A comparative study in prediction of surface roughness and flank wear using artificial neural network and response surface methodology method during hard turning in dry and forced air-cooling condition

In the present work, a turning operation is performed in a green environment of dry and forced air-cooled condition to avoid the flooded coolant or minimum quantity lubrication. The work piece material considered is hardened AISI D2 steel (48 HRC) and the tool material is tungsten coated carbide tool. Cutting speed (v), feed rate (f) and depth of cut are taken as process parameters and surface roughness, flank wear, cutting force and feed force as performance parameters. Dry turning (DT) is found to be favourable for minimising surface roughness, cutting force and feed force, while air-cooled turning (ACT) is favourable for reducing flank wear. Artificial neural network (ANN) and response surface methodology (RSM) models have been developed for prediction of surface roughness and flank wear. Regression coefficient (R2), confirmed that ANN model is better as compared to that of RSM model.