基于机器视觉的微小轴承几何量精度检测研究  

Precision detection of geometric accuracy of tiny bearings based on machine vision

作　　者：林海波[1] 杨建西[1] LIN Hai-bo;YANG Jian-xi(School of Mechanical Engineering,Taizhou Vocational&Technical College,Taizhou 318000,China)

机构地区：[1]台州职业技术学院机电工程学院,浙江台州318000

出　　处：《机电工程》2023年第2期245-251,共7页Journal of Mechanical & Electrical Engineering

基　　金：浙江省公益技术研究计划资助项目(LGG20E050005);浙江省教育厅科研项目(Y202250374);台州市科技计划资助项目(1901gy23);台州市高层次人才特殊支持计划项目(台人才领〔2020〕4号)。

摘　　要：微小轴承在精密仪器设备中使用广泛,其内外径尺寸及其同轴度的精度与整个仪器的精密准确性密切相关。为此,针对滚动轴承内外径尺寸和形位公差检测的研究较为匮乏,且精度较低的问题,提出了一种基于机器视觉的微小轴承几何量精度检测方法。首先,通过背光视觉系统获取了高质量的轴承图像,利用各向异性双边滤波(ABF)算法对其进行了滤波;然后,基于局部区域特征的三次曲线模型,得到了轴承内外圈边缘亚像素信息,并精确计算了其边界的位置;最后,计算了所测轴承内外径尺寸及其同轴度,并以此数据来判断轴承是否合格,同时也验证了该方法的可行性和优越性。研究结果表明:该检测方法的边缘提取精度为0.2像素,测量精度可达到3μm,可以对零件尺寸进行非接触、高精度、智能化、快速目标检测;该方法检测效率高、准确性好,可同时检测多项指标,在准确性和精度上均可满足工业检测的要求。Micro bearings were widely used in precision instruments and equipment,and the accuracy of their inner and outer diameter dimensions and coaxiality were closely related to the precision and accuracy of the entire instrument.Therefore,in view of the lack of research on the detection of the inner and outer diameters and geometric tolerances of rolling bearings and the low accuracy,a machine vision-based detection method for the precision and high-efficiency of the geometric quantity of small bearings was proposed.Firstly,high-quality bearing images were obtained through a backlight vision system,and an anisotropic bilateral filtering(ABF)algorithm was used for filtering.Then,the sub-pixel information of the edge of the inner and outer circles was obtained to accurately calculate the boundary position based on the cubic curve model of local area features.Finally,the inner and outer diameters of the measured bearings and their coaxiality were calculated,and the experimental data was analyzed to judge whether the bearings were qualified or not,which verified the feasibility and superiority of the method.The experimental results show that the accuracy of this method can reach 3μm,realize non-contact,high-precision,intelligent and fast target detection of part size.The method has high detection efficiency and good accuracy,and can detect multiple indicators at the same time.The conclusion is stable and reliable,and both accuracy and precision can meet the requirements of industrial detection.

关 键 词：微小轴承质量检测 滚动轴承视觉检测 各向异性双边滤波 三次函数模型 亚像素 同轴度 

分 类 号：TH133.3[机械工程—机械制造及自动化] TP391.4[自动化与计算机技术—计算机应用技术]