Home|News|Literature|Journal|Instruction|Forum|Member|Introduction

Chinese  Old version

By    In    Search 

  HomeContents of Chinese Journal of Mechanical Engineering (English Edition),2005 No.1SIGNAL FEATURE EXTRACTION BASED UPON INDEPENDENT COMPONENT ANALYSIS AND WAVELET TRANSFORM

Ji Zhong

 

Jin Tao

 

Qin Shuren

College of Mechanical Engineering,

Chongqing University,

Chongqing 400030, China

 

 

SIGNAL FEATURE EXTRACTION

BASED UPON INDEPENDENT COMPONENT ANALYSIS AND

WAVELET TRANSFORM*

 

Abstract: It is an important precondition for machine fault diagnosis that vibration signal can be extracted effectively. Based on the characteristic of noise interfused during the course of sampling vibration signal, independent component analysis (ICA) method is combined with wavelet to de-noise. Firstly, The sampled signal can be separated with ICA, then the function of frequency band chosen with multi-resolution wavelet transform can be used to judge whether the stochastic disturbance singular signal is interfused. By these ways, the vibration signals can be extracted effectively, which provides favorable condition for subsequent feature detection of vibration signal and fault diagnosis.

Key words: Independent component analysis (ICA)  Wavelet transform  De-noising  Fault diagnosis  Feature extraction

 


* This project is supported by National Natural Science Foundation of China (No.50275154) and Municipal Natural Science Foundation of Chongqing, China (No.8773). Received May 18, 2004; received in revised form December 3, 2004; accepted December 25, 2004

 

Open or Download Full Text of this Paper (PDF File)

About us-Contact us-Site map-Advertisement service-Cooperation-Legal statement

Address: 22 Baiwanzhuang Dajie, Beijing 100037 China    Tel: 8610-88379907    Fax: 8610-68994557

E-mail: cjme@mail.machineinfo.gov.cn  http: //www.cjmenet.com
©2006 Editorial Office of CJME. All Right Reserved