A computational framework to establish data-driven constitutive models for time- or path-dependent heterogeneous solids

• Published in: Scientific reports Vol. 11; no. 1; pp. 15916 - 18
• Main Authors: Ge, Weijian, Tagarielli, Vito L.
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 05.08.2021; Nature Publishing Group; Nature Portfolio
• Subjects: 639/301/1034; 639/301/1034/1037; Boundary conditions; Computer applications; Cost control; Homogenization; Humanities and Social Sciences; Machine learning; Mathematical models; Mechanical loading; Mechanical properties; multidisciplinary; Neural networks; Science; Science (multidisciplinary); Simulation; Viscoelasticity

We propose and implement a computational procedure to establish data-driven surrogate constitutive models for heterogeneous materials. We study the multiaxial response of non-linear n-phase composites via Finite Element (FE) simulations and computational homogenisation. Pseudo-random, multiaxial, no...