There are no files associated with this item.
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.citation.startPage | 107465 | - |
dc.citation.title | COMPUTERS & CHEMICAL ENGINEERING | - |
dc.citation.volume | 154 | - |
dc.contributor.author | Kim, Jong Woo | - |
dc.contributor.author | Park, Byung Jun | - |
dc.contributor.author | Oh, Tae Hoon | - |
dc.contributor.author | Lee, Jong Min | - |
dc.date.accessioned | 2024-03-13T10:05:12Z | - |
dc.date.available | 2024-03-13T10:05:12Z | - |
dc.date.created | 2024-03-13 | - |
dc.date.issued | 2021-11 | - |
dc.description.abstract | In this study, we propose a two-stage optimal control framework for a fed-batch bioreactor. The high-level controller aims to obtain the optimal feed trajectory that maximizes the final time productivity and yield using a nominal model. By contrast, the low-level controller maintains the high-level performance in the presence of the model-plant mismatch and real-time disturbances. This two-stage decomposition can perform the closed-loop operation with less online recomputation. To solve the high-level optimiza-tion, differential dynamic programming (DDP), a model-based reinforcement learning that employs the derivatives of the model is applied. Three types of low-level controllers are proposed: DDP controller, a model predictive control (MPC) that tracks the high-level trajectory, and an economic MPC. We first validate that DDP yields as good result as the direct method. Second, we compare the three low-level controllers and verify the necessity of the two-stage decomposition through the studies on a bioreactor. (c) 2021 Elsevier Ltd. All rights reserved. | - |
dc.identifier.bibliographicCitation | COMPUTERS & CHEMICAL ENGINEERING, v.154, pp.107465 | - |
dc.identifier.doi | 10.1016/j.compchemeng.2021.107465 | - |
dc.identifier.issn | 0098-1354 | - |
dc.identifier.scopusid | 2-s2.0-85111935118 | - |
dc.identifier.uri | https://scholarworks.unist.ac.kr/handle/201301/81577 | - |
dc.identifier.wosid | 000697031900005 | - |
dc.language | 영어 | - |
dc.publisher | PERGAMON-ELSEVIER SCIENCE LTD | - |
dc.title | Model-based reinforcement learning and predictive control for two-stage optimal control of fed-batch bioreactor | - |
dc.type | Article | - |
dc.description.isOpenAccess | FALSE | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Interdisciplinary Applications; Engineering, Chemical | - |
dc.relation.journalResearchArea | Computer Science; Engineering | - |
dc.type.docType | Article; Early Access | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.subject.keywordAuthor | Fed-batch bioreactor | - |
dc.subject.keywordAuthor | Dynamic optimization | - |
dc.subject.keywordAuthor | Reinforcement learning | - |
dc.subject.keywordAuthor | Model predictive control | - |
dc.subject.keywordPlus | DYNAMIC OPTIMIZATION | - |
dc.subject.keywordPlus | ADAPTIVE-CONTROL | - |
dc.subject.keywordPlus | FERMENTATION | - |
Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Tel : 052-217-1404 / Email : scholarworks@unist.ac.kr
Copyright (c) 2023 by UNIST LIBRARY. All rights reserved.
ScholarWorks@UNIST was established as an OAK Project for the National Library of Korea.