Meshgraphnets informed locally by thermodynamics for the simulation of flows around arbitrarily shaped objects

Bermejo, Carlos (Universidad de Zaragoza) ; Badías, Alberto ; González, David (Universidad de Zaragoza) ; Cueto, Elías (Universidad de Zaragoza)

Resumen: We present a thermodynamics-informed graph neural network framework for learning the time evolution of complex physical systems, incorporating thermodynamic structure via a nodal port-metriplectic formulation. Built upon the MeshGraphNet architecture, our method replaces the standard decoder with multiple specialized decoders that predict local energy and entropy gradients, along with Poisson and dissipative operators. These components are assembled at each graph node according to the GENERIC formalism, enforcing the first and second laws of thermodynamics. The framework is evaluated on two examples involving incompressible fluid flow past obstacles: one with varying cylindrical obstacles and another with obstacles of different types, not seen during training. The proposed model shows accurate long-term predictions, robust generalization to unseen geometries, and substantial speedups compared to traditional numerical solvers.

Idioma: Inglés

DOI: 10.1186/s40323-025-00311-8

Año: 2025

Publicado en: Advanced modeling and simulation in engineering sciences 12, 1 (2025), [18 pp.]
ISSN: 2213-7467

Financiación: info:eu-repo/grantAgreement/ES/MICINN/PID2023-147373OB-I00
Financiación: info:eu-repo/grantAgreement/ES/MTFP/TSI-100930-2023-1

Tipo y forma: Artículo (Versión definitiva)

Área (Departamento): Área Mec.Med.Cont. y Teor.Est. (Dpto. Ingeniería Mecánica)