EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Scientific machine learning for modeling and simulating complex fluids

Kyle R Lennon iD, Gareth H McKinley iD, James W Swan

Proceedings of the National Academy of Sciences · 04.07.2023 · 120 (27)

DOI: 10.1073/pnas.2304669120 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the National Academy of Sciences, online erschienen am 26.06.2023. Verfasst von Kyle R Lennon und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02142. Die Arbeit wurde bisher 65-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: U.S. Department of Energy (DOE).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The 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.

Schlagwörter

Stichwörter der Autor:innen

constitutive equationmachine learningrheologysoft matter

Autor:innen und Institutionen

  • Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02142.
  • Hatsopoulos Microfluids Laboratory, Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139.

ORCID-Profile: Kyle R Lennon, Gareth H McKinley

Förderung

  • U.S. Department of Energy (DOE)

Zitieren

APA

Lennon, K. R., McKinley, G. H., & Swan, J. W. (2023). Scientific machine learning for modeling and simulating complex fluids. Proceedings of the National Academy of Sciences, 120(27). https://doi.org/10.1073/pnas.2304669120

Vancouver

Lennon KR, McKinley GH, Swan JW. Scientific machine learning for modeling and simulating complex fluids. Proceedings of the National Academy of Sciences. 2023;120(27). doi:10.1073/pnas.2304669120

BibTeX
@article{Lennon2023,
  author = {Lennon, Kyle R and McKinley, Gareth H and Swan, James W},
  title = {Scientific machine learning for modeling and simulating complex fluids},
  journal = {Proceedings of the National Academy of Sciences},
  year = {2023},
  volume = {120},
  number = {27},
  doi = {10.1073/pnas.2304669120}
}
Kostenlos starten →