Nonlinear Shape-Manifold Learning Approach: Concepts, Tools and Applications - Université de Rennes Accéder directement au contenu
Article Dans Une Revue Archives of Computational Methods in Engineering Année : 2018

Nonlinear Shape-Manifold Learning Approach: Concepts, Tools and Applications

Liang Meng
  • Fonction : Auteur
  • PersonId : 974720
Piotr Breitkopf
Connectez-vous pour contacter l'auteur
Pierre Villon
  • Fonction : Auteur
  • PersonId : 872911

Résumé

In this paper, we present the concept of a “shape manifold” designed for reduced order representation of complex “shapes” encountered in mechanical problems, such as design optimization, springback or image correlation. The overall idea is to define the shape space within which evolves the boundary of the structure. The reduced representation is obtained by means of determining the intrinsic dimensionality of the problem, independently of the original design parameters, and by approximating a hyper surface, i.e. a shape manifold, connecting all admissible shapes represented using level set functions. Also, an optimal parameterization may be obtained for arbitrary shapes, where the parameters have to be defined a posteriori. We also developed the predictor-corrector optimization manifold walking algorithms in a reduced shape space that guarantee the admissibility of the solution with no additional constraints. We illustrate the approach on three diverse examples drawn from the field of computational and applied mechanics.
Fichier non déposé

Dates et versions

hal-01362497 , version 1 (08-09-2016)

Identifiants

Citer

Liang Meng, Piotr Breitkopf, Guenhael Le Quilliec, Balaji Raghavan, Pierre Villon. Nonlinear Shape-Manifold Learning Approach: Concepts, Tools and Applications. Archives of Computational Methods in Engineering, 2018, 25 (1), pp.1. ⟨10.1007/s11831-016-9189-9⟩. ⟨hal-01362497⟩
203 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More