Computer vision with error estimation for reduced order modeling of macroscopic mechanical tests

Abstract : In this paper, computer vision enables recommending a reduced order model for fast stress prediction according to various possible loading environments. This approach is applied on a macroscopic part by using a digital image of a mechanical test. We propose a hybrid approach that simultaneously exploits a data-driven model and a physics-based model, in mechanics of materials. During a machine learning stage, a classification of possible reduced order models is obtained through a clustering of loading environments by using simulation data. The recognition of the suitable reduced order model is performed via a convolutional neural network (CNN) applied to a digital image of the mechanical test. The CNN recommend a convenient mechanical model available in a dictionary of reduced order models. The output of the convolutional neural network being a model, an error estimator, is proposed to assess the accuracy of this output. This article details simple algorithmic choices that allowed a realistic mechanical modeling via computer vision.
Type de document :
Article dans une revue
Liste complète des métadonnées

https://hal-mines-paristech.archives-ouvertes.fr/hal-01955929
Contributeur : Bibliothèque Umr7633 <>
Soumis le : vendredi 14 décembre 2018 - 16:53:43
Dernière modification le : jeudi 7 février 2019 - 17:13:56
Document(s) archivé(s) le : vendredi 15 mars 2019 - 17:16:00

Fichier

Nguyen-Barhli-Pino Munoz-Rycke...
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

Citation

Franck N'Guyen, Selim M. Barhli, Daniel Pino Muñoz, David Ryckelynck. Computer vision with error estimation for reduced order modeling of macroscopic mechanical tests. Complexity, Wiley, 2018, 2018, 10 p. ⟨10.1155/2018/3791543⟩. ⟨hal-01955929⟩

Partager

Métriques

Consultations de la notice

29

Téléchargements de fichiers

26