Statistical analysis of tool wear using rsm and ann

The research reported herein is to model the tool wear during face milling of Hybrid composites using response surface methodologies (RSM) and artificial neural network (ANN). Aiming to achieve this goal, several milling experiments were carried out with polycrystalline diamond (PCD) inserts at different machining parameters namely cutting speed, feed, depth of cut, and weight fraction of Al2O3. Materials used for the present investigation are Al 6061-aluminum alloy reinforced with alumina (Al2O3) of size 45 microns and graphite (Gr) of an average size 60 μ, which are produced by stir casting route. Central composite face centered second order RSM was employed to create a mathematical model and the adequacy of the model was verified using analysis of variance. Comparison has been made between prediction capabilities of model based on RSM and ANN. The comparison clearly indicates that the models provide accurate prediction of tool wear in which ANN perform better than RSM.