基于多尺度本征模态排列熵和SA-SVM的轴承故障诊断研究

doi:10.3901/JME.2018.09.168

机械工程学报 ›› 2018, Vol. 54 ›› Issue (9): 168-176.doi: 10.3901/JME.2018.09.168

基于多尺度本征模态排列熵和SA-SVM的轴承故障诊断研究

姚德臣^1,2, 杨建伟^1,2, 程晓卿³, 王兴⁴

1. 北京建筑大学机电与车辆工程学院北京 100044;
2. 北京建筑大学城市轨道交通车辆服役性能保障北京市重点实验室北京 100044;
3. 北京交通大学轨道交通控制与安全国家重点实验室北京 100044;
4. 太原科技大学计算机科学与技术学院太原 030024

收稿日期:2017-05-05 修回日期:2018-02-01 出版日期:2018-05-05 发布日期:2018-05-05
通讯作者: 姚德臣(通信作者),男,1984年出生,博士,副教授。主要研究方向为机械设备故障诊断、车辆动力学、转子动力学等。E-mail:yaodechen@bucea.edu.cn
基金资助:
国家自然科学基金（51605023）、长城学者培养计划（CIT&TCD20150312）、国家重点研发计划课题（2016YFB1200402）、轨道交通控制与安全国家重点实验室自主课题（RCS2010ZZ002）、建大英才培养计划课题资助项目。

Railway Rolling Bearing Fault Diagnosis Based on Muti-scale IMF Permutation Entropy and SA-SVM Classifier

YAO Dechen^1,2, YANG Jianwei^1,2, CHENG Xiaoqing³, WANG Xing⁴

1. School of Machine-electricity and Automobile Engineering, Beijing University of Civil Engineering and Architecture, Beijing 100044;
2. Beijing Key Laboratory of Performance Guarantee on Urban Rail Transit Vehicles, Beijing University of Civil Engineering Architecture, Beijing 100044;
3. State Key Laboratory of Rail Traffic Control and Safety, Beijing Jiaotong University, Beijing 100044;
4. Department of Computer Science and Technology, Taiyuan University of Science and Technology, Taiyuan 030024

Received:2017-05-05 Revised:2018-02-01 Online:2018-05-05 Published:2018-05-05

摘要/Abstract

摘要： 针对轴承振动信号的非线性、非平稳性，提出一种基于多尺度本征模态排列熵和模拟退火优化支持向量机（Simulated annealing-support vector machine，SA-SVM）的列车轴承故障诊断方法。该方法首先对获取的轴承振动信息进行小波降噪处理，接着通过集合经验模态分解（Ensemble empirical mode decompose，EEMD）将去噪信号分解成若干个平稳的本征模态函数（Intrinsic mode function，IMF），并提取多尺度本征模态排列熵作为SVM输入，在用样本训练SVM时，用SA对SVM的核函数进行优化，提高其分类准确率，最终实现智能化故障诊断。试验结果表明，基于多尺度本征模态排列熵和SA-SVM的列车轴承故障诊断方法能准确识别列车轴承故障类型，具有重要的实际工程应用价值。

关键词: EEMD, SA-SVM, 多尺度本征模态排列熵, 故障诊断, 列车轴承

Abstract: The vibration signals resulting from rolling bearings are non-linear and non-stationary, an approach for the fault diagnosis of railway rolling bearings using the multi-scale IMF permutation entropy and SA-SVM classifier is proposed. The signal is first denoised using wavelet de-noising (WD) as a pre-filter, which improves the subsequent decomposition into a number of intrinsic mode functions (IMFs) using ensemble empirical mode decompose (EEMD). Secondly, the multi-scale IMF permutation entropy are extracted as feature parameters. Finally, the extracted features are given input to SA-SVM for an automated fault diagnosis procedure. The results demonstrate its effectiveness for railway rolling bearings fault diagnosis. The fault diagnosis system has high application value in practical engineering.

Key words: EEMD, fault diagnosis, multi-scale IMF permutation entropy, railway rolling bearing, SA-SVM

中图分类号:

TH133
U279

姚德臣, 杨建伟, 程晓卿, 王兴. 基于多尺度本征模态排列熵和SA-SVM的轴承故障诊断研究[J]. 机械工程学报, 2018, 54(9): 168-176.

YAO Dechen, YANG Jianwei, CHENG Xiaoqing, WANG Xing. Railway Rolling Bearing Fault Diagnosis Based on Muti-scale IMF Permutation Entropy and SA-SVM Classifier[J]. Journal of Mechanical Engineering, 2018, 54(9): 168-176.

参考文献

[1] HE Q, WANG J, HU F, et al. Wayside acoustic diagnosis of defective train bearings based on signal resampling and information enhancement[J]. Journal of Sound and Vibration, 2013, 332(21):5635-5649.
[2] 唐贵基,邓飞跃,何玉灵. 基于自适应多尺度自互补Top-Hat变换的轴承故障增强检测[J]. 机械工程学报, 2015, 51(19):93-100. TANG Guiji, DENG Feiyue, HE Yuling. Enhanced detection of bearing faults based on adaptive multi-scale self-complementary Top-Hat transformation[J]. Journal of Mechanical Engineering, 2015, 51(19):93-100.
[3] 隋文涛,张丹, WILSON Wang. 基于EMD和MKD的滚动轴承故障诊断方法[J]. 振动与冲击, 2015, 34(9):55-59. SUI Wentao, ZHANG Dan, WILSON Wang. Fault diagnosis of rolling element bearings based on EMD and MKD[J]. Journal of Vibration and Shock, 2015, 34(9):55-59.
[4] 苏文胜,王奉涛,张志新. EMD降噪和谱峭度法在滚动轴承早期故障诊断中的应用[J]. 振动与冲击, 2010, 29(3):18-21. SU Wensheng, WANG Fengtao, ZHANG Zhixin. Application of EMD denoising and spectral kurtosis in fault early diagnosis of element bearing[J]. Journal of Vibration and Shock, 2010, 29(3):18-21.
[5] 张志刚,石晓辉,陈哲明. 基于改进EMD与滑动峰态算法的滚动轴承故障特征提取[J]. 振动与冲击, 2012, 31(22):80-83. ZHANG Zhigang, SHI Xiaohui, CHEN Zheming. Fault feature extraction of rolling element bearing based on improved EMD and sliding kurtosis algorithm[J]. Journal of Vibration and Shock, 2012, 31(22):80-83.
[6] 徐卓飞,刘凯,张海燕,等. 基于经验模态分解和主元分析的滚动轴承故障诊断方法研究[J]. 振动与冲击, 2014, 33(23):133-139. XU Zhuofei, LIU Kai, ZHANG Haiyan, et al. A fault diagnosis method for rolling bearings based on empirical mode decomposition and principal component analysis[J]. Journal of Vibration and Shock, 2014, 33(23):133-139.
[7] WU Z H, HUANG N E. Ensemble empirical mode decomposition:A noise-assisted data analysis method[J]. Advanced in Adaptive Data Analysis, 2009, 1(1):1-41.
[8] BANDT C, POMPER B. Permutation entropy:A natural complexity measure for time series[J]. Physical Review Letters, 2002, 88(17):1-4.
[9] YAN R Q, LIU Y B, GAO R X. Permutation entropy:A nonlinear statistical measure for status characterization of rotary machine[J]. Mechanical System and Signal Processing, 2012, 29:474-484.
[10] 冯辅周,饶国强,司爱威. 基于排列熵和神经网络的滚动轴承异常检测与诊断[J]. 噪声与振动控制, 2013, 33(3):212-217. FENG Fuzhou, RAO Guoqiang, SI Aiwei. Abnormality detection and diagnosis of rolling bearing based on permutation entropy and neural network[J]. Noise and Vibration Control, 2013, 33(3):212-217.
[11] 冯辅周,饶国强,司爱威. 排列熵算法研究及其在振动信号突变检测中的应用[J]. 振动工程学报,2012,25(2):221-224. FENG Fuzhou, RAO Guoqiang, SI Aiwei. Research and application of the arithmetic of PE in testing the sudden change of vibration signal[J]. Journal of Vibration Engineering, 2012, 25(2):221-224.
[12] 郑近德,程军圣,杨宇. 多尺度排列熵及其在滚动轴承故障诊断中的应用[J]. 中国机械工程, 2013, 24(19):2641-2646. ZHENG Jinde, CHENG Junsheng, YANG Yu. Multi-scale permutation entropy and its applications to rolling bearing fault diagnosis[J]. China Mechanical Engineering, 2013, 24(19):2641-2646.
[13] 武兵,林健,熊晓燕. 基于支持向量回归的多参数设备故障预测方法[J]. 振动、测试与诊断, 2012, 32(5):791-795. WU Bing, LIN Jian, XIONG Xiaoyan. Method of mechanical equipment fault prognosis based on multi-parameter support vector regression[J]. Journal of Vibration, Measurement & Diagnosis, 2012, 32(5):791-795.
[14] 胡玉霞,张红涛. 基于模拟退火算法-支持向量机的储粮害虫识别分类[J]. 农业机械学报, 2008, 39(9):108-111. HU Yuxia, ZHANG Hongtao. Recognition of the stored-grain pests based on simulated annealing algorithm and support vector machine[J]. Transactions of the Chinese Society for Agricultural Machinery, 2008, 39(9):108-111.
[15] 张超,陈建军. EEMD方法和EMD方法抗模态混叠对比研究[J]. 振动与冲击, 2010, 29(S):87-90. ZHANG Chao, CHEN Jianjun. Contrast of ensemble empirical mode decomposition and empirical mode decomposition in modal mixture[J]. Journal of Vibration and Shock, 2010, 29(S):87-90.
[16] 李昌林,孔凡让,黄伟国. 基于EEMD和Laplace小波的滚动轴承故障诊断[J]. 振动与冲击, 2014, 33(3):63-69. LI Changlin, KONG Fanrang, HUANG Weiguo. Rolling bearing fault diagnosis based on EEMD and laplace wavelet[J]. Journal of Vibration and Shock, 2014, 33(3):63-69.
[17] WU Z H, HUANG N E. Ensemble empirical mode decomposition:A noise assisted data analysis method[J]. Advances in Adaptive Data Analysis, 2009, 1:1-41.
[18] 雷亚国,孔德同,李乃鹏,等. 自适应总体平均经验模态分解及其在行星齿轮箱故障检测中的应用[J]. 机械工程学报, 2014, 50(3):64-70. LEI Yaguo, KONG Detong, LI Naipeng, et al. Adaptive ensemble empirical mode decomposition and its application to fault detection of planetary gearboxes[J]. Journal of Mechanical Engineering, 2014, 50(3):64-70.
[19] 任静波,孙根正,陈冰,等. 基于多尺度排列熵的铣削颤振在线监测方法[J]. 机械工程学报, 2015, 51(9):206-212. REN Jingbo, SUN Genzheng, CHEN Bing, et al. Multi-scale permutation entropy based on-line milling chatter detection method[J]. Journal of Mechanical Engineering, 2015, 51(9):206-212.
[20] 纪华, 马伏龙. 模拟退火算法与支持向量机在机械故障诊断中的应用[J]. 宁夏大学学报, 2014, 35(2):141-143. JI Hua, MA Fulong. The application on the simulated annealing algorithm and the support vector machines in mechanical fault diagnosis[J]. Journal of Ningxia University, 2014, 35(2):141-143.

基于多尺度本征模态排列熵和SA-SVM的轴承故障诊断研究

Railway Rolling Bearing Fault Diagnosis Based on Muti-scale IMF Permutation Entropy and SA-SVM Classifier

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	王奉涛, 刘晓飞, 敦泊森, 邓刚, 韩清凯, 李宏坤. 基于萤火虫优化的核自动编码器在中介轴承故障诊断中的应用[J]. 机械工程学报, 2019, 55(7): 58-64.
[2]	姜洪开, 邵海东, 李兴球. 基于深度学习的飞行器智能故障诊断方法[J]. 机械工程学报, 2019, 55(7): 27-34.
[3]	熊鹏, 汤宝平, 邓蕾, 赵明航. 基于动态加权密集连接卷积网络的变转速行星齿轮箱故障诊断[J]. 机械工程学报, 2019, 55(7): 52-57.
[4]	沈长青, 汤盛浩, 江星星, 石娟娟, 王俊, 朱忠奎. 独立自适应学习率优化深度信念网络在轴承故障诊断中的应用研究[J]. 机械工程学报, 2019, 55(7): 81-88.
[5]	李川, 张绍辉, José Valente de Oliveira. 基于次优网络深度学习的3D打印机故障诊断[J]. 机械工程学报, 2019, 55(7): 73-80.
[6]	胡茑庆, 陈徽鹏, 程哲, 张伦, 张宇. 基于经验模态分解和深度卷积神经网络的行星齿轮箱故障诊断方法[J]. 机械工程学报, 2019, 55(7): 9-18.
[7]	汪久根, 柯梁亮. 基于残差网络的RV减速器故障诊断[J]. 机械工程学报, 2019, 55(3): 73-80.
[8]	翁军华,张剑锐,李达,郑海兴. 光伏系统直流电弧故障检测的抗干扰技术综述[J]. 电气工程学报, 2019, 14(3): 9-15.
[9]	程礼, 杨武奎, 梁涛, 文璧, 姚东野. 基于声模态的压气机/风扇气路故障诊断[J]. 机械工程学报, 2019, 55(13): 38-44.
[10]	陈雪峰, 王诗彬, 程礼. 航空发动机快变信号的匹配同步压缩变换研究[J]. 机械工程学报, 2019, 55(13): 13-22.
[11]	胡超凡, 王衍学. 基于张量分解的滚动轴承复合故障多通道信号降噪方法研究[J]. 机械工程学报, 2019, 55(12): 50-57.
[12]	彭丹丹, 刘志亮, 靳亚强, 秦勇. 基于软筛分停止准则的改进经验模态分解及其在旋转机械故障诊断中的应用[J]. 机械工程学报, 2019, 55(10): 122-132.
[13]	宗鸣,冯超,郑安琪. 基于FPGA自适应滤波器的磁轴承位移传感器故障信号处理分析[J]. 电气工程学报, 2018, 13(8): 1-6.
[14]	侯文擎, 叶鸣, 李巍华. 基于改进堆叠降噪自编码的滚动轴承故障分类[J]. 机械工程学报, 2018, 54(7): 87-96.
[15]	李允公, 戴丽, 李国萌, 王波, 吴文寿. 基于听觉显著图的瞬态振动信号表征方法研究[J]. 机械工程学报, 2018, 54(7): 54-62.