Logo do repositório
 
Publicação

Bioprocess model-predictive control with physics-informed neural networks

2025-12Artigo científico Acesso aberto
Ver registo simples
dc.contributor.authorCatalão, Marta
dc.contributor.authorPinto, José
dc.contributor.authorTorres, Criatiana A. V.
dc.contributor.authorFreitas, Filomena
dc.contributor.authorReis, Maria
dc.contributor.authorCosta, Rafael S.
dc.contributor.authorOliveira, Rui
dc.contributor.institutionDQ - Departamento de Química
dc.contributor.institutionUCIBIO - Applied Molecular Biosciences Unit
dc.contributor.pblElsevier Science B.V., Amsterdam.
dc.date.accessioned2026-02-05T12:40:01Z
dc.date.available2026-02-05T12:40:01Z
dc.date.issued2025-12
dc.description.abstractMany previous studies have investigated the economic production of polyhydroxyalkanoates (PHA) by natural microbiomes. A key underlying strategy is the feast and famine (F/F) feeding regimen for bacteria selection. For this purpose, a sequencing batch reactor (SBR) is commonly operated in a sequence of F/F cycles until an evolved microbiome is attained with high PHA storage capacity. The effectiveness of this process is critically dependent on control parameters such as the hydraulic retention time (HRT), organic loading rate (OLR) and carbon-to-nitrogen ratio (C/N) applied at each cycle. This study evaluates for the first time a physics-informed neural network (PINN) for model predictive control (MPC) of microbiome evolution in a SBR. A PINN model was trained on historical data collected in a SBR operated over 93 days and 31 cycles. Carbon (acetate), Nitrogen (ammonium), Volatile Suspended Solids (VSS) and intracellular PHA concentration data were used to train and validate the PINN. Subsequently, a second SBR experiment was conducted under automatic control of the PINN over a period of 36 days and 12 cycles. A transfer learning method was implemented leverage on in-process data to minimize process-model mismatch. The results showed a systematic cycle-to-cycle prediction error decrease. The intracellular PHA concentration systematic increased from 0.51 % (w/w) to 16.5 % (w/w) at the 12th cycle (32-fold increase). The final evolved microbiome, collected at the 12th cycle, was inoculated in a production reactor yielding a final intracellular PHA content of 52.86 % (w/w) and volumetric concentration of 8.93 g PHA/L. Overall, the PINN-MPC method has shown high potential to efficiently explore the reactor design space and to implement in autonomy efficient strategies for natural microbiome evolution.en
dc.description.versionpublishersversion
dc.description.versionpublished
dc.format.extent13
dc.format.extent5306706
dc.identifier.doi10.1016/j.jprocont.2025.103594
dc.identifier.issn0959-1524
dc.identifier.otherPURE: 136387695
dc.identifier.otherPURE UUID: fc3d0f41-b732-433e-baa6-d4f0d64cb612
dc.identifier.otherWOS: 001627660300002
dc.identifier.otherScopus: 105025824539
dc.identifier.otherORCID: /0000-0002-9430-4640/work/204875709
dc.identifier.urihttp://hdl.handle.net/10362/200041
dc.identifier.urlhttps://www.scopus.com/pages/publications/105025824539
dc.identifier.urlhttps://www.webofscience.com/wos/woscc/full-record/WOS:001627660300002
dc.language.isoeng
dc.peerreviewedyes
dc.subjectPhysics Informed Neural Networks (PINN)
dc.subjectTransfer learning
dc.subjectModel-predictive control (MPC)
dc.subjectPolyhydroxyalkanoates (PHA)
dc.subjectNatural microbiomes
dc.subjectSequencing Batch Reactor (SBR)
dc.titleBioprocess model-predictive control with physics-informed neural networksen
dc.title.subtitleDriving microbiome evolution toward high polyhydroxyalkanoates production capacityen
dc.typejournal article
degois.publication.firstPage1
degois.publication.lastPage13
degois.publication.titleJournal of Process Control
degois.publication.volume156
dspace.entity.typePublication
rcaap.rightsopenAccess

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura
Nome:
Costa._2025_..pdf
Tamanho:
5.06 MB
Formato:
Adobe Portable Document Format
Ver/Abrir

Coleções

Home collection (FCT)