Research on aeroengine rub-impact fault analysis based on wavelet transform and the local binary patterns

Author

Wu, Ya-Hui ; Xue, Jing-Feng ; Zhang, Da-Zhi ; Li, Xin-Liang

Author_Institution

Nat. Key Lab. of Sci. & Technol. on Metrol. & Calibration, AVIC Changcheng Inst. of Metrol., & Meas., Beijing, China

fYear

2010

fDate

11-14 July 2010

Firstpage

421

Lastpage

426

Abstract

The local binary patterns statistical characteristics of the continuous wavelet transform scalogram of the aeroengine vibration signal are explored in this paper. The method is based on recognizing that certain uniform local binary patterns which are fundamental properties of local image texture and their occurrence histogram is proven to be a very powerful texture feature. Three patterns are studied on the rub-impact faulty signals from the aeroengine test. The analysis indicates that these features are suitable to reflect the local information of the scalogram and can reveal the characteristic of vibration signals well.

Keywords

aerospace engines; fault diagnosis; image texture; statistical analysis; vibrations; wavelet transforms; aeroengine rub-impact fault analysis; aeroengine vibration signal; continuous wavelet transform scalogram; local binary patterns; local image texture; occurrence histogram; statistical characteristics; Continuous wavelet transforms; Indexes; Pattern recognition; Vibrations; Wavelet analysis; Aeroengine; Continuous wavelet transform; Local binary patterns; Rub-impact;

fLanguage

English

Publisher

ieee

Conference_Titel

Wavelet Analysis and Pattern Recognition (ICWAPR), 2010 International Conference on

Conference_Location

Qingdao

Print_ISBN

978-1-4244-6530-9

Type

conf

DOI

10.1109/ICWAPR.2010.5576414

Filename

5576414