Abstract
Titanium alloys are widely used in various applications including biomedicine, aerospace, marine, energy, and chemical industries because of their superior characteristics such as high hot strength and hardness, low density, and superior fracture toughness and corrosion resistance. However, there are different challenges when machining titanium alloys because of the high heat generated during cutting processes which adversely affects the product quality and process performance in general. Thus, optimization of the machining conditions while machining such alloys is necessary. In this work, an experimental investigation into the influence of different cutting parameters (i.e., depth of cut, cutting length, feed rate, and cutting speed) on surface roughness (Rz), flank wear (VB), power consumption as well as the material removal rate (MRR) during high-speed turning of Ti-6Al-4V alloy is presented and discussed. In addition, a backpropagation neural network (BPNN) along with the technique for order of preference by similarity to ideal solution (TOPSIS)-fuzzy integrated approach was employed to model and optimize the overall cutting performance. It should be stated that the predicted values for all machining outputs demonstrated excellent agreement with the experimental values at the selected optimal solution. In addition, the selected optimal solution did not provide the best performance for each measured output, but it achieved a balance among all studied responses.