EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

Artificial Intelligence of Things for Next-Generation Predictive Maintenance

Taimia Bitam iD, Aya Yahiaoui iD, Djallel Eddine Boubiche iD, Rafael Martínez-Peláez iD, Homero Toral-Cruz iD, Pablo Velarde-Alvarado iD

Sensors · 16.12.2025 · 25 (24) · 7636

DOI: 10.3390/s25247636 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Sensors, online erschienen am 16.12.2025. Verfasst von Taimia Bitam und 5 weiteren Autor:innen. Beteiligte Einrichtung: LEREESI Laboratory, HNS-RE2SD, Batna 05000, Algeria. Die Arbeit wurde bisher 44-mal zitiert (Crossref) und nennt 184 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Industry 5.0 introduces a shift toward human-centric, sustainable, and resilient industrial ecosystems, emphasizing intelligent automation, collaboration, and adaptive operations. Predictive Maintenance (PdM) plays a critical role in this transition, addressing the limitations of traditional maintenance approaches in increasingly complex and data-driven environments. The convergence of Artificial Intelligence and the Industrial Internet of Things, referred to as the Artificial Intelligence of Things (AIoT), enables real-time sensing, learning, and decision-making for advanced fault detection, Remaining Useful Life estimation, and prescriptive maintenance actions. This study provides a systematic and structured review of AIoT-enabled PdM aligned with Industry 5.0 objectives. It presents a unified taxonomy integrating AI models, Industrial Internet of Things (IIoT) infrastructures, and AIoT architectures; reviews AI-driven techniques, sector-specific implementations in manufacturing, transportation, and energy; and analyzes emerging paradigms such as Edge–Cloud collaboration, federated learning, self-supervised learning, and digital twins for autonomous and privacy-preserving maintenance. Furthermore, this paper synthesizes strengths, limitations, and cross-industry challenges, and outlines future research directions centered on explainability, data quality and heterogeneity, resource-constrained intelligence, cybersecurity, and human–AI collaboration. By bridging technological advancements with Industry 5.0 principles, this review contributes a comprehensive foundation for the development of scalable, trustworthy, and next-generation AIoT-based predictive maintenance systems.

Schlagwörter

Stichwörter der Autor:innen

Artificial Intelligence of ThingsIndustry 5.0predictive maintenancesmart manufacturing

Autor:innen und Institutionen

  • LEREESI Laboratory, HNS-RE2SD, Batna 05000, Algeria.
  • Unidad Académica de Computación, Universidad Politécnica de Sinaloa, Mazatlán 82199, Mexico.
  • Departamento de Ingeniería de Sistemas y Computación, Universidad Católica del Norte, Antofagasta 1270709, Chile.
  • Departamento de Ingeniería y Tecnología, Universidad Autónoma del Estado de Quintana Roo, Chetumal 77019, Mexico.
  • Unidad Académica de Ciencias Básicas e Ingenierías, Universidad Autónoma de Nayarit, Tepic 63000, Mexico.

ORCID-Profile: Taimia Bitam, Aya Yahiaoui, Djallel Eddine Boubiche, Rafael Martínez-Peláez, Homero Toral-Cruz, Pablo Velarde-Alvarado

Zitieren

APA

Bitam, T., Yahiaoui, A., Boubiche, D. E., Martínez-Peláez, R., Toral-Cruz, H., & Velarde-Alvarado, P. (2025). Artificial Intelligence of Things for Next-Generation Predictive Maintenance. Sensors, 25(24), 7636. https://doi.org/10.3390/s25247636

Vancouver

Bitam T, Yahiaoui A, Boubiche DE, Martínez-Peláez R, Toral-Cruz H, Velarde-Alvarado P. Artificial Intelligence of Things for Next-Generation Predictive Maintenance. Sensors. 2025;25(24):7636. doi:10.3390/s25247636

BibTeX
@article{Bitam2025,
  author = {Bitam, Taimia and Yahiaoui, Aya and Boubiche, Djallel Eddine and Martínez-Peláez, Rafael and Toral-Cruz, Homero and Velarde-Alvarado, Pablo},
  title = {Artificial Intelligence of Things for Next-Generation Predictive Maintenance},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {24},
  pages = {7636},
  doi = {10.3390/s25247636}
}
Kostenlos starten →