Deep learning of thermodynamics-aware reduced-order models from data
Article dans une revue avec comité de lecture
Auteur
Date
2021Journal
Computer Methods in Applied Mechanics and EngineeringRésumé
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 autoencoders, which reduce the dimensionality of the full order model to a set of sparse latent variables with no prior knowledge of the coded space dimensionality. Then, a second neural network is trained to learn the metriplectic structure of those reduced physical variables and predict its time evolution with a so-called structure-preserving neural network. This data-based integrator is guaranteed to conserve the total energy of the system and the entropy inequality, and can be applied to both conservative and dissipative systems. The integrated paths can then be decoded to the original full-dimensional manifold and be compared to the ground truth solution. This method is tested with two examples applied to fluid and solid mechanics.
Fichier(s) constituant cette publication
- Nom:
- PIMM_CMAME_2021_HERNANDEZ.pdf
- Taille:
- 2.800Mo
- Format:
- Fin d'embargo:
- 2022-01-01
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 lectureHERNÁNDEZ, Quercus; BADÍAS, Alberto; GONZÁLEZ, David; CUETO, Elías; CHINESTA SORIA, Francisco (Elsevier, 2020)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 ...
-
Article dans une revue avec comité de lectureHERNÁNDEZ, Quercus; BADÍAS, Alberto; GONZÁLEZ, David; CUETO, Elías; CHINESTA SORIA, Francisco (Elsevier, 2021)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 ...
-
Article dans une revue avec comité de lectureWe 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 ...
-
Article dans une revue avec comité de lectureThe imminent impact of immersive technologies in society urges for active research in real-time and interactive physics simulation for virtual worlds to be realistic. In this context, realistic means to be compliant to the ...
-
Article dans une revue avec comité de lectureBADIAS, Alberto; GONZALEZ, David; CUETO, Elias; ALFARO, Icíar; CHINESTA SORIA, Francisco (Elsevier, 2018)In this work we explore the possibilities of reduced order modeling for augmented reality applications. We consider parametric reduced order models based upon separate (affine) parametric dependence so as to speedup the ...