EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Diffusion-Based Data Augmentation Framework for Few-Shot Fault Diagnosis of Intelligent High-Speed Train Components

Jianjun Xu, Qingbin Tong iD, Ruize Zhu, Shouxin Du, Jilong Zhao, Xuedong Jiang, Baohua Wang iD

Sensors · 13.05.2026 · 26 (10) · 3091

DOI: 10.3390/s26103091 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 13.05.2026. Verfasst von Jianjun Xu und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Electrical Engineering, Beijing Jiaotong University, Beijing 100044, China. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundamental Research Funds for the Central Universities, Beijing Natural Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Few-shot fault diagnosis of intelligent high-speed train components remains challenging because fault samples are scarce and highly imbalanced. To address this issue, this paper proposes MR-DDIM, a class-conditional diffusion-based data augmentation framework for generating high-fidelity fault vibration signals from limited labeled data. A WT-UNet denoising backbone is developed by combining one-dimensional wavelet convolution with Feature-Wise Linear Modulation (FiLM) to capture multiscale time–frequency structures and enable class-controllable generation. To improve training stability and spectral fidelity, log-σ regularization and a multi-resolution STFT consistency loss are introduced into the optimization process. In addition, this paper proposed the multi-resolution spectral correlation coefficient (MR-SCC) and class-intrinsic maximum mean discrepancy (cMMD) to evaluate generation quality from spectral and distributional perspectives. Experiments on the BJTU-RAO datasets show that the proposed method can generate fault samples with high spectral consistency and reasonable intra-class diversity, thereby improving the robustness of downstream few-shot fault diagnosis. The results indicate that MR-DDIM provides an effective data augmentation solution for intelligent fault diagnosis in high-speed railway systems.

Schlagwörter

Stichwörter der Autor:innen

diffusion modelfault diagnosishigh-speed trainimbalanced samples

Autor:innen und Institutionen

  • School of Electrical Engineering, Beijing Jiaotong University, Beijing 100044, China.
  • Key Laboratory of Vehicular Multi-Energy Drive Systems, Beijing Jiaotong University, Ministry of Education, Beijing 100044, China.

ORCID-Profile: Qingbin Tong, Baohua Wang

Förderung

  • Fundamental Research Funds for the Central Universities
  • Beijing Natural Science Foundation

Zitieren

APA

Xu, J., Tong, Q., Zhu, R., Du, S., Zhao, J., Jiang, X., & Wang, B. (2026). A Diffusion-Based Data Augmentation Framework for Few-Shot Fault Diagnosis of Intelligent High-Speed Train Components. Sensors, 26(10), 3091. https://doi.org/10.3390/s26103091

Vancouver

Xu J, Tong Q, Zhu R, Du S, Zhao J, Jiang X, et al. A Diffusion-Based Data Augmentation Framework for Few-Shot Fault Diagnosis of Intelligent High-Speed Train Components. Sensors. 2026;26(10):3091. doi:10.3390/s26103091

BibTeX
@article{Xu2026,
  author = {Xu, Jianjun and Tong, Qingbin and Zhu, Ruize and Du, Shouxin and Zhao, Jilong and Jiang, Xuedong and Wang, Baohua},
  title = {A Diffusion-Based Data Augmentation Framework for Few-Shot Fault Diagnosis of Intelligent High-Speed Train Components},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {10},
  pages = {3091},
  doi = {10.3390/s26103091}
}
Kostenlos starten →