摘要
衬芯是汽车制动系统中连接刹车油管与制动器的重要零部件,其内径超差会严重影响车辆刹车性能.针对人工测量衬芯内径尺寸方法效率低、精度差、检测标准不一致等问题,提出基于机器视觉的衬芯内径尺寸测量方法.利用双边滤波、改进的Otsu阈值法和形态学方法对衬芯内径进行预处理和定位,采用一种改进的Canny边缘检测算子提取内径轮廓点,并基于Tukey权函数实现最小二乘法拟合圆以计算内径尺寸.试验验证该检测算法的测量误差在±0.01 mm之内,测量准确率为98.9%、漏检率为0、过检率为1.1%,能够满足企业的实际测量要求.
Liner is an important component connecting brake oil pipe and brake in automobile brake system,and the oversize of inner diameter will seriously affect the brake performance of vehicles.Aiming at the problems of low efficiency,poor accuracy and inconsistent detection standards in the manual measurement of liner inner diameter,a method for measuring liner inner diameter based on machine vision was proposed.The inner diameter of liner was preprocessed and located by using bilateral filtering,improved Otsu threshold method and morphological method.An improved Canny edge detection operator was used to extract the inner diameter contour points,and the least square method was used to fit the circle based on Tukey weight function to calculate the inner diameter size.The experimental verification shows that the measurement error value of the detection algorithm is within±0.01 mm,the measurement accuracy is 98.9%,the missing rate is 0,and the passing rate is 1.1%,which can meet the actual measurement requirements of enterprises.
作者
范狄庆
李晋鑫
沙玲
方宇
FAN Diqing;LI Jinxin;SHA Ling;FANG Yu(School of Mechanical and Automotive Engineering,Shanghai University of Engineering Science,Shanghai 201620,China)
出处
《上海工程技术大学学报》
CAS
2023年第1期61-67,共7页
Journal of Shanghai University of Engineering Science
基金
2021松江区科技攻关揭榜挂帅项目资助(21SJJBGS5)。
关键词
机器视觉
图像处理
尺寸检测
machine vision
image processing
dimension detection
