基于主成分和小波分析的复杂纺织设备系统的信号处理方法研究  

Research on signal processing method for complex textile machinery system based on principal component analysis and wavelet analysis

作　　者：林正英[1] 时维元[2] 张伟[1] 

机构地区：[1]福州大学机械工程及自动化学院,福建福州350002 [2]同济大学机械工程学院,上海200092

出　　处：《合肥工业大学学报（自然科学版）》2010年第9期1285-1289,共5页Journal of Hefei University of Technology：Natural Science

基　　金：福建省教育科技资助项目(JA08020)

摘　　要：文章提出了主成分加小波分析的复杂系统的信息处理模式。该方法首先选择基于相关系数矩阵的主成分分析法对原始数据进行特征提取,经主成分变换之后得到矩阵的特征值与特征向量,并按照贡献率和累积贡献率来确定其主成分,从而简化了信息,提高了效率;其次,采用小波分析法,把重组后的信息分解成近似和细节的信号,提供时频同时局部化的信息,并对细节信号做Hilbert包络及谱分析,从而为进一步的故障诊断提供了基础。实例表明此法可行,并取得了很好的效果。This paper proposes a signal processing method for the complex textile machinery system based on principal component analysis（PCA） and wavelet analysis.At first,the original signals are simplified by principal component transform,which is conducted by calculating the eigenvalue and eigenvector of correlation coefficient matrix,and the first few principal components（PCs） containing most of the variables are defined according to contribution rate and cumulative contribution rate.Secondly,the restructured signals are decomposed into approximative and detailed ones for obtaining meaningful captures of instantaneous frequency by wavelet analysis.And then,Hilbert Envelope Analysis of the first layer detail signal is also carried out to find its power spectrum.This signal processing method is validated by practical application.

关 键 词：主成分分析 小波分析 信号处理 

分 类 号：TP206.3[自动化与计算机技术—检测技术与自动化装置]