A Meta-Heuristic Evolutionary Algorithm to Optimize Machining Parameters in Turning AISI 4340 Steel

In this work, optimization of machining parameters cutting speed, feed rate and depth of cut is performed during turning AISI 4340 steel with uncoated carbide cutting inserts. An L9(33) Orthogonal Array is chosen based on Taguchi’s Design of Experiments and the output responses flank wear, surface roughness and Material Removal Rate (MRR) were measured. Empirical models representing the output responses are developed using linear regression models. A metaheuristic evolutionary algorithm, Non-dominated Sorting Genetic Algorithm (NSGA-II) is applied to determine the optimum set of machining parameters for minimizing flank wear and maximizing MRR considering the surface roughness values within a specific limit (constraint). Pareto optimal front comprising of a set of solutions is obtained between the objective functions. From the results obtained, it is observed that NSGA-II can be used for predicting the machining parameters and output responses with at most precision showing the supremacy of the algorithm