Modeling of cutting forces as function of cutting parameters for face milling of satellite 6 using an artificial neural network

In this study, artificial neural networks (ANNs) was used for modeling the effects of machinability on chip removal cutting parameters for face milling of stellite 6 in asymmetric milling processes. Cutting forces with three axes (F-x, F-y and F-z) were predicted by changing cutting speed (V-c), feed rate (f) and depth of cut (a(p)) under dry conditions. Experimental studies were carried out to obtain training and test data and scaled conjugate gradient (SCG) feed-forward back-propagation algorithm was used in the networks. Main parameters for the experiments are the cutting speed (V-c n/min), feed rate (f, mm/min), depth of cut (ap, mm) and cutting forces (F-x, F-y and F-z, N). V-c, f and a(p) were used as the input dataset while F-x, F-y and F-z were used as the output dataset. Average percentage error (APEs) values for F-x, F-y and F-z using the proposed model were obtained around 2 and 10% for training and testing, respectively. These results show that the ANNs can be used for predicting the effects of machinability on chip removal cutting parameters for face milling of stellite 6 in asymmetric milling processes. (c) 2007 Published by Elsevier B.V.