Applying blind signal separation theory to diagnose heavy-duty vehicle

Author

Huimin Zhao ; Jianmin Mei ; Hong Shen ; Qingle Yang

Author_Institution

Automobile Eng. Dept., Mil. Transp. Univ., Tianjin, China

fYear

2014

fDate

Aug. 31 2014-Sept. 3 2014

Firstpage

1

Lastpage

4

Abstract

It is common to see difficult feature extraction in heavy-duty vehicles fault diagnosis due to strong interference. Blind signal separation(BSS) technology proves to be effective to extract the principal component out of the multi-sources signals. Therefore, it is used to extract the fault information for heavy-duty vehicle in this paper. A bispectrum of the data after BSS is obtained and scanned in frequency field. The result indicates that BSS can reduce the interference out of the engine vibration and extract the wanted fault features more effectively.

Keywords

blind source separation; engines; fault diagnosis; feature extraction; interference (signal); machine bearings; mechanical engineering computing; principal component analysis; shafts; vehicle dynamics; vibrations; BSS technology; bispectrum; blind signal separation theory; crankshaft bearing; engine vibration; fault features extraction; fault information; heavy-duty vehicles fault diagnosis; multisources signals; principal component analysis; strong interference; Covariance matrices; Eigenvalues and eigenfunctions; Engines; Feature extraction; Frequency-domain analysis; Principal component analysis; Vibrations; Blind Signal Separation; Crankshaft bearing; Fault Diagnosis; Nonlinear Principal Component Analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Transportation Electrification Asia-Pacific (ITEC Asia-Pacific), 2014 IEEE Conference and Expo

Conference_Location

Beijing

Print_ISBN

978-1-4799-4240-4

Type

conf

DOI

10.1109/ITEC-AP.2014.6940794

Filename

6940794