基于改进局部保持映射算法的故障诊断  

FAULT DIAGNOSIS BASED ON IMPROVED LOCALITY PRESERVING PROJECTIONS ALOGRITHM

作　　者：卢莉[1] 陈瑛 LU Li;CHEN Ying(School of Information Engineering,Guangzhou Institute of Technology,Guangzhou 510075,China)

机构地区：[1]广州工程技术职业学院信息工程学院

出　　处：《机械强度》2019年第6期1298-1303,共6页Journal of Mechanical Strength

基　　金：广东省特色创新类项目(自然科学)(2017GKTSCX050)资助~~

摘　　要：针对局部保持映射(LPP)应用于故障诊断存在识别精度不高的问题,提出了基于无参数监督核局部保持映射(NPSKLPP)降维的故障诊断新方法。NPSKLPP采用对离群数据更为鲁棒得余弦距离对LPP中的欧氏距离进行替换,并融入样本标签信息构造无参数近邻图,利用核方法将提取的高维故障特征映射到一个高维线性空间再进行降维,避免了相似矩阵计算过程中人为选择参数的问题,能够获得更有效的低维流形。齿轮故障诊断结果表明,该方法是有效的。Aiming at the problem that accuracy of orthogonal locality preserving projections(LPP)for fault diagnosis is not high enough,a fault diagnosis method based on none parameter supervised kernel locality preserving projections(NPSKLPP)for dimension reduction is proposed.In NPSKLPP,firstly,by changing the Euclidean distance to the Cosine distance which is more robust to outline,and constructing a none parameter nearest-neighbor graph which combined sample label information.And then use the nonlinear mapping to map the high dimension fault feature into an implicit feature space to dimension reduction.Thus a linear transformation is performed to preserve locality geometric structures of the fault feature,which solves the difficulty of parameter selection in computing affinity matrix,as a result,better fault diagnosis accuracy can achieved.The experiment results of gear fault diagnosis verified the effectiveness of the method.

关 键 词：故障诊断 局部保持映射 无参数 监督 齿轮 

分 类 号：TH113.1[机械工程—机械设计及理论]