Prediction of flank wear of different coated drills for JIS SUS 304 stainless steel using neural network

The purpose of this study was to use the Taguchi methods to establish a qualitative database of drilling parameters and flank wear. The qualitative database was constructed for the training of a radial basis function network (RBFN). The RBFN can accurately forecast the flank wear of different coated drills for JIS SUS 304 stainless steel. The simulation consequence indicated that the RBFN on the maximum drill wear error has reached 0.0065 mm, and the average absolute error has dropped to 0.4%.