AUTHOR=Champaney Victor , Pasquale Angelo , Ammar Amine , Chinesta Francisco 

TITLE=Parametric Curves Metamodelling Based on Data Clustering, Data Alignment, POD-Based Modes Extraction and PGD-Based Nonlinear Regressions

JOURNAL=Frontiers in Materials

VOLUME=Volume 9 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/materials/articles/10.3389/fmats.2022.904707

DOI=10.3389/fmats.2022.904707

ISSN=2296-8016

ABSTRACT=In the context of parametric surrogates, several nontrivial issues arise when a whole curve shall be predicted from given input features. For instance, when considering time series, different sampling or ending times lead to non-aligned curves. This also happens when the curves exhibit a common pattern characterized by critical points at shifted locations (e.g., in physics, the change of phase for a fluid, the elastic-plastic transition or the rupture point for a material). In such cases, classical interpolation methods fail in giving physics-consistent results and appropriate pre-processing steps are required. Moreover, when bifurcations occur into the parametric space, to enhance the accuracy of the surrogate, a coupling with clustering and classification algorithms is needed. In this work we present several methodologies to overcome these matters. We also exploit such surrogates to quantify and propagate uncertainty, furnishing parametric stastistical bounds for the predicted curves. The procedures are exemplified over two problems in Computational Mechanics.