Modeling of tool wear parameters in high-pressure coolant assisted turning of Titanium Alloy Ti-6Al-4V using artificial neural networks

Abstract

Titanium alloy (Ti-6Al-4V) can be economically machined with high-pressure coolant (HPC) supply. In this study, an artificial neural network (ANN) model was developed for the analysis and prediction of tool wear parameters when machining Ti-6Al-4V alloy with conventional flow and high-pressure coolant flow, up to 203 bar. Machining trials were conducted at different cutting conditions for both rough and finish turning operations with uncoated carbide (K10 grade) and double TiAIN/TiN, PVD coated carbide (K10 substrate) inserts. The cutting parameters (cutting speed, feed rate, depth of cut, coolant pressure, and tool type) and the process parameters (cutting forces, feed force, machined surface roughness, and circularity) were used as input data set to train the three-layered feed-forward, back-propagation artificial neural networks. The networks were trained to predict tool life and wear rate separately. The results show that the correlation coefficients between the neural network predictions and experimental values of tool life, tool wear and wear rate were 0.996 and 0.999, respectively, suggesting the reliability of the neural network model for analysis and optimization of cutting process.