EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Cross-Modal Graph Attention for Bridge SHM Data Imputation

Jiawei Xiong, Liangliang Hu iD, Xiaolin Meng iD, Xiangdong An iD, Yilin Xie

Sensors · 25.05.2026 · 26 (11) · 3339

DOI: 10.3390/s26113339 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 25.05.2026. Verfasst von Jiawei Xiong und 4 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Comprehensive PNT Network and Equipment Technology, School of Instrument Science and Engineering, Southeast University, Nanji…. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Jiangsu Provincial International Science and Technology Cooperation Program, European Space Agency.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Bridge structural health monitoring (SHM) systems often suffer from large-scale data missing due to sensor faults, communication interruptions and other reasons during long-term operation, which seriously restricts the reliability of structural state assessment and maintenance decision-making. Compared with conventional single-channel independent modeling strategies commonly used for data imputation, their inherent neglect of spatial correlations and cross-modal causal associations among multi-source heterogeneous monitoring data such as displacement, wind speed, and temperature constrain the imputation capability, particularly when the target channel suffers from long-term continuous data loss. To address the above problems, this paper proposes a collaborative imputation framework integrating a graph attention network (GAT), a modal-aware cross-attention (MACA) mechanism and temporal encoder–decoder architecture (ITimeGAN). Firstly, the sensor feature topological graph is constructed based on the Pearson correlation coefficient, and the spatial dependency among multi-source features is adaptively learned through GAT. Then, the MACA module is introduced, which takes the target displacement as Query and environmental loads as Key/Value, and dynamically aggregates cross-modal driving information through multi-head attention. Finally, a bidirectional LSTM encoder and a unidirectional LSTM decoder are adopted to capture long-range temporal dependencies, so as to realize the accurate reconstruction of missing displacement data. Validated on the 9-dimensional real-world monitoring data from the GeoSHM system of the Forth Road Bridge (UK) under both random missing (10–50%) and continuous long-term missing (1–10 days) scenarios, ITimeGAN achieves an R2 of 0.9950 (MAE = 4.25 mm) for longitudinal displacement and 0.9759 (MAE = 6.70 mm) for vertical displacement even under 10 consecutive days of complete data absence. Ablation analysis further reveals that the incorporation of graph attention and cross-modal attention modules reduces the longitudinal displacement MAE by 57% over the baseline, with the imputation performance ranking across three displacement directions being fully consistent with the underlying physical correlation strengths, thereby confirming the effectiveness of the proposed cross-modal collaborative strategy.

Schlagwörter

Stichwörter der Autor:innen

bridge structural health monitoringcross-modal attention mechanismdeep learninggraph attention networkmissing data imputationmulti-source heterogeneous time series

Autor:innen und Institutionen

  • State Key Laboratory of Comprehensive PNT Network and Equipment Technology, School of Instrument Science and Engineering, Southeast University, Nanjing 211189, China.
  • The UK-China Intelligent Mobility Research Center, Southeast University, Nanjing 211189, China.
  • College of Architecture and Civil Engineering, Beijing University of Technology, Beijing 100124, China.
  • Jiangsu Hydraulic Research Institute, Nanjing 210098, China.

ORCID-Profile: Liangliang Hu, Xiaolin Meng, Xiangdong An

Förderung

  • National Natural Science Foundation of China
  • Jiangsu Provincial International Science and Technology Cooperation Program
  • European Space Agency

Zitieren

APA

Xiong, J., Hu, L., Meng, X., An, X., & Xie, Y. (2026). Cross-Modal Graph Attention for Bridge SHM Data Imputation. Sensors, 26(11), 3339. https://doi.org/10.3390/s26113339

Vancouver

Xiong J, Hu L, Meng X, An X, Xie Y. Cross-Modal Graph Attention for Bridge SHM Data Imputation. Sensors. 2026;26(11):3339. doi:10.3390/s26113339

BibTeX
@article{Xiong2026,
  author = {Xiong, Jiawei and Hu, Liangliang and Meng, Xiaolin and An, Xiangdong and Xie, Yilin},
  title = {Cross-Modal Graph Attention for Bridge SHM Data Imputation},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {11},
  pages = {3339},
  doi = {10.3390/s26113339}
}
Kostenlos starten →