EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Vibration-Based Anomaly Detection for Induction Motors Using Machine Learning

Ihsan Ullah iD, Nabeel Khan, Sufyan Ali Memon iD, Wan-Gu Kim, Jawad Saleem, Sajjad Manzoor

Sensors · 27.01.2025 · 25 (3) · 773

DOI: 10.3390/s25030773 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 27.01.2025. Verfasst von Ihsan Ullah und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical Engineering, COMSATS University Islamabad Abbottabad Campus, Abbottabad 22060, Pakistan. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea, National Research Foundation of Korea (NRF) funded by the Korean Government Ministry of Science and ICT (MSIT).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Predictive maintenance of induction motors continues to be a significant challenge in ensuring industrial reliability and minimizing downtime. In this study, machine learning techniques are utilized to enhance fault diagnosis through the use of the Machinery Fault Database (MAFAULDA). A detailed extraction of statistical features was performed on multivariate time-series data to capture essential patterns that could indicate potential faults. Three machine learning algorithms—deep neural networks (DNNs), support vector machines (SVMs), and K-nearest neighbors (KNNs)—were applied to the dataset. Optimization strategies were carefully implemented along with oversampling techniques to improve model performance and handle imbalanced data. The results achieved through these models are highly promising. The SVM model demonstrated an accuracy of 95.4%, while KNN achieved an accuracy of 92.8%. Notably, the combination of deep neural networks with fast Fourier transform (FFT)-based autocorrelation features produced the highest performance, reaching an impressive accuracy of 99.7%. These results provide a novel approach to machine learning techniques in enhancing operational health and predictive maintenance of induction motor systems.

Schlagwörter

Stichwörter der Autor:innen

K-nearest neighborsdeep neural networksfault detectionfrequency domain analysisstatistical featuresupport vector machinestime domain analysisvibration monitoring

Autor:innen und Institutionen

  • Department of Electrical Engineering, COMSATS University Islamabad Abbottabad Campus, Abbottabad 22060, Pakistan.
  • Department of Defense Systems Engineering, Sejong University, Gwangjin-gu 05006, Republic of Korea.
  • Marine Domain & Security Research Department, Korea Institute of Ocean Science & Technology, Busan 49111, Republic of Korea.
  • Department of Electrical Engineering, Mirpur University of Science and Technology, Mirpur AJK 10250, Pakistan.

ORCID-Profile: Ihsan Ullah, Sufyan Ali Memon

Förderung

  • National Research Foundation of Korea
  • National Research Foundation of Korea (NRF) funded by the Korean Government Ministry of Science and ICT (MSIT)

Zitieren

APA

Ullah, I., Khan, N., Memon, S. A., Kim, W. G., Saleem, J., & Manzoor, S. (2025). Vibration-Based Anomaly Detection for Induction Motors Using Machine Learning. Sensors, 25(3), 773. https://doi.org/10.3390/s25030773

Vancouver

Ullah I, Khan N, Memon SA, Kim WG, Saleem J, Manzoor S. Vibration-Based Anomaly Detection for Induction Motors Using Machine Learning. Sensors. 2025;25(3):773. doi:10.3390/s25030773

BibTeX
@article{Ullah2025,
  author = {Ullah, Ihsan and Khan, Nabeel and Memon, Sufyan Ali and Kim, Wan-Gu and Saleem, Jawad and Manzoor, Sajjad},
  title = {Vibration-Based Anomaly Detection for Induction Motors Using Machine Learning},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {3},
  pages = {773},
  doi = {10.3390/s25030773}
}
Kostenlos starten →