Laser powder bed fusion dataset for relative density prediction of commercial metallic alloys

Laser-based powder bed fusion (L-PBF) technology stands out for its ability to create complex, high-performance parts, optimizing design freedom and material efficiency. Despite technical and financial challenges, it is attractive to industries where performance, weight reduction, and customization are critical. In L-PBF, relative density (RD) is a key factor that directly impacts the mechanical properties and overall quality of printed parts. However, predicting RD is a complex and costly task due to the numerous factors involved. This study addresses this need by creating a large-scale dataset for RD prediction in L-PBF, consisting of 1579 samples of commercial alloys from the literature. It includes printing conditions and other crucial inputs like protective atmosphere, powder size distribution, and part geometry. This dataset offers a valuable resource for researchers to benchmark their results, better understand key factors influencing RD, and validate models or explore new machine-learning approaches tailored to L-PBF.