Orthogonal array and artificial neural network approach for cutting force optimization during machining of Ti-6Al-4V under minimum quantity lubrication (MQL)

Growing demand for titanium due to its excellent material properties has made them applicable in industrial as well as commercial applications, such as aerospace industries, nuclear waste storage, automobile industries and surgical implantation. However, titanium alloy is classified as difficult to machine materials because of its low modulus of elasticity, low thermal conductivity and high chemical reactivity resulting in high tool vibration and high cutting temperature has made the researchers to explore the machinability behavior of Ti-6Al-4V. In this paper an attempt has been made for cutting force optimization during machining of Ti-6Al-4V under Minimum Quantity Lubrication using L27 Orthogonal Array and Artificial Neural Network approach. From the investigation it is observed that the developed ANN model resulted in minimum error with comparison with L27 Orthogonal Array. Hence we can conclude that ANN model developed can effectively used to predict and estimate the cutting force.