Automated intelligent machine vision system for monitoring the image

The texture of machined surfaces provides reliable information regarding the extent of tool wear. The vision-based of automated tool wear monitoring systems are very important and efficient for unmanned machining systems. This research is use the machine vision inspection technique to automatic tool wear monitoring measurement of different coated drills. A new method based on computer vision and a neural network classifier is proposed to estimate the wear of metal cutting inserts in order to identify the time for their replacement. Classification of wear level in two classes -low and too high wear- is possible followed by a supervised approach, so as tool replacement is carried out before the wear reaches the second level or class. A total of 1383 wear flank images were acquired using a vision system and a binary image was generated for each one. The perimeter of the wear region was described by means of a shape signature, which was normalized and resized to 40 and 100 values. These vectors have been classified using both k-nn and MLP, obtaining 5.5% and 5.1% error rates, respectively.