基于VMD_MPE和FCM聚类的变转速工况下转子不平衡故障诊断方法

Method of rotor unbalance fault diagnosis under variable-speed conditions based on VMD_MPE and FCM clustering

旋转机械在变转速工况下转子不平衡故障诊断问题一直是故障诊断领域的难点,为解决该问题,提出一种基于变分模态分解(variational mode decomposition,VMD)与多尺度排列熵(multiscale permutation entropy,MPE)和模糊C均值(fuzzy C means,FCM)聚类结合的故障诊断方法(VMD_MPE-FCM)。首先,用VMD对转子的振动信号进行处理,得到若干本征模态分量(intrinsic mode function,IMF);然后,根据转子不平衡故障时一倍频(1×)处振幅剧烈增加的现象,从VMD得到的各IMF频谱图中筛选出最能表征转子不平衡故障特征的IMF;进而采用MPE法对筛选出的IMF进行量化;最后,将量化所得值作为特征向量输入FCM,得到各转速工况下的标准聚类中心,采用择近原则,运用模糊贴近算法计算出待识别数据与标准聚类中心的贴近度,从而实现变转速工况下转子不平衡的故障识别。在转子试验台上采用VMD_MPE-FCM法进行了变转速工况下转子不平衡故障诊断试验,试验结果表明:该方法是有效的,可以准确、高效地提取出转子故障特征,能够很好地识别出不同转速工况下转子的不平衡故障。

Rotor fault diagnosis of rotating machinery under variable speed conditions is a difficult problem in the field of fault diagnosis.To solve the problem,a method based on variational mode decomposition(VMD)combined with multiscale permutation entropy(MPE)and fuzzy C means(FCM)clustering(VMD_MPE-FCM)was proposed.Firstly,the vibration signals of the rotor were decomposed by VMD into a series of intrinsic mode functions(IMFs).Then,the IMF containing the most notable unbalance fault features was selected according to the phenomenon that the amplitude at the first harmonic(1×)frequency increases sharply when the rotor unbalance fault occurs.Furthermore,the MPE method was taken to quantify the selected IMF.Finally,the quantified values were put into FCM as feature vectors to obtain the standard cluster center of each speed condition.Following this,the nearness of the data to be identified to the standard cluster center was calculated with a series of fuzzy nearness algorithms,so as to realize the identification and classification.The displacement signals of the unbalanced rotor under variable-speed conditions were analyzed with VMD_MPE-FCM on a test rig.The results show that the proposed method can extract unbalance fault features of the rotor precisely and effectively,so as to diagnose the rotor unbalance fault under variable speed conditions accurately.