Dissémination

Consulter le flux RSS

Publications

Toutes les publications du projet ERC.

Affichage des publications 11 à 20 sur 48 au total

Artificial Intelligence

Unsupervised learning of history-dependent constitutive material laws with thermodynamically-consistent neural networks in the modified Constitutive Relation Error framework.

This article proposes a consistent and general approach to train physics-augmented neural networks with observable data to enrich and represent nonlinear history-dependent material behaviors in terms of both state equations and evolution laws. In…

Antoine Benady, Emmanuel Baranger, Ludovic Chamoin

Computer Methods in Applied Mechanics and Engineering -

Artificial Intelligence

Apprentissage non-supervisé de lois de comportement nonlinéaires avec réseau de neurones thermodynamiquement consistent par minimisation de l'erreur en relation de comportement modifiée

Cet article propose une méthode d'apprentissage de lois de comportement nonsupervisé, fondée sur la minimisation de l'erreur en relation de comportement modifiée. La loi de comportement, en termes de loi d'état et d'équation d'évolution, est…

Antoine Benady, Emmanuel Baranger, Ludovic Chamoin

Artificial Intelligence

Physics-Augmented Neural Networks for Constitutive Modeling: Toward an Application for Structural Health Monitoring

Structural health monitoring is a major concern in the field of engineering [1]. On-board sensing techniques, such as fiber optics, enable accurate in-situ measurements of mechan- ical strain, providing rich experimental data that can be used in…

Antoine Benady, Emmanuel Baranger, Ludovic Chamoin

The 9th European Congress on Computational Methods in Applied Sciences and Engineering -

Neural and Evolutionary Computing

NN-mCRE: a modified Constitutive Relation Error framework for unsupervised learning of nonlinear state laws with physics-augmented Neural Networks

This article proposes a new approach to train physics-augmented neural net-works with observable data to represent mechanical constitutive laws. To trainthe neural network and learn thermodynamics potentials, the proposed methoddoes not rely on…

Antoine Benady, Emmanuel Baranger, Ludovic Chamoin

International Journal for Numerical Methods in Engineering -

Engineering Sciences

A novel DDDAS architecture combining advanced sensing and simulation technologies for effective real-time structural health monitoring

A still open question is how to design smart and autonomous mechanical structures able to perform online monitoring of their integrity and take anticipated actions during service before downtime of failure occur. To address this question, we present…

Ludovic Chamoin, Emmanuel Baranger, Antoine Benady, Pierre-Étienne Charbonnel, Matthieu Diaz, Sahar Farahbakhsh, Laurent Fribourg, Daniel Martin Xavier, Martin Poncelet