A robust radial point interpolation method empowered with neural network solvers (RPIM-NNS) for nonlinear solid mechanics

Computer Methods in Applied Mechanics and Engineering, Journal Year: 2024, Volume and Issue: 429, P. 117159 - 117159

Published: June 26, 2024

In this work, we proposed a robust radial point interpolation method empowered with neural network solvers (RPIM-NNS) for solving highly nonlinear solid mechanics problems. It is enabled by via minimizing an energy-based functional loss. The RPIM-NNS has the following key ingredients: (1) uses basis functions (RBFs) displacement at arbitrary points in problem domain, permitting irregular node distributions. (2) Nodes are placed also beyond domain boundary, allowing convenient implementation of boundary conditions both Dirichlet and Neumann types. (3) strain energy integral form as part loss function, ensuring solution stability. (4) A well-developed gradient descendant algorithm machine learning employed to find optimal solution, enabling robustness ease handling material geometrical nonlinearities. (5) compatible parallel computing schemes. performance tested using problems including Cook's membrane 3D twisting rubber problems, demonstrating its remarkable stability robustness. This which seamlessly integrates governing equations computational techniques, offers excellent alternative MATLAB codes made available https://github.com/JinshuaiBai/RPIM_NNS free downloading.

Language: Английский

---

Fundamental Understanding of Heat and Mass Transfer Processes for Physics-Informed Machine Learning-Based Drying Modelling

Energies, Journal Year: 2022, Volume and Issue: 15(24), P. 9347 - 9347

Published: Dec. 9, 2022

Drying is a complex process of simultaneous heat, mass, and momentum transport phenomena with continuous phase changes. Numerical modelling one the most effective tools to mechanistically express different physics drying processes for accurately predicting kinetics understanding morphological changes during drying. However, mathematical computationally very expensive due multiphysics multiscale nature heat mass transfer Physics-informed machine learning (PIML)-based has potential overcome these drawbacks could be an exciting new addition research describing by embedding fundamental laws constraints in models. To develop such novel PIML-based model applications, it necessary have their formulation processes, data-driven knowledge. Based on comprehensive literature review, this paper presents two types information: physics-based information about strategies models applications. The current status limitations are discussed. A sample framework application presented. Finally, challenges addressing PIML optimizing presented at end paper. It expected that manuscript will beneficial further advancing field.

Language: Английский

---

Mixed form based physics-informed neural networks for performance evaluation of two-phase random materials

Engineering Applications of Artificial Intelligence, Journal Year: 2023, Volume and Issue: 127, P. 107250 - 107250

Published: Nov. 6, 2023

Language: Английский

---

Physics-constrained deep learning approach for solving inverse problems in composite laminated plates

Composite Structures, Journal Year: 2024, Volume and Issue: 348, P. 118514 - 118514

Published: Aug. 23, 2024

Language: Английский

---

Geometrically nonlinear bending analysis of laminated thin plates based on classical laminated plate theory and deep energy method

Composite Structures, Journal Year: 2024, Volume and Issue: 344, P. 118314 - 118314

Published: June 25, 2024

Language: Английский

---

Physics-Informed Neural Network (PINN) model for predicting subgrade settlement induced by shield tunnelling beneath an existing railway subgrade

Transportation Geotechnics, Journal Year: 2024, Volume and Issue: unknown, P. 101409 - 101409

Published: Oct. 1, 2024

Language: Английский

---

Physics-Informed Neural Networks for the Structural Analysis and Monitoring of Railway Bridges: A Systematic Review

Mathematics, Journal Year: 2025, Volume and Issue: 13(10), P. 1571 - 1571

Published: May 10, 2025

Physics-informed neural networks (PINNs) offer a mesh-free approach to solving partial differential equations (PDEs) with embedded physical constraints. Although PINNs have gained traction in various engineering fields, their adoption for railway bridge analysis remains under-explored. To address this gap, systematic review was conducted across Scopus and Web of Science (2020–2025), filtering records by relevance, journal impact, language. From an initial pool, 120 articles were selected categorised into nine thematic clusters that encompass computational frameworks, hybrid integration conventional solvers, domain decomposition strategies. Through natural language processing (NLP) trend mapping, evidences growing but fragmented research landscape. demonstrate promising capabilities load distribution modelling, structural health monitoring, failure prediction, particularly under dynamic train loads on multi-span bridges. However, methodological gaps persist large-scale simulations, plasticity experimental validation. Future work should focus scalable PINN architectures, refined modelling inelastic behaviours, real-time data assimilation, ensuring robustness generalisability through interdisciplinary collaboration.

Language: Английский

---

A deep difference collocation method and its application in elasticity problems

International Journal of Solids and Structures, Journal Year: 2024, Volume and Issue: 291, P. 112692 - 112692

Published: Feb. 2, 2024

Language: Английский

---

GPINN: Physics-Informed Neural Network with Graph Embedding

2022 International Joint Conference on Neural Networks (IJCNN), Journal Year: 2024, Volume and Issue: unknown, P. 1 - 8

Published: June 30, 2024

Language: Английский

---

Physics-Informed Neural Network for Solving a One-Dimensional Solid Mechanics Problem

Modelling—International Open Access Journal of Modelling in Engineering Science, Journal Year: 2024, Volume and Issue: 5(4), P. 1532 - 1549

Published: Oct. 18, 2024

Our objective in this work is to demonstrate how physics-informed neural networks, a type of deep learning technology, can be utilized examine the mechanical properties helicopter blade. The blade regarded as one-dimensional prismatic cantilever beam that exposed triangular loading, and comprehending its behavior utmost importance aerospace field. PINNs utilize physical information, including differential equations boundary conditions, within loss function network approximate solution. approach determines overall by aggregating losses from equation, data. We employed (PINN) an artificial (ANN) with equivalent hyperparameters solve fourth-order equation. By comparing performance PINN model against analytical solution equation results obtained ANN model, we have conclusively shown exhibits superior accuracy, robustness, computational efficiency when addressing high-order govern physics-based problems. In conclusion, study demonstrates offers alternative for solid mechanics problems applications industry.

Language: Английский

---