Predictive modelling of laser powder bed fusion of Fe-based nanocrystalline alloys based on experimental data using...

This study harnessed bivariate correlational analysis, multiple linear regression analysis and tree-based regression analysis to examine the relationship between laser process parameters and the final material properties (bulk density, saturation magnetization (M ), and coercivity (H )) of Fe-based nano-crystalline alloys fabricated via laser powder bed fusion (LPBF). A dataset comprising of 162 experimental data points served as the foundation for the investigation. Each data point encompassed five independent variables: laser power (P), laser scan speed (v), hatch spacing (h), layer thickness (t), and energy density (E), along with three dependent variables: bulk density, M , and H . The bivariate correlational analysis unveiled that bulk density exhibited a significant correlation with P, v, h, and E, whereas M and H displayed significant correlations exclusively with v and P, respectively. This divergence may stem from the strong influence of microstructure on magnetic properties, which can be impacted not only by the laser process parameters explored in this study but also by other factors such as oxygen levels within the build chamber. Furthermore, our statistical analysis revealed that bulk density increased with rising P, h, and E, while decreased with higher v. Regarding the magnetic properties, a high M was achievable through low v, while low H resulted from high P. It was concluded that P and v were considered as the primary laser process parameters, influencing h and t due to their control over the melt-pool size. The application of multiple linear regression analysis allowed the prediction of the bulk density by using both laser process parameters and energy density. This approach offered a valuable alternative to time-consuming and costly trial-and-error experiments, yielding a low error of less than 1 % between the mean predicted and experimental values. Although a slightly higher error of approximately 6 % was observed for M , a clear association was established between M and v, with lower v values corresponding to higher M values. Additionally, a further comparison was conducted between multiple linear regression and three tree-based regression models to explore the effectiveness of these approaches.