A Novel Evaluation Metric Based on Dispersion of Wear Distance for In Situ Tool Condition Monitoring

Abstract

As the direct performer of the cutting process in computer numerical control (CNC) machine tools, the tool wear condition directly affects the product quality. However, the existing evaluation metrics, e.g., flank wear width and wear area, cannot accurately determine the wear form conversion. In this article, a novel metric based on the dispersion of wear distance is proposed to describe the flank wear forms in more detail. The wear distance refers to the distance projected from the flank wear edge to the main cutting edge. Then, the wear distance of the indirect contact on the tool–chip interface is filtered out by the normal distribution model. Finally, the rate of distance dispersion over time named RDDT is constructed to identify the time nodes during wear forms’ conversion. In the experiment of accelerating milling cutter life, the Mann-Kendall (MK) inspection statistics of the proposed metric is 3.74, and the correlation with the maximum flank wear is 99.58%. Compared with the existing evaluation metrics, RDDT can accurately and robustly identify the two time nodes where the flank wear form changes in the whole life cycle.