This work investigates the porosity distribution of Wire Arc Directed Energy Deposition (WA-DED) Al-12Si alloys using image processing and three deep learning techniques. The UNet model outperformed the two models based on accuracy and Jaccard index score and exhibited strong similarity with manually segmented ground truth images. The porosity tends to increase along the build owing to oxidation anomalies and improper shielding environment. The top region exhibited the highest porosity, whereas the middle region exhibited stable porosity variations owing to interlayer reheating. The work offers an automated deep learning segmentation approach that is fast and accurate, and scalable for XCT analysis of WA-DED.
XiaCPanZPoldenJ, et al.A review on wire arc additive manufacturing: monitoring, control and a framework of automated system. J Manuf Syst2020; 57: 31–45.
4.
ZhangKChenYMarussiS, et al.Pore evolution mechanisms during directed energy deposition additive manufacturing. Nat Commun2024; 15: 1715–1729.
5.
WangYNgCHBerminghamM, et al.Machine learning driven instance segmentation providing new porosity insights into wire arc directed energy deposited Ti-22V-4Al. Addit Manuf [Internet]2024; 90: 104323.
6.
GobertCReutzelEWPetrichJ, et al.Application of supervised machine learning for defect detection during metallic powder bed fusion additive manufacturing using high resolution imaging. Addit Manuf [Internet]2018; 21: 517–528.
7.
BellensSVandewallePDewulfW. Deep learning based porosity segmentation in X-ray CT measurements of polymer additive manufacturing parts. Procedia CIRP [Internet]2020; 96: 336–341.
8.
GobertCKudzalASietinsJ, et al.Porosity segmentation in X-ray computed tomography scans of metal additively manufactured specimens with machine learning. Addit Manuf2020; 36: 101460.
9.
ZhuYWuZHartleyWD, et al.Unraveling pore evolution in post-processing of binder jetting materials: x-ray computed tomography, computer vision, and machine learning. Addit Manuf2020; 34: 101183.
10.
BellensSProbstGMJanssensM, et al.Evaluating conventional and deep learning segmentation for fast X-ray CT porosity measurements of polymer laser sintered AM parts. Polym Test2022; 110: 107540.
11.
ZiabariAVenkatakrishnanSVSnowZ, et al.Enabling rapid X-ray CT characterisation for additive manufacturing using CAD models and deep learning-based reconstruction. NPJ Comput Mater2023; 9: 91.
12.
AgrawalAKSinghBSinghaiP, et al.The white beam station at imaging beamline BL-4, Indus-2. J Synchrotron Radiat [Internet]2021 Sep; 28: 1639–1648.
CongBDingJWilliamsS. Effect of arc mode in cold metal transfer process on porosity of additively manufactured Al-6.3%Cu alloy. Int J Adv Manuf Technol2015; 76: 1593–1606.
15.
YiHYangLJiaL, et al.Porosity in wire-arc directed energy deposition of aluminum alloys: formation mechanisms, influencing factors and inhibition strategies. Addit Manuf2024; 19: 104108.
16.
RyanEMSabinTJWattsJF, et al.The influence of build parameters and wire batch on porosity of wire and arc additive manufactured aluminium alloy 2319. J Mater Process Technol [Internet]2018; 262: 577–584, https://www.sciencedirect.com/science/article/pii/S0924013618303248.
17.
YangMYangZCongB, et al.How ultra high frequency of pulsed gas tungsten arc welding affects weld porosity of Ti-6Al-4V alloy. Int J Adv Manuf Technol [Internet]2015; 76: 955–960.
18.
HauserTReischRTBreesePP, et al.Oxidation in wire arc additive manufacturing of aluminium alloys. Addit Manuf2021; 41: 101958.
