基于ELMD与LS-SVM的滚动轴承故障诊断方法

doi:10.3969/j.issn.0438-1157.2013.12.059

摘要/Abstract

摘要： 针对局部均值分解（local mean decomposition，LMD）实现过程中存在的模式混淆现象，提出了一种基于总体局部均值分解（ensemble local mean decomposition，ELMD）与最小二乘支持向量机（least squares support vector machine，LS-SVM）相结合的滚动轴承故障诊断方法。该方法先对滚动轴承振动信号进行ELMD分解，并得到若干乘积函数（product function，PF），然后选取包含主要故障信息的PF分量，提取其峭度系数与能量特征参数以构造故障特征向量，并作为LS-SVM的输入来识别滚动轴承的工作状态和故障类型。通过对滚动轴承正常状态，内圈故障和外圈故障的分析结果表明，基于ELMD与LS-SVM的诊断方法可以准确有效识别滚动轴承的工作状态和故障类型。

关键词: ELMD, 模式混淆, LS-SVM, 滚动轴承, 故障诊断

Abstract: A problem of mode mixing occurred in implementation process of local mean decomposition (LMD) method,a fault diagnosis approach for rolling bearing based on ensemble local mean decomposition (ELMD) and least squares support vector machine (LS-SVM) was proposed.Firstly,by using ELMD method,the vibrational signal of rolling bearing was decomposed a series of product function (PF) components,and then the PF components which contain main fault information were selected,and the kurtosis coefficients and energy characteristic parameters extracted from selected PF components were regarded as fault feature which was served as input parameters of LS-SVM to identify the working status and fault types of rolling bearing.The analytic results of fault-free,inner-race fault and outer-race fault of rolling bearing indicate that the working status and fault types of rolling bearing can be identified accurately and effectively by using the approach based on ELMD and LS-SVM.

Key words: ELMD, mode mixing, LS-SVM, rolling bearing, fault diagnosis

中图分类号:

TP181

廖星智, 万舟, 熊新. 基于ELMD与LS-SVM的滚动轴承故障诊断方法[J]. 化工学报, 2013, 64(12): 4667-4673.

LIAO Xingzhi, WAN Zhou, XIONG Xin. Fault diagnosis method of rolling bearing based on ensemble local mean decomposition and least squares support vector machine[J]. CIESC Journal, 2013, 64(12): 4667-4673.

参考文献 23

[1]	Li Zhinong (李志农), Liu Weibing (刘卫兵), Xiao Yaoxian (肖尧先), Wu Guanhua (邬冠华).Fault diagnosis method of rolling bearing based on local mean decomposition envelope spectrum and support vector machine (SVM)[J].Machinery Design and Manufacture (设计与制造), 2011, 11:170-172
[2]	Zhang Kang (张亢), Cheng Junsheng (程军圣), Yang Yu (杨宇).The local mean decomposition method based on rational spline and its application[J].Journal of Vibration Engineering (振动工程学报), 2011, 24 (1):96-103
[3]	Cheng Junsheng (程军圣), Yang Yu (杨宇), Yu Dejie (于德介).The local mean decomposition method and its application to gear fault diagnosis[J].Journal of Vibration Engineering (振动工程学报), 2009, 22 (1):76-84
[4]	Huang N E, Shen Z, Long S R.The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J].Proceeding of Royal Society London, Series A, 1998, 454:903-995
[5]	Yu Lei (余磊), Liu Quan (刘泉).Restrict end defect of empirical mode decomposition[J].Journal of Wuhan University of Technology (武汉理工大学学报), 2010, 32 (10):151-154
[6]	Dou Dongyang (窦东阳), Zhao Yingkai (赵英凯).Method of improving ending effect of Hilbert-Huang transform using autoregressive integrated moving average model[J].Journal of Vibration, Measurement & Diagnosis (振动、测试与诊断), 2010, 30 (3):249-253
[7]	Deering R, Kaiser J F.The use of a masking signal to improve empirical mode decomposition//ICASSP, IEEE International Conference on Acoustics, Speech and signal Processing-Proceeding[C].MA, USA:MIT Press, 2005:485-488
[8]	Wu Z, Huang N E.Ensemble empirical mode decomposition:a noise-assisted data analysis method[J].Advances in Adaptive Data Analysis, 2009, 1 (1):1-41
[9]	Lei Yaguo.Machinery fault diagnosis based on improved Hilbert-Huang transform[J].Chinese Journal of Mechanical Engineering, 2011, 47 (5):71-77
[10]	Jiao bin (焦斌), Xu Zhixiang (徐志翔).Parameters optimization of LSSVM and application in fault diagnosis of wind power gearbox[J].Control Engineering of China (控制工程), 2012, 19 (4):681-686
[11]	Zhao Yang (赵洋), Chen Guoshun (陈国顺), Ma Sasa (马飒飒), Zhao Qiao (赵俏).Research on online fault prediction model of electronic equipment based on online sparse least square support vector machine[J].Computer Measurement&Control (计算机测量与控制), 2012, 20 (11):2903-2908
[12]	Yang Xianyong (杨先勇), Zhou Xiaojun (周晓军), Zhang Wenbin (张文斌), Yang Fuchun (杨富春).Rolling bearing fault diagnosis based on local wave method and KPCA-LSSVM[J].Journal of Zhejiang University:Engineering Science (浙江大学学报:工学版), 2010, 4 (8):1519-1524
[13]	Sui Wentao (隋文涛), Lu Changhou (路长厚), Wilson Wang, Zhang Dan (张丹).Bearing fault diagnosis using simulated annealing algorithm and least squares support vector machines[J].Journal of Vibration, Measurement & Diagnosis (振动、测试与诊断), 2010, 30 (2):119-122
[14]	Jonathan S Smith.The local mean decomposition and its application to EEG perception data[J].Journal of the Royal Society Interface, 2005, 2 (5):443-454
[15]	Li Zhinong (李志农), Liu Weibing (刘卫兵), Yi Xiaobing (易小兵).The method of mechanical failure underdetermined blind source separation based on local mean decomposition[J].Journal of Mechanical Engineering (机械工程学报), 2011, 47 (7):97-102
[16]	Wang Mingda (王明达), Zhang Laibin (张来斌), Liang Wei (梁伟), Duan Lixiang (段礼祥).Research on local mean decomposition method based on B-spline interpolation[J].Journal of Vibration and Shock (振动与冲击), 2010, 29 (11):73-77
[17]	Cheng Junsheng (程军圣), Zhang Kang (张亢), Yang Yu (杨宇).Ensemble local mean decomposition method based on noise-assisted analysis[J].Journal of Mechanical Engineering (机械工程学报), 2011, 47 (3):55-62
[18]	Vapnik V.The Nature of Statistical Learning Theory[M].2nd ed.New York:Springer-Verlag, 1998:360-374
[19]	Jiang Baihua (蒋白桦), Liu Wei (刘伟), Dai Zhijun (戴志军), Wang Hong'an (王宏安).Working condition-based optimization framework for operational patterns and its application in petrochemical industry[J].CIESC Journal (化工学报), 2012, 63 (12):3978-3984
[20]	Ma Longbo (马龙博), Zhang Hongjian (张宏建), Zhou Hongliang (周洪亮), He Qing (贺庆).Flow regime identification of oil-water two-phase flow based on HHT and SVM[J].Journal of Chemical Industry and Engineering (China) (化工学报), 2007, 58 (3):617-622
[21]	Tao Shaohui (陶少辉), Chen Dezhao (陈德钊), Hu Wangming (胡望明).Gradient algorithm for selecting hyper parameters of LSSVM in process modeling[J].Journal of Chemical Industry and Engineering (China) (化工学报), 2007, 58 (6):1514-1517
[22]	Zhang Quanming (张全明), Liu Huijin (刘会金).Application of LS-SVM in classification of power quality disturbances[J].Proceedings of the CSEE (中国电机工程学报), 2008, 28 (1):106-110
[23]	Wang Qiang (王强), Tian Xuemin (田学民).Soft sensing based on KPCA and LSSVM[J].CIESC Journal (化工学报), 2011, 62 (10):2813-1817