EMD模糊聚类法及在滚动轴承故障诊断中的应用  

FAULT DIAGNOSIS OF ROLLER BEARING BASED ON EMD AND FUZZY CLUSTER

作　　者：蒋玲莉[1,2] 刘义伦[2] 李学军[1] 陈安华[1] 

机构地区：[1]湖南科技大学机械设备健康维护省重点实验室,湖南湘潭411201 [2]中南大学机电学院,长沙410083

出　　处：《机械强度》2011年第5期650-654,共5页Journal of Mechanical Strength

基　　金：国家自然科学基金(50775070);国家863计划项目(2007AA04Z415);湖南省自然科学基金湘潭联合基金重点项目(09JJ8005);湖南省高校科技创新团队支持计划资助~~

摘　　要：轴承故障是导致旋转机械失效的重要原因,故障诊断对保障轴承正常运行至关重要。文中提出经验模态分解(empirical mode decomposition,EMD)和模糊聚类相结合的滚动轴承故障诊断方法,以经验模态分解所得内禀模态函数能量值作为特征向量建立模糊关系矩阵,基于欧氏距离建立模糊相似矩阵,基于传递闭包法建立模糊等价矩阵,利用λ截矩阵实现聚类分析与模式识别。实例验证该方法可对不同故障状态的滚动轴承准确分类,实现故障诊断,诊断过程简单、准确、有效,具有一定的实用价值。Bearing failure is one of the foremost causes of breakdowns in rotating machinery and such failure can be catastrophic.Fault diagnosis is critical to maintaining the normal operation of the bearings.A framwork combining empirical mode decomposition（EMD） with fuzzy cluster analysis for roller bearing fault diagnosis is proposed.The EMD method is used to decompose the non-stationary vibration signal of a roller bearing into a number of intrinsic mode function（IMF） components,and the IMFs energy as discriminative features are extracted,which are used to construct the fuzzy relation matrix,then,via a series of further transformed,the fuzzy similar matrix and the fuzzy equivalent matrix are constructed one after the other,finally,the cut matrix is obtained for clustering and pattern recognition by choosing proper cutting value.The proposed framework has been successfully applied to bearing fault diagnosis application.Experiment results show that the proposed method can accurately,simply and effectively process fault pattern recognition,so it has a certain value to engineering applications.

关 键 词：滚动轴承 经验模态分解(empirical moded ecomposition EMD) 模糊聚类 故障诊断 

分 类 号：TH133.33[机械工程—机械制造及自动化] TH165.3