000126016 001__ 126016
000126016 005__ 20241125101151.0
000126016 0247_ $$2doi$$a10.1007/s00466-023-02296-w
000126016 0248_ $$2sideral$$a133478
000126016 037__ $$aART-2023-133478
000126016 041__ $$aeng
000126016 100__ $$aHernández, Quercus
000126016 245__ $$aPort-metriplectic neural networks: thermodynamics-informed machine learning of complex physical systems
000126016 260__ $$c2023
000126016 5060_ $$aAccess copy available to the general public$$fUnrestricted
000126016 5203_ $$aWe develop inductive biases for the machine learning of complex physical systems based on the port-Hamiltonian formalism. To satisfy by construction the principles of thermodynamics in the learned physics (conservation of energy, non-negative entropy production), we modify accordingly the port-Hamiltonian formalism so as to achieve a port-metriplectic one. We show that the constructed networks are able to learn the physics of complex systems by parts, thus alleviating the burden associated to the experimental characterization and posterior learning process of this kind of systems. Predictions can be done, however, at the scale of the complete system. Examples are shown on the performance of the proposed technique.
000126016 536__ $$9info:eu-repo/grantAgreement/ES/MICINN-AEI/PID2020-113463RB-C31/AEI/10.13039/501100011033
000126016 540__ $$9info:eu-repo/semantics/openAccess$$aby$$uhttp://creativecommons.org/licenses/by/3.0/es/
000126016 590__ $$a3.7$$b2023
000126016 592__ $$a1.265$$b2023
000126016 591__ $$aMATHEMATICS, INTERDISCIPLINARY APPLICATIONS$$b13 / 135 = 0.096$$c2023$$dQ1$$eT1
000126016 593__ $$aApplied Mathematics$$c2023$$dQ1
000126016 591__ $$aMECHANICS$$b33 / 170 = 0.194$$c2023$$dQ1$$eT1
000126016 593__ $$aComputational Mathematics$$c2023$$dQ1
000126016 593__ $$aOcean Engineering$$c2023$$dQ1
000126016 593__ $$aComputational Theory and Mathematics$$c2023$$dQ1
000126016 593__ $$aMechanical Engineering$$c2023$$dQ1
000126016 593__ $$aComputational Mechanics$$c2023$$dQ1
000126016 594__ $$a7.8$$b2023
000126016 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion
000126016 700__ $$0(orcid)0000-0001-7639-6767$$aBadías, Alberto
000126016 700__ $$aChinesta, Francisco
000126016 700__ $$0(orcid)0000-0003-1017-4381$$aCueto, Elías$$uUniversidad de Zaragoza
000126016 7102_ $$15004$$2605$$aUniversidad de Zaragoza$$bDpto. Ingeniería Mecánica$$cÁrea Mec.Med.Cont. y Teor.Est.
000126016 773__ $$g72, 3 (2023), 553–561$$pComput. mech.$$tCOMPUTATIONAL MECHANICS$$x0178-7675
000126016 8564_ $$s533413$$uhttps://zaguan.unizar.es/record/126016/files/texto_completo.pdf$$yVersión publicada
000126016 8564_ $$s2232810$$uhttps://zaguan.unizar.es/record/126016/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada
000126016 909CO $$ooai:zaguan.unizar.es:126016$$particulos$$pdriver
000126016 951__ $$a2024-11-22-12:07:08
000126016 980__ $$aARTICLE