Physics-informed neural networks for friction-involved nonsmooth dynamics problems

Nonlinear Dynamics, Journal Year: 2024, Volume and Issue: 112(9), P. 7159 - 7183

Published: March 19, 2024

Language: Английский

---

Boundary integrated neural networks for 2D elastostatic and piezoelectric problems

International Journal of Mechanical Sciences, Journal Year: 2024, Volume and Issue: 280, P. 109525 - 109525

Published: July 6, 2024

In this paper, we make the first attempt to adopt boundary integrated neural networks (BINNs) for numerical solution of two-dimensional (2D) elastostatic and piezoelectric problems. The proposed BINNs combine artificial with exact integral equations (BIEs) effectively solve value problems based on corresponding partial differential (PDEs). BIEs are utilized localize all unknown physical quantities boundary, which approximated by using resolved via a training process. contrast many traditional network methods domain discretization, present offer several distinct advantages. Firstly, embedding analytical into learning procedure, only need discretize problem domain, reduces number unknowns can lead faster more stable Secondly, operators in original PDEs substituted operators, eliminate additional differentiations (high-order derivatives may instabilities process). Thirdly, loss function contains residuals BIEs, as conditions have been inherently incorporated within formulation. Therefore, there is no necessity employing any weighting functions, commonly used most balance gradients among different objective functions. Extensive experiments show that much easier train usually provide accurate solutions compared methods.

Language: Английский

---

Comprehensive review of deep learning in orthopaedics: Applications, challenges, trustworthiness, and fusion

Artificial Intelligence in Medicine, Journal Year: 2024, Volume and Issue: 155, P. 102935 - 102935

Published: July 26, 2024

Deep learning (DL) in orthopaedics has gained significant attention recent years. Previous studies have shown that DL can be applied to a wide variety of orthopaedic tasks, including fracture detection, bone tumour diagnosis, implant recognition, and evaluation osteoarthritis severity. The utilisation is expected increase, owing its ability present accurate diagnoses more efficiently than traditional methods many scenarios. This reduces the time cost diagnosis for patients surgeons. To our knowledge, no exclusive study comprehensively reviewed all aspects currently used practice. review addresses this knowledge gap using articles from Science Direct, Scopus, IEEE Xplore, Web between 2017 2023. authors begin with motivation orthopaedics, enhance treatment planning. then covers various applications detection supraspinatus tears MRI, osteoarthritis, prediction types arthroplasty implants, age assessment, joint-specific soft tissue disease. We also examine challenges implementing scarcity data train lack interpretability, as well possible solutions these common pitfalls. Our work highlights requirements achieve trustworthiness outcomes generated by DL, need accuracy, explainability, fairness models. pay particular fusion techniques one ways increase trustworthiness, which been address multimodality orthopaedics. Finally, we approval set forth US Food Drug Administration enable use applications. As such, aim function guide researchers develop reliable application tasks scratch market.

Language: Английский

---

Crack propagation simulation and overload fatigue life prediction via enhanced physics-informed neural networks

International Journal of Fatigue, Journal Year: 2024, Volume and Issue: 186, P. 108382 - 108382

Published: May 11, 2024

Language: Английский

---

Physics-Informed neural network solver for numerical analysis in geoengineering

Georisk Assessment and Management of Risk for Engineered Systems and Geohazards, Journal Year: 2024, Volume and Issue: 18(1), P. 33 - 51

Published: Jan. 2, 2024

Engineering-scale problems generally can be described by partial differential equations (PDEs) or ordinary (ODEs). Analytical, semi-analytical and numerical analysis are commonly used for deriving the solutions of such PDEs/ODEs. Recently, a novel physics-informed neural network (PINN) solver has emerged as promising alternative to solve PINN resembles mesh-free method which leverages strong non-linear ability deep learning algorithms (e.g. networks) automatically search correct spatial-temporal responses constrained embedded This study comprehensively reviews current state including its principles forward inverse problems, baseline PINN, enhanced variants combined with special sampling strategies loss functions. shows an easier modelling process superior feasibility compared conventional methods. Meanwhile, limitations challenges applications solvers constitutive multi-scale/phase also discussed in terms convergence computational costs. exhibited huge potential geoengineering brings revolutionary way numerous domain problems.

Language: Английский

---

Dynamically configured physics-informed neural network in topology optimization applications

Computer Methods in Applied Mechanics and Engineering, Journal Year: 2024, Volume and Issue: 426, P. 117004 - 117004

Published: April 26, 2024

Language: Английский

---

Physics-informed radial basis function neural network for efficiently modeling oil–water two-phase Darcy flow

Physics of Fluids, Journal Year: 2025, Volume and Issue: 37(1)

Published: Jan. 1, 2025

Physics-informed neural networks (PINNs) improve the accuracy and generalization ability of prediction by introducing physical constraints in training process. As a model combining laws deep learning, it has attracted wide attention. However, cost PINNs is high, especially for simulation more complex two-phase Darcy flow. In this study, physics-informed radial basis function network (PIRBFNN) proposed to simulate flow oil water efficiently. Specifically, each time step, phase equations are discretized based on finite volume method, then, loss constructed according residual their coupling equations, pressure approximated RBFNN. Based obtained pressure, another discrete equation saturation For boundary conditions, we use “hard constraints” speed up PIRBFNN. The straightforward structure PIRBFNN also contributes an efficient addition, have simply proved RBFNN fit continuous functions. Finally, experimental results verify computational efficiency Compared with convolutional network, reduced than three times.

Language: Английский

---

Physics-Informed Neural Network-Based Input Shaping for Vibration Suppression of Flexible Single-Link Robots

Actuators, Journal Year: 2025, Volume and Issue: 14(1), P. 14 - 14

Published: Jan. 5, 2025

The vibration suppression of flexible robotic arms is challenging due to their nonlinear spatiotemporal dynamics. This paper presents a novel physics-informed neural network (PINN)-based input-shaping method for the problem. Through two-phase training process based on loss function that follows both physical model constraints and modal conditions, we identify optimal parameters minimize residual vibration. With use powerful computational resources handle multimode information about vibration, PINN-based approach outperforms traditional methods in terms efficiency performance. Extensive simulations are carried out validate effectiveness highlight its potential complex control tasks systems.

Language: Английский

---

Adaptive Interface-PINNs (AdaI-PINNs) for transient diffusion: Applications to forward and inverse problems in heterogeneous media

Finite Elements in Analysis and Design, Journal Year: 2025, Volume and Issue: 244, P. 104305 - 104305

Published: Jan. 10, 2025

Language: Английский

---

A physics-informed neural network framework for laminated composite plates under bending

Thin-Walled Structures, Journal Year: 2025, Volume and Issue: unknown, P. 113014 - 113014

Published: Jan. 1, 2025

Language: Английский

---