Application of machine learning and deep learning in finite element analysis: a comprehensive review

D Nath, Ankit, DR Neog, SS Gautam - Archives of computational methods …, 2024 - Springer
Abstract Machine learning (ML) has evolved as a technology used in even broader domains,
ranging from spam detection to space exploration, as a result of the boom in available data …

A comparative study on different neural network architectures to model inelasticity

M Rosenkranz, KA Kalina, J Brummund… - … Journal for Numerical …, 2023 - Wiley Online Library
The mathematical formulation of constitutive models to describe the path‐dependent, that is,
inelastic, behavior of materials is a challenging task and has been a focus in mechanics …

[HTML][HTML] Micromechanics-based deep-learning for composites: Challenges and future perspectives

M Mirkhalaf, I Rocha - European Journal of Mechanics-A/Solids, 2024 - Elsevier
During the last few decades, industries such as aerospace and wind energy (among others)
have been remarkably influenced by the introduction of high-performance composites. One …

FE2 Computations with Deep Neural Networks: Algorithmic Structure, Data Generation, and Implementation

H Eivazi, JA Tröger, S Wittek, S Hartmann… - Mathematical and …, 2023 - mdpi.com
Multiscale FE 2 computations enable the consideration of the micro-mechanical material
structure in macroscopical simulations. However, these computations are very time …

[HTML][HTML] How can machine learning be used for accurate representations and predictions of fracture nucleation in zirconium alloys with hydride populations?

T Hasan, L Capolungo, MA Zikry - APL Materials, 2023 - pubs.aip.org
Zirconium alloys are critical material components of systems subjected to harsh
environments such as high temperatures, irradiation, and corrosion. When exposed to water …

ML-based identification of the interface regions for coupling local and nonlocal models

N Nader, P Diehl, M D'Elia, C Glusa… - arXiv preprint arXiv …, 2024 - arxiv.org
Local-nonlocal coupling approaches combine the computational efficiency of local models
and the accuracy of nonlocal models. However, the coupling process is challenging …

[HTML][HTML] A microstructure-based graph neural network for accelerating multiscale simulations

J Storm, IBCM Rocha, FP van der Meer - Computer Methods in Applied …, 2024 - Elsevier
Simulating the mechanical response of advanced materials can be done more accurately
using concurrent multiscale models than with single-scale simulations. However, the …

Slip tendency analysis from sparse stress and satellite data using physics‐guided deep neural networks

T Poulet, P Behnoudfar - Geophysical Research Letters, 2024 - Wiley Online Library
The significant risk associated with fault reactivation often necessitates slip tendency
analyses for effective risk assessment. However, such analyses are challenging, particularly …

Mechanisms of Component Degradation and Multi-Scale Strategies for Predicting Composite Durability: Present and Future Perspectives

PR Ferreira Rocha, G Fonseca Gonçalves… - Journal of Composites …, 2024 - mdpi.com
Composite materials, valued for their adaptability, face challenges associated with
degradation over time. Characterising their durability through traditional experimental …

Computational homogenization for aerogel-like polydisperse open-porous materials using neural network--based surrogate models on the microscale

A Klawonn, M Lanser, L Mager, A Rege - arXiv preprint arXiv:2403.00571, 2024 - arxiv.org
The morphology of nanostructured materials exhibiting a polydisperse porous space, such
as aerogels, is very open porous and fine grained. Therefore, a simulation of the …