Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/40566
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Elmaz, Furkan | - |
dc.contributor.author | DI CAPRIO, Ulderico | - |
dc.contributor.author | WU, Min | - |
dc.contributor.author | Wouters, Yentl | - |
dc.contributor.author | Van Der Vorst, Geert | - |
dc.contributor.author | Vandervoort, Niels | - |
dc.contributor.author | Anwar, Ali | - |
dc.contributor.author | LEBLEBICI, Mumin enis | - |
dc.contributor.author | Hellinckx, Peter | - |
dc.contributor.author | Mercelis, Siegfried | - |
dc.date.accessioned | 2023-07-12T12:37:44Z | - |
dc.date.available | 2023-07-12T12:37:44Z | - |
dc.date.issued | 2023 | - |
dc.date.submitted | 2023-07-06T13:06:30Z | - |
dc.identifier.citation | COMPUTERS & CHEMICAL ENGINEERING, 176 (Art N° 108310) | - |
dc.identifier.uri | http://hdl.handle.net/1942/40566 | - |
dc.description.abstract | In chemical and pharmaceutical industries, process control optimization is a crucial step to improve economical efficiency and the environmental impact. The current state-of-practice heavily relies on expert knowledge and extensive lab experiments. This not only increases the development time but also limits the discovery of new strategies. In this study, we propose Reinforcement Learning-based optimization approach for solvent-switch processes. We utilize a digital twin as the environment for a process designed to switch the THF to 1-propanol. A reward function is created for minimizing the process time and constraints are implemented using logarithmic barrier functions. A PPO agent is trained on the environment. The agent proposed a novel strategy that combines two conventionally separate phases, evaporation and constant volume distillation. This strategy resulted in an overall cost decrease of 24.9% compared to the baseline strategy. Moreover, results were verified experimentally on a pilot plant of Johnson & Johnson (J & J). | - |
dc.description.sponsorship | The authors acknowledge the support of the DAP2CHEM ICON project, funded by VLAIO, Belgium and Catalisti under project number HBC.2020.2455. This funding has been instrumental for the completion of this work. | - |
dc.language.iso | en | - |
dc.publisher | PERGAMON-ELSEVIER SCIENCE LTD | - |
dc.rights | 2023 Elsevier Ltd. All rights reserved | - |
dc.subject.other | Reinforcement learning | - |
dc.subject.other | Process control | - |
dc.subject.other | Solvent-switch optimization | - |
dc.subject.other | Separation process | - |
dc.title | Reinforcement learning-based approach for optimizing solvent-switch | - |
dc.type | Journal Contribution | - |
dc.identifier.volume | 176 | - |
local.format.pages | 10 | - |
local.bibliographicCitation.jcat | A1 | - |
dc.description.notes | Elmaz, F (corresponding author), Univ Antwerp, IDLab, imec, Fac Appl Engn, St Pietersvliet 7, B-2000 Antwerp, Belgium. | - |
dc.description.notes | furkan.elmaz@uantwerpen.be; ulderico.dicaprio@kuleuven.be; | - |
dc.description.notes | min.wu@kuleuven.be; ywouters@ITS.JNJ.com; ulderico.dicaprio@kuleuven.be; | - |
dc.description.notes | nvanderv@its.jnj.com; ali.anwar@uantwerpen.be; | - |
dc.description.notes | muminenis.leblebici@kuleuven.be; peter.hellinckx@uantwerpen.be; | - |
dc.description.notes | siegfried.mercelis@uantwerpen.be | - |
local.publisher.place | THE BOULEVARD, LANGFORD LANE, KIDLINGTON, OXFORD OX5 1GB, ENGLAND | - |
local.type.refereed | Refereed | - |
local.type.specified | Article | - |
local.bibliographicCitation.artnr | 108310 | - |
dc.identifier.doi | 10.1016/j.compchemeng.2023.108310 | - |
dc.identifier.isi | 001012429400001 | - |
dc.contributor.orcid | Leblebici, Mumin Enis/0000-0003-4599-9412 | - |
local.provider.type | wosris | - |
local.description.affiliation | [Elmaz, Furkan; Anwar, Ali; Mercelis, Siegfried] Univ Antwerp, IDLab, imec, Fac Appl Engn, St Pietersvliet 7, B-2000 Antwerp, Belgium. | - |
local.description.affiliation | [Di Caprio, Ulderico; Wu, Min; Leblebici, M. Enis] Katholieke Univ Leuven, Ctr Ind Proc Technol, Dept Chem Engn, Agoralaan Bldg B, B-3590 Diepenbeek, Belgium. | - |
local.description.affiliation | [Wouters, Yentl; Van Der Vorst, Geert; Vandervoort, Niels] Janssen Pharmaceut NV, Chem Proc R&D, Turnhoutseweg 30, B-2340 Beerse, Belgium. | - |
local.description.affiliation | [Hellinckx, Peter] Univ Antwerp, Fac Appl Engn, Groenenborgerlaan 171, B-2020 Antwerp, Belgium. | - |
local.uhasselt.international | no | - |
item.fullcitation | Elmaz, Furkan; DI CAPRIO, Ulderico; WU, Min; Wouters, Yentl; Van Der Vorst, Geert; Vandervoort, Niels; Anwar, Ali; LEBLEBICI, Mumin enis; Hellinckx, Peter & Mercelis, Siegfried (2023) Reinforcement learning-based approach for optimizing solvent-switch. In: COMPUTERS & CHEMICAL ENGINEERING, 176 (Art N° 108310). | - |
item.fulltext | With Fulltext | - |
item.accessRights | Restricted Access | - |
item.contributor | Elmaz, Furkan | - |
item.contributor | DI CAPRIO, Ulderico | - |
item.contributor | WU, Min | - |
item.contributor | Wouters, Yentl | - |
item.contributor | Van Der Vorst, Geert | - |
item.contributor | Vandervoort, Niels | - |
item.contributor | Anwar, Ali | - |
item.contributor | LEBLEBICI, Mumin enis | - |
item.contributor | Hellinckx, Peter | - |
item.contributor | Mercelis, Siegfried | - |
crisitem.journal.issn | 0098-1354 | - |
crisitem.journal.eissn | 1873-4375 | - |
Appears in Collections: | Research publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Reinforcement learning-based approach for optimizing solvent-switch processes.pdf Restricted Access | Published version | 1.88 MB | Adobe PDF | View/Open Request a copy |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.