Parametric analysis and machine learning-based parametric modeling of wire laser metal deposition induced porosity - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue International Journal of Material Forming Année : 2022

Parametric analysis and machine learning-based parametric modeling of wire laser metal deposition induced porosity

Résumé

Additive manufacturing is an appealing solution to produce geometrically complex parts, difficult to manufacture using traditional technologies. The extreme process conditions, in particular the high temperature, complex interactions and couplings, rich metallurgical transformations and combinatorial deposition trajectories, induce numerous process defects and in particular porosity. Simulating numerically porosity appearance remains extremely complex because of the multiple physics induced by the laser-material interaction, the multiple space and time scales, with a strong impact on the simulation efficiency and performances. Moreover, when analyzing parts build-up by using the wire laser metal deposition —wLMD— technology it can be noticed a significant variability in the porosity size and distribution even when process parameters remain unchanged. For these reasons the present paper aims at proposing an alternative modeling approach based on the use of neural networks to express the porosity as a function of different process parameters that will be extracted from the process analysis.
Fichier principal
Vignette du fichier
PIMM_IJMF_2022_LOREAU (4.79 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03708263 , version 1 (29-06-2022)

Identifiants

Citer

Tanguy Loreau, Victor Champaney, Nicolas Hascoet, Jon Lambarri, Mikel Madarieta, et al.. Parametric analysis and machine learning-based parametric modeling of wire laser metal deposition induced porosity. International Journal of Material Forming, 2022, 15 (3), ⟨10.1007/s12289-022-01687-3⟩. ⟨hal-03708263⟩
47 Consultations
41 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More