There are no files associated with this item.
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.citation.number | 6 | - |
dc.citation.startPage | e17658 | - |
dc.citation.title | AICHE JOURNAL | - |
dc.citation.volume | 68 | - |
dc.contributor.author | Oh, Tae Hoon | - |
dc.contributor.author | Park, Hyun Min | - |
dc.contributor.author | Kim, Jong Woo | - |
dc.contributor.author | Lee, Jong Min | - |
dc.date.accessioned | 2024-03-13T09:35:09Z | - |
dc.date.available | 2024-03-13T09:35:09Z | - |
dc.date.created | 2024-03-13 | - |
dc.date.issued | 2022-06 | - |
dc.description.abstract | As the digital transformation of the bioprocess is progressing, several studies propose to apply data-based methods to obtain a substrate feeding strategy that minimizes the operating cost of a semi-batch bioreactor. However, the negligent application of model-free reinforcement learning (RL) has a high chance to fail on improving the existing control policy because the available amount of data is limited. In this article, we propose an integrated algorithm of double-deep Q-network and model predictive control. The proposed method learns the action-value function in an off-policy fashion and solves the model-based optimal control problem where the terminal cost is assigned by the action-value function. For simulation study, the proposed method, model-based method, and model-free methods are applied to the industrial scale penicillin process. The results show that the proposed method outperforms other methods, and it can learn with fewer data than model-free RL algorithms. | - |
dc.identifier.bibliographicCitation | AICHE JOURNAL, v.68, no.6, pp.e17658 | - |
dc.identifier.doi | 10.1002/aic.17658 | - |
dc.identifier.issn | 0001-1541 | - |
dc.identifier.scopusid | 2-s2.0-85126045658 | - |
dc.identifier.uri | https://scholarworks.unist.ac.kr/handle/201301/81565 | - |
dc.identifier.wosid | 000767144600001 | - |
dc.language | 영어 | - |
dc.publisher | WILEY | - |
dc.title | Integration of reinforcement learning and model predictive control to optimize semi-batch bioreactor | - |
dc.type | Article | - |
dc.description.isOpenAccess | FALSE | - |
dc.relation.journalWebOfScienceCategory | Engineering, Chemical | - |
dc.relation.journalResearchArea | Engineering | - |
dc.type.docType | Article; Early Access | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.subject.keywordAuthor | bioprocess | - |
dc.subject.keywordAuthor | deep neural network | - |
dc.subject.keywordAuthor | model predictive control | - |
dc.subject.keywordAuthor | optimal control | - |
dc.subject.keywordAuthor | reinforcement learning | - |
dc.subject.keywordPlus | FED-BATCH FERMENTATION | - |
dc.subject.keywordPlus | PENICILLIN PRODUCTION | - |
dc.subject.keywordPlus | STRUCTURED MODEL | - |
dc.subject.keywordPlus | BIG DATA | - |
dc.subject.keywordPlus | STABILITY | - |
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.