Machine Learning Approaches for Predictive Maintenance of Electrical Equipment
DOI:
https://doi.org/10.66238/jaeee38Keywords:
Predictive maintenance, machine learning, electrical equipment, fault diagnosis, remaining useful lifeAbstract
Electrical equipment is essential to industrial production, energy distribution, transportation, and infrastructure services. Unexpected failures of motors, transformers, generators, and other electrical assets can result in operational disruptions, repair costs, and safety risks. Predictive maintenance offers an alternative to maintenance based solely on fixed schedules by using equipment condition data to identify developing problems and support timely intervention. Machine learning can analyze measurements such as vibration, temperature, current, voltage, and acoustic signals to detect anomalies, classify faults, and estimate remaining useful life. This review discusses the principal machine learning approaches used in predictive maintenance, including supervised learning, unsupervised learning, and deep learning. It examines data collection, signal processing, model evaluation, and practical deployment for electrical equipment. Particular attention is given to limited fault data, changing operating conditions, model interpretability, and the distinction between identifying a current fault and forecasting a future failure. The review concludes that machine learning can strengthen maintenance decisions when models are evaluated on representative equipment data and combined with engineering knowledge, appropriate safeguards, and human oversight
References
Carvalho, T. P., Soares, F. A. A. M. N., Vita, R., Francisco, R. da P., Basto, J. P., & Alcalá, S. G. S. (2019). A systematic literature review of machine learning methods applied to predictive maintenance. Computers & Industrial Engineering. https://doi.org/10.1016/j.cie.2019.106024
Application-wise review of machine learning-based predictive maintenance: Trends, challenges, and future directions. (2025). Applied Sciences. https://www.mdpi.com/2076-3417/15/9/4898
Data-driven fault diagnosis for electric drives: A review. (2021). Sensors. https://doi.org/10.3390/s21124024
From corrective to predictive maintenance—a review of maintenance approaches for the power industry. (2023). Sensors. https://www.mdpi.com/1424-8220/23/13/5970
A comprehensive review of conventional and intelligence-based approaches for the fault diagnosis and condition monitoring of induction motors. (2022). Energies. https://doi.org/10.3390/en15238938
Review of fault detection and diagnosis techniques for AC motor drives. (2023). Energies. https://www.mdpi.com/1996-1073/16/15/5602
A review of artificial intelligence applications in predicting faults in electrical machines. (2025). Energies. https://www.mdpi.com/1996-1073/18/7/1616
A review of artificial intelligence techniques in fault diagnosis of electric machines. (2025). Sensors. https://www.mdpi.com/1424-8220/25/16/5128
A review on data-driven condition monitoring of industrial equipment. (2023). Algorithms. https://www.mdpi.com/1999-4893/16/1/9
Lee, J., Qiu, H., Yu, G., Lin, J., & Rexnord Technical Services. (2007). Bearing data set. NASA Prognostics Center of Excellence Data Set Repository. https://www.nasa.gov/intelligent-systems-division/discovery-and-systems-health/pcoe/pcoe-data-set-repository/
Metrics for offline evaluation of prognostic performance. International Journal of Prognostics and Health Management. https://papers.phmsociety.org/index.php/ijphm/article/view/1336
A survey on data mining for data-driven industrial assets maintenance. (2025). Technologies. https://www.mdpi.com/2227-7080/13/2/67
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Professor Nagi Gebraeel
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles published in the Journal of Advanced Electrical and Electronic Engineering (JAEEE) are distributed under the Creative Commons Attribution 4.0 International License (CC BY 4.0). Authors retain copyright of their work while granting the journal the right of first publication.
Under this license, users are permitted to read, download, copy, distribute, print, share, adapt, and reuse published material for both commercial and non-commercial purposes, provided appropriate credit is given to the original author(s), the source of publication is acknowledged, a link to the license is provided, and any changes made are clearly indicated.
The license does not permit users to imply endorsement by the original authors or the journal. No additional restrictions may be imposed that prevent others from exercising the rights granted under CC BY 4.0.
By submitting to the journal, authors confirm that their work is original, does not infringe upon third-party rights, and complies with ethical publishing standards.
