摘要
针对实际生产中测量刀具磨损需要人工操作、停机检测等问题,开发了一个基于机器视觉的加工刀具磨损测量系统.首先提出基于Laplacian算子边缘信息的Otsu分割算法将图像二值化,再通过基于形态学的Canny算子边缘检测粗定位及图像配准提取清晰的刀具磨损区域.最后,使用基于Zernike矩的亚像素边缘检测方法提高测量精度,并通过主曲线方法拟合亚像素边缘点得到光滑的边缘曲线,实现了刀具磨损量的在线测量.实际加工过程中的刀具磨损测试结果表明,该系统检测自动化程度高、运行速度快、测量精度可以达到微米级,可以有效地应用于工业上对加工刀具磨损的实时监控.
In order to solve the problems of tool wear measurement in actual production,such as manual operation and shutdown detection,a machining tool wear measurement system based on machine vision is developed in this paper.First,the Otsu segmentation algorithm based on Laplacian edge information is proposed to binarize the images.Then,through rough positioning by morphology-based Canny operator edge detection and image registration,the tool wear area is extracted effectively.Finally,sub-pixel edge detection based on Zernike moment is used to improve the measurement accuracy while the principal curve method is used to fit sub-pixel edge points so as to obtain the smooth edge curve and realize the online measurement of tool wear.In real machining process,the tool wear test results show that the system has a high degree of automation and a rapid running speed.Moreover,its measurement accuracy can reach micron level.This system can be effectively applied to real-time monitoring of tool wear in industry.
作者
周俊杰
余建波
ZHOU Junjie;YU Jianbo(School of Mechanical Engineering,Tongji University,Shanghai 201804,China)
出处
《上海交通大学学报》
EI
CAS
CSCD
北大核心
2021年第6期741-749,共9页
Journal of Shanghai Jiaotong University
基金
国家自然科学基金(71777173)
上海科委“科技创新行动计划”高新技术领域项目(19511106303)
中央高校基本业务经费项目(22120180068
22120190196)。
关键词
加工刀具
磨损测量
机器视觉
图像分割
边缘检测
machining tool
wear measurement
machine vision
image segmentation
edge detection
