Surface roughness prediction in end milling using multiple regression and adaptive neuro-fuzzy inference system

Multiple regression and adaptive neuro-fuzzy inference system (ANFIS) were used to predict the surface roughness in the end milling process. Spindle speed, feed rate and depth of cut were used as predictor variables. Generalized bell memberships function (gbellmf) was adopted during the training process of ANFIS in this study. The predicted surface roughness using multiple regression and ANFIS were compared with measured data, the achieved accuracy were 91.9% and 94% respectively. These results indicate that the training of ANFIS with the gbellmf is accurate than multiple regression in the prediction of surface roughness.