An enhanced deep learning approach for vascular wall fracture analysis DOI Creative Commons

Alexandros Tragoudas,

Marta Alloisio,

Elsayed S. Elsayed

et al.

Archive of Applied Mechanics, Journal Year: 2024, Volume and Issue: 94(9), P. 2519 - 2532

Published: April 15, 2024

Abstract This work outlines an efficient deep learning approach for analyzing vascular wall fractures using experimental data with openly accessible source codes ( https://doi.org/10.25835/weuhha72 ) reproduction. Vascular disease remains the primary cause of death globally to this day. Tissue damage in these disorders is closely tied how diseases develop, which requires careful study. Therefore, scientific community has dedicated significant efforts capture properties vessel fractures. The symmetry-constrained compact tension (symconCT) test combined digital image correlation (DIC) enabled study tissue fracture various aorta specimens under different conditions. Main purpose experiments was investigate displacement and strain field ahead crack tip. These were support development verification computational models. FEM model used DIC information material parameters identification. Traditionally, analysis processes biological tissues involves extensive due complex nature behavior stress. high costs have posed challenges, demanding solutions accelerate research progress reduce embedded costs. Deep techniques shown promise overcoming challenges by indicate patterns relationships between input label data. In study, we integrate methodologies attention residual U-Net architecture predict responses porcine specimens, enhanced a Monte Carlo dropout technique. By training network on sufficient amount data, learns features influencing progression. parameterized datasets consist pictures describing evolution path along measurements. integration should not only enhance predictive accuracy, but also significantly burden, thereby enabling more response.

Language: Английский

A survey on deep learning tools dealing with data scarcity: definitions, challenges, solutions, tips, and applications DOI Creative Commons
Laith Alzubaidi, Jinshuai Bai, Aiman Al-Sabaawi

et al.

Journal Of Big Data, Journal Year: 2023, Volume and Issue: 10(1)

Published: April 14, 2023

Abstract Data scarcity is a major challenge when training deep learning (DL) models. DL demands large amount of data to achieve exceptional performance. Unfortunately, many applications have small or inadequate train frameworks. Usually, manual labeling needed provide labeled data, which typically involves human annotators with vast background knowledge. This annotation process costly, time-consuming, and error-prone. every framework fed by significant automatically learn representations. Ultimately, larger would generate better model its performance also application dependent. issue the main barrier for dismissing use DL. Having sufficient first step toward any successful trustworthy application. paper presents holistic survey on state-of-the-art techniques deal models overcome three challenges including small, imbalanced datasets, lack generalization. starts listing techniques. Next, types architectures are introduced. After that, solutions address listed, such as Transfer Learning (TL), Self-Supervised (SSL), Generative Adversarial Networks (GANs), Model Architecture (MA), Physics-Informed Neural Network (PINN), Deep Synthetic Minority Oversampling Technique (DeepSMOTE). Then, these were followed some related tips about acquisition prior purposes, well recommendations ensuring trustworthiness dataset. The ends list that suffer from scarcity, several alternatives proposed in order more each Electromagnetic Imaging (EMI), Civil Structural Health Monitoring, Medical imaging, Meteorology, Wireless Communications, Fluid Mechanics, Microelectromechanical system, Cybersecurity. To best authors’ knowledge, this review offers comprehensive overview strategies tackle

Language: Английский

Citations

379
Physics-Guided, Physics-Informed, and Physics-Encoded Neural Networks and Operators in Scientific Computing: Fluid and Solid Mechanics DOI
Salah A. Faroughi, Nikhil M. Pawar, Célio Fernandes

et al.

Journal of Computing and Information Science in Engineering, Journal Year: 2024, Volume and Issue: 24(4)

Published: Jan. 8, 2024

Abstract Advancements in computing power have recently made it possible to utilize machine learning and deep push scientific forward a range of disciplines, such as fluid mechanics, solid materials science, etc. The incorporation neural networks is particularly crucial this hybridization process. Due their intrinsic architecture, conventional cannot be successfully trained scoped when data are sparse, which the case many engineering domains. Nonetheless, provide foundation respect physics-driven or knowledge-based constraints during training. Generally speaking, there three distinct network frameworks enforce underlying physics: (i) physics-guided (PgNNs), (ii) physics-informed (PiNNs), (iii) physics-encoded (PeNNs). These methods advantages for accelerating numerical modeling complex multiscale multiphysics phenomena. In addition, recent developments operators (NOs) add another dimension these new simulation paradigms, especially real-time prediction systems required. All models also come with own unique drawbacks limitations that call further fundamental research. This study aims present review four (i.e., PgNNs, PiNNs, PeNNs, NOs) used state-of-the-art architectures applications reviewed, discussed, future research opportunities presented terms improving algorithms, considering causalities, expanding applications, coupling solvers.

Language: Английский

Citations

54
Deep learning in computational mechanics: a review DOI Creative Commons
Leon Herrmann, Stefan Kollmannsberger

Computational Mechanics, Journal Year: 2024, Volume and Issue: 74(2), P. 281 - 331

Published: Jan. 13, 2024

Abstract The rapid growth of deep learning research, including within the field computational mechanics, has resulted in an extensive and diverse body literature. To help researchers identify key concepts promising methodologies this field, we provide overview deterministic mechanics. Five main categories are identified explored: simulation substitution, enhancement, discretizations as neural networks, generative approaches, reinforcement learning. This review focuses on methods rather than applications for thereby enabling to explore more effectively. As such, is not necessarily aimed at with knowledge learning—instead, primary audience verge entering or those attempting gain discussed are, therefore, explained simple possible.

Language: Английский

Citations

30
A complete Physics-Informed Neural Network-based framework for structural topology optimization DOI Creative Commons
Hyogu Jeong,

Chanaka Batuwatta-Gamage,

Jinshuai Bai

et al.

Computer Methods in Applied Mechanics and Engineering, Journal Year: 2023, Volume and Issue: 417, P. 116401 - 116401

Published: Sept. 9, 2023

Physics-Informed Neural Networks (PINNs) have recently gained increasing attention in the field of topology optimization. The fusion deep learning and optimization has emerged as a prominent area insightful research, where minimization loss function neural networks can be comparable to objective Inspired by concepts PINNs, this paper proposes novel framework, 'Complete Network-based Topology Optimization (CPINNTO)', address various challenges optimization, particularly related structural key innovation proposed framework lies introducing first complete machine-learning-based through integration two distinct PINNs. Herein, Deep Energy Method (DEM) PINN is implemented determine deformation state corresponding structures numerically. In addition, derivation with respect design variables replaced automatic differentiation sensitivity-analysis (S-PINN). feasibility potential CPINNTO been assessed several case studies while highlighting strengths limitations utilizing PINNs Subsequent findings indicate that achieve optimal topologies without labeled data nor FEA. numerical examples demonstrate capable stably obtaining for applications, including compliance problems, multi-constrained three-dimensional problems. Resulting designs exhibit favorable values obtained via density-based summary, opens up interesting possibilities

Language: Английский

Citations

40
Energy-based physics-informed neural network for frictionless contact problems under large deformation DOI
Jinshuai Bai, Zhongya Lin, Yizheng Wang

et al.

Computer Methods in Applied Mechanics and Engineering, Journal Year: 2025, Volume and Issue: 437, P. 117787 - 117787

Published: Jan. 30, 2025

Language: Английский

Citations

2
A comprehensive review of fiber-reinforced polymer-matrix composites under low-velocity impact DOI

Yuxin Yang,

Zhengwei Miao,

Yuewu Liu

et al.

Mechanics of Advanced Materials and Structures, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 39

Published: Feb. 6, 2025

Language: Английский

Citations

2
Energy-based PINNs using the element integral approach and their enhancement for solid mechanics problems DOI
Junwei Chen,

Jian-Xiang Ma,

Zhihe Zhao

et al.

International Journal of Solids and Structures, Journal Year: 2025, Volume and Issue: unknown, P. 113315 - 113315

Published: Feb. 1, 2025

Language: Английский

Citations

1
A novel physics-informed neural networks approach (PINN-MT) to solve mass transfer in plant cells during drying DOI

Chanaka Batuwatta-Gamage,

Charith Rathnayaka, H.C.P. Karunasena

et al.

Biosystems Engineering, Journal Year: 2023, Volume and Issue: 230, P. 219 - 241

Published: May 11, 2023

Language: Английский

Citations

20
A robust radial point interpolation method empowered with neural network solvers (RPIM-NNS) for nonlinear solid mechanics DOI Creative Commons
Jinshuai Bai,

Gui-Rong Liu,

Timon Rabczuk

et al.

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

Citations

8
Physics-constrained deep learning approach for solving inverse problems in composite laminated plates DOI
Yang Li, Detao Wan, Zhe Wang

et al.

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

Published: Aug. 23, 2024

Language: Английский

Citations

7