Physics-guided, physics-informed, and physics-encoded neural networks and operators in scientific computing: Fluid and solid mechanics

SA Faroughi, NM Pawar… - Journal of …, 2024 - asmedigitalcollection.asme.org
Advancements in computing power have recently made it possible to utilize machine
learning and deep learning to push scientific computing forward in a range of disciplines …

Perspective: Machine learning in design for 3D/4D printing

X Sun, K Zhou, F Demoly… - Journal of Applied …, 2024 - asmedigitalcollection.asme.org
Abstract 3D/4D printing offers significant flexibility in manufacturing complex structures with
a diverse range of mechanical responses, while also posing critical needs in tackling …

Spiking neural networks for nonlinear regression

A Henkes, JK Eshraghian… - Royal Society Open …, 2024 - royalsocietypublishing.org
Spiking neural networks (SNN), also often referred to as the third generation of neural
networks, carry the potential for a massive reduction in memory and energy consumption …

Prediction and control of fracture paths in disordered architected materials using graph neural networks

K Karapiperis, DM Kochmann - Communications Engineering, 2023 - nature.com
Architected materials typically rely on regular periodic patterns to achieve improved
mechanical properties such as stiffness or fracture toughness. Here we introduce a class of …

Using dropout based active learning and surrogate models in the inverse viscoelastic parameter identification of human brain tissue

J Hinrichsen, C Ferlay, N Reiter, S Budday - Frontiers in Physiology, 2024 - frontiersin.org
Inverse mechanical parameter identification enables the characterization of ultrasoft
materials, for which it is difficult to achieve homogeneous deformation states. However, this …

Liquid Crystal Orientation and Shape Optimization for the Active Response of Liquid Crystal Elastomers

JL Barrera, C Cook, E Lee, K Swartz, D Tortorelli - Polymers, 2024 - mdpi.com
Liquid crystal elastomers (LCEs) are responsive materials that can undergo large reversible
deformations upon exposure to external stimuli, such as electrical and thermal fields …

On the implementation in Abaqus of the global–local iterative coupling and acceleration techniques

O Bettinotti, S Guinard, E Véron, P Gosselet - Finite Elements in Analysis …, 2024 - Elsevier
This paper presents results and convergence study of the Global–Local Iterative Coupling
through the implementation in the commercial software Abaqus making use of the co …

Generative AI and image based numerical mechanics in wind blade adhesive composites

AW Khan, C Balzani - IOP Conference Series: Materials Science …, 2023 - iopscience.iop.org
Numerical modelling of adhesive composites in wind energy is complicated in part due to
material heterogeneity. Microstructural CT scan fibre composite patterns or representative …

A Perspective on Democratizing Mechanical Testing: Harnessing Artificial Intelligence to Advance Sustainable Material Adoption and Decentralized Manufacturing

CE Athanasiou, X Liu, H Gao - Journal of Applied …, 2024 - asmedigitalcollection.asme.org
Democratized mechanical testing offers a promising solution for enabling the widespread
adoption of recycled and renewably sourced feedstocks. Locally sourced, sustainable …