EUVIMEDEUVIMED entdecken
Crossref

Learning-based near-optimal tracking control for industrial processes with slow and fast modes

Jinna Li, Mingwei Yang

ISA Transactions · 2023-10 · 141 · 212-222

DOI: 10.1016/j.isatra.2023.06.021 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ISA Transactions, 2023-10. Verfasst von Jinna Li und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Information and Control Engineering, Liaoning Petrochemical University, Fushun, 113001, PR China. Electronic address: jnli@lnpu.edu.cn. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 39 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Department of Education of Liaoning Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper devotes to solving the optimal tracking control (OTC) problem of singular perturbation systems in industrial processes under the framework of reinforcement learning (RL) technology. The encountered challenges include the different time scales in system operations and an unknown slow process. The immeasurability of slow process states especially increases the difficulty of finding the optimal tracking controller. To overcome these challenges, a novel off-policy ridge RL method is developed after decomposing the singular perturbed systems using the singular perturbation (SP) theory and replacing unmeasured states using important mathematical manipulations. Theoretical analysis of approximate equivalence of the sum of solutions of subproblems to the solution of the OTC problem is presented. Finally, a mixed separation thickening process (MSTP) and a numerical example are used to verify the effectiveness.

Schlagwörter

Stichwörter der Autor:innen

Off-policy learningOptimal tracking controlReinforcement learningSingular perturbation theory

Autor:innen und Institutionen

  • School of Information and Control Engineering, Liaoning Petrochemical University, Fushun, 113001, PR China. Electronic address: jnli@lnpu.edu.cn.
  • School of Information and Control Engineering, Liaoning Petrochemical University, Fushun, 113001, PR China. Electronic address: yangmingweiqhz@outlook.com.

Förderung

  • National Natural Science Foundation of China
  • Department of Education of Liaoning Province

Zitieren

APA

Li, J., & Yang, M. (2023). Learning-based near-optimal tracking control for industrial processes with slow and fast modes. ISA Transactions, 141, 212-222. https://doi.org/10.1016/j.isatra.2023.06.021

Vancouver

Li J, Yang M. Learning-based near-optimal tracking control for industrial processes with slow and fast modes. ISA Transactions. 2023;141:212-222. doi:10.1016/j.isatra.2023.06.021

BibTeX
@article{Li2023,
  author = {Li, Jinna and Yang, Mingwei},
  title = {Learning-based near-optimal tracking control for industrial processes with slow and fast modes},
  journal = {ISA Transactions},
  year = {2023},
  volume = {141},
  pages = {212--222},
  doi = {10.1016/j.isatra.2023.06.021}
}
Kostenlos starten →