EUVIMEDEUVIMED entdecken
Crossref

Decentralized Federated Learning for Multi-Class Predictive Maintenance in Industrial IoT Systems

Ruaa Abdala, Ali Hamad, Osamah Abdulateef

International Journal of Mechatronics, Robotics, and Artificial Intelligence · 01.12.2026 · 2 (2) · 120-127

DOI: 10.33971/ijmrai.2.2.3 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Mechatronics, Robotics, and Artificial Intelligence, online erschienen am 01.12.2026. Verfasst von Ruaa Abdala und 2 weiteren Autor:innen. Die Arbeit nennt 22 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Predictive maintenance (PdM) is a key enabler of reliability and cost reduction in Industrial Internet of Things (IIoT) systems. However, conventional centralized learning approaches require raw data aggregation, raising serious concerns regarding data privacy, communication overhead, and single points of failure. Federated Learning (FL) addresses part of this challenge by enabling distributed model training, yet centralized FL architectures still rely on a central aggregator. This paper proposes a decentralized federated learning (DFL) framework based on a ring topology for multi-class predictive maintenance in IIoT environments. The proposed approach enables collaborative model training among distributed edge nodes without relying on a central server, thereby enhancing system robustness, scalability, and data privacy. A lightweight deep neural network (DNN) is employed to classify five machine operating states using multi-sensor data, including vibration, temperature, and current measurements. Extensive experiments are conducted using a real-world sensor dataset collected from three-phase AC motors under multiple fault conditions. The performance of the proposed DFL approach is systematically compared against a non-federated baseline and a centralized FL (CFL) scheme. Experimental results demonstrate that the decentralized framework achieves clas-sification performance comparable to centralized FL, with an accuracy of up to 99.83%, while eliminating the dependency on a central coordinator. The findings confirm the feasibility of decentralized federated learning for predictive maintenance applica-tions, particularly in distributed industrial settings where data privacy, fault tolerance, and communication efficiency are critical.

Zitieren

APA

Abdala, R., Hamad, A., & Abdulateef, O. (2026). Decentralized Federated Learning for Multi-Class Predictive Maintenance in Industrial IoT Systems. International Journal of Mechatronics, Robotics, and Artificial Intelligence, 2(2), 120-127. https://doi.org/10.33971/ijmrai.2.2.3

Vancouver

Abdala R, Hamad A, Abdulateef O. Decentralized Federated Learning for Multi-Class Predictive Maintenance in Industrial IoT Systems. International Journal of Mechatronics, Robotics, and Artificial Intelligence. 2026;2(2):120-127. doi:10.33971/ijmrai.2.2.3

BibTeX
@article{Abdala2026,
  author = {Abdala, Ruaa and Hamad, Ali and Abdulateef, Osamah},
  title = {Decentralized Federated Learning for Multi-Class Predictive Maintenance in Industrial IoT Systems},
  journal = {International Journal of Mechatronics, Robotics, and Artificial Intelligence},
  year = {2026},
  volume = {2},
  number = {2},
  pages = {120--127},
  doi = {10.33971/ijmrai.2.2.3}
}
Kostenlos starten →