126016 20241125101151.0 doi 10.1007/s00466-023-02296-w sideral 133478 ART-2023-133478 eng Hernández, Quercus Port-metriplectic neural networks: thermodynamics-informed machine learning of complex physical systems 2023 Access copy available to the general public Unrestricted We 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. info:eu-repo/grantAgreement/ES/MICINN-AEI/PID2020-113463RB-C31/AEI/10.13039/501100011033 info:eu-repo/semantics/openAccess by http://creativecommons.org/licenses/by/3.0/es/ 3.7 2023 MATHEMATICS, INTERDISCIPLINARY APPLICATIONS 13 / 135 = 0.096 2023 Q1 T1 MECHANICS 33 / 170 = 0.194 2023 Q1 T1 1.265 2023 Applied Mathematics 2023 Q1 Computational Mathematics 2023 Q1 Ocean Engineering 2023 Q1 Computational Theory and Mathematics 2023 Q1 Mechanical Engineering 2023 Q1 Computational Mechanics 2023 Q1 7.8 2023 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion Badías, Alberto (orcid)0000-0001-7639-6767 Chinesta, Francisco Cueto, Elías Universidad de Zaragoza (orcid)0000-0003-1017-4381 5004 605 Universidad de Zaragoza Dpto. Ingeniería Mecánica Área Mec.Med.Cont. y Teor.Est. 72, 3 (2023), 553–561 Comput. mech. COMPUTATIONAL MECHANICS 0178-7675 533413 http://zaguan.unizar.es/record/126016/files/texto_completo.pdf Versión publicada 2232810 http://zaguan.unizar.es/record/126016/files/texto_completo.jpg?subformat=icon icon Versión publicada oai:zaguan.unizar.es:126016 articulos driver 2024-11-22-12:07:08 ARTICLE