Article Dans Une Revue Chemical Engineering Journal Advances Année : 2025

Bridging experiments and models, towards a new paradigm : DROP-PINN, a physics-informed neural network to predict droplet rupture in multiphase systems

Résumé

A fast and robust PINN-based algorithm is introduced to model turbulent breakage

• DROP-PINN infers breakage frequencies directly from image sequences of droplets.

• The methodology, based on various simulated configurations, is caseindependent

• The DROP-PINN performance is demonstrated by dedicated stirred tank experiments

Fichier principal
Vignette du fichier
FPSP_Chemical_Engineering (3).pdf (10.34 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05227239 , version 1 (28-08-2025)

Licence

Identifiants

Citer

Grégory Bana, Fabrice Lamadie, Sophie Charton, Didier Lucor, Nida Sheibat-Othman. Bridging experiments and models, towards a new paradigm : DROP-PINN, a physics-informed neural network to predict droplet rupture in multiphase systems. Chemical Engineering Journal Advances, 2025, 23, pp.100829. ⟨10.1016/j.ceja.2025.100829⟩. ⟨hal-05227239⟩
651 Consultations
188 Téléchargements

Altmetric

Partager

  • More