Uncertain Dynamics Characteristic Forecasting in Composite Plates with Multi-defects of Electric Aircraft via Physics-Augmented Meta-Learning DOI
Duo Xu, Jian Zang,

Xu-Yuan Song

и другие.

Aerospace Science and Technology, Год журнала: 2025, Номер unknown, С. 110363 - 110363

Опубликована: Июнь 1, 2025

Язык: Английский

Temporal Forecasting of Distributed Temperature Sensing in a Thermal Hydraulic System with Machine Learning and Statistical Models DOI Creative Commons
Stella Pantopoulou, M. Weathered, Darius Lisowski

и другие.

IEEE Access, Год журнала: 2025, Номер 13, С. 10252 - 10264

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

1
Continuous High-Throughput Characterization of Mechanical Properties via Deep Learning DOI
Guohua Zhu,

Xueyan Hu,

Rui‐Ying Bao

и другие.

International Journal of Mechanical Sciences, Год журнала: 2025, Номер unknown, С. 110137 - 110137

Опубликована: Март 1, 2025

Язык: Английский

Процитировано

1
Advancements in Physics-Informed Neural Networks for Laminated Composites: A Comprehensive Review DOI Creative Commons
Salman Khalid,

Muhammad Haris Yazdani,

Muhammad Muzammil Azad

и другие.

Mathematics, Год журнала: 2024, Номер 13(1), С. 17 - 17

Опубликована: Дек. 25, 2024

Physics-Informed Neural Networks (PINNs) integrate physics principles with machine learning, offering innovative solutions for complex modeling challenges. Laminated composites, characterized by their anisotropic behavior, multi-layered structures, and intricate interlayer interactions, pose significant challenges traditional computational methods. PINNs address these issues embedding governing physical laws directly into neural network architectures, enabling efficient accurate modeling. This review provides a comprehensive overview of applied to laminated highlighting advanced methodologies such as hybrid PINNs, k-space Theory-Constrained optimal disjointed PINNs. Key applications, including structural health monitoring (SHM), analysis, stress-strain failure multi-scale modeling, are explored illustrate how optimize material configurations enhance reliability. Additionally, this examines the associated deploying identifies future directions further advance capabilities. By bridging gap between classical physics-based models data-driven techniques, advances understanding PINN composites underscores transformative role in addressing complexities solving real-world problems.

Язык: Английский

Процитировано

7
Inverse Multi-Parameter Analysis of Oblique Incidence Laser Interaction Based on a Multivariate Thermal-Mechanical Response DOI
Wenqi Du, Te Ma, Lingling Lu

и другие.

Thin-Walled Structures, Год журнала: 2025, Номер unknown, С. 112970 - 112970

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0
A novel PINNs based surrogate model for multi-objective reliability-based design optimization of airfoil-shaped printed circuit heat exchangers DOI
Yang Li, Detao Wan,

Rongdong Wang

и другие.

International Communications in Heat and Mass Transfer, Год журнала: 2025, Номер 164, С. 108954 - 108954

Опубликована: Апрель 11, 2025

Язык: Английский

Процитировано

0
Buckling modeling and numerical validation of composite panels for sandwich structures DOI
Yuan Zhang,

Pengyu Cao,

Xihao Yang

и другие.

Journal of Sandwich Structures & Materials, Год журнала: 2025, Номер unknown

Опубликована: Апрель 19, 2025

Sandwich structures with composite laminate panels have gained increasing prominence in the aerospace, automotive, and transportation industries, particularly design of high-performance components such as aircraft fuselages, automotive bodies, infrastructure. Their exceptional specific strength, stiffness, improved structural stability make them critical these industries for enhancing performance while reducing weight. However, accurately predicting their buckling behavior under compressive loads remains a significant challenge, traditional isotropic plate models are often inadequate. To address this issue, study develops an innovative theoretical model sandwich panels, integrating stress function method first-order shear deformation theory (FSDT) to capture unique characteristics laminated composites. The produces exact closed-form solutions global wrinkling, offering valuable insights into underlying mechanisms. A sufficiently broad range material parameter ratios, including face-to-core stiffness ratio, thickness aspect were selected based on realistic engineering conditions. analytical solution was rigorously validated against three-dimensional finite element (FEM) structure orthotropic face sheets, demonstrating high agreement FEM simulations, maximum deviation less than 6%. This proposed approach provides rapid effective means verifying numerical simulation accuracy, establishing robust foundation optimization structures.

Язык: Английский

Процитировано

0
A micromechanical solving method integrating the physics-informed neural network with the self-consistent cluster analysis method for composites laminate DOI
Wenlong Hu, Hui Cheng,

Caoyang Wang

и другие.

Composite Structures, Год журнала: 2025, Номер unknown, С. 119264 - 119264

Опубликована: Май 1, 2025

Язык: Английский

Процитировано

0
Hybrid-PINNs approach for predicting high-fidelity flow and heat transfer in printed circuit heat exchangers of sodium-cooled fast reactors DOI
Yang Li,

Rongdong Wang,

Detao Wan

и другие.

Energy, Год журнала: 2025, Номер unknown, С. 136862 - 136862

Опубликована: Май 1, 2025

Язык: Английский

Процитировано

0
Uncertain Dynamics Characteristic Forecasting in Composite Plates with Multi-defects of Electric Aircraft via Physics-Augmented Meta-Learning DOI
Duo Xu, Jian Zang,

Xu-Yuan Song

и другие.

Aerospace Science and Technology, Год журнала: 2025, Номер unknown, С. 110363 - 110363

Опубликована: Июнь 1, 2025

Язык: Английский

Процитировано

0