基于经验模态分解和支持向量机的滚动轴承故障诊断
|
摘要
本文针对滚动轴承的故障诊断问题,首先提出一种自适应波形匹配的延拓方法对经验模态分解(EMD)存在的端点效应进行改进,然后基于改进的EMD和粒子群优化算法(PSO)优化的支持向量机(SVM)设计了一种两阶段的滚动轴承故障诊断方法.离线阶段对典型的正常、故障振动信号进行EMD分解并提取能量信息作为特征,送入PSO–SVM进行训练并保存模型待用,在线阶段对实时的振动信号进行EMD分解并提取特征,利用离线阶段训练好的模型进行诊断并输出诊断结果.使用美国西储大学轴承数据对该方法进行了验证,实验结果证明了该方法的有效性.
In this paper, an adaptive waveform matching method is proposed to improve the end effect of empirical mode decomposition(EMD). Then a two-phase fault diagnosis method for rolling bearing is presented based on improved EMD and Particle Swarm Optimization(PSO) optimized support vector machine(SVM). In the offline phase, the typical normal and fault vibration signals are decomposed by IEMD and energy information is extracted as the feature. A PSO–SVM model is trained and saved as diagnostic model. In the online phase, the real-time vibration signal is decomposed by IEMD and the feature is extracted. The model trained in offline phase executes diagnostic process and output the diagnosis results.The method is verified using Case Western bearing datasets. The experimental results show the effectiveness of the method in fault diagnosis of rolling bearing.
In this paper, an adaptive waveform matching method is proposed to improve the end effect of empirical mode decomposition(EMD). Then a two-phase fault diagnosis method for rolling bearing is presented based on improved EMD and Particle Swarm Optimization(PSO) optimized support vector machine(SVM). In the offline phase, the typical normal and fault vibration signals are decomposed by IEMD and energy information is extracted as the feature. A PSO–SVM model is trained and saved as diagnostic model. In the online phase, the real-time vibration signal is decomposed by IEMD and the feature is extracted. The model trained in offline phase executes diagnostic process and output the diagnosis results.The method is verified using Case Western bearing datasets. The experimental results show the effectiveness of the method in fault diagnosis of rolling bearing.
引文
[1]ZOU Jiansheng,HAO Yanfang.Fault analysis and diagnosis method of rolling bearing of rail vehicle running section.Technical and Institutional Administration,2015,47(9):43-46.(邹建生,郝艳芳.轨道车辆走行部滚动轴承故障分析及诊断方法.铁道机车与动车,2015,47(9):43-46.)
[2] ZHANG Xuewu, LU Yanyun, DING Yanqiong, et al. Surface defect inspection based on wavelet statistical analysis. Control Theory&Applications, 2010, 27(10):1331–1336.(张学武,吕艳云,丁燕琼,等.小波统计法的表面缺陷检测方法.控制理论与应用, 2010, 27(10):1331–1336.)
[3] PAN Lisha, CHEN Hao, QIN Yong, et al. Fault diagnosis of rolling bearing for rail vehicles based on wavelet packet and RBF neural network. Journal of Railway Applications, 2012, 21(7):8–11.(潘丽莎,陈皓,秦勇,等.基于小波包和RBF神经网络的轨道车辆滚动轴承故障诊断.铁路计算机应用, 2012, 21(7):8–11.)
[4] QIN Na, JIN Weidong, HUANG Jin, et al. Ensemble empirical mode decomposition and fuzzy entropy in fault feature analysis for highspeed train bogie. Control Theory&Applications, 2014, 31(9):1245–1251.(秦娜,金炜东,黄进,等.高速列车转向架故障信号的聚合经验模态分解和模糊熵特征分析.控制理论与应用, 2014, 31(9):1245–1251.)
[5] ZHANG Yongjian, KONG Xiangzhen, ZHANG Yongchao, et al.Fault diagnosis method of bearing based on EMD and BP network.Microcomputer and Application, 2014, 33(4):77–80.(张永建,孔祥振,张永超,等.基于EMD和BP网络的轴承故障诊断方法.微型机与应用, 2014, 33(4):77–80.)
[6] TIAN Feng, ZHAO Chong, LIU Yong, et al. Fault diagnosis of rolling bearings based on EMD and RBF. Ship Electronic Engineering, 2014,34(7):149–151.(田峰,赵翀,刘勇,等.基于EMD和RBF的滚动轴承故障诊断.舰船电子工程, 2014, 34(7):149–151.)
[7] AN Xiaohong, NIU Jiangchuan, REN Bin, et al. Bearing fault diagnosis based on Gabor transform and EMD. Journal of Shijiazhuang Railway University:Natural Science Edition, 2017, 30(1):81–85.(安晓红,牛江川,任彬,等.基于Gabor变换和EMD的轴承故障诊断.石家庄铁道大学学报:自然科学版, 2017, 30(1):81–85.)
[8] HE Guangjian, XING Zongyi, ZUO Cheng, et al. Study on fault diagnosis method of rolling bearing for urban rail train based on EMD and SVM. Journal of Railway Applications, 2015, 24(8):1–4.(何广坚,邢宗义,左成,等.基于EMD与SVM的城轨列车滚动轴承故障诊断方法研究.铁路计算机应用, 2015, 24(8):1–4.)
[9] HE Zhijing, WANG Xing, LI Kai, et al. Fault diagnosis of railway bearing based on FIR–EMD and improved SVM. Noise and Vibration Control, 2017, 37(2):143–147.(贺志晶,王兴,李凯,等.基于FIR–EMD和改进SVM的铁路轴承故障诊断.噪声与振动控制, 2017, 37(2):143–147.)
[10] FU Dapeng, ZHAI Yong, YU Qingmin. Fault diagnosis of rolling bearings based on EMD and support vector machine. Machine Tool&Hydraulics, 2017, 45(11):184–187.(付大鹏,翟勇,于青民.基于EMD和支持向量机的滚动轴承故障诊断研究.机床与液压, 2017, 45(11):184–187.)
[11] YU Qingmin, LI Xiaolei, ZHAI Yong. Fault feature extraction method of bearing inner ring based on improved EMD and data cylinder. Journal of Shandong University(Engineering Science), 2017,47(3):89–95.(于青民,李晓磊,翟勇.基于改进EMD和数据分箱的轴承内圈故障特征提取方法.山东大学学报(工学版), 2017, 47(3):89–95.)
[12] ZHAO J P, HUANG D J. Mirror extending and circular spline function for empirical mode decomposition method. Journal of Zhejiang University Science, 2001, 2(3):247–252.
[13] HUANG Chengti. Hilbert-Huang transform and its application research. Chengdu:Southwest Jiao-tong University, 2006.(黄诚惕.希尔伯特–黄变换及其应用研究.成都:西南交通大学,2006.)
[14] XU Bin, XU Decheng, ZHU Weiping. Improvement of HilbertHuang transformation method. Journal of Northwestern Polytechnical University, 2011, 29(2):268–272.(徐斌,徐德城,朱卫平.希尔伯特–黄变换方法的改进.西北工业大学学报, 2011, 29(2):268–272.)
[15] DENG Yongjun, WANG Wei, QIAN Chengchun, et al. EMD method and the processing of boundary problem in Hilbert transform. Science Bulletin, 2001, 46(3):257–263.(邓拥军,王伟,钱成春,等. EMD方法及Hilbert变换中边界问题的处理.科学通报, 2001, 46(3):257–263.)
[16] SHAO Chenxi, WANG Jian, FAN Jinfeng, et al. An adaptive EMD endpoint extension method. Journal of Electronics, 2007, 35(10):1944–1948.(邵晨曦,王剑,范金锋,等.一种自适应的EMD端点延拓方法.电子学报, 2007, 35(10):1944–1948.)
[17] The Case Western Reserve University. Bearing data center website.http://csegroups.case.edu/bearingdatacenter/home, 2017.
[18] PLATT J. Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Advances in Large Margin Classifiers, 1999, 10(3):61–74.
[19] LIN H T, LIN C J, WENG R C. A note on Platt’s probabilistic outputs for support vector machines. Machine Learning, 2007, 68(3):267–276.
[2] ZHANG Xuewu, LU Yanyun, DING Yanqiong, et al. Surface defect inspection based on wavelet statistical analysis. Control Theory&Applications, 2010, 27(10):1331–1336.(张学武,吕艳云,丁燕琼,等.小波统计法的表面缺陷检测方法.控制理论与应用, 2010, 27(10):1331–1336.)
[3] PAN Lisha, CHEN Hao, QIN Yong, et al. Fault diagnosis of rolling bearing for rail vehicles based on wavelet packet and RBF neural network. Journal of Railway Applications, 2012, 21(7):8–11.(潘丽莎,陈皓,秦勇,等.基于小波包和RBF神经网络的轨道车辆滚动轴承故障诊断.铁路计算机应用, 2012, 21(7):8–11.)
[4] QIN Na, JIN Weidong, HUANG Jin, et al. Ensemble empirical mode decomposition and fuzzy entropy in fault feature analysis for highspeed train bogie. Control Theory&Applications, 2014, 31(9):1245–1251.(秦娜,金炜东,黄进,等.高速列车转向架故障信号的聚合经验模态分解和模糊熵特征分析.控制理论与应用, 2014, 31(9):1245–1251.)
[5] ZHANG Yongjian, KONG Xiangzhen, ZHANG Yongchao, et al.Fault diagnosis method of bearing based on EMD and BP network.Microcomputer and Application, 2014, 33(4):77–80.(张永建,孔祥振,张永超,等.基于EMD和BP网络的轴承故障诊断方法.微型机与应用, 2014, 33(4):77–80.)
[6] TIAN Feng, ZHAO Chong, LIU Yong, et al. Fault diagnosis of rolling bearings based on EMD and RBF. Ship Electronic Engineering, 2014,34(7):149–151.(田峰,赵翀,刘勇,等.基于EMD和RBF的滚动轴承故障诊断.舰船电子工程, 2014, 34(7):149–151.)
[7] AN Xiaohong, NIU Jiangchuan, REN Bin, et al. Bearing fault diagnosis based on Gabor transform and EMD. Journal of Shijiazhuang Railway University:Natural Science Edition, 2017, 30(1):81–85.(安晓红,牛江川,任彬,等.基于Gabor变换和EMD的轴承故障诊断.石家庄铁道大学学报:自然科学版, 2017, 30(1):81–85.)
[8] HE Guangjian, XING Zongyi, ZUO Cheng, et al. Study on fault diagnosis method of rolling bearing for urban rail train based on EMD and SVM. Journal of Railway Applications, 2015, 24(8):1–4.(何广坚,邢宗义,左成,等.基于EMD与SVM的城轨列车滚动轴承故障诊断方法研究.铁路计算机应用, 2015, 24(8):1–4.)
[9] HE Zhijing, WANG Xing, LI Kai, et al. Fault diagnosis of railway bearing based on FIR–EMD and improved SVM. Noise and Vibration Control, 2017, 37(2):143–147.(贺志晶,王兴,李凯,等.基于FIR–EMD和改进SVM的铁路轴承故障诊断.噪声与振动控制, 2017, 37(2):143–147.)
[10] FU Dapeng, ZHAI Yong, YU Qingmin. Fault diagnosis of rolling bearings based on EMD and support vector machine. Machine Tool&Hydraulics, 2017, 45(11):184–187.(付大鹏,翟勇,于青民.基于EMD和支持向量机的滚动轴承故障诊断研究.机床与液压, 2017, 45(11):184–187.)
[11] YU Qingmin, LI Xiaolei, ZHAI Yong. Fault feature extraction method of bearing inner ring based on improved EMD and data cylinder. Journal of Shandong University(Engineering Science), 2017,47(3):89–95.(于青民,李晓磊,翟勇.基于改进EMD和数据分箱的轴承内圈故障特征提取方法.山东大学学报(工学版), 2017, 47(3):89–95.)
[12] ZHAO J P, HUANG D J. Mirror extending and circular spline function for empirical mode decomposition method. Journal of Zhejiang University Science, 2001, 2(3):247–252.
[13] HUANG Chengti. Hilbert-Huang transform and its application research. Chengdu:Southwest Jiao-tong University, 2006.(黄诚惕.希尔伯特–黄变换及其应用研究.成都:西南交通大学,2006.)
[14] XU Bin, XU Decheng, ZHU Weiping. Improvement of HilbertHuang transformation method. Journal of Northwestern Polytechnical University, 2011, 29(2):268–272.(徐斌,徐德城,朱卫平.希尔伯特–黄变换方法的改进.西北工业大学学报, 2011, 29(2):268–272.)
[15] DENG Yongjun, WANG Wei, QIAN Chengchun, et al. EMD method and the processing of boundary problem in Hilbert transform. Science Bulletin, 2001, 46(3):257–263.(邓拥军,王伟,钱成春,等. EMD方法及Hilbert变换中边界问题的处理.科学通报, 2001, 46(3):257–263.)
[16] SHAO Chenxi, WANG Jian, FAN Jinfeng, et al. An adaptive EMD endpoint extension method. Journal of Electronics, 2007, 35(10):1944–1948.(邵晨曦,王剑,范金锋,等.一种自适应的EMD端点延拓方法.电子学报, 2007, 35(10):1944–1948.)
[17] The Case Western Reserve University. Bearing data center website.http://csegroups.case.edu/bearingdatacenter/home, 2017.
[18] PLATT J. Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Advances in Large Margin Classifiers, 1999, 10(3):61–74.
[19] LIN H T, LIN C J, WENG R C. A note on Platt’s probabilistic outputs for support vector machines. Machine Learning, 2007, 68(3):267–276.