EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Vibration-based gearbox fault diagnosis using a multi-scale convolutional neural network with depth-wise feature concatenation

Van-Trang Nguyen iD, Quoc Bao Diep iD

PLOS One · 07.07.2025 · 20 (7) · e0324905

DOI: 10.1371/journal.pone.0324905 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 07.07.2025. Verfasst von Van-Trang Nguyen und 1 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Vehicle and Energy Engineering, Ho Chi Minh City University of Technology and Education, Ho Chi Minh City, Vietnam. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This article proposes a novel approach for vibration-based gearbox fault diagnosis using a multi-scale convolutional neural network with depth-wise feature concatenation named MixNet. In industrial environments where equipment reliability directly impacts productivity, safety, and operational efficiency, timely and accurate fault detection in gearboxes is of paramount importance. As critical components in manufacturing, energy production, transportation, and heavy machinery, gearboxes constitute major potential failure points, with malfunctions leading to costly downtime and, in severe cases, catastrophic incidents. The proposed method addresses these industrial challenges by integrating advanced signal processing techniques with deep learning architectures to enhance diagnostic accuracy and robustness. Specifically, MixNet utilizes multi-scale convolutional layers combined with depth-wise feature concatenation to extract discriminative features from spectrogram representations of vibration signals, generated via the Short-time Fourier transform (STFT). This approach offers several practical advantages for engineering applications, including non-invasive monitoring that eliminates the need for disassembly, early fault detection that facilitates condition-based maintenance strategies, automated diagnosis that minimizes reliance on domain-specific expertise, and robust performance under noisy and variable operating conditions. Experimental results on the Gearbox fault diagnosis dataset demonstrate that MixNet outperforms existing deep learning models, achieving a significantly higher accuracy of 99.32% with a relatively fast training time of only 4 minutes and 29 seconds. The combination of high accuracy and computational efficiency renders the proposed method well-suited for deployment in real-time monitoring systems across manufacturing plants, power generation facilities, and automotive applications, where it has the potential to reduce maintenance costs by up to 30% and improve equipment availability by enabling the detection of incipient faults before catastrophic failures.

Autor:innen und Institutionen

  • Faculty of Vehicle and Energy Engineering, Ho Chi Minh City University of Technology and Education, Ho Chi Minh City, Vietnam.
  • Computational Science and Applications Research Group, Faculty of Mechanical - Electrical and Computer Engineering, School of Technology, Van Lang University, Ho Chi Minh City, Vietnam.

ORCID-Profile: Van-Trang Nguyen, Quoc Bao Diep

Zitieren

APA

Nguyen, V. T., & Diep, Q. B. (2025). Vibration-based gearbox fault diagnosis using a multi-scale convolutional neural network with depth-wise feature concatenation. PLOS One, 20(7), e0324905. https://doi.org/10.1371/journal.pone.0324905

Vancouver

Nguyen VT, Diep QB. Vibration-based gearbox fault diagnosis using a multi-scale convolutional neural network with depth-wise feature concatenation. PLOS One. 2025;20(7):e0324905. doi:10.1371/journal.pone.0324905

BibTeX
@article{Nguyen2025,
  author = {Nguyen, Van-Trang and Diep, Quoc Bao},
  title = {Vibration-based gearbox fault diagnosis using a multi-scale convolutional neural network with depth-wise feature concatenation},
  journal = {PLOS One},
  year = {2025},
  volume = {20},
  number = {7},
  pages = {e0324905},
  doi = {10.1371/journal.pone.0324905}
}
Kostenlos starten →