Metal additive manufacturing is a disruptive technology that is changing how various alloys are processed. Although this technology has several advantages over conventional manufacturing, it is still necessary to standardize its properties, which are dependent on the relative density (RD). In addition, since experimental designs are costly, one solution is using machine learning algorithms that allow the effects of variations in the processing parameters on the resulting density of the additively manufactured components to be anticipated. This work assembled a database based on data from 673 observations and 10 predictors to forecast the relative density of 316L stainless steel and AlSi10Mg components produced by laser powder bed fusion (L-PBF). LazyPredict was employed to select the algorithm that best models the variability of the inherent data. Ensemble boosting regressors offer higher accuracy, providing hyperparameter fitting and optimization advantages. The predictions’ precision for aluminum and stainless steel obtained an R² value greater than 0.86 and 0.83, respectively. The results of the SHAP values indicated that laser power and energy density are the parameters that have the greatest impact on the predictability of the relative density of Al-Si10-Mg and SS 316L materials processed by L-PBF. This study presents a compendium of data for the additive fabrication of stainless steel and aluminum alloys, offering researchers a guide to understanding how processing parameters influence RD.

This study aims to optimize the performance of cyclone separators by simultaneously maximizing separation efficiency and minimizing pressure drop through a CFD-based multi-objective optimization framework. The research objectives are explicitly focused on (i) developing accurate predictive surrogate models for cyclone behavior and (ii) identifying optimal geometric configurations that balance both performance criteria. The methodology integrates Design of Experiments (DOE), Response Surface Methodology (RSM), and the Non-dominated Sorting Genetic Algorithm II (NSGA-II), using a full factorial design of 25 simulations to construct fourth-order surrogate models. This formulation was strictly necessary to capture the severe non-linearities observed in preliminary CFD runs. These models exhibited high predictive capability, with coefficients of determination (R²) above 0.94. The NSGA-II optimization generated a Pareto-optimal front that clearly describes the trade-off between separation efficiency and pressure drop, enabling systematic decision-making. The selected optimal configuration achieved a separation efficiency of 94.5% and a pressure drop of 194.78 Pa. CFD validation confirmed the robustness of the surrogate models, with relative errors below 1% for efficiency and below 5% for pressure drop. Overall, the results demonstrate that integrating CFD, surrogate modeling, and evolutionary optimization provides a reliable and computationally efficient strategy for cyclone separator design optimization.