[HTML][HTML] Numerical and experimental crack-tip cohesive zone laws with physics-informed neural networks

H Tran, YF Gao, HB Chew - Journal of the Mechanics and Physics of Solids, 2024 - Elsevier
The cohesive zone law represents the constitutive traction versus separation response
along the crack-tip process zone of a material, which bridges the microscopic fracture …

Learning solutions of thermodynamics-based nonlinear constitutive material models using physics-informed neural networks

S Rezaei, A Moeineddin, A Harandi - Computational Mechanics, 2024 - Springer
We applied physics-informed neural networks to solve the constitutive relations for
nonlinear, path-dependent material behavior. As a result, the trained network not only …

Model-free chemomechanical interfaces: History-dependent damage under transient mass diffusion

L Zhou, W Liu, Y Mao, S Hou - Computer Methods in Applied Mechanics …, 2024 - Elsevier
This paper presents a data-driven framework based on distance functional for chemo-
mechanical cohesive interfaces to capture transient diffusion and resulting interfacial …

Data-driven and physics-based methods to optimize structures against delamination

TR Kumar, M Paggi - Mechanics of Advanced Materials and …, 2024 - Taylor & Francis
Composite materials and multi-material components often fail at their internal
interfaces/adhesive joints, and hence special attention should be given to such catastrophic …

Review of multi‐scale mechanical behavior research on composite solid propellants based on data‐driven approach

B Yuan, H Qiang, X Wang… - Propellants, Explosives …, 2024 - Wiley Online Library
Composite solid propellant is a kind of viscoelastic composite with high filling ratio and multi‐
scale composition characteristics, and its macroscopic mechanical properties strongly …

Deep-green inversion to extract traction-separation relations at material interfaces

C Wei, J Zhang, KM Liechti, C Wu - International Journal of Solids and …, 2022 - Elsevier
The traction-separation relationship of an interface is a critical component to understand and
model the delamination behavior of multi-layer composites in situations where large scale …

Predicting peak tensile stress in mesoscale concrete considering size effects: A data-physical hybrid-driven approach

Z Wang, J Zhang, Y Liu, G Ma, W Huang… - Construction and Building …, 2024 - Elsevier
The size effect and strength discreteness observed in concrete stem primarily from its
mesoscopic heterogeneity. Despite this understanding, establishing a clear relationship …

Recurrent neural network (RNN) and long short-term memory neural network (LSTM) based data-driven methods for identifying cohesive zone law parameters of …

Y Dai, J Wei, F Qin - Materials Today Communications, 2024 - Elsevier
In this paper, we presented three neural network models including deep neural network
(DNN), recurrent neural network (RNN), and long short-term memory neural network …

Determination traction-separation parameters and its sensitivity analysis of bilinear cohesive zone model through experimental and numerical peeling analysis of …

B Jiang, ZS Guo - International Journal of Adhesion and Adhesives, 2024 - Elsevier
The optimization of traction-separation parameters within the cohesive zone model (CZM) is
crucial for accurately simulating electrode peeling failure in lithium-ion batteries. This study …

Learning solution of nonlinear constitutive material models using physics-informed neural networks: COMM-PINN

S Rezaei, A Moeineddin, A Harandi - arXiv preprint arXiv:2304.06044, 2023 - arxiv.org
We applied physics-informed neural networks to solve the constitutive relations for
nonlinear, path-dependent material behavior. As a result, the trained network not only …