In this paper, an approach for prediction deformation of upsetting processes is developed. The approach combines the finite element method and Neural Network to view the resultant deformation changes in upsetting. Because real time deformation simulation is a time consuming repeated analysis, the neural networks are employed in this work as numerical devices for substituting the finite element code needed for the upsetting deformation. The input data for the artificial neural network are a set of parameters generated randomly (aspect ratio d/h, material properties, temperature and coefficient of friction). The output data are the coefficient of polynomial that fitted on barreling curves. Neural network was trained using barreling curves generated by finite element simulations of the upsetting and the corresponding material parameters. This technique was tested for three different specimens and can be successfully employed to determine barreling curve.