Extracting of Fault Features for Rotating Machinery of High-speed Train Based on EEMD Energy Entropy-LPP

Chen ZHANG; Tao FANG; Kaiqi YAN

doi:10.13890/j.issn.1000-128x.2021.01.026

您当前的位置：

首页 >

文章列表页 >

Extracting of Fault Features for Rotating Machinery of High-speed Train Based on EEMD Energy Entropy-LPP

Intelligent Technology | 更新时间：2021-12-09

- Extracting of Fault Features for Rotating Machinery of High-speed Train Based on EEMD Energy Entropy-LPP
- Electric Drive for Locomotives Issue 1, Pages: 145-150(2021)
- 作者机构：
  
  1.武警工程大学（乌鲁木齐校区）装甲车技术系，新疆　乌鲁木齐　830000
- 作者简介：
- 基金信息：
- DOI：10.13890/j.issn.1000-128x.2021.01.026
  CLC：
扫描看全文
Chen ZHANG, Tao FANG, Kaiqi YAN. Extracting of Fault Features for Rotating Machinery of High-speed Train Based on EEMD Energy Entropy-LPP. [J]. Electric Drive for Locomotives (1):145-150(2021)
DOI：

Chen ZHANG, Tao FANG, Kaiqi YAN. Extracting of Fault Features for Rotating Machinery of High-speed Train Based on EEMD Energy Entropy-LPP. [J]. Electric Drive for Locomotives (1):145-150(2021) DOI： 10.13890/j.issn.1000-128x.2021.01.026.

摘要

针对高速列车轴承转子系统微弱故障特征提取难的问题，提出了一种基于EEMD能量熵-LPP的高速列车转子系统故障特征提取方法。该方法结合EEMD、能量熵和LPP，首先对振动信号进行EEMD自适应分解，计算高频IMF分量的能量熵获得高维特征向量集完成初步特征提取；然后通过LPP算法将高维特征向量集投影到低维空间对特征进一步提取形成低维样本集，在保留故障特征的局部几何结构信息的同时降低特征数据的复杂度，提高故障模式识别的分类性能；最后将低维样本集输入到KNN分类器中进行故障识别。通过比较初次提取特征和再次提取特征，结果表明该模型具有优越的聚类性能，可准确地识别几种常见的高速列车转子系统故障类型。

Abstract

Aiming at the difficulty of extracting the weak fault features of the high-speed train bearing rotor system, a method for extracting the fault features of the high-speed train rotor system based on EEMD energy entropy-LPP was proposed. By combining EEMD, energy entropy and LPP, the vibration signal was subjected to EEMD adaptive decomposition, and the energy entropy of the high-frequency IMF component was calculated to obtain a high-dimensional feature vector set to complete the preliminary feature extraction; then the high-dimensional feature vector was converted by the LPP algorithm set projection to low-dimensional space to further extract features to form a low-dimensional sample set, which reduced the complexity of feature data while preserving the local geometric information of fault features, while improved the classification performance of fault pattern recognition; finally, the low-dimensional sample set was input to the KNN classifier for fault recognition. By comparing the classification effects of the first feature extraction and the second feature extraction, the results show that the model had superior clustering performance and could accurately identify several common high-speed train rotor system failure types.

关键词

高速列车特征提取EEMD能量熵LPP故障诊断

Keywords

high-speed trainfeature extractionEEMDenergy entropyLPPfault diagnosis

references

王国彪, 何正嘉, 陈雪峰, 等. 机械故障诊断基础研究“何去何从”[J]. 机械工程学报, 2013, 49(1): 63-72.

WANG Guobiao, HE Zhengjia, CHEN Xuefeng, et al. Basic research on machinery fault diagnosis: What is the prescription[J]. Journal of Mechanical Engineering, 2013, 49(1): 63-72.

何正嘉, 曹宏瑞, 訾艳阳, 等. 机械设备运行可靠性评估的发展与思考[J]. 机械工程学报, 2014, 50(2): 171-186.

HE Zhengjia, CAO Hongrui, ZI Yanyang, et al. Developments and thoughts on operational reliability assessment of mechanical equipment[J]. Journal of Mechanical Engineering, 2014, 50(2): 171-186.

AMAR M, GONDAL I, WILSON C. Vibration spectrum imaging: a novel bearing fault classification approach[J]. IEEE Transaction on Industrial Electronics, 2015, 62(1): 494-502.

陈仁祥, 汤宝平, 马婧华. 基于EEMD的振动信号自适应降噪方法[J]. 振动与冲击, 2012, 31(15): 82-86.

CHEN Renxiang, TANG Baoping, MA Jinghua. Adaptive de-noising method based on EEMD for vibration signal[J]. Journal of Vibration and Shock, 2012, 31(15): 82-86.

雷亚国. 基于改进Hilbert-Huang变换的机械故障诊断[J]. 机械工程学报, 2011, 47(5): 71-77.

LEI Yaguo. Machinery fault diagnosis based on improved Hilbert-Huang transform[J]. Journal of Mechanical Engineering, 2011, 47(5): 71-77.

张琛, 赵荣珍, 邓林峰. 基于变分模态分解奇异值熵的滚动轴承微弱故障辨识方法[J]. 振动与冲击, 2018, 37(21): 87-91.

ZHANG Chen, ZHAO Rongzhen, DENG Linfeng. Weak fault identification of rolling bearings based on VMD singular value entropy[J]. Journal of Vibration and Shock, 2018, 37(21): 87-91.

张琛, 赵荣珍, 邓林峰. 基于EEMD奇异值熵的滚动轴承故障诊断方法[J]. 振动、测试与诊断, 2019, 39(2): 353-358.

ZHANG Chen, ZHAO Rongzhen, DENG Linfeng. Rolling bearing fault diagnosis method based on EEMD singular value entropy[J]. Journal of Vibration, Measurement and Diagnosis, 2019, 39(2): 353-358.

YANG Y, YU Dejie, CHENG J S. A roller bearing fault diagnosis method based on EMD energy entropy and ANN[J]. Journal of Sound and Vibration, 2006, 294(1/2): 269-277.

张超, 陈建军, 郭迅. 基于EMD能量熵和支持向量机的齿轮故障诊断方法[J]. 振动与冲击, 2010, 29(10): 216-220.

ZHANG Chao, CHEN Jianjun, GUO Xun. A gear fault diagnosis method based on EMD energy entropy and SVM[J]. Journal of Vibration and Shock, 2010, 29(10): 216-220.

李锋, 汤宝平, 宋涛, 等. 归一Laplacian矩阵有监督最优局部保持映射故障辨识[J]. 机械工程学报, 2013, 49(13): 100-107.

LI Feng, TANG Baoping, SONG Tao, et al. Fault identification method based on normalized Laplacian-based supervised optimal lpcality preserving projection[J]. Journal of Mechanical Engineering, 2013, 49(13): 100-107.

杨望灿, 张培林, 张云强. 基于邻域自适应局部保持投影的轴承故障诊断模型[J]. 振动与冲击, 2014(1): 39-44.

YANG Wangcan, ZHANG Peilin, ZHANG Yunqiang. Bearing fault diagnosis model based on neighborhood adaptive locality preserving projections[J]. Journal of Vibration and Shock, 2014(1): 39-44.

郭金玉, 苑玮琦. 基于局部保持投影的掌纹识别[J]. 光学学报, 2008, 28(10): 1920-1924.

GUO Jinyu, YUAN Weiqi. Palmprint recognition based on locality preserving projection[J]. Acta Optica Sinica, 2008, 28(10): 1920-1924.

WU Z H, HUANG N E. Ensemble empirical mode decomposition: a noise-assisted data analysis method[J]. Advances in Adaptive Data Analysis, 2009, 1(1): 1-41.

HE X F, NIYOGI P. Locality Preserving Projections[C]//Advances in Neural Information Processing Systems 16. Cambridge: MIT PRESS, 2004: 153-160.

赵荣珍, 邓林峰. 基于粗糙集数据分类概念的故障知识发现[J]. 振动、测试与诊断, 2012, 32(1): 17-22.

ZHAO Rongzhen, DENG Linfeng. Faults knowledge discovery based on data classification concept of rough set theory[J]. Journal of Vibration, Measurement and Diagnosis, 2012, 32(1): 17-22.

ZHANG X Y, LIANG Y T, ZHOU J Z, et al. A novel bearing fault diagnosis model integrated permutation entropy, ensemble empirical mode decomposition and optimized SVM[J]. Measurement, 2015, 69: 164-179.

Views

下载量

CSCD

CNKI被引量

Alert me when the article has been cited

提交

Tools

Publicity Resources

Stator Insulation Partial Discharge Test and Reliability Evaluation of Traction Motor

Application of an Impact Feature Extracting Method Based on WATV in Fault Diagnosis of High-speed Train Bearing

Feature extraction and fault diagnosis of gearbox based on ICEEMDAN, MPE, RF and SVM

Application of optimized VMD in fault diagnosis of motor bearings of high-speed train

Bearing fault diagnosis for high-speed train based on improved VMD and APSO-SVM

Related Author

No data

Related Institution

School of Electrical Engineering, Beijing Jiaotong University

Motor Vehicle Maintenance Department, CRRC Tangshan Co., Ltd.

School of Mechanical Engineering, Southwest Jiaotong University

College of Electrical Engineering, Shanghai University of Electric Power

CRRC Yongji Electric Co., Ltd., Yongji

⁰