大跨距孔组同轴度视觉检测系统设计  

Design of Coaxiality Visual Inspection System for Large Span Hole Group

作　　者：尹顺 叶秀军 张志存 梁蔓安[1,2] 张厅瑞 杨宇航 Yin Shun;Ye Xiujun;Zhang Zhicun;Liang Man′an;Zhang Tingrui;Yang Yuhang(School of Mechanical and Automotive Engineering,Guangxi University of Science and Technology,Liuzhou,Guangxi 545006,China;不详)

机构地区：[1]广西科技大学机械与汽车工程学院,广西壮族自治区柳州市545006 [2]广西土方机械协同创新中心 [3]广西柳工机械股份有限公司

出　　处：《工具技术》2025年第3期137-143,共7页Tool Engineering

基　　金：广西自然科学基金项目(2021JJA160278);广西科技重大专项项目(桂科AA22068064);广西重点研发计划项目(桂科AB22035066)。

摘　　要：针对大跨距孔组同轴度误差传统测量方法效率低、无法在线检测等问题,提出一种基于空间坐标变换的视觉检测方案。此方案通过伺服运动定位平台控制相机采集孔组侧面图像,运用图像处理技术获得孔组圆心像素坐标,经空间坐标变换后获得其对应于基础坐标系下的位置及同轴度误差。为获得精确的孔组圆心像素坐标,针对车间环境光不稳定问题,提出一种自适应Gamma校正图像增强方法,通过卡尺边缘检测改进算法的设计,提高孔组轮廓识别精度。就孔组空间坐标变换问题,给出其中具体的标定和旋转偏移补偿方法。使用该方案搭建的实验平台对装载机动臂样件孔组进行测量,并与三坐标测量机测量的结果进行对照,实验论证了该方案的可行性和实用性,且视觉测量精度满足检测要求,方便在线检测实施。Aiming at the problem that the traditional measurement method of coaxiality error of long-span hole group is inefficient and cannot be detected online,a visual detection scheme based on spatial coordinate transformation is proposed.This scheme controls the camera to collect the side image of the hole group through the servo motion positioning platform,and uses the image processing technology to obtain the pixel coordinates of the center of the hole group.After the spatial coordinate transformation,the position and coaxiality error corresponding to the basic coordinate system are obtained.To obtain the accurate pixel coordinates of the center of the hole group,an adaptive Gamma correction image enhancement method is proposed for the problem of unstable ambient light in the workshop.Through the design of the improved algorithm of caliper edge detection,the accuracy of hole group contour recognition is improved.For the problem of space coordinate transformation of hole group,the specific calibration and rotation offset compensation methods are given.The experimental platform built by this scheme is used to measure the hole group of the loader boom sample,and compared with the measurement results of the coordinate measuring machine.The experiment demonstrates the feasibility and practicability of the scheme,the visual measurement accuracy meets the detection requirements,which is convenient for online detection.

关 键 词：大跨距孔组 同轴度 视觉测量 图像增强 边缘检测 

分 类 号：TG806[金属学及工艺—公差测量技术] TH124[机械工程—机械设计及理论] TP391.41[自动化与计算机技术—计算机应用技术]