EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MSFF-Net: Multi-Sensor Frequency-Domain Feature Fusion Network with Lightweight 1D CNN for Bearing Fault Diagnosis

Miao Dai iD, Hangyeol Jo iD, Moonsuk Kim iD, Sang-Woo Ban iD

Sensors · 11.07.2025 · 25 (14) · 4348

DOI: 10.3390/s25144348 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 11.07.2025. Verfasst von Miao Dai und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information & Communication Engineering, Graduate School, Dongguk University, Gyeongju 38066, Republic of Korea. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Korea Institute of Energy Technology Evaluation and Planning (KETEP) grant funded by the Korea government (MOTIE).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study proposes MSFF-Net, a lightweight deep learning framework for bearing fault diagnosis based on frequency-domain multi-sensor fusion. The vibration and acoustic signals are initially converted into the frequency domain using the fast Fourier transform (FFT), enabling the extraction of temporally invariant spectral features. These features are processed by a compact one-dimensional convolutional neural network, where modality-specific representations are fused at the feature level to capture complementary fault-related information. The proposed method demonstrates robust and superior performance under both full and scarce data conditions, as verified through experiments on a publicly available dataset. Experimental results on a publicly available dataset indicate that the proposed model attains an average accuracy of 99.73%, outperforming state-of-the-art (SOTA) methods in both accuracy and stability. With only about 70.3% of the parameters of the SOTA model, it offers faster inference and reduced computational cost. Ablation studies confirm that multi-sensor fusion improves all classification metrics over single-sensor setups. Under few-shot conditions with 20 samples per class, the model retains 94.69% accuracy, highlighting its strong generalization in data-limited scenarios. The results validate the effectiveness, computational efficiency, and practical applicability of the model for deployment in data-constrained industrial environments.

Schlagwörter

Stichwörter der Autor:innen

Multi-sensor data fusionVibration dataacoustic databearing fault diagnosisone-dimensional convolutional neural network

Autor:innen und Institutionen

  • Department of Information & Communication Engineering, Graduate School, Dongguk University, Gyeongju 38066, Republic of Korea.
  • Department of Electronics, Information & Communication Engineering, Dongguk University, Gyeongju 38066, Republic of Korea.

ORCID-Profile: Miao Dai, Hangyeol Jo, Moonsuk Kim, Sang-Woo Ban

Förderung

  • Korea Institute of Energy Technology Evaluation and Planning (KETEP) grant funded by the Korea government (MOTIE)

Zitieren

APA

Dai, M., Jo, H., Kim, M., & Ban, S. W. (2025). MSFF-Net: Multi-Sensor Frequency-Domain Feature Fusion Network with Lightweight 1D CNN for Bearing Fault Diagnosis. Sensors, 25(14), 4348. https://doi.org/10.3390/s25144348

Vancouver

Dai M, Jo H, Kim M, Ban SW. MSFF-Net: Multi-Sensor Frequency-Domain Feature Fusion Network with Lightweight 1D CNN for Bearing Fault Diagnosis. Sensors. 2025;25(14):4348. doi:10.3390/s25144348

BibTeX
@article{Dai2025,
  author = {Dai, Miao and Jo, Hangyeol and Kim, Moonsuk and Ban, Sang-Woo},
  title = {MSFF-Net: Multi-Sensor Frequency-Domain Feature Fusion Network with Lightweight 1D CNN for Bearing Fault Diagnosis},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {14},
  pages = {4348},
  doi = {10.3390/s25144348}
}
Kostenlos starten →