Reinforcement Learning With Model-Based Assistance for Shape Control in Sendzimir Rolling Mills

As one of the most popular tandem cold rolling mills, the Sendzimir rolling mill (ZRM) aims to obtain a flat steel strip shape by properly allocating the rolling pressure. To improve the performance of the ZRM, it is meaningful to adopt recently emerging deep reinforcement learning (DRL) that is pow...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on control systems technology 2023-07, Vol.31 (4), p.1867-1874
Hauptverfasser:	Park, Jonghyuk, Kim, Beomsu, Han, Soohee
Format:	Artikel
Sprache:	eng
Schlagworte:	Actor-critic policy gradient Actuators Cluster mills cold rolling mill Cold rolling mills Cold tandem mills Controllers Deep learning Heuristic algorithms Metal strips Observability Optimization partially observable Markov decision process (MDP) reinforcement learning Sendzimir rolling mill (ZRM) Sendzimir Z mills Shape Shape control Singularities State estimation Static models Steel Strip steel Strips System effectiveness
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!