Experimental Investigation on Tool Wear in AISI H13 Die Steel Turning Using RSM and ANN Methods

Abstract

An attempt was made in the present work to study the influence of machining parameters on wear of different types of cutting tools during turning of hardened die steel. Multilayer CVD (chemical vapor deposition) coated, uncoated and PVD (physical vapor deposition) coated ceramic inserts were employed. Response surface method and artificial neural network (ANN) models were employed to predict tool wear. The machining parameters considered in the study were feed rate, cutting speed, depth of cut and cutting time. Central composite design (CCD) technique was utilized to plan and carry out the trials in a systematic manner. The ANN and RSM (response surface methodology) models were developed. Models have exhibited higher degree of accuracy (R2 > 98.5% and MSE < 0.2%) ensuring better feasibility for prediction. ANOVA analysis revealed that cutting speed, cutting time, feed rate and depth of cut as individual were statistically significant influencing parameters on tool wear. Scanning electron microscope images have illustrated that multilayer coated cutting tool exhibited principal wear mechanisms such as abrasion, crater wear and edge chip-off. Cutting tools demonstrated adhesive wear at low machining parameters range and abrasive wear at greater machining parameter range.