An improved surface roughness prediction model using Box-Cox transformation with RSM in end milling of EN 353

Abstract

In the present work, an attempt has been made to use Box-Cox transformation with response surface methodology to develop improve surface roughness prediction model in end milling of EN 353 steel using carbide inserts. The analysis has been carried out in two stages. In the first stage quadratic model has been developed in terms of feed, speed, depth of cut and nose radius using response surface methodology (RSM) based on center composite rotatable design (CCRD). The quadratic model, thus developed predicts the surface roughness with 92% accuracy. In the second stage, the improved quadratic model has been developed using Box-Cox transformation with RSM based on CCRD. The prediction ability of this develop model has been found more accurate (mean absolute error 4.7%) than previous one. An attempt has also been made to investigate the influence of cutting parameters on surface roughness. The result shows that the machining speed is the main influencing factor on the surface roughness while the depth of cut has no significant influence.