铁塔螺栓松动的视觉检测方法研究  

Research on Visual Detection Method of Iron Tower Bolt Looseness

作　　者：张建立[1] 王亚龙[1] ZHANG Jian-li;WANG Ya-long(School of Mechanical and Power Engineering,Zhengzhou University,He’nan Zhengzhou 450001,China)

机构地区：[1]郑州大学机械与动力工程学院,河南郑州450001

出　　处：《机械设计与制造》2023年第12期63-66,共4页Machinery Design & Manufacture

基　　金：河南省科技攻关计划(172102210480)。

摘　　要：为实现无接触的铁塔螺栓松动检测,通过模拟实验的方法对螺栓连接板进行图像采集,使用C++程序对采集到的图像进行处理,研究了图像配准对于铁塔螺栓松动检测的可行性。在传统图像配准的基础上,结合对象检测、边缘检测、轮廓提取等图像处理技术,提出了一套针对铁塔螺栓的松动检测算法。结果表明:相较于直接使用传统图像配准算法,新算法的检测效果有很大提升,准确率达到90%以上。可见利用图像配准技术进行铁塔螺栓松动检测是可行的,能够有效减少检测工作量,缩短检测周期,提高塔架可靠性。In order to realize the non-contact detection of iron tower bolt looseness,through the method of simulation experiment we carried out images acquisition on the bolt connection plate,then the collected images were processed by the C++program,and the feasibility of image registration for the iron tower bolt looseness detection was studied.Based on traditional image registration,a set of looseness detection algorithms is proposed for iron tower bolts combined with image processing techniques such as object detection,edge detection,and contour extraction.The results show that:Compared with the direct use of traditional image registration algorithms,the detection effect of the new algorithm is greatly improved,and the accuracy rate is more than 90%.It can be seen that it is feasible to use image registration technology to detect the looseness of iron tower bolts,which can effectively reduce the detection workload,shorten the detection period,and improve the reliability of the tower.

关 键 词：图像配准 对象检测 边缘检测 轮廓提取 

分 类 号：TH16[机械工程—机械制造及自动化] TN911.73[电子电信—通信与信息系统]