为解决人工切割大型铸件冒口对人体损害大,生产效率低和切割平面粗糙的问题,对视觉检测技术和机器人切割轨迹规划进行研究.首先,利用3D工业相机采集铸件三维场景点云信息;然后,通过提出的三点模板点云配准(three-point template point cloud registration,TTPCR)方法获取铸件切割点位的位姿信息,利用手眼标定变换矩阵把切割点位的信息变换到机械臂的基坐标系下;最后,利用空间圆弧的姿态插补求出切割轨迹的位姿信息,并用RoboDK软件开展实验.实验结果表明切割的误差小于1.3 mm,相对于传统的人工切割方法,切割豁口缝隙减少了37.5%,切割表面粗糙度降低了70.8%,切割表面平均粗糙深度降低了65.6%,满足铸件切割工艺要求,具有一定的工业应用价值.
Planning of Cutting Trajectory for Large Casting Risers Based on 3D Point Cloud
In order to solve the problems of manual cutting of large casting risers causing significant dam-age to human health,low production efficiency,and rough cutting planes,visual inspection technology and robot cutting trajectory planning are studied.Firstly,use a 3D industrial camera to capture the point cloud information of the casting's 3D scene;Then,using the proposed three point template point cloud registration(TTPCR)method,the pose information of the casting cutting points is obtained.The hand eye calibration transformation matrix is used to transform the information of the cutting points into the base coordinate sys-tem of the robotic arm;Finally,the pose information of the cutting trajectory is obtained through the inter-polation of spatial arcs,and experiments are conducted using RoboDK software.The experimental results show that the cutting error is less than 1.3 mm.Compared to traditional manual cutting methods,the cutting gap is reduced by 37.5%,the cutting surface roughness is reduced by 70.8%,and the average roughness depth of the cutting surface is reduced by 65.6%.This meets the requirements of casting cutting technology and has certain industrial application value.