Minimizing vibrations and power consumption in milling of AZ31 alloy through parameter optimization

• Conducted 25 Taguchi L25 milling experiments on AZ31 alloy. • Stepwise regression models achieved R² > 0.90 for all responses. • Optimal parameters: 4374 RPM, 20.19 mm/min feed, 0.3 mm depth. • Predicted power 68 W; vibration errors ≤10 % after validation. This study presents an integrated optimization framework for minimizing vibration and power consumption during the milling of AZ31 magnesium alloy. A total of 25 experiments were performed using a Taguchi L 25 orthogonal array to investigate the influence of spindle speed, feed rate, and depth of cut. Real-time data acquisition captured vibrations along the X, Y, and Z axes, as well as power consumption. Stepwise regression models were developed using Pearson’s correlation analysis, revealing spindle speed as the most influential parameter. These models were input into the NSGA-II algorithm, generating a Pareto front of optimal solutions. The best theoretical solution predicted vibration amplitudes of −8.2 mm (X), 7.7 mm (Y), 4.2 mm (Z), and a power consumption of 68.13 W. Experimental validation yielded errors of 4 % (X), 4 % (Y), 10 % (Z), and −6 % (power), confirming the model's accuracy. Correlation analysis indicated that spindle speed had the greatest influence on power consumption and Z-axis vibrations ( r = 0.45 and r = 0.16), depth of cut significantly affected X-axis and Y-axis vibrations ( r = 0.27 and r = 0.15) The framework effectively improves machining sustainability by optimizing process parameters. An integrated experimental and computational framework for optimizing AZ31 milling parameters by reducing vibrations and power consumption.