转子故障数据集降维的CKLPMDP算法研究

CKLPMDP algorithm for dimension reduction of a rotor fault data set

针对传统的数据降维方法难以兼顾局部流形结构和多流形判别结构学习的问题,提出一种相关熵测度核局部保持多流形判别投影算法(correntropy kernel locality preserving multi-manifold discriminant projection,CKLPMDP)的转子故障数据集降维方法。该方法的显著特点是采用相关熵测度监督近邻图的构建,首先将数据集映射到高维核空间,然后在核空间中综合考虑数据集的局部流形结构和多流形判别结构信息,提取出最优表征故障数据集的低维敏感特征矢量,采用三维图直观地显示出低维分类效果,并以低维敏感特征矢量输入K近邻分类器(K-nearest neighbor,KNN)中的辨识率和聚类分析中类间距S_(b)、类内距S_(w)作为衡量降维效果的指标。通过双跨转子实验台的振动信号数据集进行验证,与其他几种典型特征提取方法对比,该方法能更有效地提取出局部流形和多流形判别信息,在转子故障辨识中表现出更好的分类性能。

Aiming at the problem of the traditional data dimension reduction methods being difficult to consider both the local manifold structure learning and multi-manifold discriminant structure learning,a new algorithm for dimension reduction of a rotor fault data set was proposed based on the correlation-entropy kernel locality preserving multi-manifold discriminant projection(CKLPMDP).The remarkable feature of this algorithm was the correlation entropy measure being used to supervise construction of neighbor graphs.Firstly,the data set was mapped to a high-dimensional kernel space,and then the data set’s local manifold structure and multi-manifold discrimination structure information was comprehensively considered in the kernel space to extract low-dimensional sensitive feature vectors of the optimal characterizing fault data set.The low-dimensional classification effect was visually displayed by using 3-D graphs.Low-dimensional sensitive feature vectors were input into a K-nearest neighbor(KNN)classifier,the class spacing and within class distance in KNN classifier’s recognition rate and clustering analysis were taken as the indexes to measure the effect of dimension reduction.The vibration signal data set of a double-span rotor test platform was used to verify the proposed algorithm.Compared with other typical feature extraction methods,it was shown that the proposed algorithm can extract local manifold and multi-manifold discriminant information more effectively,and have better classification performance in rotor fault recognition.