Application of machine vision method in tool wear monitoring

Aiming at the low tool utilization rate caused by tool wear in the milling process, a tool wear automatic monitoring system based on machine vision is proposed. The tool wear images are automatically acquired by a charge-coupled device (CCD) camera. The system selects the image with obvious characteristics and cuts the wear area for processing, thus extracting the tool wear value. On one hand, the reliability of using the wear area of flank face as a technical index to judge the degree of tool wear is explored. On the other hand, the changes in the surface texture of workpiece are also analyzed by the gray-level co-occurrence matrix (GLCM) method. A milling experiment was carried out and the wear value measured by the monitoring system was compared with the real wear value. The result showed that the accuracy of the monitoring system met the industrial requirements. The wear area of the flank face and the wear width are consistent in trend under different cutting parameters, which means that the wear area of the flank face could be used as an index for judging the degree of tool wear. In addition, the characteristic parameters of the surface texture of workpiece change regularly with the tool wear, which shows that the tool wear can be characterized from another aspect.