WEKO3
アイテム
Scalable reinforcement learning for plant-wide control of vinyl acetate monomer process
http://hdl.handle.net/10061/0002000120
http://hdl.handle.net/10061/0002000120e4c76e85-287c-4f31-a882-482b0734693a
| アイテムタイプ | 学術雑誌論文 / Journal Article(1) | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2024-02-07 | |||||||||||||
| タイトル | ||||||||||||||
| タイトル | Scalable reinforcement learning for plant-wide control of vinyl acetate monomer process | |||||||||||||
| 言語 | ||||||||||||||
| 言語 | eng | |||||||||||||
| キーワード | ||||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | Chemical process control | |||||||||||||
| キーワード | ||||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | Reinforcement learning | |||||||||||||
| キーワード | ||||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | Vinyl acetate monomer | |||||||||||||
| 資源タイプ | ||||||||||||||
| 資源タイプ | journal article | |||||||||||||
| アクセス権 | ||||||||||||||
| アクセス権 | open access | |||||||||||||
| 著者 |
Zhu, Lingwei
× Zhu, Lingwei
× Cui, Yunduan
× Takami, Go
× Kanokogi, Hiroaki
× 松原, 崇充 |
|||||||||||||
| 抄録 | ||||||||||||||
| 内容記述タイプ | Abstract | |||||||||||||
| 内容記述 | This paper explores a reinforcement learning (RL) approach that designs automatic control strategies in a large-scale chemical process control scenario as the first step for leveraging an RL method to intelligently control real-world chemical plants. The huge number of units for chemical reactions as well as feeding and recycling the materials of a typical chemical process induces a vast amount of samples and subsequent prohibitive computation complexity in RL for deriving a suitable control policy due to high-dimensional state and action spaces. To tackle this problem, a novel RL algorithm: Factorial Fast-food Dynamic Policy Programming (FFDPP) is proposed. By introducing a factorial framework that efficiently factorizes the action space, Fast-food kernel approximation that alleviates the curse of dimensionality caused by the high dimensionality of state space, into Dynamic Policy Programming (DPP) that achieves stable learning even with insufficient samples. FFDPP is evaluated in a commercial chemical plant simulator for a Vinyl Acetate Monomer (VAM) process. Experimental results demonstrate that without any knowledge of the model, the proposed method successfully learned a stable policy with reasonable computation resources to produce a larger amount of VAM product with comparative performance to a state-of-the-art model-based control. | |||||||||||||
| 書誌情報 |
en : Control Engineering Practice 巻 97, 発行日 2020-02-10 |
|||||||||||||
| 出版者 | ||||||||||||||
| 出版者 | Elsevier | |||||||||||||
| ISSN | ||||||||||||||
| 収録物識別子タイプ | EISSN | |||||||||||||
| 収録物識別子 | 0967-0661 | |||||||||||||
| 出版者版DOI | ||||||||||||||
| 関連タイプ | isReplacedBy | |||||||||||||
| 識別子タイプ | DOI | |||||||||||||
| 関連識別子 | https://doi.org/10.1016/j.conengprac.2020.104331 | |||||||||||||
| 出版者版URI | ||||||||||||||
| 関連タイプ | isReplacedBy | |||||||||||||
| 識別子タイプ | URI | |||||||||||||
| 関連識別子 | https://www.sciencedirect.com/science/article/pii/S0967066120300186 | |||||||||||||
| 権利 | ||||||||||||||
| 権利情報Resource | http://creativecommons.org/licenses/by-nc-nd/4.0/ | |||||||||||||
| 権利情報 | c 2020 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license(http://creativecommons.org/licenses/by-nc-nd/4.0/). | |||||||||||||
| 著者版フラグ | ||||||||||||||
| 出版タイプ | NA | |||||||||||||
