PSI - Issue 84

Alessandro Pucci et al. / Procedia Structural Integrity 84 (2026) 433–440

439

All the geometric properties required for calculating the priority index p (Eq. 1) were computed for each defect. Defects have been assigned by RINA inspectors to the same BIM element and belonging to the same defect category. Then, all findings were aggregated based on their spatial positioning on the element and on their location within critical zones. Thus, it was possible, for each structural element, to compute the corresponding defectiveness level L d and priority score I d (Eq. 3). The workflow subsequently advanced to the global structural risk assessment, where the evaluated elements have been grouped into coherent structural assemblies. This step allowed for the determination of an overall priority score and defectiveness level for the entire bridge. 4. Conclusions This paper has presented the application of the Civil Engineer Assistant (CEA) platform to the inspection, assessment, and maintenance planning of an existing large-scale motorway bridge, demonstrating its effectiveness on a full-scale case study. The proposed framework integrates UAV-based image acquisition, AI-assisted defect detection, and BIM-oriented digital modeling into a coherent and scalable workflow that supports the entire bridge management process, from inspection to decision-making. The results highlight how the systematic use of dense image datasets and three-dimensional models enables a surface-oriented and spatially consistent inspection, overcoming many of the limitations of traditional visual surveys. By automatically identifying, locating, and characterizing defects, and by assigning the indices prescribed by the Italian Guidelines (k1, k2, G and the derived priority indices), CEA enhances objectivity, repeatability, and traceability in defect assessment, while maintaining expert supervision (RINA inspectors) as a key validation step. The hierarchical multi-level analysis—from individual defects to elements and up to the entire structure—allows local damage phenomena to be consistently propagated to element-level and global risk indicators, supporting the assignment of the Attention Class required by current regulations. In addition, the integration of inspection outcomes with the Maintenance Module demonstrates how defect geometry and spatial distribution can be directly translated into quantitative and optimized maintenance strategies. Automatic clustering of defects according to intervention type and spatial proximity provides road operators with actionable information on repair extents and supports cost-effective planning of restoration activities. Overall, the case study confirms that the CEA platform represents a mature and highly operational digital solution for bridge asset management, capable of supporting daily engineering practice while aligning with national regulatory frameworks. Future developments will focus on extending the approach to multi-temporal inspections for degradation tracking, refining AI models for defect classification, and further strengthening the link between inspection data, structural performance assessment, and long-term life-cycle management of bridge infrastructure. Acknowledgement The authors would like to thank Archetipo s.r.l. and DiMoRe s.r.l. for their support in the development of the project. Their contribution was instrumental in the successful completion of this activity. References Frangopol, D. M., 2011. Life-cycle performance, management, and optimization of structural system under uncertainty: Accomplishments and challenges. Structure and Infrastructure Engineering , 7(6), 389-413. Ayyub, B. M., 2018. Risk Analysis in Engineering and Economics (2nd ed.), CRC Press / Taylor & Francis, Boca Raton, FL, USA. Frangopol, D.M and Soliman, M., 2016. Life-cycle of structural systems: Recent achievements and future directions. Structure and Infrastructure Engineering , 12(1), 1–20. Alessandro Scala, Laura Niero, Lorenzo Brezzi, Fabio Gabrieli, Fabiola Gibin, Carlo Pellegrino, Paolo Simonini, Vasilis Sarhosis, Paolo Zampieri,2025, Extreme natural events and bridge collapses: statistical insights in Italy, International Journal of Disaster Risk Reduction , 131, 105880, ISSN 2212-4209, https://doi.org/10.1016/j.ijdrr.2025.105880. Santarsiero G, Masi A, Picciano V, Digrisolo A. The Italian Guidelines on Risk Classification and Management of Bridges: Applications and Remarks on Large Scale Risk Assessments. Infrastructures . 2021; 6(8):111. https://doi.org/10.3390/infrastructures6080111 Gucunski, N., et al., 2013. Nondestructive testing to identify concrete bridge deck deterioration. Journal of Infrastructure Systems , 19(4), 384–394.