基于EEMD-ICA去噪方法在转子故障特征识别中的应用研究  

Application Study of Rotor Fault Feature Recognition Based on EEMD-ICA Denoising Method

作　　者：刘书溢 田梅[1] 周小龙[2] 刘文亮 LIU Shuyi;TIAN Mei;ZHOU Xiaolong;LIU Wenliang(School of Mechanical Engineering,Jilin Engineering Normal University,Changchun 130052,China;Engineering Training Center,Northeast Electric Power University,Jilin 132012,China;Design Department,Yeal Electric Co.,Ltd.,Changchun 130113,China)

机构地区：[1]吉林工程技术师范学院机械工程学院,长春130052 [2]东北电力大学工程训练中心,吉林吉林132012 [3]研奥电气股份有限公司设计部,长春130113

出　　处：《机械工程师》2018年第8期72-73,76,共3页Mechanical Engineer

基　　金：吉林工程技术师范学院仿生表面成形成性一体化技术创新团队资助项目;吉林工程技术师范学院科研发展基金项目(XYB201701)

摘　　要：针对转子故障诊断过程中噪声干扰大,故障特征难以提取的问题,首次将基于集合经验模态分解-独立分量分析(EEMD-ICA)方法应用到转子故障特征识别中。该方法可有效抑制模态混叠现象,准确分离出包含在信号内部的噪声成分。实验结果表明,所提方法去噪效果明显,能够有效提取转子故障特征。Aiming at the problem of large noise disturbance and difficult to extract fault features in rotor fault diagnosis process, the ensemble empirical mode decomposition-independent component analysis（EEMD-ICA） method is applied in rotor fault feature identification. This method can effectively suppress the modal aliasing phenomenon and accurately separate the noise components contained in the signal. Experimental results show that the proposed method has obvious denoising effect and can effectively extract fault characteristics of the rotor.

关 键 词：EEMD-ICA 特征提取 转子故障诊断 

分 类 号：TM303.3[电气工程—电机]