EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Condition Monitoring and Fault Prediction in PMSM Drives Using Machine Learning for Elevator Applications

Vasileios I. Vlachou, Theoklitos S. Karakatsanis, Dimitrios E. Efstathiou, Eftychios I. Vlachou, Stavros D. Vologiannidis, Vasiliki E. Balaska, Antonios C. Gasteratos

Machines · 24.06.2025 · 13 (7) · 549

DOI: 10.3390/machines13070549 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machines, online erschienen am 24.06.2025. Verfasst von Vasileios I. Vlachou und 6 weiteren Autor:innen. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 94 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Elevators are a vital part of urban infrastructure, playing a key role in smart cities where increasing population density has driven the rise in taller buildings. As an essential means of vertical transportation, elevators have become an integral part of daily life, making their design, construction, and maintenance crucial to ensuring safety and compliance with evolving industry standards. The safety of elevator systems depends on the continuous monitoring and fault-free operation of Permanent Magnet Synchronous Motor (PMSM) drives, which are critical to their performance. Furthermore, the fault-free operation of PMSM drives reduces operating costs, increases service life, and improves reliability. The PMSM drive components may be susceptible to electrical, mechanical, and thermal faults that, if undetected, can lead to operational disruptions or safety risks. The integration of artificial intelligence and Internet of Things (IoT) technologies can enhance fault prediction, reducing downtime and improving efficiency. Ongoing challenges such as managing machine thermal load and developing more durable materials for PMSMs require the development of suitable models that are adapted to existing drive systems. The proposed framework for fault prediction is validated on a real residential elevator equipped with a PMSM drive. Multimodal signal data is processed through a Generative Adversarial Network (GAN)-enhanced Positive Unlabeled (PU) classifier and a Reinforcement Learning (RL)-based adaptive decision engine, enabling robust and scalable fault prediction in a non-intrusive fashion.

Zitieren

APA

Vlachou, V. I., Karakatsanis, T. S., Efstathiou, D. E., Vlachou, E. I., Vologiannidis, S. D., Balaska, V. E., & Gasteratos, A. C. (2025). Condition Monitoring and Fault Prediction in PMSM Drives Using Machine Learning for Elevator Applications. Machines, 13(7), 549. https://doi.org/10.3390/machines13070549

Vancouver

Vlachou VI, Karakatsanis TS, Efstathiou DE, Vlachou EI, Vologiannidis SD, Balaska VE, et al. Condition Monitoring and Fault Prediction in PMSM Drives Using Machine Learning for Elevator Applications. Machines. 2025;13(7):549. doi:10.3390/machines13070549

BibTeX
@article{Vlachou2025,
  author = {Vlachou, Vasileios I. and Karakatsanis, Theoklitos S. and Efstathiou, Dimitrios E. and Vlachou, Eftychios I. and Vologiannidis, Stavros D. and Balaska, Vasiliki E. and Gasteratos, Antonios C.},
  title = {Condition Monitoring and Fault Prediction in PMSM Drives Using Machine Learning for Elevator Applications},
  journal = {Machines},
  year = {2025},
  volume = {13},
  number = {7},
  pages = {549},
  doi = {10.3390/machines13070549}
}
Kostenlos starten →