EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Reinforcement Learning for Imbalanced Data in Robotic Anomaly Detection within Autonomous Manufacturing

Salma Messaoudi, Ahmed Bendaouia, El Hassan Abdelwahed, Mohammed Ameksa, Hajar Mousannif, Jianzhi Li

SN Computer Science · 09.03.2026 · 7 (3)

DOI: 10.1007/s42979-026-04858-0 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SN Computer Science, online erschienen am 09.03.2026. Verfasst von Salma Messaoudi und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Office of Local Defense Community Cooperation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Ensuring reliable anomaly detection in industrial robots is critical for safe and autonomous manufacturing operations. However, it remains challenging due to temporal dependencies and class imbalance in sensor data. This study presents a reinforcement learning approach using Deep Q-Network (DQN) enhanced with Long Short-Term Memory (LSTM) and Gradient Boosting Machine (GBM) for robust anomaly detection in robotic systems. The proposed framework integrates an LSTM into the DQN policy to capture temporal patterns. It also introduces a novel GBM-based reward mechanism that mitigates class imbalance by applying SMOTE (Synthetic Minority Over-sampling Technique) after removing temporal dependencies. Experimental results demonstrate that this hybrid DQN-GBM framework achieves superior performance in precision, recall, and F1-score compared to standalone DQN and DQN-LSTM variants. Beyond technical improvements, this approach enables truly autonomous manufacturing environments by providing adaptive, real-time anomaly detection that reduces human intervention and prevents costly production failures, ultimately contributing to more resilient and self-optimizing industrial systems.

Förderung

  • Office of Local Defense Community Cooperation

Zitieren

APA

Messaoudi, S., Bendaouia, A., Abdelwahed, E. H., Ameksa, M., Mousannif, H., & Li, J. (2026). Reinforcement Learning for Imbalanced Data in Robotic Anomaly Detection within Autonomous Manufacturing. SN Computer Science, 7(3). https://doi.org/10.1007/s42979-026-04858-0

Vancouver

Messaoudi S, Bendaouia A, Abdelwahed EH, Ameksa M, Mousannif H, Li J. Reinforcement Learning for Imbalanced Data in Robotic Anomaly Detection within Autonomous Manufacturing. SN Computer Science. 2026;7(3). doi:10.1007/s42979-026-04858-0

BibTeX
@article{Messaoudi2026,
  author = {Messaoudi, Salma and Bendaouia, Ahmed and Abdelwahed, El Hassan and Ameksa, Mohammed and Mousannif, Hajar and Li, Jianzhi},
  title = {Reinforcement Learning for Imbalanced Data in Robotic Anomaly Detection within Autonomous Manufacturing},
  journal = {SN Computer Science},
  year = {2026},
  volume = {7},
  number = {3},
  doi = {10.1007/s42979-026-04858-0}
}
Kostenlos starten →