Modelling of Flank wear, Surface roughness and Cutting Temperature in Sustainable Hard Turning of AISI D2 Steel

Productivity and quality of products are major concern for industries aspects. However present paper focused on the investigation of flank wear, average roughness of the surface and chip-tool interface temperature in the machine turning of heat-treated AISI D2 grade tool steel using indexable multi-layer coated carbide inserts. Abrasion, diffusion, chipping and catastrophic breakage are major tool failure mechanisms involved. Response surface methodology (RSM) based models and Artificial-Neural-Network (ANN) models are implemented for forecasting the responses in hard-turning. Comparative assessment between actual and predicted results has been carried. ANN model for flank wear generated more accurate results compare to RSM Model whereas for surface finish and chip-tool interface temperature, the accuracy of RSM based prediction is more precise compared to ANN.