基于EMD和模糊C均值聚类的滚动轴承故障诊断  

Rolling Bearing Fault Diagnosis Based on EMD and Fuzzy C Means Clustering

作　　者：周川[1] 伍星[1] 刘畅[1] 贺玮[1] 

机构地区：[1]昆明理工大学机电工程学院,云南昆明650093

出　　处：《昆明理工大学学报（理工版）》2009年第6期34-39,共6页Journal of Kunming University of Science and Technology(Natural Science Edition)

基　　金：国家自然科学基金资助项目(项目编号:50805071);云南省教育厅科学研究基金资助项目(项目编号:08J0009)

摘　　要：针对滚动轴承故障振动信号的非平稳特征,提出了一种基于经验模态分解和奇异值分解的特征提取与模糊C均值(FCM)聚类的滚动轴承故障诊断方法.该方法首先对滚动轴承振动信号进行EMD分解,组成初始特征向量矩阵;并对该矩阵进行奇异值分解,将矩阵的奇异值作为故障特征向量;最后以FCM聚类为故障分类器,实现滚动轴承不同故障类型的识别.实验结果分析表明,该方法能有效地进行滚动轴承故障诊断.For the non - stationary feature of a vibration signal of defective rolling beatings, a fault diagnosis method of rolling bearings is proposed using EMD （ Empirical Mode Decomposition） , SVD （ Singular Value Decomposition） and FCM（ Fuzzy C Means）clustering. Firstly, an EMD method was used to decompose a vibration signal of a rolling bearing, from which an initial feature vector matrix was formed. Then, by using a SVD method to the initial vector matrix, these singular values regarded as fault feature vectors were obtained. Finally, a FCM clustering method was used as a fault feature classifier to recognize different fault types of a rolling bearing. Experiment result shows that this method can be applied to diagnosis the fault of rolling bearings.

关 键 词：滚动轴承 经验模态分解 模糊C均值聚类 奇异值分解 故障诊断 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]