A machine learning approach for the prediction of tensile deformation behavior in wire arc additive manufacturing

Wire arc additive manufacturing (WAAM) applications have expanded significantly in recent years, but the technology’s widespread adoption across a wide range of sectors is still in the early stages. Since WAAM specimens vary in mechanical properties along the built direction, it is necessary to predict the properties and thereby reduce the experimental cost. Hence, machine learning tools that can enhance and make the process more efficient are being implemented for the current work. In this study, location and orientation-based tensile strength and elongation behavior have been studied. The elongation of WAAMed alloy specimens in vertical, inclined, and horizontal orientations are determined to be 44.1 ± 1.9