EUVIMEDEUVIMED entdecken
Crossref

Predictive maintenance for axle counters of urban railway train control signaling systems using deep learning methods

Việt Nguyễn Duy

Transport and Communications Science Journal · 21.12.2025 · 77 (3) · 282-296

DOI: 10.47869/tcsj.77.3.5 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Transport and Communications Science Journal, online erschienen am 21.12.2025. Verfasst von Việt Nguyễn Duy.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Axle Counter systems (ACS) are a critical safety component of urban rail signalling and train control systems. Current maintenance practices for ACS mainly rely on corrective maintenance after failures or scheduled periodic maintenance, without the capability to predict degradation prior to failure, resulting in reduced system availability. This paper proposes a predictive maintenance approach for ACS based on deep learning, integrated within the RAMS (Reliability, Availability, Maintainability and Safety) framework. A multi-source data model is developed to construct a Health Index (HI) that represents the health condition of the ACS over time. The HI is then used as an input feature for a Long Short-Term Memory (LSTM) recurrent neural network to predict the degradation trend of the system. The applicability of the proposed approach is validated using a simulated dataset designed to be consistent with real-world conditions. The results demonstrate that the LSTM model can accurately predict the degradation trend of the HI with low prediction error. The proposed method shows strong potential for supporting proactive maintenance planning, reducing downtime, and improving the availability of urban rail signalling systems while maintaining safety requirements.

Zitieren

APA

Duy, V. N. (2025). Predictive maintenance for axle counters of urban railway train control signaling systems using deep learning methods. Transport and Communications Science Journal, 77(3), 282-296. https://doi.org/10.47869/tcsj.77.3.5

Vancouver

Duy VN. Predictive maintenance for axle counters of urban railway train control signaling systems using deep learning methods. Transport and Communications Science Journal. 2025;77(3):282-296. doi:10.47869/tcsj.77.3.5

BibTeX
@article{Duy2025,
  author = {Duy, Việt Nguyễn},
  title = {Predictive maintenance for axle counters of urban railway train control signaling systems using deep learning methods},
  journal = {Transport and Communications Science Journal},
  year = {2025},
  volume = {77},
  number = {3},
  pages = {282--296},
  doi = {10.47869/tcsj.77.3.5}
}
Kostenlos starten →