Machinability and ANN based prediction of surface roughness for TiAlN and PCD coated end mill cutters on AA6061 hybrid composite

This research is conducted to evaluate the impact of TiAlN and polycrystalline diamond coated (PCD) end mill cutters on the machinability of a hybrid composite made from 90% AA6061, 5% C, and 5% ZrO₂. The composite was fabricated using the stir casting method. An examination of the particle distribution of reinforcements in the AA6061 substrate was conducted using SEM. The milling operation was processed in a CNC milling machine using different cutting parameters. These included spindle velocities of 3000, 4000 and 5000 rpm, depth of cut of 0.5, 1, and 1.5 mm, and feed rate of 50, 150, and 250 mm/min. The experiment was designed using an orthogonal array (L₉) that was generated using Taguchi's method to optimize the cutting parameters and coating. The study analyzed the width to thickness ratio and surface roughness for the 9 experimental trials. The results showed that the PCD coating had a significant effect, leading to a remarkable surface polish and reduced tool wear. Further, the prediction of the surface roughness of the TiAlN and polycrystalline diamond coated (PCD) end mill cutters were explored through the machine learning-based artificial neural network model which exhibits R² value of 0.9838 for showing the high accuracy.