Machine Learning, Low-Rank Approximations and Reduced Order Modeling in Computational Mechanics

• Main Author: Fritzen, Felix (auth)
• Other Authors: Ryckelynck, David (auth)
• Format: Electronic Book Chapter
• Language: English
• Published: MDPI - Multidisciplinary Digital Publishing Institute 2019
• Subjects: History of engineering & technology; supervised machine learning; proper orthogonal decomposition (POD); PGD compression; stabilization; nonlinear reduced order model; gappy POD; symplectic model order reduction; neural network; snapshot proper orthogonal decomposition; 3D reconstruction; microstructure property linkage; nonlinear material behaviour; proper orthogonal decomposition; reduced basis; ECSW; geometric nonlinearity; POD; model order reduction; elasto-viscoplasticity; sampling; surrogate modeling; model reduction; enhanced POD; archive; modal analysis; low-rank approximation; computational homogenization; artificial neural networks; unsupervised machine learning; large strain; reduced-order model; proper generalised decomposition (PGD); a priori enrichment; elastoviscoplastic behavior; error indicator; computational homogenisation; empirical cubature method; nonlinear structural mechanics; reduced integration domain; model order reduction (MOR); structure preservation of symplecticity; heterogeneous data; reduced order modeling (ROM); parameter-dependent model; data science; Hencky strain; dynamic extrapolation; tensor-train decomposition; hyper-reduction; empirical cubature; randomised SVD; machine learning; inverse problem plasticity; proper symplectic decomposition (PSD); finite deformation; Hamiltonian system; DEIM; GNAT
• Online Access: DOAB: download the publication; DOAB: description of the publication

The use of machine learning in mechanics is booming. Algorithms inspired by developments in the field of artificial intelligence today cover increasingly varied fields of application. This book illustrates recent results on coupling machine learning with computational mechanics, particularly for the...