Prediction of tool wear in milling of Inconel 625 using and integrated kurtosis-based algorithm with vibration signals

Abstract

Tool wear may depreciate the quality of the machined product owing to its poor surface roughness and dimensional inaccuracy. Tool condition monitoring system (TCMs) is necessary for the manufacturing industry to obtain better quality products with minimal time and improve productivity. Currently, TCMs uses different sensor signals and features to examine the tool wear. In this work, an Integrated kurtosis-based algorithm for Z-filter (I-Kaz) 2D and 3D analysis is employed to examine the vibration signals in milling of Inconel 625 for monitoring the tool condition during the milling process. The results from vibration signals revealed that the I-Kaz coefficient correlates with flank wear. I-Kaz coefficient was increased for raise in flank wear. When the I-Kaz 2D coefficient value increased above 0.5, it indicates that the tool was worn out and has to be replaced.