Thermodynamically consistent data-driven computational mechanics
Article dans une revue avec comité de lecture
Date
2019Journal
Continuum Mechanics and ThermodynamicsRésumé
In the paradigm of data-intensive science, automated, unsupervised discovering of governing equations for a given physical phenomenon has attracted a lot of attention in several branches of applied sciences. In this work, we propose a method able to avoid the identification of the constitutive equations of complex systems and rather work in a purely numerical manner by employing experimental data. In sharp contrast to most existing techniques, this method does not rely on the assumption on any particular form for the model (other than some fundamental restrictions placed by classical physics such as the second law of thermodynamics, for instance) nor forces the algorithm to find among a predefined set of operators those whose predictions fit best to the available data. Instead, the method is able to identify both the Hamiltonian (conservative) and dissipative parts of the dynamics while satisfying fundamental laws such as energy conservation or positive production of entropy, for instance. The proposed method is tested against some examples of discrete as well as continuum mechanics, whose accurate results demonstrate the validity of the proposed approach.
Fichier(s) constituant cette publication
Cette publication figure dans le(s) laboratoire(s) suivant(s)
Documents liés
Visualiser des documents liés par titre, auteur, créateur et sujet.
-
Article dans une revue avec comité de lectureWe address the problem of machine learning of constitutive laws when large experimental deviations are present. This is particularly important in soft living tissue modeling, for instance, where large patient-dependent ...
-
Article dans une revue avec comité de lectureALFARO, Icíar; GONZALEZ, David; BORDEU, Felipe; LEYGUE, Adrien;
AMMAR, Amine;
CUETO, Elias;
CHINESTA SORIA, Francisco (Springer Verlag, 2014)
Simulation of all phenomena taking place in a surgical procedure is a formidable task that involves, when possible, the use of supercomputing facilities over long time periods. However, decision taking in the operating ... -
Article dans une revue avec comité de lectureMany models in Science and Engineering are defined in spaces (the so-called conformation spaces) of high dimensionality. In kinetic theory, for instance, the micro scale of a fluid evolves in a space whose number of ...
-
Article dans une revue avec comité de lecture
CHINESTA SORIA, Francisco; LEYGUE, Adrien; BORDEU, Felipe; AGUADO, Jose Vicente;
CUETO, Elias; GONZALEZ, David; ALFARO, Icíar;
AMMAR, Amine; HUERTA, Antonio (Springer Verlag, 2013)
In this paper we are addressing a new paradigm in the field of simulation-based engineering sciences (SBES) to face the challenges posed by current ICT technologies. Despite the impressive progress attained by simulation ... -
Article dans une revue avec comité de lectureHERNANDEZ, Quercus; BADIAS, Alberto; GONZALEZ, David;
CHINESTA SORIA, Francisco;
CUETO, Elias (Elsevier, 2021)
We present an algorithm to learn the relevant latent variables of a large-scale discretized physical system and predict its time evolution using thermodynamically-consistent deep neural networks. Our method relies on sparse ...