基于视觉的飞机蒙皮锪窝孔径在线测量研究  

Research on On-Line Measurement of Aircraft Skin Countersink Holes Aperture Based on Vision

作　　者：罗辉 胥云 袁秀坤 LUO Hui;XU Yun;YUAN Xiukun(College of Mechanical Engineering,Sichuan University of Science&Engineering,Yibin,Sichuan 644000,China;Department of Traffic Engineering,Sichuan Engineering Technical College,Deyang,Sichuan 618000,China)

机构地区：[1]四川轻化工大学机械工程学院,四川宜宾644000 [2]四川工程职业技术学院交通工程系,四川德阳618000

出　　处：《自动化应用》2024年第2期156-160,共5页Automation Application

基　　金：四川大学自贡市校地科技合作专项资金2022年立项项目(2022CDZG-19)。

摘　　要：为解决飞机蒙皮锪窝孔人工测量效率低的问题,满足锪窝检测自动化要求,开发了一套基于OpenCV与Qt研发平台用于自动化检测飞机蒙皮锪窝孔径参数的在线测量系统。该系统采用相机标定解决图像的桶形失真问题;使用直方图均衡化、双边滤波及轮廓查找算法,避免碳纤维材料锪窝孔反光带来的噪声;基于二次插值的亚像素算法准确提取锪窝轮廓,并使用最小二乘法与距离最小算法,利用梯度下降算法计算拟合,准确测量锪窝孔径参数。结果表明,该系统的测量精度在30μm以内,重复检测精度高,满足测量的自动化要求。To solve the problem of low efficiency of manual measurement of aircraft skin countersink holes and meet the automation requirements of countersink holes detection,an online measurement system based on OpenCV and Qt R&D platform was developed for automated detection of aircraft skin countersink hole diameter parameters.The system uses camera calibration to solve the problem of barrel distortion in images.Using histogram equalization,bilateral filtering,and contour search algorithms to avoid noise caused by the reflection of countersink holes in carbon fiber materials.The sub-pixel algorithm based on quadratic interpolation accurately extracts the countersink contour,and uses the least squares method and the minimum distance algorithm to calculate the fitting using the gradient descent algorithm,accurately measuring the dimple holes aperture parameters.The results indicate that the measurement accuracy of the system is within 30μm,the repeated detection accuracy is high,meeting the automation requirements of measurement.

关 键 词：机器视觉 飞机蒙皮 亚像素算法 相机标定 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置] TG806[自动化与计算机技术—控制科学与工程]