Development of Hybrid Intelligent Models for Prediction Machining Performance Measure in End Milling of Ti6Al4V Alloy with PVD Coated Tool under Dry Cutting Conditions

Ti6Al4V alloy is widely used in aerospace and medical applications. It classified as a difficult to machine material due its low thermal conductivity high chemical reactivity. In this study, hybrid intelligent models have been developed predict surface roughness when end milling with Physical Vapor Deposition PVD coated tool under dry cutting conditions. Back propagation neural network (BPNN) has hybridized two heuristic optimization techniques, namely: gravitational search algorithm (GSA) genetic (GA). Taguchi method was an L27 orthogonal array generate 27 experiment runs. Design expert software do analysis of variances (ANOVA). The experimental data were divided randomly into three subsets for training, validation, testing the model. ANOVA results revealed that feed rate highly affected by followed depth cut. One-way ANOVA, including Post-Hoc test, evaluate performance models. model Artificial Neural Network-Gravitational Search Algorithm (ANN-GSA) outperformed Network (ANN) Network-Genetic (ANN-GA) ANN-GSA achieved minimum mean square error 7.41 × 10−13 maximum R-value 1. Further, convergence speed faster than ANN-GA. GSA proved ability improve BPNN, which suffers from local minima problems.