In the process of fault feature extraction of rolling bearing, the feature information is difficult to be extracted fully. A novel method of fault feature extraction called hierarchical dispersion entropy is proposed in this paper. In this method, the vibration signals firstly are decomposed hierarchically. Secondly, dispersion entropies of different nodes are calculated. Hierarchical dispersion entropy can realize the comprehensive feature extraction of the high- and low-frequency band information of vibration signals and overcome the problems that dispersion entropy and multiscale dispersion entropy are insufficient to extract the fault feature information of vibration signals. The feasibility of hierarchical dispersion entropy is obtained by analyzing the hierarchical dispersion entropy of Gaussian white noise and compared with the multiscale dispersion entropy of Gaussian white noise. Meanwhile, a fault diagnosis method for rolling bearings based on hierarchical dispersion entropy and k-nearest neighbor (KNN) classifier is developed. Finally, the superiority of the proposed fault diagnosis method is verified in the realization of fault diagnosis of the rolling bearing in different positions and different degrees of damage.

中文翻译：

---

基于层次色散熵的故障特征提取新方法

在滚动轴承的故障特征提取过程中，难以充分提取特征信息。提出了一种新的故障特征提取方法，称为层次弥散熵。在这种方法中，首先对振动信号进行分层分解。其次，计算了不同节点的色散熵。分层色散熵可以实现振动信号高，低频信息的综合特征提取，克服了色散熵和多尺度色散熵不足以提取振动信号故障特征信息的问题。通过对高斯白噪声的分层色散熵进行分析，并与高斯白噪声的多尺度色散熵进行比较，得出了分层色散熵的可行性。同时，提出了一种基于层次色散熵的滚动轴承故障诊断方法。开发了k近邻（KNN）分类器。最后，在实现不同位置，不同损伤程度的滚动轴承故障诊断中，验证了本文提出的故障诊断方法的优越性。