Surface roughness modeling of high speed machining TC4 based on artificial neural network method

Recent works suggests that substantial gains in surface quality can be realized by better selection of high speed machining parameters. Machining parameters such as cutting speed, feed per tooth, axial depth of cut and radial depth of cut deeply affect the surface quality. This paper developed an artificial neural network (ANN) model for analysis and prediction of the relationship between roughness and machining parameters. The input parameters of the ANN model are the cutting speed, feed rate, axial depth of cut and radial depth of cut. The output parameters of the model are surface roughness measured after the machining trials. The model consists of a three-layered feed-forward back-propagation neural network. The network is trained with pairs of inputs/outputs datasets generated when high speed milling titanium alloy (TC4). A very good performance of the neural network, in terms of agreement with experimental data was achieved. The model can not only be used to determine in advance the surface roughness of work piece, but also make us know how these machining parameters affect the surface roughness