基于信息熵距的旋转机械振动故障诊断方法

Research on Diagnosis of Vibration Faults for Rotating Machinery Based on Distance of Information Entropy

介绍了信息融合的基本概念和目前在旋转机械振动故障诊断当中用得比较多的一些融合诊断方法。从信息融合的思想出发,利用时域的奇异谱熵、频域的功率谱熵、时-频域的小波能谱熵和小波空间特征谱熵,通过特征级的信息融合,提出了一种基于信息熵距的旋转机械振动故障监测和诊断的方法。数学推导表明,信息熵距符合模糊理论中最大隶属度原则,将它作为判别指标是可行的。实例计算表明,信息熵距能够较好的区分故障类别,在此基础上,通过多转速下的熵距曲线图可以提高转子故障诊断的准确性。

In this paper,firstly the basic conception of the information fusion(IF) is introduced as well as some fusion diagnosis methods which are commonly used nowadays.Then,from the thought of the IF,a new monitoring and diagnosis method of vibration faults for rotating machinery based on distance of the information entropy is put forward.It is based on the feature IF by using the singular spectrum entropy in the time domain,power spectrum entropy in the frequency domain,wavelet energy spectrum entropy and wavelet space feature entropy in the time-frequency domain.The mathematic deduction shows that the conception of distance of the information entropy is accordant with the maximum subordination principle in the fuzzy theory,so it's reasonable to use this conception as the judgment index and it has been proved that this method can distinguish different fault types effectively.Based on this,the veracity of the rotor fault diagnosis can be improved through the distance of the information entropy curve chart at the multi-speed.