The DOI displayed above is for this specific version of this dataset, which is currently the latest. Newer versions may be published in the future. For a link that will always point to the latest version, please use
DOI: 10.4121/48e6341d-b5a4-4525-b16d-ceef5a61525a

Khadijeh, Mahmoud; Kasbergen, Cor; Erkens, Sandra; Varveri, Aikaterini (2025): Code underlying the publication: Multistage physics informed neural network for solving coupled multiphysics problems in material degradation and fluid dynamics. Version 1. 4TU.ResearchData. software. https://doi.org/10.4121/48e6341d-b5a4-4525-b16d-ceef5a61525a.v1

Categories

• Civil Engineering
• Engineering

Keywords

Asphalt aging Multiphysics modeling Multistage learning Partial differential equations Physics informed neural networks

Licence

CC BY 4.0

Interoperability

• RO-Crate Metadata

Export as...

RefWorks BibTeX Reference Manager Endnote DataCite NLM DC CFF

by Mahmoud Khadijeh , Cor Kasbergen , Sandra Erkens , Aikaterini Varveri

Physics Informed Neural Networks (PINNs) have been rarely applied to solve multiphysics systems due to the inherent challenges in optimizing their complex loss functions, which typically incorporate multiple physics-based terms. This study presents a multistage PINN approach designed to efficiently solve coupled multiphysics systems with strong interdependencies. The multistage PINN progressively increases the complexity of the physical system being modeled, enabling more effective capture of coupling between different physics. The computational merits of this approach are demonstrated through two illustrative applications: prediction of asphalt aging and modeling of lid-driven cavity flow. Quantitative and qualitative comparisons with standard PINN and adaptive weight PINN approaches demonstrate the enhanced precision and computational efficiency of the proposed algorithm. The multistage PINN achieves a reduction in training time of more than 90% compared to standard PINNs while maintaining better alignment with the finite element method (FEM) solutions. The improvement in computational efficiency, coupled with enhanced accuracy, positions the multistage PINN as a powerful tool for addressing complex multiphysics problems across various engineering disciplines. The method’s ability to handle interactions between multiple physical processes, such as diffusion, chemical reactions, and fluid dynamics, makes it suitable for simulating long-term material behavior and complex fluid system.

History

• 2025-07-11 first online, published, posted

Publisher

4TU.ResearchData

Format

Python codes (.py)

Associated peer-reviewed publication

Multistage physics informed neural network for solving coupled multiphysics problems in material degradation and fluid dynamics

Code hosting project url

https://github.com/mkhadijeh26/Multistage-PINN

Organizations

TU Delft, Faculty Civil Engineering and Geosciences, Department of Engineering Structures, Section of Pavement Engineering