EUVIMEDEUVIMED entdecken
Crossref

Physics-informed neural network analysis of magnetohydrodynamic squeezing flow of hyaluronic acid in periodically oscillating joints

Ananya Rout, Madhusmita Chand, Raj Nandkeolyar

Physics of Fluids · 01.11.2026 · 38 (11)

DOI: 10.1063/5.0333266 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Physics of Fluids, online erschienen am 10.11.2026. Verfasst von Ananya Rout und 2 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben. Gefördert von: Department of Science and Technology, Ministry of Science and Technology, India.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Synovial fluid ensures smooth joint movement by providing lubrication, primarily through hyaluronic acid (HA). In osteoarthritis (OA), the level of HA decreases, leading to increased friction, inflammation, and impaired joint function. OA is a common global disease that greatly affects patients' daily activities. To compensate for this deficiency and reduce synovial inflammation, viscosupplementation is widely used, in which HA is injected into the joint cavity. The present work analyzes the flow dynamics and thermal characteristics of HA in joint spaces by modeling joint motion as the axisymmetric, oscillatory squeezing flow with thermal transport of an incompressible Maxwell fluid under magnetohydrodynamic effects between two rigid disks. The governing equations are tackled using a physics-informed neural network (PINN) to determine the flow and temperature fields. The PINN model is validated by comparison with the Keller–Box method, showing minimal discrepancy. Error analysis shows that increasing the number of hidden layers and neurons improves solution accuracy. The results reveal that a higher Hartmann number increases the viscosity of HA and dampens fluid motion, whereas increasing the frequency of joint motion leads to a more uniform velocity profile. Elevating Reynolds and Prandtl numbers reduces heat transfer, altering wall temperatures. Higher Hartmann number and porous parameter increase wall shear stress and entropy generation, potentially reducing lubrication efficiency and contributing to cartilage damage in OA. The study demonstrates the effectiveness of PINNs in solving complex partial differential equations and provides theoretical insight into the rheological and thermal behavior of HA relevant to OA therapy.

Förderung

  • Department of Science and Technology, Ministry of Science and Technology, India

Zitieren

APA

Rout, A., Chand, M., & Nandkeolyar, R. (2026). Physics-informed neural network analysis of magnetohydrodynamic squeezing flow of hyaluronic acid in periodically oscillating joints. Physics of Fluids, 38(11). https://doi.org/10.1063/5.0333266

Vancouver

Rout A, Chand M, Nandkeolyar R. Physics-informed neural network analysis of magnetohydrodynamic squeezing flow of hyaluronic acid in periodically oscillating joints. Physics of Fluids. 2026;38(11). doi:10.1063/5.0333266

BibTeX
@article{Rout2026,
  author = {Rout, Ananya and Chand, Madhusmita and Nandkeolyar, Raj},
  title = {Physics-informed neural network analysis of magnetohydrodynamic squeezing flow of hyaluronic acid in periodically oscillating joints},
  journal = {Physics of Fluids},
  year = {2026},
  volume = {38},
  number = {11},
  doi = {10.1063/5.0333266}
}
Kostenlos starten →