On-line monitoring of a machining operation

Abstract

Surface roughness(R_a) on-line monitoring and prediction model using artificial neural network (ANN) are developed in this work for dry turning of mild steel using carbide inserts. Cutting parameters (cutting speed (v), feed rate (f), and depth of cut (d)), root mean square amplitude of the radial vibration (r) and grey level of the surface image (g) are used as network inputs. Also investigations of the effect of cutting parameters are presented. The analysis reveals that increasing the cutting speed will decrease surface roughness, increasing feed rate will increase surface roughness, and increasing depth of cut will increase surface roughness but with small effect. The results show that the developed ANN model can predict surface roughness with high accuracy. The details of experimentation, ANN network structure are presented in this paper.