A physics-informed neural network framework for laminated composite plates under bending
Thin-Walled Structures · 2025-05 · 210 · 113014
DOI: 10.1016/j.tws.2025.113014 ↗Kurz gefasst
Fachartikel in der Zeitschrift Thin-Walled Structures, 2025-05. Verfasst von Weixi Wang und 1 weiteren Autor:innen. Die Arbeit wurde bisher 63-mal zitiert (Crossref) und nennt 74 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Australian Research Council.
Abstract (Originalsprache)
. The use of machine learning techniques in the field of structural engineering is becoming more common. However, the high dependence of traditional purely data-driven algorithms on the size and quality of the database has hindered the practical application of machine learning in engineering. Applying physics-informed machine learning can achieve accurate predictions while reducing the need for extensive input data by incorporating established principles of mechanics into the construction of the model loss function. This study develops a physics-informed neural network (PINN) framework to predict the bending behaviour of clamped laminated composite plates. In the training process of this framework, the classic laminated plates theory (CLPT) is adopted, and the model loss function is formulated based on the energy method. The comparisons between the machine learning prediction results with the CLPT analytical solutions and finite elements (FE) results reveal that the physics-informed neural network framework can achieve satisfactory predictions while offering improved computational efficiency.
Förderung
- Australian Research Council
Zitieren
APA
Wang, W., & Thai, H. (2025). A physics-informed neural network framework for laminated composite plates under bending. Thin-Walled Structures, 210, 113014. https://doi.org/10.1016/j.tws.2025.113014
Vancouver
Wang W, Thai H. A physics-informed neural network framework for laminated composite plates under bending. Thin-Walled Structures. 2025;210:113014. doi:10.1016/j.tws.2025.113014
BibTeX
@article{Wang2025,
author = {Wang, Weixi and Thai, Huu-Tai},
title = {A physics-informed neural network framework for laminated composite plates under bending},
journal = {Thin-Walled Structures},
year = {2025},
volume = {210},
pages = {113014},
doi = {10.1016/j.tws.2025.113014}
}
EUVIMED