| 一种基于经验模态分解和流形学习的滚动轴承故障诊断方法 |
| |
| 引用本文： | 蔡江林,戚晓利,叶绪丹,郑近德,潘紫微,张兴权.一种基于经验模态分解和流形学习的滚动轴承故障诊断方法[J].井冈山大学学报（自然科学版）,2017(2):66-73. |
| |
| 作者姓名： | 蔡江林 戚晓利 叶绪丹 郑近德 潘紫微 张兴权 |
| |
| 作者单位： | 安徽工业大学机械工程学院, 安徽, 马鞍山 243002,安徽工业大学机械工程学院, 安徽, 马鞍山 243002,安徽工业大学机械工程学院, 安徽, 马鞍山 243002,安徽工业大学机械工程学院, 安徽, 马鞍山 243002,安徽工业大学机械工程学院, 安徽, 马鞍山 243002,安徽工业大学机械工程学院, 安徽, 马鞍山 243002 |
| |
| 基金项目： | 国家自然科学基金项目（51505002，51375013） |
| |
| 摘 要： | 提出一种基于经验模态分解(EMD)和流形学习(LTSA)的滚动轴承故障诊断方法。首先,利用EMD对滚动轴承振动信号进行自适应分解,计算IMF分量的协方差矩阵特征值,组成滚动轴承状态原始特征集;然后利用LTSA对原始特征集进一步的融合提取;将所得新特征输入到K-means分类器中进行故障识别与聚类。实验分析结果表明:该方法可以有效地对滚动轴承的工作状态和故障类型进行识别。
|
| 关 键 词： | 滚动轴承 经验模态分解 流形学习 局部切空间排列算法 K-means分类器 |
| 收稿时间： | 2016/12/13 0:00:00 |
| 修稿时间： | 2017/3/4 0:00:00 |
A ROLLER BEARING FAULT DIAGNOSIS METHOD BASED ON THE EMPIRICAL MODE DECOMPOSITION (EMD) AND MANIFOLD LEARNING (LTSA) |
| |
| CAI Jiang-lin,QI Xiao-li,YE Xu-dan,ZHENG Jin-de,PAN Zi-wei and ZHANG Xing-quan.A ROLLER BEARING FAULT DIAGNOSIS METHOD BASED ON THE EMPIRICAL MODE DECOMPOSITION (EMD) AND MANIFOLD LEARNING (LTSA)[J].Journal of Jinggangshan University(Natural Sciences Edition),2017(2):66-73. |
| |
| Authors: | CAI Jiang-lin QI Xiao-li YE Xu-dan ZHENG Jin-de PAN Zi-wei and ZHANG Xing-quan |
| |
| Institution: | School of Mechanical Engineering, Anhui University of Technology, Ma''anshan 243002, China,School of Mechanical Engineering, Anhui University of Technology, Ma''anshan 243002, China,School of Mechanical Engineering, Anhui University of Technology, Ma''anshan 243002, China,School of Mechanical Engineering, Anhui University of Technology, Ma''anshan 243002, China,School of Mechanical Engineering, Anhui University of Technology, Ma''anshan 243002, China and School of Mechanical Engineering, Anhui University of Technology, Ma''anshan 243002, China |
| |
| Abstract: | A roller bearing fault diagnosis method based on the empirical mode decomposition (EMD) and manifold learning (LTSA) was presented. After the adaptive decomposition of the roller bearing vibration signal by the EMD technique, its original state feature set of the rolling bearing was acquired by calculating eigenvalues of IMF''s covariance matrix. The extraction performance of the original feature set was further fusion implemented by using the LTSA. The new features obtained were input into a K-means classifier, and the output of the K-means classifier was clustering results. Finally, the experiment results show that the proposed method can effectively identify work status and fault type of roller bearing. |
| |
| Keywords: | roller bearing EMD(empirical mode decomposition) manifold learning LTSA (local tangent space alignment algorithm) K-means classifier |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《井冈山大学学报（自然科学版）》浏览原始摘要信息 |
| 点击此处可从《井冈山大学学报（自然科学版）》下载免费的PDF全文 |
|
