Learning slosh dynamics by means of data

In this work we study several learning strategies for fluid sloshing problems based on data. In essence, a reduced-order model of the dynamics of the free surface motion of the fluid is developed under rigorous thermodynamics settings. This model is extracted from data by exploring several strategies. First, a linear one, based on the employ of Proper Orthogonal Decomposition techniques is analyzed. Second, a strategy based on the employ of Locally Linear Embedding is studied. Finally, Topological Data Analysis is employed to the same end. All the three distinct possibilities rely on a numerical integration scheme to advance the dynamics in time. This thermodynamically consistent integrator is developed on the basis of the General Equation for Non-Equilibrium Reversible–Irreversible Coupling, GENERIC [M. Grmela and H.C Oettinger (1997). Phys. Rev. E. 56 (6): 6620–6632], framework so as to guarantee the satisfaction of first principles (particularly, the laws of thermodynamics). We show how the resulting method employs a few degrees of freedom, while it allows for a realistic reconstruction of the fluid dynamics of sloshing processes under severe real-time constraints. The proposed method is shown to run faster than real time in a standard laptop.

[1]  Marcelo Epstein,et al.  The Geometrical Language of Continuum Mechanics , 2010 .

[2]  Connor Schenck,et al.  SPNets: Differentiable Fluid Dynamics for Deep Neural Networks , 2018, CoRL.

[3]  Pep Español,et al.  Consistent scaling of thermal fluctuations in smoothed dissipative particle dynamics. , 2009, The Journal of chemical physics.

[4]  Francisco Chinesta,et al.  Hybrid constitutive modeling: data-driven learning of corrections to plasticity models , 2018, International Journal of Material Forming.

[5]  Wei Chen,et al.  A framework for data-driven analysis of materials under uncertainty: Countering the curse of dimensionality , 2017 .

[6]  Vin de Silva,et al.  On the Local Behavior of Spaces of Natural Images , 2007, International Journal of Computer Vision.

[7]  Markus H. Gross,et al.  Particle-based fluid simulation for interactive applications , 2003, SCA '03.

[8]  Hans Christian Öttinger,et al.  General projection operator formalism for the dynamics and thermodynamics of complex fluids , 1998 .

[9]  H. C. Öttinger.  Beyond Equilibrium Thermodynamics: Öttinger/Beyond , 2005 .

[10]  H. Tran,et al.  Modeling and control of physical processes using proper orthogonal decomposition , 2001 .

[11]  Pep Español,et al.  Statistical Mechanics of Coarse-Graining , 2004 .

[12]  K. Willcox,et al.  Data-driven operator inference for nonintrusive projection-based model reduction , 2016 .

[13]  Ignacio Romero,et al.  Algorithms for coupled problems that preserve symmetries and the laws of thermodynamics: Part I: Monolithic integrators and their application to finite strain thermoelasticity , 2010 .

[14]  Steven L. Brunton,et al.  Dynamic Mode Decomposition with Control , 2014, SIAM J. Appl. Dyn. Syst..

[15]  Joshua L. Proctory,et al.  Generalizing Koopman Theory to Allow for Inputs and Control , 2018, SIAM journal on applied dynamical systems.

[16]  E. Munch.  A User's Guide to Topological Data Analysis , 2017, J. Learn. Anal..

[17]  Ignacio Romero,et al.  A Characterization of Conserved Quantities in Non-Equilibrium Thermodynamics , 2013, Entropy.

[18]  Giovanni Samaey,et al.  Equation-free modeling , 2010, Scholarpedia.

[19]  Alessandro Alla,et al.  Nonlinear Model Order Reduction via Dynamic Mode Decomposition , 2016, SIAM J. Sci. Comput..

[20]  Markus H. Gross,et al.  Deep Fluids: A Generative Network for Parameterized Fluid Simulations , 2018, Comput. Graph. Forum.

[21]  Steven L. Brunton,et al.  Dynamic mode decomposition - data-driven modeling of complex systems , 2016 .

[22]  Francisco Chinesta,et al.  Data-driven non-linear elasticity: constitutive manifold construction and problem discretization , 2017 .

[23]  Francisco Chinesta,et al.  A Manifold Learning Approach to Data-Driven Computational Elasticity and Inelasticity , 2016, Archives of Computational Methods in Engineering.

[24]  Lior Horesh,et al.  Should You Derive, Or Let the Data Drive? An Optimization Framework for Hybrid First-Principles Data-Driven Modeling , 2017, 1711.04374.

[25]  S. Brunton,et al.  Discovering governing equations from data by sparse identification of nonlinear dynamical systems , 2015, Proceedings of the National Academy of Sciences.

[26]  Miroslav Grmela.  Multiscale Thermodynamics , 2021, Entropy.

[27]  David González,et al.  Learning Corrections for Hyperelastic Models From Data , 2019, Front. Mater..

[28]  Antonio Huerta,et al.  Viscous flow with large free surface motion , 1988 .

[29]  Barbara Solenthaler,et al.  Data-driven fluid simulations using regression forests , 2015, ACM Trans. Graph..

[30]  Steven L. Brunton,et al.  Generalizing Koopman Theory to Allow for Inputs and Control , 2016, SIAM J. Appl. Dyn. Syst..

[31]  Jan Bender,et al.  Divergence-free smoothed particle hydrodynamics , 2015, Symposium on Computer Animation.

[32]  Steven L. Brunton,et al.  Discovering Conservation Laws from Data for Control , 2018, 2018 IEEE Conference on Decision and Control (CDC).

[33]  L. Wasserman.  Topological Data Analysis , 2016, 1609.08227.

[34]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[35]  J. Monaghan,et al.  Smoothed particle hydrodynamics: Theory and application to non-spherical stars , 1977 .

[36]  Miroslav Grmela,et al.  Dynamics and thermodynamics of complex fluids. I. Development of a general formalism , 1997 .

[37]  Connor Schenck,et al.  Perceiving and reasoning about liquids using fully convolutional networks , 2017, Int. J. Robotics Res..

[38]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[39]  Ignacio Romero,et al.  Thermodynamically consistent time‐stepping algorithms for non‐linear thermomechanical systems , 2009 .

[40]  David González,et al.  Thermodynamically consistent data-driven computational mechanics , 2018, Continuum Mechanics and Thermodynamics.

[41]  Uri Shaham,et al.  Dynamic Mode Decomposition , 2013 .

[42]  H. Ch. Öttinger,et al.  Beyond Equilibrium Thermodynamics , 2005 .

[43]  Trenton Kirchdoerfer,et al.  Data-driven computational mechanics , 2015, 1510.04232.

[44]  Francisco Chinesta,et al.  A Multidimensional Data-Driven Sparse Identification Technique: The Sparse Proper Generalized Decomposition , 2018, Complex..

[45]  Connor Schenck,et al.  Reasoning About Liquids via Closed-Loop Simulation , 2017, Robotics: Science and Systems.

[46]  Christopher K. I. Williams.  Prediction with Gaussian Processes: From Linear Regression to Linear Prediction and Beyond , 1999, Learning in Graphical Models.

[47]  Marino Arroyo,et al.  Nonlinear manifold learning for model reduction in finite elastodynamics , 2013 .