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.