EUVIMEDEUVIMED entdecken
Crossref

Multi-class fault classification in conveyor systems using machine learning: enhancing reliability in production logistics

Hassan Hijry

Acta Logistica · 30.06.2026 · 13 (2) · 374

DOI: 10.22306/al.v13i2.780 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Acta Logistica, online erschienen am 30.06.2026. Verfasst von Hassan Hijry. Die Arbeit nennt 23 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Industrial conveyor systems are vital to modern manufacturing and logistics operations, where unexpected failures can cause substantial operational disruptions in material flows and economic losses. Traditional maintenance strategies often fall short in addressing the complex and interrelated failure patterns present in contemporary conveyor systems. This study presents a machine learning-based framework for developing multi-class classification models, designed to enable reliable deployment for real-time fault diagnosis in logistics environments. Using real-world operational data with sensor-derived features, multiple machine learning models are trained and evaluated to classify key types of conveyor faults. Experimental results demonstrate that ensemble methods achieved the highest performance, attaining an accuracy of 92.56% and significantly outperforming linear and instance-based approaches. This research aims to advance predictive maintenance by introducing a unified framework for the development of a multi-class classification model, enabling the identification of the most effective model for deployment in logistics settings. The main contribution of this work lies in the integration of machine learning techniques into logistics systems for predictive maintenance, offering an advanced, scalable solution that can be deployed to improve system reliability, reduce downtime, and enhance operational efficiency.

Zitieren

APA

Hijry, H. (2026). Multi-class fault classification in conveyor systems using machine learning: enhancing reliability in production logistics. Acta Logistica, 13(2), 374. https://doi.org/10.22306/al.v13i2.780

Vancouver

Hijry H. Multi-class fault classification in conveyor systems using machine learning: enhancing reliability in production logistics. Acta Logistica. 2026;13(2):374. doi:10.22306/al.v13i2.780

BibTeX
@article{Hijry2026,
  author = {Hijry, Hassan},
  title = {Multi-class fault classification in conveyor systems using machine learning: enhancing reliability in production logistics},
  journal = {Acta Logistica},
  year = {2026},
  volume = {13},
  number = {2},
  pages = {374},
  doi = {10.22306/al.v13i2.780}
}
Kostenlos starten →