Deep learning in mechanical metamaterials: from prediction and generation to inverse design
Mechanical metamaterials are meticulously designed structures with exceptional
mechanical properties determined by their microstructures and constituent materials …
mechanical properties determined by their microstructures and constituent materials …
Design, mechanical properties and optimization of lattice structures with hollow prismatic struts
Lattice structures with hollow struts exhibit superior mechanical properties as compared to
solid ones. In this study, we introduce a new type of body-centered cubic (BCC) lattice …
solid ones. In this study, we introduce a new type of body-centered cubic (BCC) lattice …
Deep-learning-based inverse design of three-dimensional architected cellular materials with the target porosity and stiffness using voxelized Voronoi lattices
Architected cellular materials are a class of artificial materials with cellular architecture-
dependent properties. Typically, designing cellular architectures paves the way to generate …
dependent properties. Typically, designing cellular architectures paves the way to generate …
[HTML][HTML] Effective elastic properties of sandwich-structured hierarchical honeycombs: an analytical solution
Sandwich-structured honeycombs (SSHCs) are hierarchical structures comprising
sandwiched cell walls and are known to exhibit enhanced mass-specific properties. Here …
sandwiched cell walls and are known to exhibit enhanced mass-specific properties. Here …
Warren truss inspired hierarchical beams for three dimensional hierarchical truss lattice materials
Networks of beams are a subject of increasing interest to create architected materials with
exceptional mechanical properties and low density. This paper investigates the mechanical …
exceptional mechanical properties and low density. This paper investigates the mechanical …
Deep learning based automated fracture identification in material characterization experiments
N Karathanasopoulos, P Hadjidoukas - Advanced Engineering Informatics, 2024 - Elsevier
In the current work, the automated fracture identification in material testing experiments is
investigated through deep learning convolutional neural network (CNN) techniques. Three …
investigated through deep learning convolutional neural network (CNN) techniques. Three …
Deep learning, deconvolutional neural network inverse design of strut-based lattice metamaterials
F Dos Reis, N Karathanasopoulos - Computational Materials Science, 2024 - Elsevier
Abstract Machine learning techniques have furnished a new paradigm in the modeling and
design of advanced materials, both in the forward prediction of their effective performance …
design of advanced materials, both in the forward prediction of their effective performance …
Machine-learning networks to predict the ultimate axial load and displacement capacity of 3D printed concrete walls with different section geometries
This paper presents details on the machine learning (ML) models for predicting the ultimate
axial load capacity and ultimate displacement capacity of 3D printed concrete (3DPC) walls …
axial load capacity and ultimate displacement capacity of 3D printed concrete (3DPC) walls …
Modeling and design of architected structures and metamaterials assisted with artificial intelligence
A Mora, G Herrera-Ramos… - Materials Research …, 2024 - iopscience.iop.org
Architected structures and metamaterials have attracted the attention of scientists and
engineers due to the contrast in behavior compared to the base material they are made …
engineers due to the contrast in behavior compared to the base material they are made …
[HTML][HTML] Elastostatics of star-polygon tile-based architectured planar lattices
A panoptic view of architectured planar lattices based on star-polygon tilings was
developed. Four star-polygon-based lattice sub-families, formed of systematically arranged …
developed. Four star-polygon-based lattice sub-families, formed of systematically arranged …