EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

End-to-End Process Optimization in Polymer Extrusion Lines Using Model Predictive Control and Multi-Task Learning

Raphael Hartner, Martin Kozek, Stefan Jakubek

IEEE Access · 2025 · 13 · 168344-168360

DOI: 10.1109/access.2025.3614061 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2025. Verfasst von Raphael Hartner und 2 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Project Data Based Expert System for Process Efficiency (DEEPEN), funded by the Austrian Research Promotion Agency (FFG) through the 41st Call of the Initiativ….

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Due to the inherent complexity of modern polymer extrusion lines caused by nonlinear, dynamic behavior with numerous influential factors, disturbances lead to higher scrap rates and downtimes. Unfortunately, conventional approaches to address this challenge rely on independent models and local control loops, neglecting the multistage characteristic of extrusion lines and therefore, cannot obtain a global optimum. Consequently, we propose a predictive control design based on a nonlinear and autoregressive multi-task learning model covering the entire extrusion line including local control loops and essential quality measurements. Training on an extended prediction horizon successfully addresses accumulating prediction errors and measurement noise. Due to its capability to predict state trajectories for up to 60 minutes, the proposed methodology enables effective model predictive control. Additionally, using an efficient method for adaptive error compensation based on previous error trajectories increases robustness substantially while the hierarchical control architecture supports global optimization and efficient local control loops. The proposed control design is validated on two polymer extrusion lines. The results show that changing operating points and optimizing process states, such as melt temperature, can be reliably achieved in spite of process disturbances. In comparison to baseline production periods, dominant oscillations are successfully damped by 62 %, reference values are closely followed and process variations are reduced by 41 % to 63 % improving product quality notably. A comparative analysis of disturbance rejection capabilities shows superior results while empirical analyses of stability and runtime further improve its closed-loop applicability. As a consequence, the proposed methodology for predictive control allows to steer extrusion processes accurately, address upcoming issues in advance and generally leads to more efficient processes.

Förderung

  • Project Data Based Expert System for Process Efficiency (DEEPEN), funded by the Austrian Research Promotion Agency (FFG) through the 41st Call of the Initiativ…

Zitieren

APA

Hartner, R., Kozek, M., & Jakubek, S. (2025). End-to-End Process Optimization in Polymer Extrusion Lines Using Model Predictive Control and Multi-Task Learning. IEEE Access, 13, 168344-168360. https://doi.org/10.1109/access.2025.3614061

Vancouver

Hartner R, Kozek M, Jakubek S. End-to-End Process Optimization in Polymer Extrusion Lines Using Model Predictive Control and Multi-Task Learning. IEEE Access. 2025;13:168344-168360. doi:10.1109/access.2025.3614061

BibTeX
@article{Hartner2025,
  author = {Hartner, Raphael and Kozek, Martin and Jakubek, Stefan},
  title = {End-to-End Process Optimization in Polymer Extrusion Lines Using Model Predictive Control and Multi-Task Learning},
  journal = {IEEE Access},
  year = {2025},
  volume = {13},
  pages = {168344--168360},
  doi = {10.1109/access.2025.3614061}
}
Kostenlos starten →