Multi-fidelity bayesian optimization using model-order reduction for viscoplastic structures

Abstract One of the main issues when dealing with the numerical optimization of mechanical structures is the balance between computation time and model accuracy. The work presented herein aims at accelerating global optimization by using the framework of Bayesian optimization on a quantity of interest together with multiple levels of fidelity. These multi-fidelity data are generated from a model-order reduction framework: the LATIN Proper Generalized Decomposition. Within this framework, a reduced-order basis is generated on-the-fly and re-exploited to reduce the computational cost of observations. This strategy is illustrated on two elasto-viscoplastic test-cases for which significant speedups can be observed.

[1]  Pierre Ladevèze,et al.  A door to model reduction in high-dimensional parameter space , 2018, Comptes Rendus Mécanique.

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

[3]  Pierre Ladevèze,et al.  A 3D shock computational strategy for real assembly and shock attenuator , 2002 .

[4]  David Néron,et al.  A model reduction technique based on the PGD for elastic-viscoplastic computational analysis , 2013 .

[5]  Kevin Leyton-Brown,et al.  Sequential Model-Based Optimization for General Algorithm Configuration , 2011, LION.

[6]  H. Zou,et al.  Regularization and variable selection via the elastic net , 2005 .

[7]  A. Nouy.  A priori model reduction through Proper Generalized Decomposition for solving time-dependent partial differential equations , 2010 .

[8]  A. Nouy.  A generalized spectral decomposition technique to solve a class of linear stochastic partial differential equations , 2007 .

[9]  Pierre Ladevèze,et al.  The Reference Point Method, a ``hyperreduction'' technique: Application to PGD-based nonlinear model reduction , 2017 .

[10]  Jonas Mockus,et al.  On Bayesian Methods for Seeking the Extremum , 1974, Optimization Techniques.

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

[12]  M. Bendsøe,et al.  Topology optimization of continuum structures with local stress constraints , 1998 .

[13]  M. Bhattacharyya,et al.  A multi-temporal scale model reduction approach for the computation of fatigue damage , 2018, Computer Methods in Applied Mechanics and Engineering.

[14]  A. O'Hagan,et al.  Predicting the output from a complex computer code when fast approximations are available , 2000 .

[15]  D. Ginsbourger,et al.  A benchmark of kriging-based infill criteria for noisy optimization , 2013, Structural and Multidisciplinary Optimization.

[16]  Adrien Leygue,et al.  The Proper Generalized Decomposition for Advanced Numerical Simulations: A Primer , 2013 .

[17]  Donald R. Jones,et al.  Efficient Global Optimization of Expensive Black-Box Functions , 1998, J. Glob. Optim..

[18]  David Néron,et al.  Integration of PGD-virtual charts into an engineering design process , 2016 .

[19]  Miss A.O. Penney.  (b) , 1974, The New Yale Book of Quotations.

[20]  O. Allix,et al.  Interlaminar interface modelling for the prediction of delamination , 1992 .

[21]  G. Matheron.  Principles of geostatistics , 1963 .

[22]  T. Hughes,et al.  Isogeometric analysis : CAD, finite elements, NURBS, exact geometry and mesh refinement , 2005 .

[23]  P. Duysinx,et al.  Analytical sensitivity analysis using the extended finite element method in shape optimization of bimaterial structures , 2016 .

[24]  J. Chaboche,et al.  Mechanics of Solid Materials , 1990 .

[25]  C. Allery,et al.  Proper general decomposition (PGD) for the resolution of Navier-Stokes equations , 2011, J. Comput. Phys..

[26]  David Dureisseix,et al.  A multi-time-scale strategy for multiphysics problems: Application to poroelasticity , 2003 .

[27]  David Néron,et al.  Multiparametric analysis within the proper generalized decomposition framework , 2012 .

[28]  Zhong-Hua Han,et al.  A New Cokriging Method for Variable-Fidelity Surrogate Modeling of Aerodynamic Data , 2010 .

[29]  G. I. Marchuk.  Optimization Techniques IFIP Technical Conference , 1975 .

[30]  Stefan Görtz,et al.  Alternative Cokriging Method for Variable-Fidelity Surrogate Modeling , 2012 .

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

[32]  Adrien Leygue,et al.  Proper Generalized Decomposition based dynamic data-driven control of thermal processes ☆ , 2012 .

[33]  Matthias De Lozzo.  Substitution de modèle et approche multifidélité en expérimentation numérique , 2015 .

[34]  Roberto Battiti,et al.  Learning and Intelligent Optimization , 2017, Lecture Notes in Computer Science.

[35]  Andy J. Keane,et al.  Multi-fidelity Kriging-assisted structural optimization of whole engine models employing medial meshes , 2019, Structural and Multidisciplinary Optimization.

[36]  R JonesDonald,et al.  Efficient Global Optimization of Expensive Black-Box Functions , 1998 .

[37]  Jean-Antoine Désidéri,et al.  Multifidelity surrogate modeling based on radial basis functions , 2017 .

[38]  Richard J. Beckman,et al.  A Comparison of Three Methods for Selecting Values of Input Variables in the Analysis of Output From a Computer Code , 2000, Technometrics.

[39]  David Dureisseix,et al.  A computational strategy for poroelastic problems with a time interface between coupled physics , 2008 .

[40]  Andy J. Keane,et al.  Optimization using surrogate models and partially converged computational fluid dynamics simulations , 2006, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[41]  Pierre-Alain Boucard,et al.  Approche multirésolution pour l'étude paramétrique d'assemblages par contact et frottement , 2003 .

[42]  L. Champaney,et al.  Large scale applications on parallel computers of a mixed domain decomposition method , 1997 .

[43]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[44]  Seongim Choi,et al.  Two-Level Multi-Fidelity Design Optimization Studies for Supersonic Jets , 2005 .

[45]  David Néron,et al.  Virtual charts of solutions for parametrized nonlinear equations , 2014 .

[46]  Francisco Chinesta,et al.  Efficient mold cooling optimization by using model reduction , 2011 .

[47]  D G Krige,et al.  A statistical approach to some mine valuation and allied problems on the Witwatersrand , 2015 .

[48]  Ralf Zimmermann,et al.  Simplified Cross-Correlation Estimation For Multi-Fidelity Surrogate Cokriging Models , 2010 .

[49]  Kirthevasan Kandasamy,et al.  Multi-fidelity Gaussian Process Bandit Optimisation , 2016, J. Artif. Intell. Res..

[50]  Donald R. Jones,et al.  A Taxonomy of Global Optimization Methods Based on Response Surfaces , 2001, J. Glob. Optim..

[51]  P. Ladevèze,et al.  A multiscale computational approach for contact problems , 2002 .

[52]  Jean-Charles Passieux,et al.  High resolution digital image correlation using proper generalized decomposition: PGD‐DIC , 2012 .

[53]  P. Ladevèze.  Nonlinear Computational Structural Mechanics: New Approaches and Non-Incremental Methods of Calculation , 1998 .

[54]  Ludovic Chamoin,et al.  Non-invasive implementation of nonlinear isogeometric analysis in an industrial FE software , 2019, Engineering Computations.

[55]  Maxime Blanchard.  Méthode global/local non-intrusive pour les simulations cycliques non-linéaires , 2018 .

[56]  Loic Le Gratiet,et al.  Bayesian Analysis of Hierarchical Multifidelity Codes , 2011, SIAM/ASA J. Uncertain. Quantification.

[57]  Stephen J. Wright,et al.  Numerical Optimization , 2018, Fundamental Statistical Inference.

[58]  David Néron,et al.  A rational strategy for the resolution of parametrized problems in the PGD framework , 2013 .

[59]  P. Villon,et al.  Multi-fidelity POD surrogate-assisted optimization: Concept and aero-design study , 2017 .

[60]  David Néron,et al.  Time‐space PGD for the rapid solution of 3D nonlinear parametrized problems in the many‐query context , 2015 .

[61]  Alexander I. J. Forrester,et al.  Multi-fidelity optimization via surrogate modelling , 2007, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[62]  Stefan Görtz,et al.  Hierarchical Kriging Model for Variable-Fidelity Surrogate Modeling , 2012 .

[63]  Qatu,et al.  Shape Optimization by the Homogenization Method. Applied Mathematical Sciences, Vol 146 , 2003 .

[64]  G. Allaire,et al.  Shape optimization by the homogenization method , 1997 .

[65]  P. Ladevèze,et al.  Sur une famille d'algorithmes en mécanique des structures , 1985 .

[66]  Pierre Ladevèze,et al.  A multiple solution method for non-linear structural mechanics , 1998 .

[67]  Pierre-Alain Boucard,et al.  Variable-fidelity modeling of structural analysis of assemblies , 2016, J. Glob. Optim..

[68]  David Néron,et al.  Coupling multi-fidelity kriging and model-order reduction for the construction of virtual charts , 2019, Computational Mechanics.