Show simple item record

dc.contributor.authorMasclans Serrat, Núria
dc.contributor.authorVázquez-Novoa, Fernando
dc.contributor.authorBernades, Marc
dc.contributor.authorBadia Sala, Rosa Maria
dc.contributor.authorJofre Cruanyes, Lluís
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Mecànica de Fluids
dc.contributor.otherUniversitat Politècnica de Catalunya. Doctorat en Enginyeria Mecànica, Fluids i Aeronàutica
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament d'Arquitectura de Computadors
dc.contributor.otherBarcelona Supercomputing Center
dc.date.accessioned2023-09-07T09:46:54Z
dc.date.available2023-09-07T09:46:54Z
dc.date.issued2023-11
dc.identifier.citationMasclans, N. [et al.]. Thermodynamics-informed neural network for recovering supercritical fluid thermophysical information from turbulent velocity data. "International journal of thermofluids", Novembre 2023, vol. 20, article 100448.
dc.identifier.issn2666-2027
dc.identifier.urihttp://hdl.handle.net/2117/393209
dc.description.abstractRecent research has highlighted the potential of supercritical fluids under high-pressure transcritical conditions to achieve microconfined turbulence as a result of the thermophysical properties they exhibit in the vicinity of the pseudo-boiling region. This has led to increased interest in understanding their hybrid thermophysical properties when operating near the pseudo-boiling transitioning region. However, despite the potential benefits of microfluidic systems working under transcritical conditions, limited experimental data is available due to the inherent challenges of performing experiments at high-pressure conditions. In addition, traditional experimental methods, such as particle image velocimetry and particle tracking velocimetry, are inadequate for measuring thermophysical properties under such conditions, since they are primarily designed for velocity-related data acquisition. In this regard, this work introduces an efficient thermodynamics-informed neural network framework for reconstructing thermophysical information from velocity data in high-pressure turbulent transcritical regimes. The proposed model incorporates thermophysical constraints through a thermodynamics-informed loss function consisting of the residual of the real-gas equation of state and integrates boundary conditions into the network’s architecture to ensure their satisfaction. The performance of the proposed framework is evaluated through the analysis of two test cases and compared against non-physically informed models. The results demonstrate the superior accuracy, robustness, and satisfaction of physical constraints achieved by the proposed model, as well as its ability to reconstruct averaged thermophysical profiles and preserve bulk quantities with a relative error reduction of approximately 2×. In addition, the physically-consistent predictions provided by the model enable a more accurate reconstruction of dependent thermophysical properties.
dc.description.sponsorshipThe authors gratefully acknowledge the Formació de Professorat Universitari scholarship (FPU-UPC 2022) of the Universitat Politècnica de Catalunya BarcelonaTech (UPC) (Spain), the SRG program (2021-SGR-01045) of the Generalitat de Catalunya (Spain), the Beatriz Galindo program (Distinguished Researcher, BGP18/00026) of the Ministerio de Educación Formación Profesional (Spain), and the computer resources at FinisTerrae III & MareNostrum and the technical support provided by CESGA & Barcelona Supercomputing Center (RES-IM-2023-1-0005, RES-IM-2023-2-0005). This work is funded by the European Union (ERC, SCRAMBLE, 101040379).
dc.language.isoeng
dc.publisherElsevier
dc.rightsAttribution 4.0 International
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subjectÀrees temàtiques de la UPC::Enginyeria mecànica::Mecànica de fluids
dc.subject.lcshDeep learning
dc.subject.lcshSupercritical fluids
dc.subject.otherThermodynamics-informed neural network
dc.subject.otherTurbulent flow
dc.titleThermodynamics-informed neural network for recovering supercritical fluid thermophysical information from turbulent velocity data
dc.typeArticle
dc.subject.lemacAprenentatge profund
dc.subject.lemacFluids supercrítics
dc.contributor.groupUniversitat Politècnica de Catalunya. GReCEF- Grup de Recerca en Ciència i Enginyeria de Fluids
dc.identifier.doi10.1016/j.ijft.2023.100448
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttps://www.sciencedirect.com/science/article/pii/S2666202723001635
dc.rights.accessOpen Access
local.identifier.drac36952863
dc.description.versionPostprint (published version)
dc.relation.projectidinfo:eu-repo/grantAgreement/EC/HE/101040379/EU/Turbulence-On-a-Chip: Supercritically Overcoming the Energy Frontier in Microfluidics/SCRAMBLE
local.citation.authorMasclans, N.; Vázquez-Novoa, F.; Bernades, M.; Badia, R.M.; Jofre, L.
local.citation.publicationNameInternational journal of thermofluids
local.citation.volume20
local.citation.numberarticle 100448


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record