Spatiotemporal Prediction Model for Joint Width Deformation in Cement Concrete Pavements Based on Physics-Informed Neural Networks

DOI

10.2991/978-94-6463-902-5_8How to use a DOI?

Keywords

Cement concrete pavement; Physics-Informed Neural Networks; Joint expansion

Abstract

To address the lack of theoretical support in predicting joint width deformation in cement concrete pavements, this study proposes a Physics-Informed Neural Network (PINN) model that integrates physical mechanisms with on-site monitoring data. By combining long-term sensor data, including environmental temperature, humidity, structural responses, and joint width deformation, the model achieves spatiotemporal quantitative prediction of joint width deformation. Through parameter sensitivity analysis, the model identifies temperature gradients and humidity gradients as the primary driving factors for joint width deformation. Experimental results demonstrate that, compared to the traditional Backpropagation Neural Network (BPNN), the proposed model exhibits significant advantages in both prediction accuracy and physical consistency. This research not only improves the accuracy of joint width deformation predictions but also provides a theoretical foundation for optimizing pavement maintenance strategies, offering valuable potential for practical engineering applications.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Sili Li
AU  - Yupeng Wang
AU  - Panpan Zhang
AU  - Dafu Li
PY  - 2025
DA  - 2025/12/16
TI  - Spatiotemporal Prediction Model for Joint Width Deformation in Cement Concrete Pavements Based on Physics-Informed Neural Networks
BT  - Proceedings of the 2025 7th International Conference on Civil Engineering, Environment Resources and Energy Materials (CCESEM 2025)
PB  - Atlantis Press
SP  - 60
EP  - 79
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-902-5_8
DO  - 10.2991/978-94-6463-902-5_8
ID  - Li2025
ER  -