This work used machine learning to forecast product density and optimize the laser powder bed fusion (LPBF) process for parts made of pure zinc (Zn). A relative density of 90–97% (6.42–6.95 g/cm3) was obtained by varying combinations of key process parameters, including laser power, scanning speed, track overlapping, hatch spacing, and layer thickness. Machine learning provided models for density prediction and better comprehension of the impact of input parameters. A SHapley Additive exPlanation (SHAP) analysis quantified the contributions of specific features, enhancing model interpretability. Fifty-one experimental runs were used to test several methods, including Bayesian ridge, CatBoost, elastic net, lasso, linear regression, random forest, ridge regression, and XGBoost. CatBoost performed best, with a test coefficient of determination (R2) of 0.893, a mean absolute error (MAPE) of 0.010 and a root mean square error (RMSE) of 0.015. A feature importance analysis showed that laser power (49%) and scanning speed (42%) had the greatest influence, while hatch spacing (5%) and layer thickness (4%) had minimal impacts on product density. Therefore, selecting the correct optimized set of process parameters determines the resulting density and can support more efficient LPBF process development.
Šket et al. (Wed,) studied this question.