Determination of Tool Wear in Turning Process Using Undecimated Wavelet Transform and Textural Features

Abstract

The state of a cutting tool is a critical factor in any metal cutting process because dull or damaged cutting tool reduces surface quality and dimensional accuracy of workpiece and damages the machine tool. This paper proposes a novel vision-based approach for determining tool wear in metal cutting. The surface irregularity changes caused by tool wear are used as a criterion for estimating the cutting tool wear. Undecimated Wavelet Transform is used to decompose the surface image of the workpiece into sub-images in which the cutting tool wear can be indicated. The texture of sub-images is analyzed using GLCM texture features. The experimental results showed that the combination of undecimated wavelet decomposition and GLCM texture features can be used as a robust method for determining tool wear in the turning process.