ENGLISH
La vitrine de diffusion des publications et contributions des chercheurs de l'ÉTS
RECHERCHER

Modeling the process-microstructure-mechanical properties in laser powder bed fusion: Review of data-driven approaches and machine learning strategy for Ti-6Al-4V

Vu, Viet-Hung, Chaudhry, Shubham et Shahzadi, Gullnaz. 2025. « Modeling the process-microstructure-mechanical properties in laser powder bed fusion: Review of data-driven approaches and machine learning strategy for Ti-6Al-4V ». In Proceedings of the CSME-CFDSC-CSR 2025 International Congress (Montreal, QC, Canada, May 25-28, 2025) Coll. « Progress in Canadian Mechanical Engineering », vol. 8.

[thumbnail of 455 - Modeling the process-microstructur.pdf]
Prévisualisation
PDF
455 - Modeling the process-microstructur.pdf - Version publiée
Licence d'utilisation : Tous les droits réservés aux détenteurs du droit d'auteur.

Télécharger (726kB) | Prévisualisation

Résumé

This paper reviews the modeling of the Process- Microstructure-Mechanical property in the laser powder bed fusion, focusing on the data-driven approaches, from which a strategy modeling by machine learning algorithms is established for the Ti-6Al-4V. A sensitivity and uncertainty analysis strategy is studied considering the variation of the process parameters to the microstructure features and the mechanical properties. A deep neural network (DNN) is introduced to construct a surrogate model between input parameters and microstructure features. The proposed strategy aims to deliver an efficient and cost-effective prediction of both Microstructure features and the mechanical properties of the laser powder bed fusion Ti-6al-4v. The proposed methodology achieves high predictive accuracy, as evidenced by strong correlations between predicted and actual values. Additionally, it identifies critical process parameters, such as the length of the melt pool tail, that play a significant role in determining the microstructure size. This research provides a cost-effective approach to enhancing process optimization and quality control within the realm of additive manufacturing for metals.

Type de document: Compte rendu de conférence
Éditeurs:
Éditeurs
ORCID
Hof, Lucas A.
NON SPÉCIFIÉ
Di Labbio, Giuseppe
NON SPÉCIFIÉ
Tahan, Antoine
NON SPÉCIFIÉ
Sanjosé, Marlène
NON SPÉCIFIÉ
Lalonde, Sébastien
NON SPÉCIFIÉ
Demarquette, Nicole R.
NON SPÉCIFIÉ
Date de dépôt: 18 déc. 2025 15:33
Dernière modification: 18 déc. 2025 15:33
URI: https://espace2.etsmtl.ca/id/eprint/32521

Actions (Authentification requise)

Dernière vérification avant le dépôt Dernière vérification avant le dépôt