IC Engine Fault Diagnosis Method Based EMD-WVD and LNMF

PDF(1628 KB)

Journal of Vibration and Shock ›› 2016, Vol. 35 ›› Issue (23) : 191-196.

MU Wei-jie,SHI Lin-suo,CAI Yan-ping,LIU Hao,JIN Guang-zhi

Author information +

History +

Abstract

The IC engine vibration signals are complex non-stationary signals, therefore, that how to accurately extract the feature information of the IC engine vibration signal for pattern recognition is very important for fault di-agnosis of an IC engine. The frequency analysis method of empirical mode decomposition and Wigner-Ville is used for IC engine vibration signal in this paper. The method of EMD-WVD is not only to avoid interference cross-terms, but also retains all the excellent characteristics of Wigner-Ville distribution. And a new method of local non-negative matrix factorization is directly used for feature extraction, because of the traditional NMF non-orthogonal basis matrix result in data redundancy is large, and it is not conducive to subsequent recognition rate of issue. The application to the practical internal combustion fault diagnosis has revealed that the LNMF algorithm classification accuracy is bet-ter than traditional NMF algorithm.

Key words

/ IC engine；fault diagnosis；time-frequency distribution；feature extraction；Local nonnegative matrix factorization（LNMF）

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

MU Wei-jie,SHI Lin-suo,CAI Yan-ping,LIU Hao,JIN Guang-zhi. IC Engine Fault Diagnosis Method Based EMD-WVD and LNMF[J]. Journal of Vibration and Shock, 2016, 35(23): 191-196

References

［1］ Kim Y H.Fault detection in a ball bearing system using a moving window [J].Mechanical Systems and Signal Processing,1991,5(6):461-473.
［2］ Samin B,Rizzoni G. Engine knock analysis and detection using time-frequency analy-sis[C]//SAE960618,1996.
［3］ Xiao J,Flandfin P.Muhitaper time-frequency reassignment for nonstationary spectrum esti-mation and chirp enhancement[J].IEEE Transaction on Signal Processing,2007,55(6):2851-2860.
［4］毛永芳,秦树.重分配谱图和多窗谱在机械故障诊断中的应用[J].振动与冲击,2009,28(1):161-165.
Mao Y F,Qin S. Re-allocation of spectrum and multi-spectral windows and its application in machinery fault diagnosis [J].Journal of Vi-bration and Shock,2009,28(1):161-165.
［5］ Bo L, Qin S R, Liu X F. Theory and application of Wavelet analysis instrument library[J]. Chinese Journal of Mechanical Engineering: English Edition,2007,19(3):464-467.
［6］ Cary S, Akujuobi C M. An approach to vibration analysis using wavelets in an application of aircraft health monitoring[J].Mechanical Sys-tems and Signal Processing,2007,21:1255-1272.
［7］张金玉，张优云，谢友柏. 机械图像的识别与重构[J].西安交通大学学报，2000，34(2)：80-84.
ZHANG Jin-yu,ZHANG You-yun,XIE You-bai.Recognition and Reconstruction of me-chanical graphics[J].Jouranl of Xi’an Jiaotong University,2000,34(2), 80-84.
［8］夏勇，商斌梁，张振仁,等. 基于小波包与图像处理的内燃机故障诊断研究[J].内燃机学报，2001，19(1)：62-68.
XIA Yong,SHANG Bin-liang,ZHANG Zhen-ren,et al.Research on fault diagnosis for internal combustion engines using wavelet packet and image processing[J].Transaction of CSICE, 2001，19(1)：62-68.
［9］沈虹，赵红东，梅检民，等.基于高阶累积量图像特征的柴油机故障诊断研究[J].振动与冲击，2015，34（11）：133-138.
SHEN Hong, ZHAO Hong-dong, MEI Jian-min, et al. Diesel engine fault diagnosis based on high-order cumulant image features[J]. Journal of Vibration and Shock, 2015，34（11）：133-138.
［10］王成栋，张优云，夏勇. 基S变换的柴油机气阀机构故障诊断研究[J].内燃机学报，2003，21(4):271-275.
WANG Cheng-dong,ZHANG You-yun,XIA Yong.Fault diagnosis for diesel valve train based on S Transform[J]. Transaction of CSICE, 2003，21(4):271-275.
［11］王成栋，张优云，夏勇. 模糊函数图像在柴油机气阀故障诊断中的应用研究[J]. 内燃机学报，2004，22(4)：162-168.
WANG Cheng-dong,ZHANG You-yun,XIA Yong.Study on the use of ambiguity function images in fault diagnosis for diesel valve train[J]. Transaction of CSICE, 2004，22(4)：162-168.
［12］ Lee D D, Seung H S. Learning the parts of objects by no n-negative matrix factorization [J].Nature,1999,401(6755):788-791.
［13］ Liu W, Zheng N. Non-negative matrix fac-torization based methods for object recognition [J].Pattern Recognition Let-ters,2004,25(8):893-897.
［14］ Zhang T,Fang B,Tang Y Y, et al. Topology preserving non-negative matrix factorization for face recognition[J].IEEE Transactions on Image Processing,2008, 17(4):574-584.
[15] Bucak S S,Gunsel B.Incremental subspace learning via non-negative matrix factorization [ J ] . Pattern Recognition, 2009, 42(5): 788-797.
[16] Qing H W, Yun Z Y, Lei C, et al. Fault diagnosis for diesel valve trains based on non-negative matrix factorization and neural network en-semble[J].Mechanical Systems and Signal Processing,2009,23(5):1683-1695.
[17] 蔡蕾, 朱永生. 基于稀疏性非负矩阵分解和支持向量机的时频图像识别[J].自动化学报, 2009, 35(10):1272-1277.
CAI Lei,ZHU Yong-Sheng.Time-frequency spectra Recognition Based on Sparse non-negative Matrix factorization and support vector machine[J].Acta Automatica Sinica, 2009, 35(10):1272-1277.
[18] 李兵，高敏，张旭光，等.用形态梯度法与非负矩阵分解的齿轮故障诊断[J].振动、测试与诊断，2014，34（2）：295-300.
LI Bing, GAO Min, ZHANG Xu-guang,et al. Feature extraction for engine fault diagnosis by utilizing adaptive multi-scale morphological gradient and non-negative matrix factoriza-tion[J].Journal of Vibration, Measurement and Diagnosis, 2014，34（2）：295-300.
[19] 李兵,米双山,刘鹏远,等.二维非负矩阵分解在齿轮故障诊断中的应用[J]. 振动、测试与诊断，2012,32(5):836-840.
LI Bing, MI Shuang-shan, LIU Peng-yuan,et al. Application of two-dimensional non-negative factorization for gear fault diagnosis[J]. Journal of Vibration, Measurement and Diagnosis, 2014，34（2）：295-300.
[20] 李兵，徐榕，贾春宁，等.基于自适应形态提升小波与改进非负矩阵分解的发动机故障诊断方法[J].兵工学报，2013，34（3）：353-360.
LI Bing, XU Rong, JIA Chun-ning, et.al.Engine fault diagnosis Utilizing adaptive morphological lifting wavelet and improved non-negative matrix factorization[J].Acta Armamentarii, 2013，34（3）：353-360.
[21] 刘东升，李元，杨博文，等.基于自适应多尺度形态梯度与非负矩阵分解的轴承故障诊断[J].振动与冲击，2013，32（19）：106-110.
LIU Dong-sheng, LI Yuan, YANG Bo-wen, et al. Bearing fault diagnosis based on adaptive multi-scale morphological gradient and non-negative matrix factorization[J].Journal of Vibration and Shock, 2013，32（19）：106-110.
[22] 蔡艳平，李艾华，王涛，等．基于EMD－Wigner-Ville的内燃机振动时频分析［J］．振动工程学报，2010，23(4)：430-437．
CAI Yan-ping,LI Ai-hua,WANG Tao,et al.I.C. engine vibration time-frequency analysis based on EMD－Wigner-Ville[J].Journal of Vibration Engineering, 2010，23(4)：430-437．
[23] Li S Z, Hou X W, Zhang H J, et al. Learning spatially localized,parts-based representa-tion[J]. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2001,1:207-212.