您的位置:首页  > 论文页面

基于图像处理的轴承套圈裂纹检测系统

发表时间:2017-11-30  浏览量:860  下载量:105
全部作者: 刘金肖,帅立国,张雨露
作者单位: 华为技术有限公司南京研究所;东南大学机械工程学院
摘 要: 针对目前轴承套圈磁粉检测自动化程度低、效率低的问题,提出一种基于图像处理的裂纹检测系统,主要包括中值滤波、构造带阻滤波器、边缘检测、主成分分析(principal component analysis,PCA)和支持向量机(support vector machine,SVM)等。边缘检测采用Deriche 算子,其相较于Canny 算子具有准确率高、运算速度快的特点。针对裂纹特征参数多、运算量大的问题,采用PCA 法将特征参数从8 维降至3 维,并对比在运算时间和准确率方面有无该算法的差异性。最后,采用SVM 对所得主成分参数进行学习分类,通过实验得出核参数在0.015 时准确率高达97.3%.
关 键 词: 图像处理;轴承套圈裂纹;主成分分析;支持向量机
Title: A bearing ring crack detection system based on image processing
Author: LIU Jinxiao, SHUAI Liguo, ZHANG Yulu
Organization: Nanjing Research Institute of Huawei Technologies Co., Ltd.; School of Mechanical Engineering, Southeast University
Abstract: To solve the problem that the automation and efficiency of bearing ring magnetic particle detection is low, a crack detection system based on image processing is introduced. It includes median filter, band elimination filter, edge detection, principal component analysis (PCA), support vector machine (SVM) and so on. Deriche operator, which is used in edge detection, has higher accuracy and faster speed compared with Canny operator. Aimed at the problem that characteristic parameters and computation are large, the PCA is adopted to reduce the characteristic parameters from 8 to 3 dimensions. Then the differences of the computation time and accuracy, with or without PCA, are analyzed. Finally, the SVM is used to learn and classify the principal component parameters. And results show that the accuracy is 97.3% when the kernel parameter is 0.015.
Key words: image processing; bearing ring crack; principal component analysis; support vector machine
发表期数: 2017年11月第22期
引用格式: 刘金肖,帅立国,张雨露. 基于图像处理的轴承套圈裂纹检测系统[J]. 中国科技论文在线精品论文,2017,10(22):2508-2517.
 
0 评论数 0
暂无评论
友情链接