基于均匀化距离局部线性嵌入的滚动轴承故障诊断

ROLLING BEARING FAULT DIAGNOSIS BASED ON UNIFORM DISTANCE LOCAL LINEAR EMBEDDING

针对局部线性嵌入(Local Linear Embedding, LLE)的降维效果受样本分布均匀与否的影响较大这一不足,设计均匀化距离对LLE中的欧氏距离进行替换,由此提出均匀化距离局部线性嵌入(Uniform Distance Local Linear Embedding, UDLLE)方法,并通过典型曲线对UDLLE的有效性进行了验证。在此基础上,提出基于UDLLE的滚动轴承故障诊断方法,并进行诊断实例验证。试验结果表明,UDLLE方法获得了比其他一些方法更为有效的低维特征,降低了后续诊断的难度,提高了故障诊断的精度。

In view of the shortcoming that the dimensivity reduction effect of local linear embedding(LLE) is greatly affected by the uniformity of sample distribution, the uniform distance is designed to replace the Euclidean distance in LLE, so the uniform distance local linear embedding(UDLLE) method is proposed, and the effectiveness of UDLLE is verified by typical curves. On this basis, a rolling bearing fault diagnosis method based on UDLLE was proposed, and the diagnosis example was verified. The experimental results show that UDLLE can obtain more effective low-dimensional features than some other methods, reduce the difficulty of subsequent diagnosis and improve the fault diagnosis accuracy.