Machine Learning Based Surface Finish Prediction and Optimization of Process Parameters in Pulsed CO₂ Laser Cutting of Particle (TiC) Reinforced Al6061 Composite Using KNN & ANN

This paper focus on surface finish enhancement of titanium carbide particles reinforced aluminium (AA6061) composites in laser cutting machine. Initially machining parameters are optimized to achieve minimum surface roughness using Taguchi L27 orthogonal array and ANOVA analysis. S/N ratio, Interaction plots and contour plots are utilized to obtain the influencing parameters on surface quality which is measured in terms of surface roughness. The machining parameters considered for optimization are Reinforcement (wt% TiC), Laser Power (W), Velocity, Gas flow Pressure and Pulse frequency. The result proved that the velocity is the more influencing parameter on surface roughness compared to other parameters. Then the experimental data is used to train the machine learning models such as Artificial Neural Network (ANN) and K Nearest Neighbour Algorithm (KNN) to predict the surface roughness. The performance of the regression algorithm is evaluated using R-Square value (R₂), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE) and Mean Squared Error (MSE). It is observed that both the algorithms have acceptable R² value of 0.987 and 0.983 which is near one which means KNN predictions has more accurate compared to ANN which is proved in terms of R²(0.987), MAE (0.452), MSE (0.311) and RMSE values (0.557).