基于DEMD和模糊熵的滚动轴承故障诊断方法研究  

Rolling Bearing Fault Diagnosis Based on Differential-based Empirical Mode Decomposition and Fuzzy Entroy

作　　者：孟宗 季艳 闫晓丽 

机构地区：[1]河北省测试计量技术及仪器重点实验室,河北秦皇岛066004 [2]国家冷轧板带装备及工艺工程技术研究中心,河北秦皇岛066004

出　　处：《计量学报》2016年第1期56-61,共6页Acta Metrologica Sinica

基　　金：国家自然科学基金(51575472,51105323);河北省自然科学基金(E2015203356);河北省高等学校科学研究计划重点项目(ZD2015049)

摘　　要：提出一种基于微分的经验模式分解（DEMD）模糊熵和支持向量机（SVM）相结合的滚动轴承故障诊断方法。首先对信号进行基于微分的经验模式分解，得到若干具有物理意义的本征模函数（IMF）分量，再利用相关度准则对固有模式分量进行筛选，计算所选分量的模糊熵，组成故障特征向量，然后将其作为支持向量机的输入来识别滚动轴承的状态。并将该方法与基于EMD模糊熵和SVM相结合的方法进行比较，实验结果表明该方法对机械故障信号能够更有效准确地进行识别分类。A comprehensive rolling bearing fault diagnosis method combining differential-based empirical mode decomposition （DEMD） with fuzzy entropy and support vector machine （SVM） is proposed. Firstly, mechanical vibration signal is decomposed with differential-based empirical mode decomposition （DEMD） to obtain a certain number of intrinsic mode functions （IMFs） that have physical meaning. With a mutual relationship rule, the IMF components that have largest correlation coefficients with the original signal are sifted out. The fuzzy entropies of these IMFs are calculated and use as eigenvectors of fault signals, then the eigenvectors are put into SVM to identify the state of the rolling bearing. Compared with the method based on empirical mode decomposition （EMD） combined with fuzzy entropy and SVM, the experimental results show that the method of mechanical failure signals can accurately identify classification effectively.

关 键 词：计量学 故障诊断 滚动轴承 微分经验模式分解 模糊熵 支持向量机 

分 类 号：TB936[一般工业技术—计量学]