7 papers
Equivariant Flow Matching for Symmetry-Breaking Bifurcation Problems
Fleur Hendriks, OndÅej RokoÅ¡, Martin DoÅ¡káŠ+2
Bifurcation phenomena in nonlinear dynamical systems often lead to multiple coexisting stable solutions, particularly in the presence of symmetry breaking. Deterministic machine le…
Auto-Regressive U-Net for Full-Field Prediction of Shrinkage-Induced Damage in Concrete
Liya Gaynutdinova, Petr Havlásek, OndÅej RokoÅ¡ +2
This paper introduces a deep learning approach for predicting time-dependent full-field damage in concrete. The study uses an auto-regressive U-Net model to predict the evolution o…
Homogenization with Guaranteed Bounds via Primal-Dual Physically Informed Neural Networks
Liya Gaynutdinova, Martin DoÅ¡káÅ, OndÅej RokoÅ¡ +1
Physics-informed neural networks (PINNs) have shown promise in solving partial differential equations (PDEs) relevant to multiscale modeling, but they often fail when applied to ma…
Non-uniform pneumatic actuation switches macroscopic properties of elastomeric honeycombs
OndÅej Faltus, Martin DoÅ¡káÅ, Jan Havelka +2
Honeycomb microstructures with circular voids are well known to undergo pattern transformations under macroscopic strain loading. Depending on the biaxiality of the applied strain,…
Wallpaper Group-Based Mechanical Metamaterials: Dataset Including Mechanical Responses
Fleur Hendriks, Vlado Menkovski, Martin DoškáŠ+3
Mechanical metamaterials often exhibit pattern transformations through instabilities, enabling applications in, e.g., soft robotics, sound reduction, and biomedicine. These transfo…
Similarity Equivariant Graph Neural Networks for Homogenization of Metamaterials
Fleur Hendriks, Vlado Menkovski, Martin DoškáŠ+2
Soft, porous mechanical metamaterials exhibit pattern transformations that may have important applications in soft robotics, sound reduction and biomedicine. To design these innova…