基于局部边缘判别投影的机械故障诊断方法

A Method of Mechanical Fault Diagnosis Based on Locality Margin Discriminant Projection

针对故障特征集维数过高的问题,提出一种基于局部边缘判别投影(locality margin discriminant projection,简称LMDP)的故障数据集降维算法。该算法定义了局部类间相似度和局部类内相似度,使相邻的异类在低维空间中离的更远、相邻的同类样本在低维空间中离的更近。分别提取转子振动信号的时域和频域统计特征,组成原始故障特征集;通过LMDP算法对原始特征集进行特征融合,选择出其中最能反映故障内在信息的低维敏感特征子集;将得到的低维特征子集输入到K近邻(K⁃nearest neighbor,简称KNN)分类器中进行训练和故障分类。通过2个不同型号的双跨度转子系统采集的振动信号集合验证了该方法的有效性。

A locality margin discriminant projection(LMDP)algorithm is proposed to reduce the dimension of the fault feature set.The algorithm defines the local intra-class similarity and the local inter-class similarity to separate the neighboring samples of different classes and join those in the same class.Then,the time-domain and frequency-domain statistical characteristics of rotor vibration signals are extracted to form the original fault feature set.The LMDP algorithm fuse the feature set to select a low-dimensional sensitive feature subset that contains the most intrinsic information.Finally,the K-nearest neighbor(KNN)classifier trains the subset and classify the faults.The vibration signal seta of two different double-span rotor systems verify the effectiveness of the proposed method.