000163253 001__ 163253
000163253 005__ 20251024172258.0
000163253 0247_ $$2doi$$a10.1186/s40323-025-00311-8
000163253 0248_ $$2sideral$$a145765
000163253 037__ $$aART-2025-145765
000163253 041__ $$aeng
000163253 100__ $$aBermejo, Carlos$$uUniversidad de Zaragoza
000163253 245__ $$aMeshgraphnets informed locally by thermodynamics for the simulation of flows around arbitrarily shaped objects
000163253 260__ $$c2025
000163253 5060_ $$aAccess copy available to the general public$$fUnrestricted
000163253 5203_ $$aWe present a thermodynamics-informed graph neural network framework for learning the time evolution of complex physical systems, incorporating thermodynamic structure via a nodal port-metriplectic formulation. Built upon the MeshGraphNet architecture, our method replaces the standard decoder with multiple specialized decoders that predict local energy and entropy gradients, along with Poisson and dissipative operators. These components are assembled at each graph node according to the GENERIC formalism, enforcing the first and second laws of thermodynamics. The framework is evaluated on two examples involving incompressible fluid flow past obstacles: one with varying cylindrical obstacles and another with obstacles of different types, not seen during training. The proposed model shows accurate long-term predictions, robust generalization to unseen geometries, and substantial speedups compared to traditional numerical solvers.
000163253 536__ $$9info:eu-repo/grantAgreement/ES/MICINN/PID2023-147373OB-I00$$9info:eu-repo/grantAgreement/ES/MTFP/TSI-100930-2023-1
000163253 540__ $$9info:eu-repo/semantics/openAccess$$aby$$uhttps://creativecommons.org/licenses/by/4.0/deed.es
000163253 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion
000163253 700__ $$0(orcid)0000-0001-7639-6767$$aBadías, Alberto
000163253 700__ $$0(orcid)0000-0003-3003-5856$$aGonzález, David$$uUniversidad de Zaragoza
000163253 700__ $$0(orcid)0000-0003-1017-4381$$aCueto, Elías$$uUniversidad de Zaragoza
000163253 7102_ $$15004$$2605$$aUniversidad de Zaragoza$$bDpto. Ingeniería Mecánica$$cÁrea Mec.Med.Cont. y Teor.Est.
000163253 773__ $$g12, 1 (2025), [18 pp.]$$pAdv. model. simul. eng. sci.$$tAdvanced modeling and simulation in engineering sciences$$x2213-7467
000163253 8564_ $$s3037454$$uhttps://zaguan.unizar.es/record/163253/files/texto_completo.pdf$$yVersión publicada
000163253 8564_ $$s2244071$$uhttps://zaguan.unizar.es/record/163253/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada
000163253 909CO $$ooai:zaguan.unizar.es:163253$$particulos$$pdriver
000163253 951__ $$a2025-10-24-16:55:49
000163253 980__ $$aARTICLE