EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Policy learning for real-time control of digital twins in additive manufacturing via Differentiable Predictive Control using multi-step time-series deep neural networks

Seul Lee, Yi-Ping Chen, Ying-Kuan Tsai, Vispi Karkaria, Wei Chen

Machine Learning: Engineering · 11.11.2026

DOI: 10.1088/3049-4761/aec0a2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machine Learning: Engineering, online erschienen am 11.11.2026. Verfasst von Seul Lee und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NSF Engineering Research Center for Hybrid Autonomous Manufacturing Moving from Evolution to Revolution, NSF MADE-PUBLIC Future Manufacturing Research Grant Program, Samsung Electronics Doctoral Scholarship.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Kein Abstract verfügbar.

Förderung

  • NSF Engineering Research Center for Hybrid Autonomous Manufacturing Moving from Evolution to Revolution
  • NSF MADE-PUBLIC Future Manufacturing Research Grant Program
  • Samsung Electronics Doctoral Scholarship
  • Taiwan-Northwestern Doctoral Scholarship

Zitieren

APA

Lee, S., Chen, Y., Tsai, Y., Karkaria, V., & Chen, W. (2026). Policy learning for real-time control of digital twins in additive manufacturing via Differentiable Predictive Control using multi-step time-series deep neural networks. Machine Learning: Engineering. https://doi.org/10.1088/3049-4761/aec0a2

Vancouver

Lee S, Chen Y, Tsai Y, Karkaria V, Chen W. Policy learning for real-time control of digital twins in additive manufacturing via Differentiable Predictive Control using multi-step time-series deep neural networks. Machine Learning: Engineering. 2026. doi:10.1088/3049-4761/aec0a2

BibTeX
@article{Lee2026,
  author = {Lee, Seul and Chen, Yi-Ping and Tsai, Ying-Kuan and Karkaria, Vispi and Chen, Wei},
  title = {Policy learning for real-time control of digital twins in additive manufacturing via Differentiable Predictive Control using multi-step time-series deep neural networks},
  journal = {Machine Learning: Engineering},
  year = {2026},
  doi = {10.1088/3049-4761/aec0a2}
}
Kostenlos starten →