Artificial Neural Network application to the friction welding of AISI 316 and Ck 45 steels

Abstract

The optimization of the friction welding parameters through experimental studies does not only cause loss of time and materials but also increases the cost. In this study, an Artificial Neural Network (ANN) model is developed for the analysis of the correlation between the friction welding parameters and tensile strength of both AISI 316 austenitic-stainless steel and Ck 45 steel. The input parameters of the model are friction time, friction pressure and upset pressure while tensile strength is the output. Experimental data are used to train and test the neural network. A good correlation was obtained between the experimental values and the ANN model prediction (R-2 = 0.9711). By using this model, the number of experiments to obtain optimal parameters of friction welding and number of tensile tests could be minimized.