Datadriven HOPGD based computational vademecum for welding parameter identification

The paper presents a datadriven framework for parameter identification of welding models. Common identification procedures are based on iterative optimization algorithms which minimize the distance between experimental measures and simulations. The cost of repetitive evaluations of objective functions is prohibitive, especially in welding cases, due to the multiphysics, nonlinear and multiparametric aspects. This is why one proposes to use a novel datadriven approach to improve the efficiency of the inverse identification procedures. Based on a sparse sampling strategy, an a posteriori non-intrusive reduction method, i.e. HOPGD, is used in the offline training stage for constructing the computational vademecum. An online subspace learning method coupled with a global optimization algorithm is proposed for the online search. The efficiency of the proposed method for multiple parameters identification is demonstrated through examples based on a 3D welding model.

[1]  Annamária R. Várkonyi-Kóczy,et al.  Reviewing the novel machine learning tools for materials design , 2017 .

[2]  N. Blal,et al.  Adaptive sparse grid based HOPGD: Toward a nonintrusive strategy for constructing space‐time welding computational vademecum , 2018 .

[3]  P Kerfriden,et al.  Bridging Proper Orthogonal Decomposition methods and augmented Newton-Krylov algorithms: an adaptive model order reduction for highly nonlinear mechanical problems. , 2011, Computer methods in applied mechanics and engineering.

[4]  Adam D. Bull,et al.  Convergence Rates of Efficient Global Optimization Algorithms , 2011, J. Mach. Learn. Res..

[5]  D. Ryckelynck,et al.  A priori hyperreduction method: an adaptive approach , 2005 .

[6]  A. Huerta,et al.  Proper generalized decomposition for parameterized Helmholtz problems in heterogeneous and unbounded domains: Application to harbor agitation , 2015 .

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

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

[9]  P. Holmes,et al.  Turbulence, Coherent Structures, Dynamical Systems and Symmetry , 1996 .

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

[11]  Tamara G. Kolda,et al.  Tensor Decompositions and Applications , 2009, SIAM Rev..

[12]  Francisco Chinesta,et al.  Computational vademecums for real‐time simulation of surgical cutting in haptic environments , 2016 .

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

[14]  P. Michaleris,et al.  Sensitivity analysis and optimization of thermo-elasto-plastic processes with applications to welding side heater design , 2004 .

[15]  Adrien Leygue,et al.  Vademecum‐based GFEM (V‐GFEM): optimal enrichment for transient problems , 2016 .

[16]  Francisco Chinesta,et al.  Recent Advances and New Challenges in the Use of the Proper Generalized Decomposition for Solving Multidimensional Models , 2010 .

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

[18]  Krishna Rajan,et al.  Materials Informatics: The Materials ``Gene'' and Big Data , 2015 .

[19]  Pierre Ladevèze,et al.  Virtual charts for shape optimization of structures , 2013 .

[20]  B. Raghavan,et al.  Identification of material properties using indentation test and shape manifold learning approach , 2015 .

[21]  J. Goldak,et al.  A new finite element model for welding heat sources , 1984 .

[22]  Tamara G. Kolda,et al.  Optimization by Direct Search: New Perspectives on Some Classical and Modern Methods , 2003, SIAM Rev..

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

[24]  Francisco Chinesta,et al.  Non-intrusive Sparse Subspace Learning for Parametrized Problems , 2019 .

[25]  Laurent Stainier,et al.  Data-based derivation of material response , 2018 .

[26]  Ye Lu,et al.  Multi-parametric space-time computational vademecum for parametric studies: Application to real time welding simulations , 2018 .

[27]  Francisco Chinesta,et al.  A new family of solvers for some classes of multidimensional partial differential equations encountered in kinetic theory modeling of complex fluids , 2006 .

[28]  Vladimir Luzin,et al.  Comprehensive numerical analysis of a three-pass bead-in-slot weld and its critical validation using neutron and synchrotron diffraction residual stress measurements , 2012 .

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

[30]  Anthony T. Patera,et al.  A Priori Convergence Theory for Reduced-Basis Approximations of Single-Parameter Elliptic Partial Differential Equations , 2002, J. Sci. Comput..

[31]  Trenton Kirchdoerfer,et al.  Data‐driven computing in dynamics , 2017, 1706.04061.

[32]  Alain Combescure,et al.  Efficient hyper reduced-order model (HROM) for parametric studies of the 3D thermo-elasto-plastic calculation , 2015 .

[33]  P. Ladevèze,et al.  A large time increment approach for cyclic viscoplasticity , 1993 .

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

[35]  Icíar Alfaro,et al.  Computational vademecums for the real-time simulation of haptic collision between nonlinear solids , 2015 .

[36]  A. Ammar,et al.  PGD-Based Computational Vademecum for Efficient Design, Optimization and Control , 2013, Archives of Computational Methods in Engineering.

[37]  C. Farhat,et al.  Interpolation Method for Adapting Reduced-Order Models and Application to Aeroelasticity , 2008 .

[38]  Alain Combescure,et al.  Efficient hyper‐reduced‐order model (HROM) for thermal analysis in the moving frame , 2017 .

[39]  Ye Lu,et al.  Space–time POD based computational vademecums for parametric studies: application to thermo-mechanical problems , 2018, Adv. Model. Simul. Eng. Sci..

[40]  Liang Meng,et al.  An objective meta-modeling approach for indentation-based material characterization , 2017 .

[41]  Siamak Niroomandi,et al.  Model order reduction for hyperelastic materials , 2010 .

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

[43]  H. Hotelling.  Analysis of a complex of statistical variables into principal components. , 1933 .

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