin Peherstorfer,et al.  Dynamic data-driven reduced-order models , 2015 .

[9]  Karen Willcox,et al.  Methodology for Dynamic Data-Driven Online Flight Capability Estimation , 2015 .

[10]  Benjamin Peherstorfer,et al.  Detecting and Adapting to Parameter Changes for Reduced Models of Dynamic Data-driven Application Systems , 2015, ICCS.

[11]  A. Antoulas,et al.  A Survey of Model Reduction by Balanced Truncation and Some New Results , 2004 .

[12]  Steven L. Brunton,et al.  Compressive Sensing and Low-Rank Libraries for Classification of Bifurcation Regimes in Nonlinear Dynamical Systems , 2013, SIAM J. Appl. Dyn. Syst..

[13]  A J M Ferreira,et al.  MATLAB Codes for Finite Element Analysis , 2020, Solid Mechanics and Its Applications.

[14]  Christian Gogu,et al.  Improving the efficiency of large scale topology optimization through on‐the‐fly reduced order model construction , 2015 .

[15]  K. Willcox,et al.  Interpolation among reduced‐order matrices to obtain parameterized models for design, optimization and probabilistic analysis , 2009 .

[16]  David Galbally,et al.  Non‐linear model reduction for uncertainty quantification in large‐scale inverse problems , 2009 .

[17]  B. Haasdonk,et al.  ONLINE GREEDY REDUCED BASIS CONSTRUCTION USING DICTIONARIES , 2012 .

[18]  R. Zimmermann.  A Locally Parametrized Reduced-Order Model for the Linear Frequency Domain Approach to Time-Accurate Computational Fluid Dynamics , 2014, SIAM J. Sci. Comput..

[19]  Boris Lohmann,et al.  Parametric Model Order Reduction by Matrix Interpolation (Parametrische Ordnungsreduktion mittels Matrixinterpolation). , 2010 .

[20]  Antonio Huerta Cerezuela.  Proper Generalized Decomposition based dynamic data-driven control of thermal processes , 2012 .

[21]  J. F. Doyle.  Thin Plates and Shells , 2020, Encyclopedia of Continuum Mechanics.

[22]  David Amsallem,et al.  Fast local reduced basis updates for the efficient reduction of nonlinear systems with hyper-reduction , 2015, Advances in Computational Mathematics.

[23]  N. Nguyen,et al.  An ‘empirical interpolation’ method: application to efficient reduced-basis discretization of partial differential equations , 2004 .

[24]  E. Ventsel,et al.  Thin Plates and Shells: Theory: Analysis, and Applications , 2001 .

[25]  Max Gunzburger,et al.  POD and CVT-based reduced-order modeling of Navier-Stokes flows , 2006 .

[26]  Lawrence Sirovich,et al.  Karhunen–Loève procedure for gappy data , 1995 .

[27]  Tiangang Cui,et al.  Data‐driven model reduction for the Bayesian solution of inverse problems , 2014, 1403.4290.

[28]  Karen Willcox,et al.  Unsteady Flow Sensing and Estimation via the Gappy Proper Orthogonal Decomposition , 2004 .

[29]  Karen Willcox,et al.  An Offline/Online DDDAS Capability for Self-Aware Aerospace Vehicles , 2013, ICCS.

[30]  Phillip L. Gould.  Thin Plates and Shells , 2013 .

[31]  C. Farhat,et al.  Efficient non‐linear model reduction via a least‐squares Petrov–Galerkin projection and compressive tensor approximations , 2011 .

[32]  Mario Ohlberger,et al.  Error Control for the Localized Reduced Basis Multiscale Method with Adaptive On-Line Enrichment , 2015, SIAM J. Sci. Comput..

[33]  Benjamin Peherstorfer,et al.  Optimal Model Management for Multifidelity Monte Carlo Estimation , 2016, SIAM J. Sci. Comput..

[34]  A. O'Hagan,et al.  Bayesian calibration of computer models , 2001 .

[35]  Siep Weiland,et al.  Missing Point Estimation in Models Described by Proper Orthogonal Decomposition , 2004, IEEE Transactions on Automatic Control.

[36]  Benjamin Peherstorfer,et al.  Online Adaptive Model Reduction for Nonlinear Systems via Low-Rank Updates , 2015, SIAM J. Sci. Comput..

[37]  A. Patera,et al.  Reduced basis approximation and a posteriori error estimation for affinely parametrized elliptic coercive partial differential equations , 2007 .

[38]  M. Brand,et al.  Fast low-rank modifications of the thin singular value decomposition , 2006 .

[39]  Anthony T. Patera,et al.  Port reduction in parametrized component static condensation: approximation and a posteriori error estimation , 2013 .

[40]  Danny C. Sorensen,et al.  Nonlinear Model Reduction via Discrete Empirical Interpolation , 2010, SIAM J. Sci. Comput..

[41]  E. Cueto,et al.  Proper Generalized Decomposition based dynamic data driven inverse identification , 2012, Math. Comput. Simul..

[42]  Benjamin Stamm,et al.  Parameter multi‐domain ‘hp’ empirical interpolation , 2012 .

[43]  Boris Lohmann,et al.  Parametric Model Order Reduction by Matrix Interpolation , 2010, Autom..

[44]  Karen Willcox,et al.  Surrogate Modeling Approach to Support Real-Time Structural Assessment and Decision Making , 2015 .

[45]  Karen Willcox,et al.  Sensitivity analysis of surrogate-based methodology for real time structural assessment , 2015 .

[46]  Oliver Lass,et al.  Reduced order modeling and parameter identification for coupled nonlinear PDE systems , 2014 .

[47]  Benjamin Peherstorfer,et al.  Localized Discrete Empirical Interpolation Method , 2014, SIAM J. Sci. Comput..

[48]  K. Willcox,et al.  Aerodynamic Data Reconstruction and Inverse Design Using Proper Orthogonal Decomposition , 2004 .

[49]  B. Haasdonk,et al.  A reduced basis Landweber method for nonlinear inverse problems , 2015, 1507.05434.

[50]  Dan Wang,et al.  Sublinear Algorithms for Big Data Applications , 2015, SpringerBriefs in Computer Science.

[51]  Charbel Farhat,et al.  Nonlinear model order reduction based on local reduced‐order bases , 2012 .

[52]  Kevin Carlberg,et al.  Adaptive h‐refinement for reduced‐order models , 2014, ArXiv.

[53]  Benjamin Stamm,et al.  Locally Adaptive Greedy Approximations for Anisotropic Parameter Reduced Basis Spaces , 2012, SIAM J. Sci. Comput..

[54]  Charbel Farhat,et al.  An Online Method for Interpolating Linear Parametric Reduced-Order Models , 2011, SIAM J. Sci. Comput..