Integrating Taguchi principle with genetic algorithm to minimize burr size in drilling of AISI 316L stainless steel using an artificial neural network model

Abstract

Burr formation in drilling has been among the most troublesome obstructions to high productivity and automation of the machining processes, thus affecting the quality. It is necessary to select the best parametric combination of drilling process parameters to minimize burr at the production stage so as to reduce deburring cost and time. The present paper illustrates a novel concept of integrating the Taguchi principle with genetic algorithm optimization during drilling of AISI 316L stainless steel, by developing a burr size model using an artificial neural network. The objective is to determine the best combination values of feed and point angle for a specified drill diameter that simultaneously minimize burr dimensions, namely, burr height and burr thickness. The results clearly indicate the need for a larger point angle for bigger drill diameter values in order to minimize the burr size in drilling.