Salvato in:
Dettagli Bibliografici
Autori principali: Ben-Yelun, Ismael, Irastorza-Valera, Luis, Saucedo-Mora, Luis, Montáns, Francisco Javier, Chinesta, Francisco
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:https://arxiv.org/abs/2310.20056
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910456064507904
author Ben-Yelun, Ismael
Irastorza-Valera, Luis
Saucedo-Mora, Luis
Montáns, Francisco Javier
Chinesta, Francisco
author_facet Ben-Yelun, Ismael
Irastorza-Valera, Luis
Saucedo-Mora, Luis
Montáns, Francisco Javier
Chinesta, Francisco
contents In the emerging field of mechanical metamaterials, using periodic lattice structures as a primary ingredient is relatively frequent. However, the choice of aperiodic lattices in these structures presents unique advantages regarding failure, e.g., buckling or fracture, because avoiding repeated patterns prevents global failures, with local failures occurring in turn that can beneficially delay structural collapse. Therefore, it is expedient to develop models for computing efficiently the effective mechanical properties in lattices from different general features while addressing the challenge of presenting topologies (or graphs) of different sizes. In this paper, we develop a deep learning model to predict energetically-equivalent mechanical properties of linear elastic lattices effectively. Considering the lattice as a graph and defining material and geometrical features on such, we show that Graph Neural Networks provide more accurate predictions than a dense, fully connected strategy, thanks to the geometrically induced bias through graph representation, closer to the underlying equilibrium laws from mechanics solved in the direct problem. Leveraging the efficient forward-evaluation of a vast number of lattices using this surrogate enables the inverse problem, i.e., to obtain a structure having prescribed specific behavior, which is ultimately suitable for multiscale structural optimization problems.
format Preprint
id arxiv_https___arxiv_org_abs_2310_20056
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle On the data-driven description of lattice materials mechanics
Ben-Yelun, Ismael
Irastorza-Valera, Luis
Saucedo-Mora, Luis
Montáns, Francisco Javier
Chinesta, Francisco
Numerical Analysis
In the emerging field of mechanical metamaterials, using periodic lattice structures as a primary ingredient is relatively frequent. However, the choice of aperiodic lattices in these structures presents unique advantages regarding failure, e.g., buckling or fracture, because avoiding repeated patterns prevents global failures, with local failures occurring in turn that can beneficially delay structural collapse. Therefore, it is expedient to develop models for computing efficiently the effective mechanical properties in lattices from different general features while addressing the challenge of presenting topologies (or graphs) of different sizes. In this paper, we develop a deep learning model to predict energetically-equivalent mechanical properties of linear elastic lattices effectively. Considering the lattice as a graph and defining material and geometrical features on such, we show that Graph Neural Networks provide more accurate predictions than a dense, fully connected strategy, thanks to the geometrically induced bias through graph representation, closer to the underlying equilibrium laws from mechanics solved in the direct problem. Leveraging the efficient forward-evaluation of a vast number of lattices using this surrogate enables the inverse problem, i.e., to obtain a structure having prescribed specific behavior, which is ultimately suitable for multiscale structural optimization problems.
title On the data-driven description of lattice materials mechanics
topic Numerical Analysis
url https://arxiv.org/abs/2310.20056