Artificial Neural Network and Process Optimization of Electrical Discharge Machining of Al 6463

Abstract

A silicon carbide strengthened aluminium 6463 composite was formed by stir casting. To assess crucial process parameters, the composite was machined. At three different levels, three variables—current, pulse ON time, and feed of the wire—were incorporated in Taguchi's experimental setup. The components that impact the process were found using a statistical analysis. The ON time of the pulse of 160 s, the current of 18 A, and the feed of the wire of 2 mm/min had the highest removal rate. The pulse on-time of 100 s, the current of 12 A, and the feed of the wire rate of 2 mm/min remained the most effective factors for obtaining a good surface quality. Feed of the wire had minimal impact on output characteristics, but pulse duty cycle and current were important elements in achieving high material removal rates with acceptable surface quality. The experimental Taguchi design improved machinability characteristics while milling the synthesized composites by maintain the higher value of the ON time of the pulse and current. The artificial neural network model is developed to predict the experimental outcome and the model predicts the result with an accuracy of 100%.