EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Fault Diagnosis Method for Boost Chopper of High-Speed Maglev Train Based on Deep Time-Series Modeling

Shuhuai Wang, Xin Zhang, Wenxin Wang, Yi Tian, Xindong Wang

Sensors · 10.07.2026 · 26 (14) · 4393

DOI: 10.3390/s26144393 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 10.07.2026. Verfasst von Shuhuai Wang und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing 100044, China. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China, Taishan Industry Leading Talent Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The boost chopper (HS) is a core electrical component of the 440 V grid in high-speed maglev trains, providing reliable power for battery charging and auxiliary systems. Fault diagnosis of the HS is crucial for identifying operational faults and ensuring stable train operation. However, HS faults exhibit both long-period fluctuations and transient characteristics, which are difficult for a single network to capture synchronously. This paper proposes a multi-scale fault diagnosis method based on a TimesNet-CNN dual-branch architecture, constructing a parallel and complementary feature extraction mechanism. The TimesNet branch uses Fast Fourier Transform (FFT) to adaptively identify dominant periods, reshaping the 1D sequence into a 2D structure to explicitly model the global evolution of intra-period fluctuations and inter-period trends via Inception convolution. Meanwhile, the CNN branch employs stacked small convolutional kernels and hierarchical downsampling to extract local high-frequency anomaly features. After feature fusion, the method achieves synergistic discrimination of global periodicity and local transiency. Finally, experiments were conducted on a real-world dataset containing 11 system states (10 fault types and 1 normal state). Experimental results show that the proposed method outperforms TimesNet, CNN, ResNet and Informer models in precision, recall and F1-score. This validates the effectiveness of the dual-branch feature fusion mechanism in capturing multi-scale fault features, achieving high-precision identification of HS faults.

Schlagwörter

Stichwörter der Autor:innen

Convolutional Neural NetworkTimesNetboost chopperfault diagnosishigh-speed maglev train

Autor:innen und Institutionen

  • School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing 100044, China.
  • State Key Laboratory of High-speed Maglev Transportation Technology, CRRC Qingdao Sifang Co., Ltd., Qingdao 266111, China.

Förderung

  • National Key Research and Development Program of China
  • Taishan Industry Leading Talent Project

Zitieren

APA

Wang, S., Zhang, X., Wang, W., Tian, Y., & Wang, X. (2026). Fault Diagnosis Method for Boost Chopper of High-Speed Maglev Train Based on Deep Time-Series Modeling. Sensors, 26(14), 4393. https://doi.org/10.3390/s26144393

Vancouver

Wang S, Zhang X, Wang W, Tian Y, Wang X. Fault Diagnosis Method for Boost Chopper of High-Speed Maglev Train Based on Deep Time-Series Modeling. Sensors. 2026;26(14):4393. doi:10.3390/s26144393

BibTeX
@article{Wang2026,
  author = {Wang, Shuhuai and Zhang, Xin and Wang, Wenxin and Tian, Yi and Wang, Xindong},
  title = {Fault Diagnosis Method for Boost Chopper of High-Speed Maglev Train Based on Deep Time-Series Modeling},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {14},
  pages = {4393},
  doi = {10.3390/s26144393}
}
Kostenlos starten →