Paper published in a book (Scientific congresses and symposiums)
Uncertainty Quantification in the Directed Energy Deposition Process Using Deep Learning-Based Probabilistic Approach
Pham Quy Duc, Thinh; Hoang, Truong Vinh; Tran, Xuan Van et al.
2022In Vincze, Gabriela; Barlat, Frédéric (Eds.) Achievements and Trends in Material Forming- Peer-reviewed extended papers selected from the 25th International Conference on Material Forming, ESAFORM 2022
Peer reviewed
 

Files


Full Text
KEM.926.323.pdf
Author postprint (612.44 kB)
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
deep learning; directed energy deposition process; melting pool; Uncertainty quantification; Materials Science (all); Mechanics of Materials; Mechanical Engineering; General Materials Science
Abstract :
[en] This study quantifies the effects of uncertainty raised from process parameters, material properties, and boundary conditions in the directed energy deposition (DED) process of M4 High-Speed Steel using deep learning (DL)-based probabilistic approach. A DL-based surrogate model is first constructed using the data obtained from a finite element (FE) model, which was validated against experiment. Then, sources of uncertainty are characterized by the probabilistic method and are propagated by the Monte-Carlo (MC) method. Lastly, the sensitivity analysis (SA) using the variance-based method is performed to identify the parameters inducing the most uncertainty to the melting pool depth. Using the DL-based surrogate model instead of solely FE model significantly reduces the computational time in the MC simulation. The results indicate that all sources of uncertainty contribute to a substantial variation on the final printed product quality. Moreover, we find that the laser power, the convection, the scanning speed, and the thermal conductivity contribute the most uncertainties on the melting pool depth based on the SA results. These findings can be used as insights for the process parameter optimization of the DED process.
Research center :
TDMU
Disciplines :
Materials science & engineering
Computer science
Mechanical engineering
Author, co-author :
Pham Quy Duc, Thinh ;  Université de Liège - ULiège > Aérospatiale et Mécanique (A&M)
Hoang, Truong Vinh;  Mathematics for Uncertainty Quantification, RWTH-Aachen University, Aachen, Germany
Tran, Xuan Van;  Institute of Strategy Development, Thu Dau Mot University, Viet Nam
Fetni, Seifallah;  University of Liège, MSM Unit, Liège, Belgium
Duchene, Laurent  ;  Université de Liège - ULiège > Département ArGEnCo > Analyse multi-échelles dans le domaine des matériaux et structures du génie civil
Tran, Hoang Son ;  Université de Liège - ULiège > Département ArGEnCo > Département Argenco : Secteur MS2F
Habraken, Anne  ;  Université de Liège - ULiège > Département ArGEnCo > Département Argenco : Secteur MS2F ; Fonds de la Recherche Scientifique de Belgique (F.R.S-FNRS), Belgium
Language :
English
Title :
Uncertainty Quantification in the Directed Energy Deposition Process Using Deep Learning-Based Probabilistic Approach
Publication date :
2022
Event name :
The 25th International ESAFORM Conference on Material Forming – ESAFORM 2022
Event organizer :
Prof. Gabriela Vincze and Prof. Frédéric Barlat
Event place :
Braga, Portugal
Event date :
27-04-2022 to 29-04-2022
Event number :
25th
Audience :
International
Main work title :
Achievements and Trends in Material Forming- Peer-reviewed extended papers selected from the 25th International Conference on Material Forming, ESAFORM 2022
Editor :
Vincze, Gabriela
Barlat, Frédéric
Publisher :
Trans Tech Publications Ltd
ISBN/EAN :
978-3-03-571759-4
Peer reviewed :
Peer reviewed
Name of the research project :
EDPOMP
Funders :
VinIF - Vingroup Innovation Foundation [VN]
Funding text :
This work was funded by Vingroup and supported by Vingroup Innovation Foundation (VINIF) under project code VINIF.2020.DA15.
Available on ORBi :
since 19 October 2023

Statistics


Number of views
9 (5 by ULiège)
Number of downloads
6 (2 by ULiège)

Scopus citations®
 
3
Scopus citations®
without self-citations
3

Bibliography


Similar publications



Contact ORBi