A fault diagnosis scheme of rolling element bearing based on near-field acoustic holography and gray level co-occurrence matrix

被引:74
作者
Lu, Wenbo [1 ]
Jiang, Weikang [1 ]
Wu, Haijun [1 ]
Hou, Junjian [1 ]
机构
[1] Shanghai Jiao Tong Univ, State Key Lab Mech Syst & Vibrat, Shanghai 200240, Peoples R China
基金
国家高技术研究发展计划(863计划);
关键词
SUPPORT VECTOR MACHINES; ARTIFICIAL NEURAL-NETWORKS; WAVELET TRANSFORM; VIBRATION SIGNALS; FEATURE-SELECTION; GEAR FAILURES; SOUND; CLASSIFICATION;
D O I
10.1016/j.jsv.2012.03.008
中图分类号
O42 [声学];
学科分类号
070206 ; 082403 ;
摘要
Vibration signal analysis is the most widely used technique in condition monitoring or fault diagnosis, whereas in some cases vibration-based diagnosis is restrained because of its contact measurement. Acoustic-based diagnosis (ABD) with non-contact measurement has received little attention, although sound field may contain abundant information related to fault pattern. A new scheme of ABD for rolling element bearing fault diagnosis based on near-field acoustic holography (NAH) and gray level co-occurrence matrix (GLCM) is presented in this paper. It focuses on applying the distribution information of sound field to bearing fault diagnosis. A series of rolling element bearings with different types of fault are experimentally studied. Sound fields and corresponding acoustic images in different bearing conditions are obtained by fast Fourier transform (FFT) based NAH. GLCM features are extracted for capturing fault pattern information underlying sound fields. The optimal feature subset selected by improved F-score is fed into multi-class support vector machine (SVM) for fault pattern identification. The feasibility and effectiveness of our proposed scheme is demonstrated on the good experimental results and the comparison with the traditional ABD method. Considering test cost, the quantized level and the number of GLCM features for each characteristic frequency is suggested to be 4 and 32, respectively, with the satisfactory accuracy rate 97.5%. (C) 2012 Elsevier Ltd. All rights reserved.
引用
收藏
页码:3663 / 3674
页数:12
相关论文
共 39 条
[31]   An overview of statistical learning theory [J].
Vapnik, VN .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, 10 (05) :988-999
[32]   NEARFIELD ACOUSTIC HOLOGRAPHY (NAH)-II - HOLOGRAPHIC RECONSTRUCTION ALGORITHMS AND COMPUTER IMPLEMENTATION [J].
VERONESI, WA ;
MAYNARD, JD .
JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 1987, 81 (05) :1307-1322
[33]   Support vector machine in machine condition monitoring and fault diagnosis [J].
Widodo, Achmad ;
Yang, Bo-Suk .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2007, 21 (06) :2560-2574
[34]   SOUND SOURCE RECONSTRUCTIONS USING A MICROPHONE ARRAY [J].
WILLIAMS, EG ;
MAYNARD, JD ;
SKUDRZYK, E .
JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 1980, 68 (01) :340-344
[35]   Cavitation detection of butterfly valve using support vector machines [J].
Yang, BS ;
Hwang, WW ;
Ko, MH ;
Lee, SJ .
JOURNAL OF SOUND AND VIBRATION, 2005, 287 (1-2) :25-43
[36]   Condition classification of small reciprocating compressor for refrigerators using artificial neural networks and support vector machines [J].
Yang, BS ;
Hwang, WW ;
Kim, DJ ;
Tan, AC .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2005, 19 (02) :371-390
[37]   Intelligent fault diagnosis of rolling element bearing based on SVMs and fractal dimension [J].
Yang, Junyan ;
Zhang, Youyun ;
Zhu, Yongsheng .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2007, 21 (05) :2012-2024
[38]  
Yang JY, 2005, LECT NOTES COMPUT SC, V3498, P857
[39]   A comparative study on time-frequency feature of cracked rotor by Wigner-Ville distribution and wavelet transform [J].
Zou, J ;
Chen, J .
JOURNAL OF SOUND AND VIBRATION, 2004, 276 (1-2) :1-11