Proceedings of the Institution of Mechanical Engineers Part B Journal of Engineering Manufacture · 2006 · 43 citations · 15 references
EngineeringComputer ScienceComputer VisionDrillingMachine VisionDrilling AutomationEdge DetectionMachiningCanny Edge DetectorDrilling Process MonitoringHigh-speed ImagingTool InspectionTool Wear
A computer vision-based approach to drilling tool condition monitoring is proposed in this paper. Firstly, image frames are captured using a high-speed CCD camera. Then, a Canny edge detector is employed to extract tool features from the acquired images. In order to obtain a measure of tool wear, the deviation from linearity (DEFROL) metric is proposed. Experimental results show that the proposed method detects the condition of all tested tools successfully.
15