冲击故障特征提取的非线性流形学习方法  

Nonlinear Manifold Learning Method of Mechanical Impact Faults Extraction

作　　者：梁霖[1] 徐光华[1] 栗茂林[2] 张熠卓[2] 梁小影[2] 

机构地区：[1]西安交通大学机械制造系统工程国家重点实验室,西安710049 [2]西安交通大学机械工程学院,西安710049

出　　处：《西安交通大学学报》2009年第11期95-99,共5页Journal of Xi'an Jiaotong University

基　　金：科技部国家"863计划"资助项目(2007AA04Z432)

摘　　要：为了提取机械设备故障引发的冲击成分,提出了一种基于非线性流形学习的冲击故障特征自适应提取方法.该方法将反映故障的振动信号重构到高维相空间中,利用局部切空间排列的流形学习方法提取出隐藏其中的低维流形,并基于峭度和偏斜度指标的特点,提出了冲击波形量化的取值策略,实现了高维相空间中局部邻域参数的自适应选取,从而提取出最优的冲击故障特征.通过仿真数据的对比分析和工程应用,表明该方法能够较好地提取出冲击成分信号,与小波软阈值方法相比,提取出的冲击特征成分更完整,周期性更好.To acquire the impact component aroused by mechanical fault, a new feature extraction method based on manifold learning is proposed. After embedding the raw vibration signal into a high dimensional phase space to reconstruct a dynamical manifold, the local target space alignment algorithm is employed for extracting nonlinear low dimensional manifold. According to the characteristics of the kurtosis index and skewness index, the adaptive selection criterion of local neighborhood parameters in phase space is introduced to reflect the optimal impacts. The experimental results and industrial measurements show that this approach, compared with the softthreshold method, is more effective to extract the weak periodic impacts from mechanical signals.

关 键 词：流形学习 特征提取 冲击故障 

分 类 号：TN911.7[电子电信—通信与信息系统]