ANN model for predicting the intergranular corrosion susceptibility of friction stir processed aluminium alloy AA5083

Abstract

Aluminium alloy AA5083 was subjected to friction stir processing with an objective to increase the intergranular corrosion resistance of the alloy. Experimental trials were performed by varying the friction stir process parameters namely Tool Rotation Speed, Tool Traverse Speed and Shoulder Diameters as per Taguchi's L18 orthogonal array. The base specimen and friction stir processed specimens were subjected to intergranular corrosion susceptibility test according to the standard ASTM G67-04. Artificial Neural Network model was developed with cascade forward propagation network architecture to predict the intergranular corrosion susceptibility of the friction stir processed specimens. The network was trained with 80% experimental data using Levenberg Marquardt algorithm and the remaining data was used for testing and validation. Least root mean squared error value and prediction error indicated high accuracy of the developed model.