摘要
针对列车滚子轴承内圈外表面缺陷人工检测方法的不足,提出了一种基于机器视觉的表面缺陷检测方法,通过对缺陷图像的处理和分析,快速、准确地实现了轴承表面缺陷的分类识别。这里使用工业内窥镜进行轴承图像的获取,通过对图像的灰度直方图分析,判断其是否为缺陷轴承;对缺陷图像分别进行二值化处理、形态学滤波和图像标记,以准确获得图像的缺陷区域;对缺陷区域进行特征提取后,利用缺陷分类决策树完成缺陷类型的识别。实验表明,该方法实时性好、运算速度快,可有效检测出列车滚子轴承表面缺陷。
Aiming at the shortcomings of the manual detection method for the outer surface defects of the inner roller of the roller bearing,a surface defect detection method based on machine vision is proposed.Through the processing and analysis of the defect image,the classification and recognition of the bearing surface defects are realized quickly and accurately.In this paper,the industrial endoscope is used to obtain the bearing image.The gray histogram of the image is analyzed to determine whether it is a defective bearing.The defect image is binarized,morphologically filtered and image-marked to obtain the image accurately.Defect area;after feature extraction of the defect area,the defect classification decision tree is used to complete the defect type identification.Experiments show that the method has good real-time performance and fast calculation speed,and can effectively detect surface defects of train roller bearings.
作者
石炜
张袁祥
李嘉楠
SHI Wei;ZHANG Yuan-xiang;LI Jia-nan(School of Mechanical Engineering,Inner Mongolia University of Science and Technology,Inner Mougolia Baotou 014010,China)
出处
《机械设计与制造》
北大核心
2022年第4期183-186,共4页
Machinery Design & Manufacture
基金
2018年内蒙古自治区自然科学基金项目(2018LH05024)
2018年内蒙古自治区高等学校科学研究项目(NJZY18149)。
关键词
机器视觉
缺陷检测
形态学滤波
特征提取
分类识别
Machine Vision
Defect Detection
Morphological Filtering
Feature Extraction
Classification
