Show simple item record

dc.contributor.authorLennon, Kyle R.
dc.contributor.authorMcKinley, Gareth H.
dc.contributor.authorSwan, James W.
dc.date.accessioned2024-03-27T19:31:12Z
dc.date.available2024-03-27T19:31:12Z
dc.date.issued2023-06-26
dc.identifier.issn0027-8424
dc.identifier.issn1091-6490
dc.identifier.urihttps://hdl.handle.net/1721.1/153959
dc.description.abstractThe formulation of rheological constitutive equations—models that relate internal stresses and deformations in complex fluids—is a critical step in the engineering of systems involving soft materials. While data-driven models provide accessible alternatives to expensive first-principles models and less accurate empirical models in many engineering disciplines, the development of similar models for complex fluids has lagged. The diversity of techniques for characterizing non-Newtonian fluid dynamics creates a challenge for classical machine learning approaches, which require uniformly structured training data. Consequently, early machine-learning based constitutive equations have not been portable between different deformation protocols or mechanical observables. Here, we present a data-driven framework that resolves such issues, allowing rheologists to construct learnable models that incorporate essential physical information, while remaining agnostic to details regarding particular experimental protocols or flow kinematics. These scientific machine learning models incorporate a universal approximator within a materially objective tensorial constitutive framework. By construction, these models respect physical constraints, such as frame-invariance and tensor symmetry, required by continuum mechanics. We demonstrate that this framework facilitates the rapid discovery of accurate constitutive equations from limited data and that the learned models may be used to describe more kinematically complex flows. This inherent flexibility admits the application of these “digital fluid twins” to a range of material systems and engineering problems. We illustrate this flexibility by deploying a trained model within a multidimensional computational fluid dynamics simulation—a task that is not achievable using any previously developed data-driven rheological equation of state.en_US
dc.language.isoen
dc.publisherProceedings of the National Academy of Sciencesen_US
dc.relation.isversionof10.1073/pnas.2304669120en_US
dc.rightsCreative Commons Attribution-NonCommercial-NoDerivs Licenseen_US
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/en_US
dc.sourcePNASen_US
dc.subjectMultidisciplinaryen_US
dc.titleScientific machine learning for modeling and simulating complex fluidsen_US
dc.typeArticleen_US
dc.identifier.citationLennon, Kyle R., McKinley, Gareth H. and Swan, James W. 2023. "Scientific machine learning for modeling and simulating complex fluids." Proceedings of the National Academy of Sciences, 120 (27).
dc.contributor.departmentMassachusetts Institute of Technology. Department of Chemical Engineering
dc.contributor.departmentHatsopoulos Microfluids Laboratory (Massachusetts Institute of Technology)
dc.contributor.departmentMassachusetts Institute of Technology. Department of Mechanical Engineering
dc.relation.journalProceedings of the National Academy of Sciencesen_US
dc.eprint.versionFinal published versionen_US
dc.type.urihttp://purl.org/eprint/type/JournalArticleen_US
eprint.statushttp://purl.org/eprint/status/PeerRevieweden_US
dc.date.updated2024-03-27T19:26:24Z
dspace.orderedauthorsLennon, KR; McKinley, GH; Swan, JWen_US
dspace.date.submission2024-03-27T19:26:26Z
mit.journal.volume120en_US
mit.journal.issue27en_US
mit.licensePUBLISHER_CC
mit.metadata.statusAuthority Work and Publication Information Neededen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record