EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A fault diagnosis method for railway signal equipment based on sample balancing and multi-granularity feature fusion

Rongchang Guo, Yankai Peng

AIP Advances · 01.03.2026 · 16 (3)

DOI: 10.1063/5.0310465 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AIP Advances, online erschienen am 04.03.2026. Verfasst von Rongchang Guo und 1 weiteren Autor:innen. Die Arbeit nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

By addressing the challenges of sample imbalance and insufficient single-granularity feature extraction in railway signal equipment fault diagnosis, this paper proposes a fault diagnosis method based on sample balancing and multi-granularity feature fusion. First, the fault text data undergoes data cleaning followed by key information extraction to obtain a structured fault representation. Based on this representation, the RoBERTa-wwm model is employed to extract global deep semantic features, generating feature vectors. Second, the Borderline SMOTified GAN (BSMOTEG) method is introduced to augment minority class feature vectors, mitigating class imbalance. Subsequently, the balanced text vectors are fed into a BiLSTM network to capture temporal dependency features, while a multi-head attention mechanism is employed to weight local features. This achieves effective fusion of global-temporal-local multi-granularity features. Finally, a softmax classifier is employed for signal equipment fault diagnosis. Experimental analysis is conducted by using signal equipment failure text data recorded by a railway bureau’s electrical engineering department, with comparisons against other methods. Results demonstrate that the proposed method achieves optimal classification metrics.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Guo, R., & Peng, Y. (2026). A fault diagnosis method for railway signal equipment based on sample balancing and multi-granularity feature fusion. AIP Advances, 16(3). https://doi.org/10.1063/5.0310465

Vancouver

Guo R, Peng Y. A fault diagnosis method for railway signal equipment based on sample balancing and multi-granularity feature fusion. AIP Advances. 2026;16(3). doi:10.1063/5.0310465

BibTeX
@article{Guo2026,
  author = {Guo, Rongchang and Peng, Yankai},
  title = {A fault diagnosis method for railway signal equipment based on sample balancing and multi-granularity feature fusion},
  journal = {AIP Advances},
  year = {2026},
  volume = {16},
  number = {3},
  doi = {10.1063/5.0310465}
}
Kostenlos starten →