Multi-response optimization while machining of stainless steel 316L using intelligent approach of grey theory and grey-TLBO

Abstract

Purpose Stainless steel is widely used in different manufacturing sectors. The purpose of this study is to optimize the process parameters of machining while processing SS316L alloy. The optimization of machining characteristics in the case of SS316L alloy greatly improves the quality and productivity economically. Design/methodology/approach The machining variables in current research are depth of cut, spindle speed and feed rate. The optimization of response characteristics was carried out using the intelligent approach of grey, regression and teaching learning-based optimization (TLBO) and Taguchi-Grey approach. Planning of experiments was made using Taguchi’s based L27 orthogonal array. With the implementation of grey, the response characteristics were normalized and converted into a single response. The regression analysis was used for empirical modeling of the single response induced from the grey application. TLBO is further used to investigate the combinations of machining variables and compared with grey theory. Findings The grey-TLBO based multi-criteria decision-making approach suggests that the optimized setting for material removal rate, mean roughness depth (Rz) and cutting force (Fz) is spindle speed (N): 720 rpm; feed rate (F): 0.3 mm/rev; depth of cut (DoC): 1.7 mm. The grey theory suggests an optimized setting as N: 720 rpm; F: 0.2 mm/rev and DoC: 1.7 mm. Originality/value The parametric optimization during the turning of SS316L using grey-TLBO based intelligent approach is not performed till now. Thus, this intelligent approach will give a path to the researchers working in this direction. However, the grey theory performs better as compared to the grey-TLBO approach.