基于机器视觉的同轴度检测与微调系统设计  

Coaxiality detection based on machine vision and design of fine-tuning system

作　　者：朱磊 张俊然[1] 佃松宜[1] ZHU Lei;ZHANG Junran;DIAN Songyi(College of Electrical Engineering,Sichuan University,Chengdu 610065,China)

机构地区：[1]四川大学电气工程学院,四川成都610065

出　　处：《传感器与微系统》2022年第6期94-98,102,共6页Transducer and Microsystem Technologies

基　　金：宁夏自然科学基金资助项目(2020AAC03485);国家自然科学基金资助项目(61902264);智能电网四川省重点实验室应对新冠应急重点项目(2020IEPG-KL-20YJ01);华西医院135交叉学科创新项目(ZYJC21041)。

摘　　要：针对现有方法在精密金属轴类组件的同轴度测量与调整中存在如调整难度大、测量精度低和速度慢等问题,设计了一种基于机器视觉在线高精度同轴度检测与微调系统。该系统在VS2019开发平台结合HALCON库实现算法设计,通过图像去噪、亚像素形状匹配粗定位、改进一维测量矩形寻找边界点、最小二乘法拟合圆轮廓寻找圆心和九眼标定算法引导微型电爪对同轴度的调整,并完成上位机界面的开发,实现了对零件同轴度实时测量调整。实验结果表明:该算法具有快速、高鲁棒、高精度性能,检测精度能达到3μm,平均检测时间为每帧60 ms。此方法符合该自动化设备生产线的组装要求,并具有一定工程实用性和可泛化性。Aiming at the problems of existing methods in coaxiality measurement and adjustment of precise metal shaft components,such as difficult adjustment,low measurement precision and slow speed,an on-line high-precision coaxiality detection and fine-tuning system based on machine vision is designed.The system realizes the algorithm design on the VS2019 development platform combined with HALCON library.Through image denoising,sub-pixel contour matching rough positioning,improved one-dimensional rectangular measurement to find the boundary point,least square method to fit the circular of circle contour to find the center of circle and nine eye calibration algorithm,the system guides the micro electric claw to adjust the coaxiality,and completes the development of the upper computer interface to realize the real-time measurement and adjustment of the coaxiality of parts.Experimental results show that the algorithm has fast speed,fast robustness and high precision,and detection precision can reach 3μm,and the average detection time is 60 ms per frame.This method meets the assembly requirements of the automatic equipment production line and has certain engineering practicability and generalization.

关 键 词：轴类组件 同轴度测量 HALCON库 机器视觉 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]