The structural integrity of railway bridges is critical for maintaining the operational safety and efficiency of Uzbekistan's expansive transportation network. Facing increased traffic loads and the challenges of an aging infrastructure in a seismically active and climatically demanding region, traditional structural health monitoring (SHM) methods are proving insufficient. This article presents an Internet of Things (IoT)- and deep learning-based digital twin framework for real-time, proactive SHM of railway bridges in Uzbekistan. The system integrates low-cost wireless accelerometers and strain gauges, a hybrid edge-cloud computing architecture for data pipeline management, and a Convolutional Neural Network (CNN) for advanced anomaly detection. Through a hypothetical pilot study on a short-span railway bridge, we demonstrate the system’s capability to continuously monitor dynamic responses, transform vibration data into the frequency domain using Fast Fourier Transform (FFT), and classify structural states with high accuracy. This applied IT solution, emphasizing software architecture, data analytics, and intelligent system design, offers a scalable and cost-effective paradigm shift from reactive to predictive maintenance, crucial for modernizing Uzbekistan's critical transport infrastructure.
Keywords
Structural Health MonitoringDigital TwinInternet of ThingsDeep LearningRailway InfrastructureUzbekistanPredictive MaintenanceApplied IT
References
E. P. Carden and P. Fanning, “Vibration based condition monitoring: A review,” Struct. Health Monit. Int. J., vol. 3, no. 4, pp. 355-377, December 2004.
G. B. Ataeva, Z. Y. Abdurakhmonova, S. S. Shadiyeva, and L. Y. Filimonova, “Change management in the corporate world,” in Sustainable Development of Business 4.0, E. G. Popkova, Ed. Cham, Switzerland: Springer, June 2025, pp. 105-109, [Online]. Available: https://doi.org/10.1007/978-3-031-83595-7_17.
I. E. Akhmedov, “Problems of and prospects for the development of railway infrastructure in Kazakhstan,” E3S Web Conf., vol. 471, p. 02006, January 2024.
L. Gao, M. Jia, and D. Liu, “Process digital twin and its application in petrochemical industry,” J. Softw. Eng. Appl., vol. 15, no. 8, pp. 85-113, August 2022.
M. Chiachío, M. Megía, J. Chiachío, J. Fernandez, and M. L. Jalón, “Structural digital twin framework: Formulation and technology integration,” Autom. Constr., vol. 140, art. no. 104333, August 2022.
D. Paredes-Palacios, F. Mota-Toledo, B. Biosca, L. Arévalo-Lomas, and J. Díaz-Curiel, “Optimization of dominant frequency and bandwidth analysis in multi-frequency 3D GPR signals to identify contaminated areas,” Sensors, vol. 22, no. 24, art. no. 9851, December 2022.
S. Mane and B. V. Mane, “Structural health monitoring of bridge using wireless sensors,” J. Harbin Eng. Univ., vol. 44, no. 8, pp. 1456-1465, August 2023.
L. Sun, Z. Shang, Y. Xia, S. Bhowmick, and S. Nagarajaiah, “Review of bridge structural health monitoring aided by big data and artificial intelligence: From condition assessment to damage detection,” J. Struct. Eng., vol. 146, no. 5, p. 04020073, May 2020.
S. Q. Nguyen, T. C. Hung, B. T. Hoang, B. V. Minh, Y. H. Chung, and T. N. Nguyen, “IoT network performance enhancement with intelligent reflecting surfaces and relay,” J. Inf. Telecommun., pp. 1-20, January 2026.
A. Armijo and D. Zamora-Sánchez, “Integration of railway bridge structural health monitoring into the internet of things with a digital twin: A case study,” Sensors, vol. 24, no. 7, p. 2115, January 2024.
C. O’Higgins, D. Hester, P. McGetrick, E. J. Cross, W. K. Ao, and J. Brownjohn, “Minimal information data-modelling (MID) and an easily implementable low-cost SHM system for use on a short-span bridge,” Sensors, vol. 23, no. 14, p. 6328, July 2023.
S.-K. Huang and T.-X. Lin, “Development of data anomaly classification for structural health monitoring based on iterative trimmed loss minimization and human-in-the-loop learning,” Struct. Health Monit., vol. 24, no. 1, pp. 548-565, April 2024.
