基于机器视觉的立铣刀几何与状 数在机检测

To prevent the tool installation errors caused by frequent changes of tools during the aeronautical components machining, a detection system based on machine vision is proposed to measure geometric and state parameters of milling cutter. The end mill is taken as the research object, and its dynamic image contour under the state of spindle rotation is extracted. Besides, the measurement algorithm for cutting edge radius, tool diameter and overhang length are also developed. To demonstrate the visual deviation caused by the camera's large view during the measurement of overhang length, the deviation correction algorithm is further studied to improve the measurement accuracy. Finally, the proposed method is verified on the CNC machine tool. The results show that the maximum error is 0.51% and the device achieves good repeatability and high precision, which can realize the on-machine detection of tool geometric and state parameters.