EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Time–Frequency Residual Neural Network Method for Bearing Fault Diagnosis Under Constantly Speed Changing

Shunming Li, Wenbei Shi, Jianfen Zhang, Jun Zhang, Haibo Zhang, Jiantao Lu

Electronics · 05.05.2026 · 15 (9) · 1957

DOI: 10.3390/electronics15091957 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 05.05.2026. Verfasst von Shunming Li und 5 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Jiangsu Province, the National Science and Technology Major Project, NIT Science and Technology Innovation Fund.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Identifying a consistent diagnostic approach for bearing faults in the same mechanical equipment operating under continuously varying rotational speeds remains a critical challenge. In this study, a time–frequency residual neural network method is proposed by integrating the short-time Fourier transform (STFT) with deep residual connections. First, the vibration signals are transformed into time–frequency representations using STFT, from which training and testing datasets are constructed. The training dataset is used to train the deep residual neural network, while the testing dataset is employed to evaluate its performance. Batch normalization (BN) is incorporated to enhance training stability, and Adapter Tuning is adopted for parameter fine-tuning to improve convergence efficiency. After validating the effectiveness of the proposed deep time–frequency residual network using publicly available datasets, its diagnostic accuracy and practical applicability are further verified through bearing vibration data collected from a dedicated experimental test bench. The experimental validation results show that, for fault diagnosis under changing bearing rotational speeds, the proposed method can achieve an accuracy of approximately 97.25% after only 200 iterations. Using a model structure with three residual blocks, the optimal diagnostic performance can be achieved with an input sample size of 3000.

Förderung

  • Natural Science Foundation of Jiangsu Province
  • the National Science and Technology Major Project
  • NIT Science and Technology Innovation Fund

Zitieren

APA

Li, S., Shi, W., Zhang, J., Zhang, J., Zhang, H., & Lu, J. (2026). Deep Time–Frequency Residual Neural Network Method for Bearing Fault Diagnosis Under Constantly Speed Changing. Electronics, 15(9), 1957. https://doi.org/10.3390/electronics15091957

Vancouver

Li S, Shi W, Zhang J, Zhang J, Zhang H, Lu J. Deep Time–Frequency Residual Neural Network Method for Bearing Fault Diagnosis Under Constantly Speed Changing. Electronics. 2026;15(9):1957. doi:10.3390/electronics15091957

BibTeX
@article{Li2026,
  author = {Li, Shunming and Shi, Wenbei and Zhang, Jianfen and Zhang, Jun and Zhang, Haibo and Lu, Jiantao},
  title = {Deep Time–Frequency Residual Neural Network Method for Bearing Fault Diagnosis Under Constantly Speed Changing},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {9},
  pages = {1957},
  doi = {10.3390/electronics15091957}
}
Kostenlos starten →