A Review of Predictive Maintenance Methods for Electrical Machines Using Machine Learning Algorithms and Sensor Data
DOI:
https://doi.org/10.64882/ijrt.v13.i4.614Keywords:
Predictive maintenance, machine learning models, downtime failureAbstract
Induction motors serve as an integral part in industrial applications, where unexpected failures lead to huge financial losses. Predictive maintenance (PdM) has emerged as a key approach for early fault detection and machine health monitoring since demand for reliability and efficiency has been increased. This paper provides a structured analysis of data-driven predictive maintenance techniques for electrical machines, combining conclusions from traditional motor fault diagnosis methods and modern machine-learning-based approaches.
For detecting motor abnormalities such as broken rotor bars, bearing defects, and stator faults ,traditional techniques such as Motor Current Signature Analysis (MCSA) and Park’s Vector Analysis (PVA) have been widely used. Under different loading conditions, variations in current, voltage, slip, and vibration patterns serves as strong indicators of motor health. Support Vector Machines (SVM) and other supervised learning algorithms have been used for detecting motor faults with high precision.
References
A. Hassoun Barazandeh, “Predictive Maintainance Models Using Supervised Learning: A Comparative Analysis”.
G. Arunkumar. (2024), AI-Based Predictive Maintainance Stratergies for Electrical Equipment and Power Networks,”International Journal of Artificial Intelligence in Electrical Engineering (IJAIEE), 2(1),1–13.
Omer Kullu and Eyup Cinar.(2022).“A Deep Learning Based MultiModal Sensor Fusion Apporach foe Detection of Equipment Faults,”Machines,10,1105.
Mohammed Bappamaudo Suleiman, Chibueze Okoro and Babalola Waisu Lasun. (2025), “Integration of Machine Learning Algorithms for Predictive Maintenance in Electrical Machines,” International Journal of Engineering and Modern Technology(IJMET)’11(8)’ 244- 251
Naveen Kumar V. Venkatesh A. and Hemanth Kumar ML. (2024),”IoT based predictive maintenance for electrical machines and industrial automation” .
A. Sharma, L. Mathew, S. Chatterji, and R. Jigyasu(2019), “Current based feature extraction and classification of induction motor faults using support vector machine,” International Journal of Innovative Technology and Exploring Engineering (IJITEE), vol. 8, no. 12, pp. 227–232.
R. Jigyasu, A. Sharma, L. Mathew, and S. Chatterji(2018), “A review of condition monitoring and fault diagnosis methods for induction motor,” in Proc. Int. Conf. Electrical, Electronics, Computers, Communication, Mechanical and Computing (EECCMC), pp. 435–441.
A. Sharma, L. Mathew, S. Chatterji, and R. Jigyasu (2018), “Analysis of broken rotor bar fault diagnosis for induction motor,” International Journal of Engineering & Technology, vol. 7, no. 3.12, pp. 502–506.
R. Jigyasu, L. Mathew, and A. Sharma(2019), “Multiple Faults Diagnosis of Induction Motor Using Artificial Neural Network,” in Proc. ICAICR, Springer CCIS.
A. Sharma et al.(2021), “Real-Time Remote Monitoring and Fault Diagnosis of Induction Motor,” Turkish Journal of Computer and Mathematics Education.
S. Chaturvedi, A. Parakh, and H. K. Verma(2018), “Wireless Sensor Network-Based Real-Time Monitoring System for Electrical Power Distribution Network,” IJLTET.
A. Sharma, S. Chatterji, and L. Mathew, “Real-time remote monitoring and fault diagnosis of induction motor,” Turkish J. Comput. Math. Educ., vol. 12, no. 13, pp. 2873–2881, 2021.
S. Upadhyay and H. K. Verma, “Design and implementation of a wireless sensor node for machine condition monitoring,” in Proc. Int. Conf. Wireless Communication and Sensor Networks (WCSN), 2017, pp. 45–50.
S. Kumar and H. K. Verma, “IoT-enabled condition monitoring architecture for electrical equipment using sensor networks,” Int. J. Eng. Trends Technol., vol. 68, no. 2, pp. 89–97, 2020.
M. Tripathy, R. P. Maheshwari, and H. K. Verma, “Probabilistic neural-network-based protection of power transformer,” IET Electr. Power Appl., vol. 1, no. 1, pp. 102–108, 20
Downloads
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
