FAULT DIAGNOSTICS OF ASYNCHRONOUS MOTOR BEARINGS BASED ON THE CURRENT SIGNATURE ANALYSIS AND MACHINE LEARNING ALGORITHMS
Bulletin of the South Ural State University series "Power Engineering" · 2026 · 26 (1) · 62-67
DOI: 10.14529/power260107 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bulletin of the South Ural State University series "Power Engineering", 2026. Verfasst von O.H. Ahmed und 3 weiteren Autor:innen. Die Arbeit nennt 13 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This paper explores the potential of using machine learning algorithms based on stator current signature analysis to detect induction motor bearing faults in variable frequency drives. The study used data on stator currents obtained from a simula-tion model at different operating frequencies and motor loads. Four machine learning methods were compared: artificial neural network (ANN), K-nearest Neighbors (KNN), support vector machine (SVM), and Naive Bayes classifier (NB). The best results (more than 90 % correct recognition probability) were achieved by ANN- and KNN-based classifiers. A clear dependence of the performance of the diagnostic methods on motor load and frequency was revealed. However, this dependence varies for different methods and in different ways and directions, which allows assuming that the reliability of diagnostics can be improved by using two (or more) types of classifiers simultaneously.
Zitieren
APA
Ahmed, O., Metelkov, V., Zyuzev, A., & Esaulkova, D. (2026). FAULT DIAGNOSTICS OF ASYNCHRONOUS MOTOR BEARINGS BASED ON THE CURRENT SIGNATURE ANALYSIS AND MACHINE LEARNING ALGORITHMS. Bulletin of the South Ural State University series "Power Engineering", 26(1), 62-67. https://doi.org/10.14529/power260107
Vancouver
Ahmed O, Metelkov V, Zyuzev A, Esaulkova D. FAULT DIAGNOSTICS OF ASYNCHRONOUS MOTOR BEARINGS BASED ON THE CURRENT SIGNATURE ANALYSIS AND MACHINE LEARNING ALGORITHMS. Bulletin of the South Ural State University series "Power Engineering". 2026;26(1):62-67. doi:10.14529/power260107
BibTeX
@article{Ahmed2026,
author = {Ahmed, O.H. and Metelkov, V.P. and Zyuzev, A.M. and Esaulkova, D.V.},
title = {FAULT DIAGNOSTICS OF ASYNCHRONOUS MOTOR BEARINGS BASED ON THE CURRENT SIGNATURE ANALYSIS AND MACHINE LEARNING ALGORITHMS},
journal = {Bulletin of the South Ural State University series "Power Engineering"},
year = {2026},
volume = {26},
number = {1},
pages = {62--67},
doi = {10.14529/power260107}
}
EUVIMED