基于LMD基本尺度熵的AP聚类滚动轴承故障诊断

发布时间：2018-02-24 09:45

  本文关键词： 局部均值分解 基本尺度熵 滚动轴承 故障诊断 AP聚类算法　出处：《计算机应用研究》2017年06期 　论文类型：期刊论文

【摘要】：针对滚动轴承聚类故障聚类模式识别方法中需要预先设定聚类数目问题,提出了一种基于局部均值分解(local mean decompoeiton,LMD)与基本尺度熵(base scale entropy,BSE)的相邻传播(affinity propagation,AP)滚动轴承聚类故障诊断方法。该方法首先使用LMD模型将滚动轴承的不同状态振动信号分解为若干乘积函数(production function,PF);其次使用BSE计算前三个PF的熵值(BSE1-BSE3),并将其作为AP的输入进行滚动轴承的故障模式识别。最后实验结果表明,在不需要划分聚类中心个数的前提条件下AP聚类模型对滚动轴承的故障划分效果较好。
[Abstract]:In order to solve the problem that the number of clusters should be set in advance in the method of rolling bearing clustering fault clustering pattern recognition, In this paper, a method of clustering fault diagnosis of rolling bearings based on local mean decomposition (LMD) and basic scale entropy (scale entropyp) is presented. The LMD model is used to divide the vibration signals of rolling bearings in different states. The results show that the entropy of the first three PF is calculated by using BSE, and it is used as the input of AP to recognize the fault pattern of the rolling bearing. Without the need to divide the number of cluster centers, AP clustering model has better effect on rolling bearing fault classification.
【作者单位】： 武汉大学自动化系;
【基金】：中央高校基本科研专项资金资助项目(121031)
【分类号】：TH133.33;TP311.13
，

本文编号：1529791