108295 20230519145348.0 doi 10.1016/j.jcp.2020.109950 sideral 120910 ART-2021-120910 eng Hernández Laín, Quercus Universidad de Zaragoza Structure-preserving neural networks 2021 Access copy available to the general public Unrestricted We develop a method to learn physical systems from data that employs feedforward neural networks and whose predictions comply with the first and second principles of thermodynamics. The method employs a minimum amount of data by enforcing the metriplectic structure of dissipative Hamiltonian systems in the form of the so-called General Equation for the Non-Equilibrium Reversible-Irreversible Coupling, GENERIC (Öttinger and Grmela (1997) [36]). The method does not need to enforce any kind of balance equation, and thus no previous knowledge on the nature of the system is needed. Conservation of energy and dissipation of entropy in the prediction of previously unseen situations arise as a natural by-product of the structure of the method. Examples of the performance of the method are shown that comprise conservative as well as dissipative systems, discrete as well as continuous ones. info:eu-repo/grantAgreement/ES/DGA-FSE/T24-20R info:eu-repo/grantAgreement/ES/MINECO-CICYT/DPI2017-85139-C2-1-R info:eu-repo/grantAgreement/ES/UZ/ESI-ENSAM-Simulated Reality info:eu-repo/semantics/openAccess by-nc-nd http://creativecommons.org/licenses/by-nc-nd/3.0/es/ 4.645 2021 PHYSICS, MATHEMATICAL 3 / 56 = 0.054 2021 Q1 T1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS 40 / 112 = 0.357 2021 Q2 T2 2.069 2021 Applied Mathematics 2021 Q1 Computational Mathematics 2021 Q1 Physics and Astronomy (miscellaneous) 2021 Q1 Numerical Analysis 2021 Q1 Modeling and Simulation 2021 Q1 7.1 2021 info:eu-repo/semantics/article info:eu-repo/semantics/acceptedVersion Badías Herbera, Alberto Universidad de Zaragoza (orcid)0000-0001-7639-6767 González Ibáñez, David Universidad de Zaragoza (orcid)0000-0003-3003-5856 Chinesta Soria, Francisco Cueto Prendes, Elías Universidad de Zaragoza (orcid)0000-0003-1017-4381 5004 605 Universidad de Zaragoza Dpto. Ingeniería Mecánica Área Mec.Med.Cont. y Teor.Est. 426, 109950 (2021), [16 pp.] J. comput. phys. Journal of Computational Physics 0021-9991 346629 http://zaguan.unizar.es/record/108295/files/texto_completo.pdf Postprint 2498922 http://zaguan.unizar.es/record/108295/files/texto_completo.jpg?subformat=icon icon Postprint oai:zaguan.unizar.es:108295 articulos driver 2023-05-18-13:23:10 ARTICLE