EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Hybrid Deep Learning Framework for Fault Diagnosis in Milling Machines

Muhammad Farooq Siddique iD, Wasim Zaman iD, Muhammad Umar iD, Jae-Young Kim, Jong-Myon Kim iD

Sensors · 19.09.2025 · 25 (18) · 5866

DOI: 10.3390/s25185866 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 19.09.2025. Verfasst von Muhammad Farooq Siddique und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical, Electronics and Computer Engineering, University of Ulsan, Ulsan 44610, Republic of Korea. Die Arbeit wurde bisher 38-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Trade, Industry and Energy, Regional Innovation System & Education (RISE), Technology Innovation Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents a hybrid fault-diagnosis framework for milling cutting tools designed to address three persistent challenges in industrial monitoring: noisy vibration signals, limited fault labels, and variability across operating conditions. The framework begins by removing baseline drift from raw signals to improve the signal-to-noise ratio. Logarithmic continuous wavelet scalograms are then constructed to provide precise time-frequency localization and reveal fault-related harmonics. To enhance feature clarity, a Canny edge operator is applied, suppressing minor artifacts and reducing intra-class variation so that key diagnostic structures are emphasized. Feature representation is obtained through a dual-branch encoder, where one pathway captures localized patterns while the other preserves long-range dependencies, resulting in compact and discriminative fault descriptors. These descriptors are integrated by an ensemble decision mechanism that assigns validation-guided weights to individual learners, ensuring reliable fault identification, improved robustness under noise, and stable performance across diverse operating conditions. Experimental validation on real-world cutting tool data demonstrates an accuracy of 99.78%, strong resilience to environmental noise, and consistent diagnostic performance under variable conditions. The framework remains lightweight, scalable, and readily deployable, providing a practical solution for high-precision tool fault diagnosis in data-constrained industrial environments.

Schlagwörter

Stichwörter der Autor:innen

acoustic emission signalscanny edge filtercondition monitoringfault diagnosishybrid deep learning modelhybrid feature extractionmilling machine

Autor:innen und Institutionen

  • Department of Electrical, Electronics and Computer Engineering, University of Ulsan, Ulsan 44610, Republic of Korea.
  • PD Technology Co., Ltd., Ulsan 44610, Republic of Korea.

ORCID-Profile: Muhammad Farooq Siddique, Wasim Zaman, Muhammad Umar, Jong-Myon Kim

Förderung

  • Ministry of Trade, Industry and Energy
  • Regional Innovation System & Education (RISE)
  • Technology Innovation Program

Zitieren

APA

Siddique, M. F., Zaman, W., Umar, M., Kim, J. Y., & Kim, J. M. (2025). A Hybrid Deep Learning Framework for Fault Diagnosis in Milling Machines. Sensors, 25(18), 5866. https://doi.org/10.3390/s25185866

Vancouver

Siddique MF, Zaman W, Umar M, Kim JY, Kim JM. A Hybrid Deep Learning Framework for Fault Diagnosis in Milling Machines. Sensors. 2025;25(18):5866. doi:10.3390/s25185866

BibTeX
@article{Siddique2025,
  author = {Siddique, Muhammad Farooq and Zaman, Wasim and Umar, Muhammad and Kim, Jae-Young and Kim, Jong-Myon},
  title = {A Hybrid Deep Learning Framework for Fault Diagnosis in Milling Machines},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {18},
  pages = {5866},
  doi = {10.3390/s25185866}
}
Kostenlos starten →