242 citations · 1.2k across the 28 of their papers we have counts for
4 papers · 1 filter
A graph-based probabilistic geometric deep learning framework with online enforcement of physical constraints to predict the criticality of defects in porous materials
Vasilis Krokos, Stéphane P. A. Bordas, Pierre Kerfriden
Stress prediction in porous materials and structures is challenging due to the high computational cost associated with direct numerical simulations. Convolutional Neural Network (C…
Local uncovering of unresolved physics in structural mechanics: seamless choice of modelling resolution using a CutFEM level-set approach
Ehsan Mikaeili, Pierre Kerfriden, Susanne Claus
In this paper, we present a robust and efficient unfitted concurrent multiscale method for continuum-continuum coupling, based on the Cut Finite Element Method (CutFEM). The comput…
Concurrent multiscale analysis without meshing: Microscale representation with CutFEM and micro/macro model blending
Ehsan Mikaeili, Susanne Claus, Pierre Kerfriden
In this paper, we develop a novel unfitted multiscale framework that combines two separate scales represented by only one single computational mesh. Our framework relies on a mixed…
A Bayesian multiscale CNN framework to predict local stress fields in structures with microscale features
Vasilis Krokos, Viet Bui Xuan, Stéphane P. A. Bordas +2
Multiscale computational modelling is challenging due to the high computational cost of direct numerical simulation by finite elements. To address this issue, concurrent multiscale…