Dimensional analysis meets AI for non-Newtonian droplet generation

Hormozinezhad, Farnoosh; Barnes, Claire; Fabregat, Alexandre; Cito, Salvatore; Giudice, Francesco Del

doi:10.1039/d4lc00946k

Journal article 120 views 38 downloads

Dimensional analysis meets AI for non-Newtonian droplet generation

Farnoosh Hormozinezhad, Claire Barnes

, Alexandre Fabregat

, Salvatore Cito

, Francesco Del Giudice

Lab on a Chip, Volume: 25, Issue: 7, Pages: 1681 - 1693

Swansea University Authors: Claire Barnes , Francesco Del Giudice

PDF | Version of Record

© The Royal Society of Chemistry 2025. This Open Access Article is licensed under a Creative Commons Attribution 3.0 Unported Licence (CC BY).
Download (3.07MB)

Check full text

DOI (Published version): 10.1039/d4lc00946k

Abstract

Non-Newtonian droplets are used across various applications, including pharmaceuticals, food processing, drug delivery and material science. However, predicting droplet formation using such complex fluids is challenging due to the intricate multiphase interactions between fluids with varying viscosi...

Full description

Published in:	Lab on a Chip
ISSN:	1473-0197 1473-0189
Published:	Royal Society of Chemistry (RSC) 2025
Online Access:	Check full text
URI:	https://cronfa.swan.ac.uk/Record/cronfa68926

first_indexed	2025-02-19T13:37:44Z
last_indexed	2025-03-29T05:27:25Z
id	cronfa68926
recordtype	SURis
fullrecord	<?xml version="1.0"?><rfc1807><datestamp>2025-03-28T13:49:34.2514832</datestamp><bib-version>v2</bib-version><id>68926</id><entry>2025-02-19</entry><title>Dimensional analysis meets AI for non-Newtonian droplet generation</title><swanseaauthors><author><sid>024232879fc13d5ceac584360af8742c</sid><ORCID>0000-0003-1031-7127</ORCID><firstname>Claire</firstname><surname>Barnes</surname><name>Claire Barnes</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>742d483071479b44d7888e16166b1309</sid><ORCID>0000-0002-9414-6937</ORCID><firstname>Francesco</firstname><surname>Del Giudice</surname><name>Francesco Del Giudice</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2025-02-19</date><deptcode>EAAS</deptcode><abstract>Non-Newtonian droplets are used across various applications, including pharmaceuticals, food processing, drug delivery and material science. However, predicting droplet formation using such complex fluids is challenging due to the intricate multiphase interactions between fluids with varying viscosities, elastic properties and geometrical constraints. In this study, we introduce a novel hybrid machine-learning architecture that integrates dimensional analysis with machine learning to predict the flow rates required to generate droplets with specified sizes in systems involving non-Newtonian fluids. Unlike previous approaches, our model is designed to accommodate shear-rate-dependent viscosities and a simple estimate of the elastic properties of the fluids. It provides accurate predictions of the dispersed and continuous phases flow rates for given droplet length, height, and viscosity curves, even when the fluid properties deviate from those used during training. Our model demonstrates strong predictive power, achieving R2 values of up to 0.82 for unseen data. The significance of our work lies in its ability to generalize across a broad range of non-Newtonian systems having different viscosity curves, offering a powerful tool for optimizing droplet generation. This model represents a significant advancement in the application of machine learning to microfluidics, providing new opportunities for efficient experimental design in complex multiphase systems.</abstract><type>Journal Article</type><journal>Lab on a Chip</journal><volume>25</volume><journalNumber>7</journalNumber><paginationStart>1681</paginationStart><paginationEnd>1693</paginationEnd><publisher>Royal Society of Chemistry (RSC)</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>1473-0197</issnPrint><issnElectronic>1473-0189</issnElectronic><keywords/><publishedDay>12</publishedDay><publishedMonth>2</publishedMonth><publishedYear>2025</publishedYear><publishedDate>2025-02-12</publishedDate><doi>10.1039/d4lc00946k</doi><url/><notes/><college>COLLEGE NANME</college><department>Engineering and Applied Sciences School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>EAAS</DepartmentCode><institution>Swansea University</institution><apcterm>SU Library paid the OA fee (TA Institutional Deal)</apcterm><funders>FH acknowledges funding from the European Union's Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No. 945413 and from the Universitat Rovira i Virgili (URV). FDG acknowledges support from Royal Society Grant RS/R1/221263, BBSRC Grant BB/Y513337/1, and the Ser Cymru programme ‘Enhancing Competitiveness Equipment Awards’ Grant MA/VG/2715/22-PN47.</funders><projectreference/><lastEdited>2025-03-28T13:49:34.2514832</lastEdited><Created>2025-02-19T13:19:52.3166854</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Engineering and Applied Sciences - Biomedical Engineering</level></path><authors><author><firstname>Farnoosh</firstname><surname>Hormozinezhad</surname><order>1</order></author><author><firstname>Claire</firstname><surname>Barnes</surname><orcid>0000-0003-1031-7127</orcid><order>2</order></author><author><firstname>Alexandre</firstname><surname>Fabregat</surname><orcid>0000-0002-6032-2605</orcid><order>3</order></author><author><firstname>Salvatore</firstname><surname>Cito</surname><orcid>0000-0001-7626-3374</orcid><order>4</order></author><author><firstname>Francesco</firstname><surname>Del Giudice</surname><orcid>0000-0002-9414-6937</orcid><order>5</order></author></authors><documents><document><filename>68926__33648__0f72753bac2a46c9a6aceecf64481a7a.pdf</filename><originalFilename>68926.VOR.pdf</originalFilename><uploaded>2025-02-19T13:35:41.1619632</uploaded><type>Output</type><contentLength>3221728</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>© The Royal Society of Chemistry 2025. This Open Access Article is licensed under a Creative Commons Attribution 3.0 Unported Licence (CC BY).</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by/3.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling	2025-03-28T13:49:34.2514832 v2 68926 2025-02-19 Dimensional analysis meets AI for non-Newtonian droplet generation 024232879fc13d5ceac584360af8742c 0000-0003-1031-7127 Claire Barnes Claire Barnes true false 742d483071479b44d7888e16166b1309 0000-0002-9414-6937 Francesco Del Giudice Francesco Del Giudice true false 2025-02-19 EAAS Non-Newtonian droplets are used across various applications, including pharmaceuticals, food processing, drug delivery and material science. However, predicting droplet formation using such complex fluids is challenging due to the intricate multiphase interactions between fluids with varying viscosities, elastic properties and geometrical constraints. In this study, we introduce a novel hybrid machine-learning architecture that integrates dimensional analysis with machine learning to predict the flow rates required to generate droplets with specified sizes in systems involving non-Newtonian fluids. Unlike previous approaches, our model is designed to accommodate shear-rate-dependent viscosities and a simple estimate of the elastic properties of the fluids. It provides accurate predictions of the dispersed and continuous phases flow rates for given droplet length, height, and viscosity curves, even when the fluid properties deviate from those used during training. Our model demonstrates strong predictive power, achieving R2 values of up to 0.82 for unseen data. The significance of our work lies in its ability to generalize across a broad range of non-Newtonian systems having different viscosity curves, offering a powerful tool for optimizing droplet generation. This model represents a significant advancement in the application of machine learning to microfluidics, providing new opportunities for efficient experimental design in complex multiphase systems. Journal Article Lab on a Chip 25 7 1681 1693 Royal Society of Chemistry (RSC) 1473-0197 1473-0189 12 2 2025 2025-02-12 10.1039/d4lc00946k COLLEGE NANME Engineering and Applied Sciences School COLLEGE CODE EAAS Swansea University SU Library paid the OA fee (TA Institutional Deal) FH acknowledges funding from the European Union's Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No. 945413 and from the Universitat Rovira i Virgili (URV). FDG acknowledges support from Royal Society Grant RS/R1/221263, BBSRC Grant BB/Y513337/1, and the Ser Cymru programme ‘Enhancing Competitiveness Equipment Awards’ Grant MA/VG/2715/22-PN47. 2025-03-28T13:49:34.2514832 2025-02-19T13:19:52.3166854 Faculty of Science and Engineering School of Engineering and Applied Sciences - Biomedical Engineering Farnoosh Hormozinezhad 1 Claire Barnes 0000-0003-1031-7127 2 Alexandre Fabregat 0000-0002-6032-2605 3 Salvatore Cito 0000-0001-7626-3374 4 Francesco Del Giudice 0000-0002-9414-6937 5 68926__33648__0f72753bac2a46c9a6aceecf64481a7a.pdf 68926.VOR.pdf 2025-02-19T13:35:41.1619632 Output 3221728 application/pdf Version of Record true © The Royal Society of Chemistry 2025. This Open Access Article is licensed under a Creative Commons Attribution 3.0 Unported Licence (CC BY). true eng http://creativecommons.org/licenses/by/3.0/
title	Dimensional analysis meets AI for non-Newtonian droplet generation
spellingShingle	Dimensional analysis meets AI for non-Newtonian droplet generation Claire Barnes Francesco Del Giudice
title_short	Dimensional analysis meets AI for non-Newtonian droplet generation
title_full	Dimensional analysis meets AI for non-Newtonian droplet generation
title_fullStr	Dimensional analysis meets AI for non-Newtonian droplet generation
title_full_unstemmed	Dimensional analysis meets AI for non-Newtonian droplet generation
title_sort	Dimensional analysis meets AI for non-Newtonian droplet generation
author_id_str_mv	024232879fc13d5ceac584360af8742c 742d483071479b44d7888e16166b1309
author_id_fullname_str_mv	024232879fc13d5ceac584360af8742c_*_Claire Barnes 742d483071479b44d7888e16166b1309_*_Francesco Del Giudice
author	Claire Barnes Francesco Del Giudice
author2	Farnoosh Hormozinezhad Claire Barnes Alexandre Fabregat Salvatore Cito Francesco Del Giudice
format	Journal article
container_title	Lab on a Chip
container_volume	25
container_issue	7
container_start_page	1681
publishDate	2025
institution	Swansea University
issn	1473-0197 1473-0189
doi_str_mv	10.1039/d4lc00946k
publisher	Royal Society of Chemistry (RSC)
college_str	Faculty of Science and Engineering
hierarchytype
hierarchy_top_id	facultyofscienceandengineering
hierarchy_top_title	Faculty of Science and Engineering
hierarchy_parent_id	facultyofscienceandengineering
hierarchy_parent_title	Faculty of Science and Engineering
department_str	School of Engineering and Applied Sciences - Biomedical Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Engineering and Applied Sciences - Biomedical Engineering
document_store_str	1
active_str	0
description	Non-Newtonian droplets are used across various applications, including pharmaceuticals, food processing, drug delivery and material science. However, predicting droplet formation using such complex fluids is challenging due to the intricate multiphase interactions between fluids with varying viscosities, elastic properties and geometrical constraints. In this study, we introduce a novel hybrid machine-learning architecture that integrates dimensional analysis with machine learning to predict the flow rates required to generate droplets with specified sizes in systems involving non-Newtonian fluids. Unlike previous approaches, our model is designed to accommodate shear-rate-dependent viscosities and a simple estimate of the elastic properties of the fluids. It provides accurate predictions of the dispersed and continuous phases flow rates for given droplet length, height, and viscosity curves, even when the fluid properties deviate from those used during training. Our model demonstrates strong predictive power, achieving R2 values of up to 0.82 for unseen data. The significance of our work lies in its ability to generalize across a broad range of non-Newtonian systems having different viscosity curves, offering a powerful tool for optimizing droplet generation. This model represents a significant advancement in the application of machine learning to microfluidics, providing new opportunities for efficient experimental design in complex multiphase systems.
published_date	2025-02-12T06:19:54Z
_version_	1830350639035580416
score	11.317152

Dimensional analysis meets AI for non-Newtonian droplet generation

Similar Items