Page 26 - IJAMD-1-3

International Journal of AI for
Materials and Design

ORIGINAL RESEARCH ARTICLE
Prediction of wall geometry for

cold-metal-transfer-based wire-arc additive
manufacturing

Robin Kromer* and Eric Lacoste

Univ. Bordeaux, CNRS, Bordeaux INP, I2M, UMR 5295, F-33400, Talence, France
(This article belongs to the Special Issue: AI Usage in the Analysis of the Additive Manufacturing
Process)

Abstract

Wire-arc additive manufacturing (WAAM) is an advanced technique for fabricating
large metal components through layer-by-layer material deposition using arc
welding methods. This study focused on optimizing the WAAM process by employing
machine learning models to predict and control bead geometries, specifically bead
height (BH) and bead width (BW), while ensuring consistent height increments
in multibead walls. Based on CMT technology in cold metal transfer experiments,
linear regression models achieved high accuracy in predicting BH and BW. Analysis
of variance results highlighted the considerable influence of voltage (V) and travel
speed (TS) on bead geometries. For multibead wall characteristics, polynomial
*Corresponding author: regression models incorporating non-linear terms, such as travel speed (TS²) and
Robin Kromer dwell time (Dt²), were developed to predict height (H) and waviness (W). Various
(robin.kromer@u-bordeaux.fr) optimization metrics were employed to balance the trade-offs between H and W for
Citation: Kromer R, Lacoste E. identifying optimal welding conditions that achieved the target H while minimizing
Prediction of wall geometry for W. A notable innovation of this research is the optimization of dwell time (Dt) for each
cold-metal-transfer-based wire-arc
additive manufacturing. layer to achieve a linear incremental H profile, minimizing W and ensuring consistent
Int J AI Mater Design. 2024;1(3): layer quality.
20-32.
doi: 10.36922/ijamd.4285
Received: July 19, 2024 Keywords: Machine learning; Dwell time; Bead geometry; Process modeling; Wire-arc
additive manufacturing
Accepted: September 2, 2024
Published Online: October 10,
2024
Copyright: © 2024 Author(s). 1. Introduction
This is an Open-Access article
distributed under the terms of the Wire-arc additive manufacturing (WAAM) is a process that creates large metal parts
Creative Commons Attribution by depositing the associated material in successive layers based on arc metal transfer.
License, permitting distribution, This technique offers several advantages, including optimized raw part designs, reduced
and reproduction in any medium,
1
provided the original work is material waste, and high production efficiency. WAAM employs various welding
properly cited. techniques to melt metal wires, including gas metal arc welding (GMAW), gas tungsten
Publisher’s Note: AccScience arc welding, and plasma arc welding. Among these, GMAW is particularly preferred
Publishing remains neutral with for its high material deposition rate. A variation of GMAW, called cold metal transfer
2
regard to jurisdictional claims in
published maps and institutional (CMT), features a controlled dip transfer mode, making it popular in WAAM owing to
affiliations. its low heat input and reduced spatter. 3

Volume 1 Issue 3 (2024) 20 doi: 10.36922/ijamd.4285