EUVIMEDEUVIMED entdecken
Crossref

Machine Learning-Based Experimental Fault Diagnosis in Induction Motors Using Grey Level Co-occurrence Matrix and Local Binary Patterns

Fatiha Behloul, Farid Tafinine, Orhan Yaman, Youcef Belkhier

Journal of Vibration Engineering & Technologies · 2026-08 · 14 (6)

DOI: 10.1007/s42417-026-02550-4 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Vibration Engineering & Technologies, online erschienen am 11.06.2026. Verfasst von Fatiha Behloul und 3 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Gefördert von: university of bejaia.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Induction machines are widely used across industrial sectors due to their robustness and efficiency. However, unexpected failures such as broken rotor bars or bearing defects can lead to severe downtime and costly repairs. To address the challenge of early and accurate fault detection, this study explores an acoustic signal-based approach using a combination of statistical texture analysis and Artificial Intelligence (AI). Acoustic signals collected from motors operating under various faulty and healthy conditions were analyzed. Feature extraction was performed using a fusion of Grey Level Co-occurrence Matrix (GLCM) with Local Binary Patterns (LBP), which together characterize both spatial dependencies and local texture variations in the signal representation. Three classifiers were subsequently trained and assessed using the collected features: multiclass Support Vector Machines (SVM), Artificial Neural Network (ANN), and K-Nearest Neighbors (KNN). According to experimental findings, the KNN classifier achieved high classification performance, while both ANN and SVM achieved high accuracy in distinguishing between different fault types, under controlled laboratory conditions. This approach demonstrates that acoustic monitoring, combined with advanced signal processing and machine learning, offers a powerful, non-invasive solution for real-time induction motor fault diagnosis, with potential benefits for predictive maintenance and improved operational reliability in industrial systems.

Förderung

  • university of bejaia

Zitieren

APA

Behloul, F., Tafinine, F., Yaman, O., & Belkhier, Y. (2026). Machine Learning-Based Experimental Fault Diagnosis in Induction Motors Using Grey Level Co-occurrence Matrix and Local Binary Patterns. Journal of Vibration Engineering & Technologies, 14(6). https://doi.org/10.1007/s42417-026-02550-4

Vancouver

Behloul F, Tafinine F, Yaman O, Belkhier Y. Machine Learning-Based Experimental Fault Diagnosis in Induction Motors Using Grey Level Co-occurrence Matrix and Local Binary Patterns. Journal of Vibration Engineering & Technologies. 2026;14(6). doi:10.1007/s42417-026-02550-4

BibTeX
@article{Behloul2026,
  author = {Behloul, Fatiha and Tafinine, Farid and Yaman, Orhan and Belkhier, Youcef},
  title = {Machine Learning-Based Experimental Fault Diagnosis in Induction Motors Using Grey Level Co-occurrence Matrix and Local Binary Patterns},
  journal = {Journal of Vibration Engineering & Technologies},
  year = {2026},
  volume = {14},
  number = {6},
  doi = {10.1007/s42417-026-02550-4}
}
Kostenlos starten →