| Abstract Scope |
Additive manufacturing, particularly laser powder bed fusion (LPBF), is used to produce complex, high-performance metal components from 3D CAD models. However, selecting optimal process parameters for 316L stainless steel is largely pragmatic, time-consuming, and reliant on costly trial-and-error experiments. This study develops a data-driven predictive model using over 600 experimental data points collected from existing literature to map the complex relationships between key inputs, such as laser power, scan speed, layer thickness, and hatch spacing, with material properties, including density, hardness, and tensile strength. The database trains a machine learning model, yielding a functional, user-friendly prototype that reduces engineering effort. While initially focused on 316L, the tool is designed to accommodate new datasets and extend to other alloys. The approach emphasizes the power of published data, combined with machine learning, in additive manufacturing applications |