基于元胞储存的小波聚类转子故障诊断

Rotor Fault Diagnosis Method Based on WaveCluster Stored By Cell Array

摘要:

针对传统小波聚类高维空间复杂度高,提出基于元胞储存的改进小波聚类算法；通过对转子故障模拟实验采集的数据,对其聚类分析,结果表明:元胞储存能够降低算法的空间复杂度,提高算法的效率；将改进的小波聚类算法应用于转子故障诊断,与常见的几种转子故障诊断方法相比,结果表明:基于元胞储存的小波聚类转子故障诊断方法具有自动聚类,处理速度快,精度高,适合应用在高维数据空间中等优点,对转子故障状态能够很好地进行区分。

Abstract:

In consideration of the high space complexity of the WaveCluster algorithm in the High-dimension, the improved WaveCluster algorithm stored by the cell array is proposed. The clustering analysis is performed with the data got by the rotor fault simulation experiment, the result shows that storing by the cell array can reduce the space complexity of the algorithm and improve the algorithm efficiency. And then the improved WaveCluster algorithm was applied to the rotor fault diagnosis , compared with the other common rotor fault diagnosis method ,the result shows that the rotor fault diagnosis method based on WaveCluster stored by the cell array has the advantages of automatic clustering, high processing speed, high precision and being applicable in high dimensional data space. It can effectively to distinguish the rotor fault state.