基于路图拉普拉斯算子范数和马氏距离的滚动轴承故障诊断

为有效提取滚动轴承振动信号的故障特征，将图信号处理技术引入故障诊断领域。首先根据滚动轴承振动信号构造路图，获得路图信号；再将计算得到的路图拉普拉斯算子范数作为特征参数，构造不同故障的标准特征空间；最后通过测试样本与标准特征空间的马氏距离实现不同故障模式的识别。实测滚动轴承振动信号的分析结果表明，该方法能有效诊断轴承故障。

Fault Diagnosis of Rolling Bearings Based on Path Graph Laplacian Norm and Mahalanobis Distance

In order to extract fault features of vibration signals of rolling bearings effectively, the graph signal processing technology was introduced into fault diagnosis of rolling bearings. Vibration signals of a rolling bearing was firstly transformed into path graph signal. Then, the path graph Laplacian norm was calculated as characteristic parameters, and the standard feature space was obtained. Finally, the Mahalanobis distance of test samples and the standard feature space were used to identify fault patterns of the rolling bearings. Analytic results of the practical vibration signals of rolling bearings demonstrate that the proposed method may be used to diagnose the rolling bearing faults effectively.