Least Squares Boosting Ensemble and Quantum-Behaved Particle Swarm Optimization for Predicting the Surface Roughness in Face Milling Process of Aluminum Material

Surface roughness is a significant factor in determining the product quality and highly impacts production price. The ability to predict surface before would save time resources of process. This research investigated performance state-of-the-art machine learning quantum behaved evolutionary computation methods predicting aluminum material face-milling machine. Quantum-behaved particle swarm optimization (QPSO) least squares gradient boosting ensemble (LSBoost) were utilized simulate numerous face milling experiments have predicted values with high extent accuracy. algorithms shown superior prediction over genetics algorithm (GA) classical (PSO) terms statistical indicators. QPSO outperformed all simulated root mean square error RMSE = 2.17% coefficient determination R2 0.95 that closely matches actual experimental values.