Next-Generation Real-World Stress Prediction for Australian Bridges via Graph Attention-Based Models

Larry M. Arjomandi; Ehsan Radman

doi:10.1109/ITSC60802.2025.11423104

Next-Generation Real-World Stress Prediction for Australian Bridges via Graph Attention-Based Models

Larry M. Arjomandi
, Ehsan Radman

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

Abstract

With rising traffic and heavier electric vehicles, Australian smart transport systems need advanced bridge stress analysis for resilience. Traditional methods lack speed and scalability. We propose a graph attention network with a variational autoencoder and piecewise neural networks, extracting latent features from Queensland bridge data to predict fatigue and yield stresses. Using 2022 to 2024 traffic data from IoT and weight sensors on heavy vehicles, the model adapts to load variations, achieving fatigue/yield errors of 3.9/7.6 MPa (Concrete), 3.7/10.3 MPa (Steel), and 2.7/8.3 MPa (other materials). Its modular, piecewise design using Mixture-ofExperts architecture outperforms traditional methods, enabling real-time monitoring, stress risk identification, and preventive maintenance.

Original language	English
Title of host publication	IEEE Intelligent Transportation Systems Conference, ITSC 2025
Editors	Ahmed Hussein
Place of Publication	Piscataway NJ USA
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	3346-3351
Number of pages	6
ISBN (Electronic)	9798331524180
ISBN (Print)	9798331524197
DOIs	https://doi.org/10.1109/ITSC60802.2025.11423104
Publication status	Published - 2025
Externally published	Yes
Event	IEEE Conference on Intelligent Transportation Systems 2025 - Gold Coast, Australia Duration: 18 Nov 2025 → 21 Nov 2025 Conference number: 28th https://ieeexplore.ieee.org/xpl/conhome/11422813/proceeding (Proceedings ) https://ieee-itsc.org/2025/ (Website)

Publication series

Name	IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC
Publisher	IEEE, Institute of Electrical and Electronics Engineers
ISSN (Print)	2153-0009
ISSN (Electronic)	2153-0017

Conference

Conference	IEEE Conference on Intelligent Transportation Systems 2025
Abbreviated title	ITSC 2026
Country/Territory	Australia
City	Gold Coast
Period	18/11/25 → 21/11/25
Internet address	https://ieeexplore.ieee.org/xpl/conhome/11422813/proceeding (Proceedings ) https://ieee-itsc.org/2025/ (Website)

Access to Document

10.1109/ITSC60802.2025.11423104

Cite this

Arjomandi, L. M., & Radman, E. (2025). Next-Generation Real-World Stress Prediction for Australian Bridges via Graph Attention-Based Models. In A. Hussein (Ed.), IEEE Intelligent Transportation Systems Conference, ITSC 2025 (pp. 3346-3351). (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ITSC60802.2025.11423104

Arjomandi, Larry M. ; Radman, Ehsan. / Next-Generation Real-World Stress Prediction for Australian Bridges via Graph Attention-Based Models. IEEE Intelligent Transportation Systems Conference, ITSC 2025. editor / Ahmed Hussein. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2025. pp. 3346-3351 (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC).

@inproceedings{9e02673377c845aca837d64324fda8bd,

title = "Next-Generation Real-World Stress Prediction for Australian Bridges via Graph Attention-Based Models",

abstract = "With rising traffic and heavier electric vehicles, Australian smart transport systems need advanced bridge stress analysis for resilience. Traditional methods lack speed and scalability. We propose a graph attention network with a variational autoencoder and piecewise neural networks, extracting latent features from Queensland bridge data to predict fatigue and yield stresses. Using 2022 to 2024 traffic data from IoT and weight sensors on heavy vehicles, the model adapts to load variations, achieving fatigue/yield errors of 3.9/7.6 MPa (Concrete), 3.7/10.3 MPa (Steel), and 2.7/8.3 MPa (other materials). Its modular, piecewise design using Mixture-ofExperts architecture outperforms traditional methods, enabling real-time monitoring, stress risk identification, and preventive maintenance.",

author = "Arjomandi, \{Larry M.\} and Ehsan Radman",

note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; IEEE Conference on Intelligent Transportation Systems 2025, ITSC 2026 ; Conference date: 18-11-2025 Through 21-11-2025",

year = "2025",

doi = "10.1109/ITSC60802.2025.11423104",

language = "English",

isbn = "9798331524197",

series = "IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

pages = "3346--3351",

editor = "Ahmed Hussein",

booktitle = "IEEE Intelligent Transportation Systems Conference, ITSC 2025",

address = "United States of America",

url = "https://ieeexplore.ieee.org/xpl/conhome/11422813/proceeding, https://ieee-itsc.org/2025/",

}

Arjomandi, LM & Radman, E 2025, Next-Generation Real-World Stress Prediction for Australian Bridges via Graph Attention-Based Models. in A Hussein (ed.), IEEE Intelligent Transportation Systems Conference, ITSC 2025. IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC, IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, pp. 3346-3351, IEEE Conference on Intelligent Transportation Systems 2025, Gold Coast, Queensland, Australia, 18/11/25. https://doi.org/10.1109/ITSC60802.2025.11423104

Next-Generation Real-World Stress Prediction for Australian Bridges via Graph Attention-Based Models. / Arjomandi, Larry M.; Radman, Ehsan.
IEEE Intelligent Transportation Systems Conference, ITSC 2025. ed. / Ahmed Hussein. Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers, 2025. p. 3346-3351 (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC).

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Next-Generation Real-World Stress Prediction for Australian Bridges via Graph Attention-Based Models

AU - Arjomandi, Larry M.

AU - Radman, Ehsan

N1 - Conference code: 28th

PY - 2025

Y1 - 2025

N2 - With rising traffic and heavier electric vehicles, Australian smart transport systems need advanced bridge stress analysis for resilience. Traditional methods lack speed and scalability. We propose a graph attention network with a variational autoencoder and piecewise neural networks, extracting latent features from Queensland bridge data to predict fatigue and yield stresses. Using 2022 to 2024 traffic data from IoT and weight sensors on heavy vehicles, the model adapts to load variations, achieving fatigue/yield errors of 3.9/7.6 MPa (Concrete), 3.7/10.3 MPa (Steel), and 2.7/8.3 MPa (other materials). Its modular, piecewise design using Mixture-ofExperts architecture outperforms traditional methods, enabling real-time monitoring, stress risk identification, and preventive maintenance.

AB - With rising traffic and heavier electric vehicles, Australian smart transport systems need advanced bridge stress analysis for resilience. Traditional methods lack speed and scalability. We propose a graph attention network with a variational autoencoder and piecewise neural networks, extracting latent features from Queensland bridge data to predict fatigue and yield stresses. Using 2022 to 2024 traffic data from IoT and weight sensors on heavy vehicles, the model adapts to load variations, achieving fatigue/yield errors of 3.9/7.6 MPa (Concrete), 3.7/10.3 MPa (Steel), and 2.7/8.3 MPa (other materials). Its modular, piecewise design using Mixture-ofExperts architecture outperforms traditional methods, enabling real-time monitoring, stress risk identification, and preventive maintenance.

UR - https://www.scopus.com/pages/publications/105036998719

U2 - 10.1109/ITSC60802.2025.11423104

DO - 10.1109/ITSC60802.2025.11423104

M3 - Conference Paper

AN - SCOPUS:105036998719

SN - 9798331524197

T3 - IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC

SP - 3346

EP - 3351

BT - IEEE Intelligent Transportation Systems Conference, ITSC 2025

A2 - Hussein, Ahmed

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

T2 - IEEE Conference on Intelligent Transportation Systems 2025

Y2 - 18 November 2025 through 21 November 2025

ER -

Arjomandi LM, Radman E. Next-Generation Real-World Stress Prediction for Australian Bridges via Graph Attention-Based Models. In Hussein A, editor, IEEE Intelligent Transportation Systems Conference, ITSC 2025. Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. 2025. p. 3346-3351. (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC). doi: 10.1109/ITSC60802.2025.11423104

Next-Generation Real-World Stress Prediction for Australian Bridges via Graph Attention-Based Models

Abstract

Publication series

Conference

Access to Document

Other files and links

Cite this