信息熵与广义集合集成的轴承-转子系统故障辨识方法

Fault identification method of bearing-rotor system based on integration of information entropy and generalized sets

基于信息融合思想,对描述振动信号能量的3种信息熵测度,即时域的奇异谱熵、频域的功率谱熵、时-频域的小波能谱熵,在轴承-转子系统故障辨识中的应用方法进行研究.在根据广义集合概念对3种信息熵测度进行特征级的信息融合基础上,提出一种基于时空(场)广义信息熵集合的轴承-转子系统故障辨识方法.分析结果表明,该方法具有在三维特征空间图形化描述故障的状态域,使不同故障类别间显示出显著差别的性能,对提高辨识故障的准确率具有参考价值.

In view of information fusion,the application methods of three kinds of information entropy measures for description of vibration signal energy,i.e.the singular spectrum entropy in the time domain,power spectrum entropy in the frequency domain and wavelet energy spectrum entropy in the time-frequency domain,were investigated in order to identify the faults in bearing-rotor system.On the basis of information fusion of characteristics of above-mentioned three kinds of information entropy measures,according to generalized sets concept,a new fault identification method was proposed for bearing-rotor system based on generalized sets concept of space-time field of the information entropy.The analysis result showed that the method had a function for describing the fault state domain,with a figured three-dimensional characteristic space,demonstrating significant differences between different fault types and presenting a valuable reference for improving the accuracy of fault identification.