EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

The research on a self-learning pressure control method for low-pressure vacuum systems

Lulu Wu, Licheng Huang, Yuan Wang, Dazhu Li

AIP Advances · 01.11.2026 · 16 (11)

DOI: 10.1063/5.0319272 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AIP Advances, online erschienen am 06.11.2026. Verfasst von Lulu Wu und 3 weiteren Autor:innen. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, The Science and Technology Project of Wuhu, The Major Science and Technology Project of Anhui Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To achieve efficient and precise pressure control in low-pressure vacuum chamber systems, a self-learning control method (SFFPI) is proposed. First, a mathematical model of the system is established. Based on this model, a self-learning feedforward predictive control strategy is put forward, which captures the dynamic relationship between valve closure and steady-state pressure via self-learning and automatically adjusts the feedforward control quantity as operating conditions change. Second, combined with the system’s characteristics, an improved feedback parameter self-tuning method based on internal model control theory is developed. Finally, a comprehensive self-learning controller integrating feedforward and feedback control is constructed, which predicts feedforward control quantities under various conditions and dynamically tunes feedback parameters, realizing efficient and precise system control. Simulation results show that under the same conditions, compared to Ziegler-Nichols, Mac PID, and Cohen-Coon methods, the proposed method significantly shortens the regulation time (by 20.61, 29.34, and 19.92 s), reduces the overshoot (by 48.30, 21.40, and 47.47 percentage points), and improves the control performance (ITAE: 86.56%, 78.52%, and 84.86% reduction; IAE: 51.58%, 36.53%, and 49.07% reduction), with enhanced control signal stability (variance reduction: 74.81%, 28.49%, and 72.41%, respectively). Experimental results further validate its practical performance: the regulation time reduced by 13.92, 5.67, and 7.95 s; ITAE reduced by 41.27%, 18.12%, and 38.67%; IAE reduced by 9.20%, 4.05%, and 11.97%; and control signal variance reduced by 7.00%, 4.12%, and 25.00%, respectively. Thus, the proposed method satisfies the demand for rapid and precise pressure control in practical low-pressure systems.

Förderung

  • National Natural Science Foundation of China
  • The Science and Technology Project of Wuhu
  • The Major Science and Technology Project of Anhui Province

Zitieren

APA

Wu, L., Huang, L., Wang, Y., & Li, D. (2026). The research on a self-learning pressure control method for low-pressure vacuum systems. AIP Advances, 16(11). https://doi.org/10.1063/5.0319272

Vancouver

Wu L, Huang L, Wang Y, Li D. The research on a self-learning pressure control method for low-pressure vacuum systems. AIP Advances. 2026;16(11). doi:10.1063/5.0319272

BibTeX
@article{Wu2026,
  author = {Wu, Lulu and Huang, Licheng and Wang, Yuan and Li, Dazhu},
  title = {The research on a self-learning pressure control method for low-pressure vacuum systems},
  journal = {AIP Advances},
  year = {2026},
  volume = {16},
  number = {11},
  doi = {10.1063/5.0319272}
}
Kostenlos starten →