In-process detection of chipping in ceramic cutting tools during turning of difficult-to-cut material using vision-based approach

Abstract

Ceramic cutting tools are prone to failure by chipping and fracture rather than gradual wear mainly because of their low impact resistance. This results in poor surface finish and low dimensional accuracy of the machined parts. In this work, a vision-based approach has been developed to detect the onset of chipping in aluminum oxide ceramic cutting tools during the dry turning of AISI 01 oil-hardening tool steel. The profile of the workpiece surface opposite the cutting tool was captured during the turning using 18-megapixel DSLR camera at a shutter speed of 0.25 ms. The surface profile of the workpiece was extracted to sub-pixel accuracy using the invariant moment method. The effect of chipping in the ceramic cutting tools on the surface profile signature of the machined workpiece was investigated using autocorrelation analysis. Chipping in the ceramic tool was found to (i) cause the peaks of autocorrelation function of the workpiece profile to decrease rapidly as the lag distance increased and (ii) cause the envelope of the peaks of the autocorrelation function to deviate significantly from one another at different workpiece rotation angles. The sum of squared deviation (SSD) of the envelope of the peak of autocorrelation function was also found to increase sharply right after tool chipping. Significant variations in the SSD at different workpiece rotation angles were observed beyond the cutting time of 11.1 s because of the continuous chipping of the ceramic insert during turning.