Artificial Neural Network Modeling for Predicting Surface Roughness and Material Removal Rate in End Milling of AA7075-SiC-Al2O3 Hybrid Metal Matrix Composites

Abstract

Aluminium Metal Matrix Composites (AMMCs) are new generation engineering materials that possess superior physical and mechanical properties compared to non-reinforced alloys. This makes them attractive for wider range of applications in automotive, aerospace and defense industries. The aluminium metal matrix composites exhibit poor machinability due to hard and abrasive reinforcement used. It results in faster tool wear leading to increased manufacturing cost and production of poor surface. The objective of this present work is to predict the surface roughness and material removal rate in end milling of AA7075-SiC-Al2O3 hybrid metal matrix composites by using artificial neural network (ANN). In this present work, Alumina and Silicon carbide are added as reinforcement particles to Aluminium 7075 alloy for preparing hybrid composite by liquid metallurgy route. End milling operation was done according to Box-Behnken design of experiments (L27) by considering four factors such as spindle speed, depth of cut, feed rate and weight percentage of silicon carbide. The predicted surface roughness and material removal rate from ANN model was very close to the experimental values. The performance of the ANN model is also compared with the response surface model (RSM) and found that the ANN model was better than RSM.