基于矢谱-HMM的旋转机械故障诊断方法研究

Study on Fault Diagnosis Methods of Rotating Machines Based on Vector Spectrum-HMM

针对传统旋转机械单通道故障诊断的不足,结合隐马尔可夫模型(HMM)的特点,提出矢谱-HMM故障诊断方法。利用矢谱技术融合截面双通道的信息,然后提取主振矢特征训练HMM模型,利用训练好的HMM模型进行故障诊断。实验表明,该方法是比较有效的。

According to the insufficiency of traditional rotary machinery fault diagnosis with single channel signal and the characteristics of HMM, fault diagnosis method of rotating machines based on vector spectrum-HMM was studied. Vector spectrun was used to fuse the double channels＇ information of the same section, and HMMs were trained with the feature of the main vibration vector, then used for fault diagnosis. Experimental results show that this method is effective.