Study of Different Process Parameters on the Surface Roughness at Superfinishing

Surface finishing and tool flank wear have been investigated in finish turning of AISID2 steels (60HRC) using ceramic wiper (multi-radii) design inserts. Multiple linear regression models and neural network models are developed for predicting surface roughness and tool flank wear. In neural network modeling, measured forces, power and specific forces are utilized in training algorithm. Experimental results indicate that surface roughness Ra values as low as 0.18–0.20m are attainable with wiper tools. Tool flank wear reaches to a tool life criterion value of VBC=0.15 mm before or around 15 min of cutting time at high cutting speeds due to elevated temperatures. Neural network based predictions of surface roughness and tool flank wear are carried out and compared with a non-training experimental data. These results show that neural network models are suitable to predict tool wear and surface roughness patterns for arrange of cutting conditions