Geometric deep learning for computational mechanics part i: Anisotropic hyperelasticity

NN Vlassis, R Ma, WC Sun - Computer Methods in Applied Mechanics and …, 2020 - Elsevier
We present a machine learning approach that integrates geometric deep learning and
Sobolev training to generate a family of finite strain anisotropic hyperelastic models that …

Theoretical overview of hydraulic fracturing break-down pressure

K Sampath, MSA Perera, PG Ranjith - Journal of Natural Gas Science and …, 2018 - Elsevier
The precise prediction of the break-down pressure is imperative to define the pumping
schedule and the relevant stimulation parameters of a hydraulic fracturing process. A …

[HTML][HTML] A neural network-based enrichment of reproducing kernel approximation for modeling brittle fracture

J Baek, JS Chen - Computer Methods in Applied Mechanics and …, 2024 - Elsevier
Numerical modeling of localizations is a challenging task due to the evolving rough solution
in which the localization paths are not predefined. Despite decades of efforts, there is a need …

RKPM2D: an open-source implementation of nodally integrated reproducing kernel particle method for solving partial differential equations

TH Huang, H Wei, JS Chen, MC Hillman - Computational particle …, 2020 - Springer
We present an open-source software RKPM2D for solving PDEs under the reproducing
kernel particle method (RKPM)-based meshfree computational framework. Compared to …

A naturally stabilized semi-Lagrangian meshfree formulation for multiphase porous media with application to landslide modeling

H Wei, JS Chen, F Beckwith, J Baek - Journal of Engineering …, 2020 - ascelibrary.org
A stabilized meshfree formulation for modeling nonlinear, multiphase porous media with
application to landslide simulation is presented. To effectively capture the hydromechanical …

Peridynamic simulation on fracture mechanical behavior of granite containing a single fissure after thermal cycling treatment

Z Yang, SQ Yang, M Chen - Computers and Geotechnics, 2020 - Elsevier
In this study, the thermal-mechanical fracturing behaviors of granite after thermal cycling
treatment are investigated using the fully coupled ordinary state-based peridynamic method …

A neural network‐enhanced reproducing kernel particle method for modeling strain localization

J Baek, JS Chen, K Susuki - International Journal for Numerical …, 2022 - Wiley Online Library
Modeling the localized intensive deformation in a damaged solid requires highly refined
discretization for accurate prediction, which significantly increases the computational cost …

A deformation-dependent coupled Lagrangian/semi-Lagrangian meshfree hydromechanical formulation for landslide modeling

J Baek, RT Schlinkman, FN Beckwith… - Advanced Modeling and …, 2022 - Springer
The numerical modelling of natural disasters such as landslides presents several
challenges for conventional mesh-based methods such as the finite element method (FEM) …

A hyper-reduction computational method for accelerated modeling of thermal cycling-induced plastic deformations

S Kaneko, H Wei, Q He, JS Chen… - Journal of the Mechanics …, 2021 - Elsevier
For materials under cyclic thermal loadings, temperature and strain rate-dependent creep
deformation can occur due to the thermal expansion mismatch near material interfaces …

A Lagrangian/semi-Lagrangian coupling approach for accelerated meshfree modelling of extreme deformation problems

M Pasetto, J Baek, JS Chen, H Wei, JA Sherburn… - Computer Methods in …, 2021 - Elsevier
In the reproducing kernel particle method (RKPM), the approximation is achieved through
construction of shape functions in the physical domain and the interaction of neighbouring …