Modeling and prediction of electrical discharge machining performance parameters for AA 8081 hybrid composite using artificial neural network

Abstract

Aluminum matrix composites (AMCs) are gaining increasing attention from various industries due to their lightweight and more excellent wear resistance than conventional materials. Manufacturers embracing that difficulty in machining MMC due to reinforcing particles abrasive nature shorten the tool life. Electro-discharge machining (EDM) is an enormously used non-conventional process to remove material in die making, aerospace, and automobile industries and machine any material with the highest hardness. Hence in the present study, EDM was performed on an aluminium alloy 8081 (AA8081) with reinforcement of 10% SiC, 5% B4C, and 5% Gr particles utilizing an ultrasonic cavitation assisted stir casting process. The machining investigation was carried out adopting face-centered central composite design (CCD) with three parameters such as current, pulse-on time, and pulse-off time to ascertain the effects of two sustainable measures, viz., Material removal rate (MRR) and tool wear rate (TWR) the data were collected. An Artificial Neural Network (ANN) model was developed based on data obtained from experiments. Finally, experimental values are compared with the predicted values of ANN and found high prediction accuracy. The advanced model results are used to approximate the responses fairly precisely. The version features a mean coefficient of correlation of 0.99072. Effects uncovered that the projected version is employed for the prediction of the complex EDM process.