基于Copula函数的高速列车转向架故障特征提取

金炜东; 吕乾勇; 孙永奎

doi:10.3969/j.issn.0258-2724.2015.04.016

基于Copula函数的高速列车转向架故障特征提取

doi: 10.3969/j.issn.0258-2724.2015.04.016

基金项目:

国家自然科学基金资助项目(61134002)

详细信息

作者简介:
金炜东(1959-),男,教授,博士生导师,研究方向为智能信息处理,电话:13320995638,E-mail:wdjin@home.swjtu.edu.cn

计量
- 文章访问数: 1225
- HTML全文浏览量: 79
- PDF下载量: 508
- 被引次数: 0
出版历程
- 收稿日期: 2014-12-15
- 刊出日期: 2015-08-25

Extracting Fault Features of High-Speed Train Bogies Using Copula Function

摘要

摘要: 为了实时监测高速列车转向架关键部件的工作状态,提出了一种基于Copula函数的特征提取方法.以某型高速列车转向架正常、抗蛇形减振器失效、空气弹簧失效、横向减振器失效4种工况的振动信号为研究对象,将信号进行聚合经验模态分解,针对得到的本征模态函数,使用Gaussian Copula函数构建它们的联合概率密度函数.提取边缘分布的Kullback-Leibler Distance值,及联合概率密度函数的均值和方差作为特征,采用支持向量机进行识别.实验结果表明,在200 km/h速度下,故障平均识别率在95%以上,表明了该特征提取方法的有效性.
- 高速列车 /
- 聚合经验模态分解 /
- Copula函数 /
- 特征提取
Abstract: To monitor the working condition of key components of high-speed train bogies in real time, an approach using Copula function to extract features is proposed. Vibration signals of a certain high-speed train are obtained under four typical working conditions, including normal condition, yaw damper fault, air spring fault, and lateral damper fault. The vibration signal is decomposed by ensemble empirical mode decomposition first. Then, the joint probability distribution of intrinsic mode functions is computed by Gaussian Copula function. The Kullback-Leibler distance of two marginal distribution functions, and the mean and variance of the joint probability density function are extracted as the features. The support vector machine is used to classify the working conditions. The experimental result shows that the average recognition rate is above 95% at the speed of 200 km/h, which verifies the effectiveness of the proposed feature extraction method.
- high-speed train /
- ensemble empirical mode decomposition /
- Copula function /
- feature extraction

HTML全文

参考文献(33)

王新锐,丁勇,李国顺. 铁路火车可靠性实验方法及评价标准的研究

唐曦凌,梁霖,高慧中,等. 结合小波变换和多约束非负矩阵分解的故障特征提取方法

[J]. 中国铁道科学,2010,31(1): 116-122. WANG Xinrui, DING Yong, LI Guoshun. Study on the reliability test method and evaluation specifications of railway freight car

[J]. China Railway Science, 2010, 31(1): 116-122.

WU Z H, HUANG N E. Ensemble empirical mode decomposition: a noise-assisted data analysis method

秦娜,金炜东,黄进,等. 基于EEMD样本熵的高速列车转向架故障特征提取

FENG Z P, ZUO M J, HAO R J. Ensemble empirical mode decomposition-based teager energy spectrum for bearing fault diagnosis

[J]. 振动与冲击,2013,24(19): 7-11. TANG Xiling, LIANG Lin, GAO Huizhong, et al. Fault feature extraction method combining continuous wavelet transformation with multi-consitraint nonnegative matrix factorization

[J]. Journal of Vibration and Shock, 2013, 24(19): 7-11.

李悦,程希骏. 上证指数和恒生指数的Copula尾部相关性分析

郭生练,闫宝伟,肖义,等. Copula函数在多变量水文分析计算中的应用及研究进展

[R]. Calverton: Center for Ocean-Land-Atmosphere Studies, 2009.

LI Chaorong, LI Jianping, FU Bo. Magnitude-phase of quaternion wavelet transform for texture representation using multilevel Copula

LASMAR N E, BERTHOUMIEU Y. Gaussian Copula multivariate modeling for texture image retrieval using wavelet transforms

[J]. 西南交通大学学报,2014,49(1): 27-32. QIN Na, JIN Weidong, HUANG Jin, et al. Feature extraction of high speed train bogie based on ensemble empirical mode decomposition and sample entropy

NELSON R B. An introduction to Copulas

[J]. Journal of Southwest Jiaotong University, 2014, 49(1): 27-32.

ZVOKELJ M,ZUPAN S,PREBEL I.Non-liner multivariate and multiscale monitoring and signal denoising strategy using kernel principal component analysis combined with ensemble empirical mode decomposition method

FISHER N I, SWITZER P. Chi-plots for assessing dependence

[J]. J. Vib. Acoust, 2013, 135(3): 031013-031033.

李朝荣. Copula驱动的小波域纹理特征提取研究

CHANG Chihchung, LIN Chihjen. LIBSVM: a library for support vector machines

[J]. 系统工程,2006,24(5): 88-92. LI Yue,CHENG Xijun. Tail dependence analysis of SZI HSI based on Copula method

[J]. Systems Engineering, 2006, 24(5): 88-92.

[J]. 水文,2008,28(3): 1-7. GUO Shenglian, YAN Baowei, XIAO Yi, et al. Multivariate hydrological analysis and estimation

[J]. Journal of China Hydrology, 2008, 28(3): 1-7.

[J]. IEEE Signal Processing Letters, 2013, 20(8): 799-802.

[J]. IEEE Transactions on Image Processing, 2012, 23(5): 2246-2261.

[M]. New York: Springer, 2006: 32-105.

[J]. Mechanical System and Signal Processing, 2011, 25(7): 2631-2653.