Keywords
damage detection
critical infrastructure
Structural Health Monitoring (SHM)
artificial intelligence
Abstract
This work concerns the modeling of a Decision Support System (DSS) for managing the technical condition of a protective shelter constituting an element of critical infrastructure, using a Structural Health Monitoring (SHM) system and artificial intelligence methods. As part of the research, a geometric model of the shelter was designed, comprising five functional zones and a network of Internet of Things (IoT) sensors enabling continuous monitoring of structural and environmental parameters. A synthetic dataset was generated, accounting for spatial correlations between sensors, seasonality of measurements, and damage and failure scenarios, including, among others, structural settlement, flooding, overload, and sensor failures. Based on the generated data, the application of artificial intelligence methods was envisaged for the classification of the object's technical condition, anomaly detection, and forecasting of damage progression. The proposed decision support model enables the assessment of the shelter's operational safety, supports the planning of maintenance activities, and may serve as a basis for the development of a digital twin of the object. The results of the work may find application in the monitoring and management of critical infrastructure facilities, increasing the reliability of protective systems and the efficiency of decision-making processes.
References
2. Eastman, C., Teicholz, P., Sacks, R. i Liston, K., 2018. BIM Handbook: A Guide to Building Infor-mation Modeling for Owners, Designers, Engineers, Contractors, and Facility Managers. 3rd ed. Hobo-ken: John Wiley & Sons. ISBN 978-1-119-28034-7.
3. Farrar, C.R. i Worden, K., 2013. Structural Health Monitoring: A Machine Learning Perspective. Chichester: John Wiley & Sons Ltd. ISBN 978-1-119-99433-6.
4. Hughes, A.J., Barthorpe, R.J., Dervilis, N., Farrar, C.R. i Worden, K., 2021. A probabilistic risk-based decision framework for structural health monitoring. Mechanical Systems and Signal Processing, 150, art. 107339. DOI: 10.1016/j.ymssp.2020.107339.
5. Malekloo, A., Ozer, E., Alhamaydeh, M. i Girolami, M., 2022. Machine learning and structural health monitoring overview with emerging technology and high-dimensional data source highlights. Structural Health Monitoring, 21(4), s. 1906–1955. DOI: 10.1177/14759217211036880.
6. Molendowska, M., Ostrowska, M. i Górski, P., 2021. Infrastruktura krytyczna jako element bezpie-czeństwa – wymiar europejski i krajowy. Toruń: Wydawnictwo Adam Marszałek. ISBN 978-83-8180-445-5.
7. Plevris, V. i Papazafeiropoulos, G., 2024. AI in Structural Health Monitoring for Infrastructure Mainte-nance and Safety. Infrastructures, 9(12), art. 225. DOI: 10.3390/infrastructures9120225.
8. Spencer, B.F. Jr., Sim, S.H., Kim, R.E. i Yoon, H., 2025. Advances in artificial intelligence for struc-tural health monitoring: A comprehensive review. KSCE Journal of Civil Engineering, 29(3), art. 100203. DOI: 10.1016/j.kscej.2025.100203.
9. Sieńko, R. i Bednarski, Ł., 2018. Systemy monitorowania konstrukcji żelbetowych i sprężonych. Mate-riały XXXIII Ogólnopolskiej Konferencji "Warsztaty Pracy Projektanta Konstrukcji", Szczyrk, s. 1–74
10. Sun, Z., Jayasinghe, S., Sidiq, A., Shahrivar, F., Mahmoodian, M. i Setunge, S., 2025. Approach To-wards the Development of Digital Twin for Structural Health Monitoring of Civil Infrastructure: A Comprehensive Review. Sensors, 25(1), art. 59. DOI: 10.3390/s25010059.
11. Wang, Y., Li, Z., Zhang, H., Liu, Y. i Chen, X., 2024. An intelligent BIM-enabled digital twin frame-work for real-time structural health monitoring using wireless IoT sensing, digital signal processing, and structural analysis. Expert Systems with Applications, 252, art. 124204. DOI: 10.1016/j.eswa.2024.124204.
This work is licensed under a Creative Commons Attribution 4.0 International License.