Multi-objective optimisation in turning AISI 304 stainless steel: an integration of the Taguchi method, response surface methodology, and NSGA-II

This study examined the impact of machining parameters [depth of cut (d), feed rate (f), and spindle speed (s)] on surface roughness and material removal rate in the turning process of AISI 304 stainless steel. Three optimisation methods were used: the Taguchi method, the response surface methodology (RSM), and the non-dominated sorting genetic algorithm II (NSGA-II). The Taguchi method identified the most influential parameter for surface roughness (f > d > s) and for material removal rate (d > f > s). RSM regression models achieved high R2 values of 0.9896 for roughness and 0.9997 for material removal rate. NSGA-II multi-objective optimisation produced 35 Pareto solutions within ranges of cutting parameters, resulting in surface roughness values from 0.239 to 3.301 μm and material removal rates from 151.53 to 594.99 mm3/s. Confirmation experiments validated the optimal values, with deviations within 10%, confirming the accuracy of the research method for solving the optimisation problem.