Numerical experiments on unsupervised manifold learning applied to mechanical modeling of materials and structures
Article dans une revue avec comité de lecture
Author
Date
2020Journal
Comptes Rendus MécaniqueAbstract
The present work aims at analyzing issues related to the data manifold dimensionality. The interest of the study is twofold: (i) first, when too many measurable variables are considered, manifold learning is expected to extract useless variables; (ii) second, and more important, the same technique, manifold learning, could be utilized for identifying the necessity of employing latent extra variables able to recover single-valued outputs. Both aspects are discussed in the modeling of materials and structural systems by using unsupervised manifold learning strategies.
Files in this item
Related items
Showing items related by title, author, creator and subject.
-
Article dans une revue avec comité de lectureIBÁÑEZ, Rubén; ABISSET-CHAVANNE, Emmanuelle; GONZÁLEZ, David; DUVAL, Jean Louis; CUETO, Elias; CHINESTA, Francisco (Springer Verlag, 2019)In recent times a growing interest has arose on the development of data-driven techniques to avoid the employ of phenomenological constitutive models. While it is true that, in general, data do not fit perfectly to existing ...
-
Article dans une revue avec comité de lectureIBÁÑEZ PINILLO, Rubén; AMMAR, Amine; CUETO, Elias; HUERTA, Antonio; DUVAL, Jean-Louis; CHINESTA, Francisco (Wiley, 2019)Solutions of partial differential equations could exhibit a multiscale behavior. Standard discretization techniques are constraints to mesh up to the finest scale to predict accurately the response of the system. The ...
-
Article dans une revue avec comité de lectureSERRATORE, Giuseppe; GAGLIARDI, Francesco; MARTÍN, Clara Argerich; PINILO, Ruben Ibanez; CUETO, Elias; FILICE, Luigino; CHINESTA, Francisco (Springer Verlag, 2020)The manufacturing research has been focusing on the improvement of product performance and lightweight design. The synergic effects between material properties and manufacturing solutions have been considered, extensively. ...
-
Article dans une revue avec comité de lectureIBAÑEZ, Ruben; ABISSET-CHAVANNE, Emmanuelle; AMMAR, Amine; GONZALEZ, David; CUETO, Elias; HUERTA, Antonio; DUVAL, Jean-Louis; CHINESTA, Francisco (Wiley, 2018)Sparse model identification by means of data is especially cumbersome if the sought dynamics live in a high dimensional space. This usually involves the need for large amount of data, unfeasible in such a high dimensional ...
-
Article dans une revue avec comité de lectureQUARANTA, Giacomo; ARGERICH MARTIN, Clara; IBÁÑEZ, Rubén; DUVAL, Jean Louis; CUETO, Elias; CHINESTA, Francisco (Elsevier Masson, 2019)The present paper analyzes different integration schemes of solid dynamics in the frequency domain involving the so-called Proper Generalized Decomposition – PGD. The last framework assumes for the solution a parametric ...