Survey on Predictive Maintenance of Electrical Machines

This survey highlights that predictive maintenance significantly outperforms traditional maintenance strategies by enabling early fault detection, accurate diagnosis, and remaining useful life estimation for electrical machines. Electrical, mechanical, and emerging non-intrusive sensing techniques provide complementary information for effective condition monitoring. Data-driven approaches, particularly machine learning and deep learning models, demonstrate superior fault classification and prognostic accuracy, while model-based methods offer better interpretability and physical insight. Hybrid frameworks combining both approaches show strong potential for robust and scalable predictive maintenance systems. The review reveals a growing trend toward IoT-enabled monitoring, edge intelligence, and digital twin integration for real-time predictive maintenance. Public datasets and benchmarking frameworks have accelerated research progress, although gaps remain between laboratory results and real-world deployment. Handling data uncertainty, operating variability, and limited labeled fault data are critical factors influencing system performance. Predictive maintenance represents a transformative approach for intelligent asset management of electrical machines. Continued research focusing on generalizable models, uncertainty-aware prognosis, and cost-effective sensing solutions will be essential to achieve reliable and widespread industrial adoption.

[1] Z. Li, Y. Wang, and K.-S. Wang, “Intelligent predictive maintenance for fault diagnosis and prognosis in machine centers: Industry 4.0 scenario,” Adv. Manuf., vol. 5, no. 4, pp. 377–387, Dec. 2017, doi: 10.1007/s40436-017-0203-8. [2] J. Wang, L. Zhang, L. Duan, and R. X. Gao, “A new paradigm of cloud-based predictive maintenance for intelligent manufacturing,” J. Intell. Manuf., vol. 28, no. 5, pp. 1125–1137, Jun. 2017, doi: 10.1007/s10845-015-1066-0. [3] T. Zhu, Y. Ran, X. Zhou, and Y. Wen, A Survey of Predictive Maintenance: Systems, Purposes and Approaches, arXiv preprint, Dec. 2019. [4] Predictive maintenance in the Industry 4.0: A systematic literature review, Computers & Industrial Engineering, vol. 150, pp. 106889, Dec. 2020. [5] J. J. M. Jimenez, S. Schwartz, R. Vingerhoeds, B. Grabot, and M. Salaün, “Towards multi-model approaches to predictive maintenance: A systematic literature survey on diagnostics and prognostics,” J. Manuf. Syst., vol. 56, pp. 539–557, Jul. 2020. [6] J.-R. Ruiz-Sarmiento, J. Monroy, F.-A. Moreno, C. Galindo, J.-M. Bonelo, and J. Gonzalez-Jimenez, “A predictive model for the maintenance of industrial machinery in the context of Industry 4.0,” Eng. Appl. Artif. Intell., vol. 87, Jan. 2020, Art. no. 103289, doi: 10.1016/j.engappai.2019.103289. [7] N. Sahasrabudhe, R. Asegaonkar, S. Deo, S. Umredkar, and K. Mundada, “Experimental analysis of machine learning algorithms used in predictive maintenance,” in Proc. 3rd Int. Conf. Smart Syst. Inventive Technol. (ICSSIT), Aug. 2020, pp. 1302–1308, doi: 10.1109/ICSSIT48917.2020.9214181. [8] Z. M. Çınar, A. A. Nuhu, Q. Zeeshan, O. Korhan, M. Asmael, and B. Safaei, “Machine learning in predictive maintenance towards sustainable smart manufacturing in Industry 4.0,” Sustainability, vol. 12, no. 19, p. 8211, Oct. 2020, doi: 10.3390/su12198211. [9] X. Dong, Z. Yu, W. Cao, Y. Shi, and Q. Ma, “A survey on ensemble learning,” Frontiers Comput. Sci., vol. 14, no. 2, pp. 241–258, Apr. 2020, doi: 10.1007/s11704-019-8208-z. [10] I. Daniyan, K. Mpofu, M. Oyesola, B. Ramatsetse, and A. Adeodu, “Artificial intelligence for predictive maintenance in the railcar learning factories,” Proc. Manuf., vol. 45, pp. 13–18, Jan. 2020, doi: 10.1016/j.promfg.2020.04.032.