EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multiclass Anomaly Detection in Bridge Health Monitoring Data via Attention Enhancement and Class Imbalance Mitigation

Wenda Ma, Qizhi Tang, Lei Huang, Shihao Zhang

Buildings · 17.03.2026 · 16 (6) · 1181

DOI: 10.3390/buildings16061181 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Buildings, online erschienen am 17.03.2026. Verfasst von Wenda Ma und 3 weiteren Autor:innen. Die Arbeit nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Postdoctoral Science Foundation of China, Science and Technology Project of Guizhou Provincial Transportation Department.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Bridge structural health monitoring (BSHM) systems are essential for assessing the operational performance and safety of long-span bridges. However, monitoring data are often affected by factors such as sensor malfunctions, environmental disturbances, or power interruptions, leading to various anomalous data. Moreover, the multiclass imbalance of the data presents a major challenge to traditional anomaly detection methods. To address this issue, a novel multiclass anomaly detection method based on an improved deep convolutional neural network is proposed. Specifically, a ResNet50 architecture integrated with the convolutional block attention module (CBAM) is developed to enhance the extraction of discriminative features. Additionally, the Focal Loss function is introduced to emphasize the loss weight of minority samples, reducing the influence of majority classes, thereby effectively overcoming the class imbalance issue in multiclass anomaly detection. The proposed method is trained and validated using measured acceleration data collected from a large-scale cable-stayed bridge. The experimental results indicate that the model achieves an overall accuracy of 98.28%, while effectively improving the classification performance of minority categories. The method further reproduces the spatiotemporal distribution of anomalies in full-month monitoring data, confirming its robustness and engineering applicability for large-scale automated anomaly diagnosis in BSHM systems.

Förderung

  • National Natural Science Foundation of China
  • Postdoctoral Science Foundation of China
  • Science and Technology Project of Guizhou Provincial Transportation Department
  • Chongqing Natural Science Foundation of China

Zitieren

APA

Ma, W., Tang, Q., Huang, L., & Zhang, S. (2026). Multiclass Anomaly Detection in Bridge Health Monitoring Data via Attention Enhancement and Class Imbalance Mitigation. Buildings, 16(6), 1181. https://doi.org/10.3390/buildings16061181

Vancouver

Ma W, Tang Q, Huang L, Zhang S. Multiclass Anomaly Detection in Bridge Health Monitoring Data via Attention Enhancement and Class Imbalance Mitigation. Buildings. 2026;16(6):1181. doi:10.3390/buildings16061181

BibTeX
@article{Ma2026,
  author = {Ma, Wenda and Tang, Qizhi and Huang, Lei and Zhang, Shihao},
  title = {Multiclass Anomaly Detection in Bridge Health Monitoring Data via Attention Enhancement and Class Imbalance Mitigation},
  journal = {Buildings},
  year = {2026},
  volume = {16},
  number = {6},
  pages = {1181},
  doi = {10.3390/buildings16061181}
}
Kostenlos starten →