Modeling of Machining Parameters in CNC End Milling Using Principal Component Analysis Based Neural Networks

Abstract

The present paper uses the principal component analysis (PCA) based neural networks for predicting the surface roughness in CNC end milling of P20 mould steel. For training and testing of the neural network model, a number of experiments have been carried out using Taguchi's orthogonal array in the design of experiments (DOE). The cutting parameters used are nose radius, cutting speed, cutting feed, axial depth of cut and radial depth of cut. The accurate mathematical model has been developed using PCAs networks. The adequacy of the developed model is verified using coefficient of determination (R). It was found that the R² value is 1. To judge the ability and efficiency of the neural network model, percentage deviation and average percentage deviation has been used. The research showed acceptable prediction results for the neural network model.