EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Dynamic Graph Attention-Based Unsupervised Bi-Learning Framework for Anomaly Detection of Urban Rail Vehicle Door Systems

Xiangyu Ren, Yuewei Xi, Jirui Guan, Bo Li, Yong Qin, Biao Wang, Mo Guo

Smart Cities · 29.10.2026 · 9 (11) · 186

DOI: 10.3390/smartcities9110186 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Smart Cities, online erschienen am 29.10.2026. Verfasst von Xiangyu Ren und 6 weiteren Autor:innen. Die Arbeit nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Independent Research Project of State Key Laboratory of Advanced Rail Autonomous Operation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The anomaly detection of urban rail vehicle door systems is crucial for the security and reliability of rail vehicles, and unsupervised methods have received particular attention in anomaly detection due to the scarcity of anomaly data. However, existing studies have the following limitations: (1) The dynamic interrelationships between different sensor variables are not explicitly considered, which is detrimental to the learning of normal patterns. (2) The detection performance is limited due to the reliance on manual threshold settings and the lack of confidence measures for different sensor variables. To overcome the abovementioned limitations, a dynamic graph attention-based unsupervised bi-learning framework for the anomaly detection of rail vehicle door systems is proposed in this paper. First, a dynamic graph attention block (DGAT block) is designed to model dynamic interactions between sensor variables and fuse information during signal coding. Then, a bi-learning framework is developed to automatically learn thresholds and quantify the confidence of sensor variables for anomaly detection. The proposed method is verified on a real rail vehicle door system. Compared with the state-of-the-art autoencoder-based methods that are applicable to multivariate time series data, the proposed method improves the best competing precision and F1-score by 7.7% and 4.3%, respectively, while reducing the false positive rate (FPR) by 88.9%.

Förderung

  • Independent Research Project of State Key Laboratory of Advanced Rail Autonomous Operation

Zitieren

APA

Ren, X., Xi, Y., Guan, J., Li, B., Qin, Y., Wang, B., & Guo, M. (2026). A Dynamic Graph Attention-Based Unsupervised Bi-Learning Framework for Anomaly Detection of Urban Rail Vehicle Door Systems. Smart Cities, 9(11), 186. https://doi.org/10.3390/smartcities9110186

Vancouver

Ren X, Xi Y, Guan J, Li B, Qin Y, Wang B, et al. A Dynamic Graph Attention-Based Unsupervised Bi-Learning Framework for Anomaly Detection of Urban Rail Vehicle Door Systems. Smart Cities. 2026;9(11):186. doi:10.3390/smartcities9110186

BibTeX
@article{Ren2026,
  author = {Ren, Xiangyu and Xi, Yuewei and Guan, Jirui and Li, Bo and Qin, Yong and Wang, Biao and Guo, Mo},
  title = {A Dynamic Graph Attention-Based Unsupervised Bi-Learning Framework for Anomaly Detection of Urban Rail Vehicle Door Systems},
  journal = {Smart Cities},
  year = {2026},
  volume = {9},
  number = {11},
  pages = {186},
  doi = {10.3390/smartcities9110186}
}
Kostenlos starten →