EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Data‐Driven Framework for Assessing Damage Development in Coupling Joints of Prestressed Concrete Bridges

Yasser Alqasem, Lydia Puttkamer

Structural Control and Health Monitoring · 2026-01 · 2026 (1)

DOI: 10.1155/stc/3195765 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Structural Control and Health Monitoring, online erschienen am 10.11.2026. Verfasst von Yasser Alqasem und 1 weiteren Autor:innen. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Coupling joints in existing prestressed concrete structures are fatigue‐critical details and often exhibit deficiencies in static analyses. The condition of coupling joints can be assessed by continuous monitoring of crack widths, with integral displacement transducers measuring both the coupling joint and a reference section. The data on crack width changes (CWCs) enable an engineering assessment of the coupling joints. As long as the concrete remains uncracked (State I), there is little risk of fatigue due to the bond. However, if the concrete is in a cracked state (State II), the stress is mainly absorbed by the prestressing steel. Depending on traffic and temperature loads, the crack may be in an open or compressed state. A data‐driven framework based on machine learning methods was developed for cross‐structural assessment. By normalizing the inhomogeneous monitoring data from different bridges to a common scale range, a comparable database can be created. This proof‐of‐concept study demonstrates that normalization facilitates a comparative analysis across the investigated bridge structures at the level of damage condition, despite variations in geometry, span length, and structural system. The normalized data can be grouped into condition‐related clusters using unsupervised learning, demonstrating the potential for condition assessment across the investigated bridges with comparable structural characteristics. Furthermore, a feedforward artificial neural network (ANN) was developed for regression‐based condition assessment and evaluated using bridge‐level cross‐validation. The results demonstrate that the ANN captures the underlying trend of CWC variation when transferred to previously unseen bridge data, while differences in the absolute CWC prediction indicate limited transferability of the prediction level across bridges. While the current study is limited to three bridge structures, the proposed framework may provide a methodological basis for broader structural health monitoring applications.

Zitieren

APA

Alqasem, Y., & Puttkamer, L. (2026). A Data‐Driven Framework for Assessing Damage Development in Coupling Joints of Prestressed Concrete Bridges. Structural Control and Health Monitoring, 2026(1). https://doi.org/10.1155/stc/3195765

Vancouver

Alqasem Y, Puttkamer L. A Data‐Driven Framework for Assessing Damage Development in Coupling Joints of Prestressed Concrete Bridges. Structural Control and Health Monitoring. 2026;2026(1). doi:10.1155/stc/3195765

BibTeX
@article{Alqasem2026,
  author = {Alqasem, Yasser and Puttkamer, Lydia},
  title = {A Data‐Driven Framework for Assessing Damage Development in Coupling Joints of Prestressed Concrete Bridges},
  journal = {Structural Control and Health Monitoring},
  year = {2026},
  volume = {2026},
  number = {1},
  doi = {10.1155/stc/3195765}
}
Kostenlos starten →