Publication:
Physics-informed recurrent neural networks and hyper-parameter optimization for dynamic process systems

dc.contributor.departmentDepartment of Chemical and Biological Engineering
dc.contributor.departmentGraduate School of Sciences and Engineering
dc.contributor.departmentKUTEM (Koç University Tüpraş Energy Center)
dc.contributor.kuauthorAsrav, Tuse
dc.contributor.kuauthorAydın, Erdal
dc.contributor.schoolcollegeinstituteCollege of Engineering
dc.contributor.schoolcollegeinstituteGRADUATE SCHOOL OF SCIENCES AND ENGINEERING
dc.contributor.schoolcollegeinstituteResearch Center
dc.date.accessioned2024-11-09T23:52:42Z
dc.date.issued2023
dc.description.abstractMany of the processes in chemical engineering applications are of dynamic nature. Mechanistic modeling of these processes is challenging due to the complexity and uncertainty. On the other hand, recurrent neural networks are useful to be utilized to model dynamic processes by using the available data. Although these networks can capture the complexities, they might contribute to overfitting and require high-quality and adequate data. In this study, two different physics-informed training approaches are investigated. The first approach is using a multi-objective loss function in the training including the discretized form of the differential equation. The second approach is using a hybrid recurrent neural network cell with embedded physics-informed and data-driven nodes performing Euler discretization. Physics-informed neural networks can improve test performance even though decrease in training performance might be observed. Finally, smaller and more robust architecture are obtained using hyper-parameter optimization when physics-informed training is performed. © 2023 Elsevier Ltd
dc.description.indexedbyScopus
dc.description.indexedbyWOS
dc.description.openaccessYES
dc.description.publisherscopeInternational
dc.description.sponsoredbyTubitakEuN/A
dc.description.volume173
dc.identifier.doi10.1016/j.compchemeng.2023.108195
dc.identifier.issn0098-1354
dc.identifier.quartileQ2
dc.identifier.scopus2-s2.0-85150051538
dc.identifier.urihttps://hdl.handle.net/20.500.14288/14873
dc.identifier.wos957463700001
dc.keywordsHybrid neural networks
dc.keywordsHyper-parameter optimization
dc.keywordsMachine learning
dc.keywordsPhysics-informed neural networks
dc.keywordsRecurrent neural networks
dc.language.isoeng
dc.publisherElsevier
dc.relation.ispartofComputers and Chemical Engineering
dc.subjectTransfer of learning
dc.subjectHybrid modeling
dc.subjectBatch fermentation
dc.titlePhysics-informed recurrent neural networks and hyper-parameter optimization for dynamic process systems
dc.typeJournal Article
dspace.entity.typePublication
local.contributor.kuauthorAsrav, Tuse
local.contributor.kuauthorAydın, Erdal
local.publication.orgunit1GRADUATE SCHOOL OF SCIENCES AND ENGINEERING
local.publication.orgunit1College of Engineering
local.publication.orgunit1Research Center
local.publication.orgunit2Department of Chemical and Biological Engineering
local.publication.orgunit2KUTEM (Koç University Tüpraş Energy Center)
local.publication.orgunit2Graduate School of Sciences and Engineering
relation.isOrgUnitOfPublicationc747a256-6e0c-4969-b1bf-3b9f2f674289
relation.isOrgUnitOfPublication3fc31c89-e803-4eb1-af6b-6258bc42c3d8
relation.isOrgUnitOfPublication6ce65247-25c7-415b-a771-a9f0249b3a40
relation.isOrgUnitOfPublication.latestForDiscoveryc747a256-6e0c-4969-b1bf-3b9f2f674289
relation.isParentOrgUnitOfPublication8e756b23-2d4a-4ce8-b1b3-62c794a8c164
relation.isParentOrgUnitOfPublication434c9663-2b11-4e66-9399-c863e2ebae43
relation.isParentOrgUnitOfPublicationd437580f-9309-4ecb-864a-4af58309d287
relation.isParentOrgUnitOfPublication.latestForDiscovery8e756b23-2d4a-4ce8-b1b3-62c794a8c164

Files