Physics-informed neural network frameworks for crack simulation based on minimized peridynamic potential energy

DOI10.1016/J.CMA.2023.116430MaRDI QIDQ6153887FDOQ6153887

Authors: Luyuan Ning, Zhenwei Cai, Han Dong, Ying-Zheng Liu, Wei-Zhe Wang 

Publication date: 14 February 2024

Published in: Computer Methods in Applied Mechanics and Engineering (Search for Journal in Brave)

Recommendations

• Solving multi-material problems in solid mechanics using physics-informed neural networks based on domain decomposition technology
• A peridynamic-informed neural network for continuum elastic displacement characterization
• A nonlocal energy‐informed neural network for isotropic elastic solids with cracks under thermomechanical loads
• A nonlocal energy-informed neural network based on peridynamics for elastic solids with discontinuities
• Deep learning phase‐field model for brittle fractures

zbMATH Keywords

transfer learningphysics-informed neural networkscrack initiation and propagationbond-based peridynamic

Mathematics Subject Classification ID

Statistical mechanics, structure of matter (82-XX) Mechanics of deformable solids (74-XX)

Cites Work

• Reformulation of elasticity theory for discontinuities and long-range forces
• Finite element method - The natural approach
• Strong discontinuity embedded approach with standard SOS formulation: element formulation, energy-based crack-tracking strategy, and validations
• Application of a constitutive model for concrete to the analysis of a precast segmental tunnel lining
• An energy approach to the solution of partial differential equations in computational mechanics via machine learning: concepts, implementation and applications
• Hidden fluid mechanics: Learning velocity and pressure fields from flow visualizations
• A generalized bond-based peridynamic model for quasi-brittle materials enriched with bond tension-rotation-shear coupling effects
• Computationally efficient and effective peridynamic model for cracks and fractures in homogeneous and heterogeneous materials
• Solving multi-material problems in solid mechanics using physics-informed neural networks based on domain decomposition technology
• Physics informed neural networks for continuum micromechanics
• A physics-guided neural network framework for elastic plates: comparison of governing equations-based and energy-based approaches
• Physics-informed neural network for modelling the thermochemical curing process of composite-tool systems during manufacture
• Multi-scale deep neural network (MscaleDNN) for solving Poisson-Boltzmann equation in complex domains
• The mixed deep energy method for resolving concentration features in finite strain hyperelasticity
• Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks
• Peridynamics boundary condition treatments via the pseudo-layer enrichment method and variable horizon approach
• A peridynamic-informed neural network for continuum elastic displacement characterization
• A physics-informed neural network technique based on a modified loss function for computational 2D and 3D solid mechanics

Cited In (5)

• Phase-field modeling of fracture with physics-informed deep learning
• Transfer learning enhanced nonlocal energy-informed neural network for quasi-static fracture in rock-like materials
• A nonlocal energy‐informed neural network for isotropic elastic solids with cracks under thermomechanical loads
• Interface crack analysis in 2D bounded dissimilar materials using an enriched physics-informed neural networks
• A nonlocal energy-informed neural network based on peridynamics for elastic solids with discontinuities

This page was built for publication: Physics-informed neural network frameworks for crack simulation based on minimized peridynamic potential energy

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6153887)