GGLCM: A Real-Time Early Anomaly Detection Method for Mechanical Vibration Data with Missing Labels

Authors

  • Hu Yu College of Mechanical Electrical & Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China https://orcid.org/0000-0002-2487-1244
  • Xiaoyu Che College of Mechanical Electrical & Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China
  • Chao Zhang College of Mechanical Electrical & Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China
  • Rupeng Zhu College of Mechanical Electrical & Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China
  • Weifang Chen College of Mechanical Electrical & Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China

DOI:

https://doi.org/10.2478/msr-2025-0019

Keywords:

early anomaly detection, feature reconstruction, missing labels, reliable detection, real-time detection

Abstract

Early anomaly detection plays a central role in the scientific maintenance of mechanical equipment. Although the application is limited by weak monitoring, it encounters the problem of missing labels. To overcome this challenge, the Gramian gray level co-occurrence matrix (GGLCM) analysis method is proposed, which includes three phases: first, the time-series are input into the Gramian angular field (GAF) in real time for signal dimension reconstruction. Second, the gray level co-occurrence matrix (GLCM) is applied to the reconstructed signal. Since the GAF preserves the dependencies in the time-series, the limitation of missing labels is significantly weakened. Third, a continuous alarm mechanism is developed for reliable detection. Finally, the GGLCM is verified by actual vibration datasets of overloaded bearings.

Downloads

Published

22.07.2024

How to Cite

GGLCM: A Real-Time Early Anomaly Detection Method for Mechanical Vibration Data with Missing Labels. (2024). Measurement Science Review, 25(4), 157-163. https://doi.org/10.2478/msr-2025-0019

Similar Articles

1-10 of 81

You may also start an advanced similarity search for this article.