EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Safety-Aware Multi-Agent Deep Reinforcement Learning for Adaptive Fault-Tolerant Control in Sensor-Lean Industrial Systems: Validation in Beverage CIP

Apolinar González-Potes, Ramón A. Félix-Cuadras, Luis J. Mena, Vanessa G. Félix, Rafael Martínez-Peláez, Rodolfo Ostos, Pablo Velarde-Alvarado, Alberto Ochoa-Brust

Technologies · 07.01.2026 · 14 (1) · 44

DOI: 10.3390/technologies14010044 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Technologies, online erschienen am 07.01.2026. Verfasst von Apolinar González-Potes und 7 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 72 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fault-tolerant control in safety-critical industrial systems demands adaptive responses to equipment degradation, parameter drift, and sensor failures while maintaining strict operational constraints. Traditional model-based controllers struggle under these conditions, requiring extensive retuning and dense instrumentation. Recent safe multi-agent reinforcement learning (MARL) frameworks with control barrier functions (CBFs) achieve real-time constraint satisfaction in robotics and power systems, yet assume comprehensive state observability—incompatible with sensor-hostile industrial environments where instrumentation degradation and contamination risks dominate design constraints. This work presents a safety-aware multi-agent deep reinforcement learning framework for adaptive fault-tolerant control in sensor-lean industrial environments, achieving formal safety through learned implicit barriers under partial observability. The framework integrates four synergistic mechanisms: (1) multi-layer safety architecture combining constrained action projection, prioritized experience replay, conservative training margins, and curriculum-embedded verification achieving zero constraint violations; (2) multi-agent coordination via decentralized execution with learned complementary policies. Additional components include (3) curriculum-driven sim-to-real transfer through progressive four-stage learning achieving 85–92% performance retention without fine-tuning; (4) offline extended Kalman filter validation enabling 70% instrumentation reduction (91–96% reconstruction accuracy) for regulatory auditing without real-time estimation dependencies. Validated through sustained deployment in commercial beverage manufacturing clean-in-place (CIP) systems—a representative safety-critical testbed with hard flow constraints (≥1.5 L/s), harsh chemical environments, and zero-tolerance contamination requirements—the framework demonstrates superior control precision (coefficient of variation: 2.9–5.3% versus 10% industrial standard) across three hydraulic configurations spanning complexity range 2.1–8.2/10. Comprehensive validation comprising 37+ controlled stress-test campaigns and hundreds of production cycles (accumulated over 6 months) confirms zero safety violations, high reproducibility (CV variation < 0.3% across replicates), predictable complexity–performance scaling (R2=0.89), and zero-retuning cross-topology transferability. The system has operated autonomously in active production for over 6 months, establishing reproducible methodology for safe MARL deployment in partially-observable, sensor-hostile manufacturing environments where analytical CBF approaches are structurally infeasible.

Zitieren

APA

González-Potes, A., Félix-Cuadras, R. A., Mena, L. J., Félix, V. G., Martínez-Peláez, R., Ostos, R., Velarde-Alvarado, P., & Ochoa-Brust, A. (2026). Safety-Aware Multi-Agent Deep Reinforcement Learning for Adaptive Fault-Tolerant Control in Sensor-Lean Industrial Systems: Validation in Beverage CIP. Technologies, 14(1), 44. https://doi.org/10.3390/technologies14010044

Vancouver

González-Potes A, Félix-Cuadras RA, Mena LJ, Félix VG, Martínez-Peláez R, Ostos R, et al. Safety-Aware Multi-Agent Deep Reinforcement Learning for Adaptive Fault-Tolerant Control in Sensor-Lean Industrial Systems: Validation in Beverage CIP. Technologies. 2026;14(1):44. doi:10.3390/technologies14010044

BibTeX
@article{GonzlezPotes2026,
  author = {González-Potes, Apolinar and Félix-Cuadras, Ramón A. and Mena, Luis J. and Félix, Vanessa G. and Martínez-Peláez, Rafael and Ostos, Rodolfo and Velarde-Alvarado, Pablo and Ochoa-Brust, Alberto},
  title = {Safety-Aware Multi-Agent Deep Reinforcement Learning for Adaptive Fault-Tolerant Control in Sensor-Lean Industrial Systems: Validation in Beverage CIP},
  journal = {Technologies},
  year = {2026},
  volume = {14},
  number = {1},
  pages = {44},
  doi = {10.3390/technologies14010044}
}
Kostenlos starten →