A Supervised Learning Framework for Arbitrary Lagrangian-Eulerian Simulations

The Arbitrary Lagrangian-Eulerian (ALE) method is used in a variety of engineering and scientific applications for enabling multi-physics simulations. Unfortunately, the ALE method can suffer from simulation failures that require users to adjust parameters iteratively in order to complete a simulation. In this paper, we present a supervised learning framework for predicting conditions leading to simulation failures. To our knowledge, this is the first time machine learning has been applied to ALE simulations. We propose a novel learning representation for mapping the ALE domain onto a supervised learning formulation. We analyze the predictability of these failures and evaluate our framework using well-known test problems.

[1]  D. Benson.  Computational methods in Lagrangian and Eulerian hydrocodes , 1992 .

[2]  Tzanio V. Kolev,et al.  High-Order Curvilinear Finite Element Methods for Lagrangian Hydrodynamics , 2012, SIAM J. Sci. Comput..

[3]  Mikhail J. Shashkov,et al.  Adaptive reconnection-based arbitrary Lagrangian Eulerian method , 2015, J. Comput. Phys..

[4]  Gao Xiang,et al.  Supervised Methods for Fault Detection in Vehicles , 2010 .

[5]  Julia Ling,et al.  Using Machine Learning to Understand and Mitigate Model Form Uncertainty in Turbulence Models , 2015, 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA).

[6]  Luis M. Camarinha-Matos,et al.  Learning failure recovery knowledge for mechanical assembly , 1996, Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. IROS '96.

[7]  P. Knupp,et al.  Reference Jacobian optimization-based rezone strategies for arbitrary Lagrangian Eulerian methods , 2002 .

[8]  Zhiling Lan,et al.  Adaptive Fault Management of Parallel Applications for High-Performance Computing , 2008, IEEE Transactions on Computers.

[9]  Philippe Pierre Pebay,et al.  The verdict geometric quality library. , 2006 .

[10]  Raghu Machiraju,et al.  An uncertainty-driven approach to vortex analysis using oracle consensus and spatial proximity , 2015, 2015 IEEE Pacific Visualization Symposium (PacificVis).

[11]  Erik E. Santiso,et al.  A general set of order parameters for molecular crystals. , 2011, The Journal of chemical physics.

[12]  Franck Cappello,et al.  Fault prediction under the microscope: A closer look into HPC systems , 2012, 2012 International Conference for High Performance Computing, Networking, Storage and Analysis.

[13]  P. G. Eltgroth,et al.  KULL: LLNL's ASCI Inertial Confinement Fusion Simulation Code , 2000 .

[14]  A. Huerta,et al.  Arbitrary Lagrangian–Eulerian Methods , 2004 .

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

[16]  Jonas A. Zukas,et al.  Introduction to Hydrocodes , 2004 .

[17]  Raghu Machiraju,et al.  Boosting Techniques for Physics‐Based Vortex Detection , 2014, Comput. Graph. Forum.

[18]  Bernhardt L Trout,et al.  Extensions to the likelihood maximization approach for finding reaction coordinates. , 2007, The Journal of chemical physics.

[19]  Veselin Dobrev,et al.  Curvilinear finite elements for Lagrangian hydrodynamics , 2011 .

[20]  Raphaël Loubère,et al.  ReALE: A reconnection-based arbitrary-Lagrangian-Eulerian method , 2010, J. Comput. Phys..

[21]  Ioannis G. Kevrekidis,et al.  Nonlinear dimensionality reduction in molecular simulation: The diffusion map approach , 2011 .

[22]  J. Templeton.  Evaluation of machine learning algorithms for prediction of regions of high Reynolds averaged Navier Stokes uncertainty , 2015 .

[23]  Joseph F. Murray,et al.  Machine Learning Methods for Predicting Failures in Hard Drives: A Multiple-Instance Application , 2005, J. Mach. Learn. Res..