Abstract

The research work is focused on Tool Condition Monitoring (TCM) of Titanium-based Super alloys and turning operation to improve the machining process and to predict the tool wear and failure. Titanium (Ti) based superalloys are widely adapted in aerospace and automotive industries because of their outstanding combination of mechanical properties and high-temperature corrosion resistance. These superalloys, however, are difficult to cut due to their poor heat conductivity, low elastic modulus, high strength, and superior chemical resistance. Also during machining of Ti superalloys at high cutting speeds and feed rate, the life of cutting tool is drastically decreased. Tool life is shortened, and adequate surface quality is sometimes impossible to achieve due to the poor machining cutting properties of uncoated cutting tools. As a result, adopting a Physical Vapor Deposition (PVD) coated carbide cutting tool can increase cutting tool life and cutting qualities. In the turning process, a lathe tool dynamometer is setup to measure the cutting forces. The findings indicate that such cutting forces and wear data, when combined with machine learning approaches based on Neural Networks, may be utilized for actual monitoring of tool wear/breakage and control mechanisms, thereby enhancing digital manufacturing techniques.