EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Efficient Dual-Stream Network with Soft-Gated Fusion for Bearing Fault Diagnosis Using Acoustic Emission Signals

Van-Loc Le, Huynh-Anh-Huy Nguyen, Cheol Hong Kim

Machines · 08.04.2026 · 14 (4) · 414

DOI: 10.3390/machines14040414 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machines, online erschienen am 08.04.2026. Verfasst von Van-Loc Le und 2 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea (NRF) grant through the Korean government [Ministry of Science and ICT (MSIT)].

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Bearings play crucial roles in industrial machinery. Therefore, the continuous monitoring and effective detection of bearing failures are essential to ensure the safety and reliability of motors. Traditional fault diagnosis methods often require information from both the time and frequency domains; however, converting them into a two-dimensional representation significantly increases computational costs. Conversely, utilizing only time-domain features while ignoring frequency-domain features results in incomplete fault information, reducing accuracy under various operating conditions. This study proposes an efficient dual-stream network with soft-gated fusion for bearing fault diagnosis that simultaneously analyzes acoustic emission signals in the time and frequency domains. Our approach employs two separate feature-learning branches: the time-domain branch directly extracts features from the segmented raw acoustic emission signals, and the frequency-domain branch learns features from one-dimensional spectral vectors obtained using the fast Fourier transform. A gated fusion mechanism adaptively balances the contribution of each domain before classifying fault types. The experimental results show that the proposed method significantly reduces the computational cost compared with that of a two-dimensional-representation-based model and improves accuracy over time-only or frequency-only baselines.

Förderung

  • National Research Foundation of Korea (NRF) grant through the Korean government [Ministry of Science and ICT (MSIT)]

Zitieren

APA

Le, V., Nguyen, H., & Kim, C. H. (2026). Efficient Dual-Stream Network with Soft-Gated Fusion for Bearing Fault Diagnosis Using Acoustic Emission Signals. Machines, 14(4), 414. https://doi.org/10.3390/machines14040414

Vancouver

Le V, Nguyen H, Kim CH. Efficient Dual-Stream Network with Soft-Gated Fusion for Bearing Fault Diagnosis Using Acoustic Emission Signals. Machines. 2026;14(4):414. doi:10.3390/machines14040414

BibTeX
@article{Le2026,
  author = {Le, Van-Loc and Nguyen, Huynh-Anh-Huy and Kim, Cheol Hong},
  title = {Efficient Dual-Stream Network with Soft-Gated Fusion for Bearing Fault Diagnosis Using Acoustic Emission Signals},
  journal = {Machines},
  year = {2026},
  volume = {14},
  number = {4},
  pages = {414},
  doi = {10.3390/machines14040414}
}
Kostenlos starten →