Citation :

Berhanu Tefera, Adil Zekaria, Abrham Gebre, "Physics-Informed Neural Network Using LSTM Architecture for Transient Thermal Analysis of a Concrete Highway Bridge Deck," International Journal of Civil Engineering, vol. 13, no. 6, pp. 169-186, 2026. Crossref, https://doi.org/10.14445/23488352/IJCE-V13I6P112

Abstract

A novel hybrid architecture combining Physics‑Informed Neural Networks (PINN) and Long Short‑Term Memory (LSTM) networks is presented to examine vertical temperature gradients and thermal‑induced stress in a T‑girder concrete highway bridge deck. Whereas traditional approaches, such as pure physics or data‑driven models, are insufficient to capture the nonlinear transient thermal response caused by complex environmental interactions, this hybrid approach successfully integrates in‑situ measurements and meteorological data. In this hybrid model, physics‑governed principles of heat conduction and thermo‑elasticity are embedded for high‑accuracy prediction of the bridge thermal response. The model was validated against field measurements and a 3D finite element (ANSYS) model using diurnal temperature records. Validation results show that the PINN‑LSTM model achieves Mean Absolute Errors (MAE) of 0.57 °C and 0.33 °C at the bottom girder and deck‑slab interface, respectively, with corresponding Root‑Mean‑Square Errors (RMSE) of 0.74 °C and 0.46 °C – significantly outperforming the ANSYS simulation. At the top asphalt surface, both models perform comparably (RMSE ≈ 1.0 °C). The hybrid PINN‑LSTM model results demonstrate a temperature profile of 49.10 °C during peak solar radiation, causing 3.67 MPa of tensile stress at the deck‑girder interface. This stress level exceeds the bridge’s concrete tensile strength, indicating a plausible cause for existing cracking patterns on the soffit of the bridge deck. The findings underscore the necessity of incorporating thermal‑induced stress analysis into bridge damage identification protocols and validate the PINN‑LSTM hybrid as an accurate, computationally efficient alternative to conventional finite element simulation.

Keywords

Concrete Bridge, Temperature Gradient, Thermal Stress, Physics-Informed Neural Network, and Long Short-Term Memory.

References

1. B. Gu et al., “Temperature Gradient and Its Effect on Long-Span Prestressed Concrete Box Girder Bridge,” Advances in Civil Engineering, vol. 2020, no. 1, pp. 1-18, 2020.
   [CrossRef] [Google Scholar] [Publisher Link]
2. Yumin Song et al., “Research on Temperature Distribution and Gradient Prediction of U-Shaped Girder Bridge under Solar Radiation Effect,” Applied Sciences, vol. 14, no. 14, pp. 1-20, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
3. Ali Hashemi, Javad Beheshti, and Mahdieh Mohammadi, “Physics-Based AI-Driven Surrogate Modeling for Structural Displacement Prediction in Mechanical Systems With Limited Sensor Data,” IEEE Access, vol. 13, pp. 130585-130602, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
4. Mahmoud Fadhel Idan, “The Role of Artificial Intelligence in Advancing Mechanical Engineering: Opportunities, Challenges, and Emerging Applications in Applied Mechanics,” Proceedings of the 8^th International Conference on Applied Engineering (ICAE 2025), Atlantis Press, pp. 350-365, 2025. [CrossRef] [Google Scholar] [Publisher Link]
5. Divyani Sen, Bharat Singh Deora, and Arun Vaishnav, “View of Explainable Deep Learning for Time Series Analysis: Integrating SHAP and LIME in LSTM-Based Models,” Journal of Information Systems Engineering and Management, vol. 10, no. 16s, pp. 1-12, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
6. Jiaxin Zhang, Congjie Wei, and Chenglin Wu, “Thermodynamic Consistent Neural Networks for Learning Material Interfacial Mechanics,” arXiv preprint, pp. 1-7, 2020.
   [CrossRef] [Google Scholar] [Publisher Link]
7. Zifei Xu et al., “Collaborative and Trustworthy Fault Diagnosis for Mechanical Systems Based on Probabilistic Neural Network with Decision-Level Information Fusion,” Journal of Industrial Information Integration, vol. 46, pp. 1-20, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
8. Yuqing Qiu et al., “Damage Identification for Bridges Using Machine Learning : Development and Application to KW51 Bridge,” Digital Engineering, vol. 10, pp. 1-17, 2026.
   [CrossRef] [Google Scholar] [Publisher Link]
9. Abdollah Malekjafarian et al., “A Machine Learning Approach to Bridge-Damage Detection Using Responses Measured on a Passing Vehicle,” Sensors, vol. 19, no. 18, pp. 1-19, 2019.
   [CrossRef] [Google Scholar] [Publisher Link]
10. Kang Yang et al., “Deep Learning-Based Bridge Damage Identification Approach Inspired by Internal Force Redistribution Effects,” Structural Health Monitoring, vol. 23, no. 2, pp. 714-732, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
11. Sardorbek Niyozov et al., “Temperature Effects Removal from Non-Stationary Bridge-Vehicle Interaction Signals for ML Damage Detection,” Sensors, vol. 23, no. 11, pp. 1-26, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
12. Taniya Kapoor et al., “Physics-Informed Neural Networks for Solving Forward and Inverse Problems in Complex Beam Systems,” IEEE Transactions on Neural Networks and Learning Systems, vol. 35, no. 5, pp. 5981-5995, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
13. NASA Prediction of Worldwide Energy Resources (POWER), Registry of Open Data on AWS. [Online]. Available: https://registry.opendata.aws/nasa-power/
14. H. Elsom, and M. Pawley, “Extreme Value Statistics for Analysing Simulated Environmental Extremes,” Extremes, vol. 28, pp. 47-73, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
15. Lukas Brunner, and Aiko Voigt, “Pitfalls in Diagnosing Temperature Extremes,” Nature Communications, vol. 15, pp. 1-9, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
16. Suresh Kumar Padala et al., “Air Temperature Prediction Models for Pavement Design: A Gradient Boosting-Based Approach,” International Journal of Pavement Engineering, vol. 25, no. 1, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
17. ACI 209R‑92, “Prediction of Creep, Shrinkage, and Temperature Effects in Concrete Structures,” ACI Committee Report, pp. 1-47, 1997.
    [Google Scholar] [Publisher Link]
18. Chengcheng Shen, Haifeng Zhao, and Jian Jiao, “A Multi-Subnets Physics-Informed Neural Network (Ms-PINN) Model for Transient Heat Transfer Analysis in Materials with Heterogeneous Microstructures,” Engineering with Computers, vol. 41, pp. 3695-3717, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
19. Ge Jin et al., “Fourier Warm Start for Physics-Informed Neural Networks,” Engineering Applications of Artificial Intelligence, vol. 132, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
20. Yanjia Wang et al., “Hybrid Physics‐Informed Neural Network with Parametric Identification for Modeling Bridge Temperature Distribution,” Computer-Aided Civil and Infrastructure Engineering, vol. 40, no. 22, pp. 3503-3524, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
21. Rahul Suresh et al., “Revolutionizing Physics: A Comprehensive Survey of Machine Learning Applications,” Frontiers in Physics, vol. 12, pp. 1-31, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
22. Xi'an Li et al., “Physical Informed Neural Networks with Soft and Hard Boundary Constraints for Solving Advection-Diffusion Equations using Fourier Expansions,” Computers & Mathematics with Applications, vol. 159, pp. 60-75, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
23. Ziad Aldirany et al., “Operator Approximation of the Wave Equation based on Deep Learning of Green’s Function,” Computers & Mathematics with Applications, vol. 159, pp. 21-30, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
24. Yiming Lu et al., “Enhanced Physics-Informed Neural Networks Using Adaptive Residual Weighting for Flow Simulations,” Proceedings of Global Power and Propulsion Society, Shanghai, pp. 1-14, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
25. Youqiong Liu et al., “Variable Separated Physics-Informed Neural Networks based on Adaptive Weighted Loss Functions for Blood Flow Model,” Computers & Mathematics with Applications, vol. 153, pp. 108-122, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
26. Yeonhwi Jeong et al., “Combined Analysis of Thermofluids and Electromagnetism Using Physics-Informed Neural Networks,” Engineering Applications of Artificial Intelligence, vol. 133, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
27. Xiaoli Wang et al., “Data-Driven Soliton Solutions and Parameters Discovery of the Coupled Nonlinear Wave Equations via a Deep Learning Method,” Chaos, Solitons & Fractals, vol. 180, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
28. Nirmal Patel, Aycin Aykutalp, and Pablo Laguna, “Novel Approach to Solving Schwarzschild Black Hole Perturbation Equations via Physics Informed Neural Networks,” General Relativity and Gravitation, vol. 56, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
29. Yushi Shan et al., “GNN-LSTM-based Full-Field Temperature Prediction of Bridges Using Sparse Sensor Data and Heat-Transfer Analysis,” Engineering Structures, vol. 342, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
30. Moez Krichen, and Alaeddine Mihoub, “Long Short-Term Memory Networks : A Comprehensive Survey,” AI, pp. 1-21, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
31. Federico Landi et al., “Working Memory Connections for LSTM,” Neural Networks, vol. 144, pp. 334-341, 2021.
    [CrossRef] [Google Scholar] [Publisher Link]
32. Ivan Malashin et al., “Applications of Long Short-Term Memory (LSTM) Networks in Polymeric Sciences: A Review,” Polymers, vol. 16, no. 18, pp. 1-44, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
33. S. Mariani et al., “Data-Driven Modeling of Long Temperature Time-Series to Capture the Thermal Behavior of Bridges for SHM Purposes,” Mechanical Systems and Signal Processing, vol. 206, pp. 1-13, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
34. Linren Zhou, Taojun Wang, and Yumeng Chen, “Bridge Temperature Prediction Method Based on Long Short-Term Memory Neural Networks and Shared Meteorological Data,” Advances in Structural Engineering, vol. 27, no. 8, pp. 1349-1360, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
35. Aiping Guo et al., “Data Mining Algorithms for Bridge Health Monitoring: Kohonen Clustering and LSTM Prediction Approaches,” The Journal of Supercomputing, vol. 76, pp. 932-947, 2019.
    [CrossRef] [Google Scholar] [Publisher Link]
36. Yuching Wu et al., “Finite Element Analysis of Perforated Prestressed Concrete Frame Enhanced by Artificial Neural Networks,” Buildings, vol. 14, no. 10, pp. 1-18, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
37. Shahin Alipour Bonab, Wenjuan Song, and Mohammad Yazdani-Asrami, “Physics-Informed Neural Network Model for Transient Thermal Analysis of Superconductors,” Superconductor Science and Technology, vol. 38, pp. 1-11, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
38. Eurocode 1: Actions on structures - Part 1-5: General actions - Thermal Actions, European Commitee for Standardization, 2003. [Online]. Available: https://www.phd.eng.br/wp-content/uploads/2015/12/en.1991.1.5.2003.pdf
39. Bridge Manual SP/M/022, no. SP/M/022, NZ Transport Agency, 2022. [Online]. Available: https://www.nzta.govt.nz/resources/bridge-manual
40. Sallal R. Abid, “Three-Dimensional Finite Element Temperature Gradient Analysis in Concrete Bridge Girders Subjected to Environmental Thermal Loads,” Cogent Engineering, vol. 5, no. 1, pp. 1-15, 2018.
    [CrossRef] [Google Scholar] [Publisher Link]
41. M. J. Nigel Priestley, “Design of Concrete Bridges for Temperature Gradients,” American Concrete Institute Journal, pp. 209-217, 1978.
    [CrossRef] [Google Scholar] [Publisher Link]
42. Ethiopia Road Administration, Bridge Design Manual - Part 1, 2013. [Online]. Available: https://bms.era.gov.et:8087/media/bridge/Combolcha/Dichoto/Mille%20-%20Semera/A1-7-009/R52.pdf
43. Shijun Huang et al., “Multi-Field Numerical Model and LSTM-based Neural Networks for Thermal Field Predictions of Concrete-Filled Steel Tubes,” Frontiers in Materials, vol. 12, pp. 1-13, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
44. Vishnu Sharma, and A.K. Dwivedi, “Effect of Temperature Stresses in Composite Girder Bridges,” International Journal of Research and Scientific Innovation, vol. 5, no. 8, pp. 97-101, 2018.
    [Google Scholar] [Publisher Link]
45. Da Wang et al., “Numerical Investigation of Temperature Gradient-Induced Thermal Stress for Steel-Concrete Composite Bridge Deck in Suspension Bridges,” Journal of Central South University, vol. 25, pp. 185-195, 2018.
    [CrossRef] [Google Scholar] [Publisher Link]
46. Jiahao Song et al., “VW-PINNs: A Volume Weighting Method for PDE Residuals in Physics-Informed Neural Networks,” Acta Mechanica Sinica, vol. 41, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
47. Xiaoting Yang et al., “Longitudinal Displacement Reconstruction Method of Suspension Bridge End Considering Multi-Type Data Under Deep Learning Framework,” Buildings, vol. 15, no. 15, pp. 1-19, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
48. Shaolun He et al., “Effect of Temperature Gradients on the Microstructural Characteristics and Mechanical Properties of Concrete,” Cement and Concrete Research, vol. 184, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
49. R. Sharmaa, and Y.B. Guo, “Thermal-Mechanical Physics Informed Deep Learning for Fast Prediction of Thermal Stress Evolution in Laser Metal Deposition,” arXiv preprint, pp. 1-18, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
50. Yushi Shan et al., “Temperature Behavior of Cable-Stayed Bridges. Part I — Global 3D Temperature Distribution by Integrating Heat-Transfer Analysis and Field Monitoring Data,” Advances in Structural Engineering, vol. 26, no. 9, pp. 1579-1599, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
51. Sallal R. Abid, Nildem Tayşi, and Mustafa Özakça, “Experimental Analysis of Temperature Gradients in Concrete Box-Girders,” Construction and Building Materials, vol. 106, pp. 523-532, 2016.
    [CrossRef] [Google Scholar] [Publisher Link]
52. Yousong Peng, and Shizhong Qiang, “Analytical Solution to Temperature Variations in Highway Concrete Bridges Due To Solar Radiation,” International Conference on Transportation Engineering, pp. 1536-1541, 2007.
    [CrossRef] [Google Scholar] [Publisher Link]
53. R. Mahto, “Thermal Stress Analysis in Pre-Stressed Concrete Bridges using COMSOL Multiphysics,” International Journal of Surveying and Structural Engineering, vol. 6, no. 1, pp. 27-32, 2025.
    [CrossRef] [Publisher Link]
54. Federal Highway Administration, Chapter 5: Assessment of Bridge Fatigue and Investigation into Bridge Deck Wear,” Comprehensive Truck Size and Weight Limits Study: Bridge Structure. Comparative Analysis Technical Report, U.S. Department of Transportation. 2025.
    [Publisher Link]