基于 EEMD 的多尺度模糊熵的齿轮故障诊断

摘要

为准确利用振动信号进行故障诊断，提出基于 EEMD 多尺度模糊熵的齿轮故障诊断方法。利用集合经验模态分解（EEMD）对振动信号进行自适应分解，获得原始信号的不同尺度分量；据模糊熵能有效区分不同信号的复杂度，计算 EEMD 分解所得本征模态函数（IMF）分量模糊熵，获得原始信号多个尺度的复杂测度作为齿轮不同状态的特征参数；将该特征参数输入最小二乘支持向量机（LS －SVM）分类器判断齿轮故障。齿轮箱齿轮故障实验结果表明，该方法能提高齿轮故障诊断精度。%In order to diagnose fault accurately by using vibration signal,a method of gear fault diagnosis based on multiscale fuzzy entropy of ensemble empirical mode decomposition (EEMD)was proposed.The vibration signal was decomposed adaptively with EEMD to obtain the components in different scales of the original signal.Considering the ability of the fuzzy entropy in distinguishing the complexity of different signals effectively,the fuzzy entropy of intrinsic mode functions (IMFs)by EEMD was calculated.Thus the complexity metric in different scales of the original signal was gained,which taken as was consequently the feature parameter to describe different gear states.The feature parameters were then put into a least square support vector machine (LS-SVM)for diagnosing the gear faults.The results of a gear box fault test indicate that the proposed method is of high accuracy in diagnosing gear faults.