基于两类特征与AFSA优化SVM的滚动轴承故障诊断研究
|
摘要
针对非线性、非平稳的滚动轴承振动信号特征"难表征"和基于支持向量机(Support vector machine, SVM)的故障分类模型"精度低"的问题,提出一种基于变分模态分解(Variational Mode Decomposition,VMD)、峭度图(Kurtogram)与人工鱼群算法(Artificial Fish Swarm Algorithm,AFSA)优化SVM相结合的滚动轴承状态辨识方法。首先,利用Kurtogram算法、相关系数最大准则"筛选"出原信号经VMD后包含有效故障信息的本征模函数(Intrinsic Mode Functions, IMF),并计算其形态谱熵和能量熵构建有效特征向量集;其次,利用AFSA寻找最优的惩罚系数C和高斯核宽度系数σ的核函数系数组合(C、σ);并将有效特征向量集作为上述算法的输入建立滚动轴承状态辨识模型。实验结果表明,所提方法不仅能凸显原信号中的有效故障成份,同时也提高了模型学习效率和分类精度。
To monitor the health of rolling bearing, the vibration signals are always used for fault diagnosis. However, the non-linear and non-stationary characteristics of vibration signals have not been solved in current methods. In this work, an intelligent fault diagnosis method is proposed, which is a sequential combinations of variational mode decomposition(VMD), Kurtogram, and artificial fish algorithm(AFSA). To begin, original vibration signals are decomposed into intrinsic mode functions(IMFs) using VMD, among which the most effective fault information is selected based on the Kurtogram algorithm and the rules of maximum correlation coefficients. Then the feature vectors are identified using the morphological entropy and energy entropy of the above IMFs. Next, two crucial tunable parameters, penalty coefficient C and Gaussian kernel width coefficient σ are optimized through AFSA algorithm. At last, the fault diagnosis model is developed based on AFSA-SVM algorithm, in which the extracted fault features are employed as inputs. The experimental results show that the proposed method accurately identifies fault features of the original signal. It has also improved model learning efficiency and classification accuracy.
To monitor the health of rolling bearing, the vibration signals are always used for fault diagnosis. However, the non-linear and non-stationary characteristics of vibration signals have not been solved in current methods. In this work, an intelligent fault diagnosis method is proposed, which is a sequential combinations of variational mode decomposition(VMD), Kurtogram, and artificial fish algorithm(AFSA). To begin, original vibration signals are decomposed into intrinsic mode functions(IMFs) using VMD, among which the most effective fault information is selected based on the Kurtogram algorithm and the rules of maximum correlation coefficients. Then the feature vectors are identified using the morphological entropy and energy entropy of the above IMFs. Next, two crucial tunable parameters, penalty coefficient C and Gaussian kernel width coefficient σ are optimized through AFSA algorithm. At last, the fault diagnosis model is developed based on AFSA-SVM algorithm, in which the extracted fault features are employed as inputs. The experimental results show that the proposed method accurately identifies fault features of the original signal. It has also improved model learning efficiency and classification accuracy.
引文
[1] Liu J,Shao Y,Zhu W D.A new model for the relationship between vibration characteristics caused by the time-varying contact stiffness of a deep groove ball bearing and defect sizes[J].ASME Journal of Tribology,2015,137(3):031101.
[2] 向丹,岑健.基于EMD熵特征融合的滚动轴承故障诊断方法[J].航空动力学报,2015,30(05):1149-1155.XIANU Dan,CEN Jian.Method of roller bearing fault diagnosis based on feature fusion of EMD entropy[J].Journal of Aerospace Power,2015,30(05):1149-1155 (In Chinese).
[3] 徐乐,邢邦圣,郎超男,等.LMD能量熵和SVM相结合的滚动轴承故障诊断[J].机械科学与技术,2017,36(06):915-918.XU Le,XING BangSheng,LANG ChaoNan.Fault diagnosis of rolling bearing combined LMD energy entropy and SVM[J].Mechanical Science and Technology for Aerospace Engineering,2017,36(06):915-918(In Chinese).
[4] 夏均忠,苏涛,张阳,等.基于EEMD能量熵及LS-SVM滚动轴承故障诊断[J].噪声与振动控制,2014,34(03):170-175.XIA JunZhong,SU Tao,ZHANG Yang.Fault diagnosis method of rolling bearings based on ensemble empirical mode decomposition energy entropy and LS-SVM.[J].Noise and Vibration Control,2014,34(03):170-175(In Chinese).
[5] 郑近德,潘海洋,张俊,等.APEEMD及其在转子碰摩故障诊断中的应用[J].振动、测试与诊断,2016.36 (2):257-263.ZHENG JinDe,PAN HaiYann,ZHANG Jun.Adaptive partly-ensemble empirical mode decomposition and its application for rotor rubbing fault diagnosis[J].Journal of Vibration,Measurement & Diagnosis,2016.36 (2):257-263(In Chinese).
[6] 张大为,段哲民,李鹏,等.基于遗传算法和支持向量机的故障诊断方法[J].计算机测量与控制,2010,18(8):1745-1747ZHANG DaWei,DUAN ZheMin,LI Peng,Fault diagnosis method based on genetic algorithm and LSSVM[J].Computer Measurement & Control,2010,18(8):1745-1747(In Chinese).
[7] 孙瑶琴.基于改进FOA优化的SVM在故障诊断中的应用[J].机械强度,2017,39(02):285-290.SUN YaoQin,Optimized SVM based on improved for and its application in fault daignosis[J].Journal of Mechanical Strength,2017,39(02):285-290(In Chinese).
[8] Dragomiretskiy K,Zosso D.Variational mode decomposition [J].IEEE Tran on Signal Processing.2014,62 (3):531-544.
[9] Antoni J,Randall R B.The spectral kurtosis:application tothe vibratory surveillance and diagnostics of rotating machines [J].Mechanical Systems and Signal Processing,2006,20(2):308-331.
[10] Antoni J.Fast computation of the kurtogram for the detection of transient faults[J].Mechanical Systems and Signal Processing,2007,21(1):108-124.
[11] 秦波,刘永亮,王建国,等基于小波包最优节点能量特征的BA-ELM齿轮故障诊断方[J].机械传动,2016,40(4):33-37.QIN Bo,LIU YongLiang,WANG JianGuo.BA-ELM gear fault diagnosis method based on energy feature of wavelet packet optimal node[J].Journal of Mechanical Transmission,2016,40(4):33-37(In Chinese).
[12] 姜万录,郑直,胡浩松.基于EEMD形态谱和支持向量机复合的滚动轴承故障诊断方法[J].工程科学学报,2015(S1):72-77.JIANG Wanlu,ZHENG Zhi,HU HaoSong.Fault diagnosis of ball bearing based vector machine on EEMD morphological spectrum and support[J].Chinese Journal of Engineering,2015(S1):72-77(In Chinese).
[13] 秦波,吴庆朝,张娟娟,等.基于PSO优化SVM的转炉炼钢用氧量预测研究[J].测控技术,2014,33(12):121-124.QIN Bo,WU QingChao,ZHANG JuanJuan.Blowing oxygen volume prediction of BOF steelmaking based on PSO-SVM.Measurement and Control Technology,2014,33(12):121-124(In Chinese).
[2] 向丹,岑健.基于EMD熵特征融合的滚动轴承故障诊断方法[J].航空动力学报,2015,30(05):1149-1155.XIANU Dan,CEN Jian.Method of roller bearing fault diagnosis based on feature fusion of EMD entropy[J].Journal of Aerospace Power,2015,30(05):1149-1155 (In Chinese).
[3] 徐乐,邢邦圣,郎超男,等.LMD能量熵和SVM相结合的滚动轴承故障诊断[J].机械科学与技术,2017,36(06):915-918.XU Le,XING BangSheng,LANG ChaoNan.Fault diagnosis of rolling bearing combined LMD energy entropy and SVM[J].Mechanical Science and Technology for Aerospace Engineering,2017,36(06):915-918(In Chinese).
[4] 夏均忠,苏涛,张阳,等.基于EEMD能量熵及LS-SVM滚动轴承故障诊断[J].噪声与振动控制,2014,34(03):170-175.XIA JunZhong,SU Tao,ZHANG Yang.Fault diagnosis method of rolling bearings based on ensemble empirical mode decomposition energy entropy and LS-SVM.[J].Noise and Vibration Control,2014,34(03):170-175(In Chinese).
[5] 郑近德,潘海洋,张俊,等.APEEMD及其在转子碰摩故障诊断中的应用[J].振动、测试与诊断,2016.36 (2):257-263.ZHENG JinDe,PAN HaiYann,ZHANG Jun.Adaptive partly-ensemble empirical mode decomposition and its application for rotor rubbing fault diagnosis[J].Journal of Vibration,Measurement & Diagnosis,2016.36 (2):257-263(In Chinese).
[6] 张大为,段哲民,李鹏,等.基于遗传算法和支持向量机的故障诊断方法[J].计算机测量与控制,2010,18(8):1745-1747ZHANG DaWei,DUAN ZheMin,LI Peng,Fault diagnosis method based on genetic algorithm and LSSVM[J].Computer Measurement & Control,2010,18(8):1745-1747(In Chinese).
[7] 孙瑶琴.基于改进FOA优化的SVM在故障诊断中的应用[J].机械强度,2017,39(02):285-290.SUN YaoQin,Optimized SVM based on improved for and its application in fault daignosis[J].Journal of Mechanical Strength,2017,39(02):285-290(In Chinese).
[8] Dragomiretskiy K,Zosso D.Variational mode decomposition [J].IEEE Tran on Signal Processing.2014,62 (3):531-544.
[9] Antoni J,Randall R B.The spectral kurtosis:application tothe vibratory surveillance and diagnostics of rotating machines [J].Mechanical Systems and Signal Processing,2006,20(2):308-331.
[10] Antoni J.Fast computation of the kurtogram for the detection of transient faults[J].Mechanical Systems and Signal Processing,2007,21(1):108-124.
[11] 秦波,刘永亮,王建国,等基于小波包最优节点能量特征的BA-ELM齿轮故障诊断方[J].机械传动,2016,40(4):33-37.QIN Bo,LIU YongLiang,WANG JianGuo.BA-ELM gear fault diagnosis method based on energy feature of wavelet packet optimal node[J].Journal of Mechanical Transmission,2016,40(4):33-37(In Chinese).
[12] 姜万录,郑直,胡浩松.基于EEMD形态谱和支持向量机复合的滚动轴承故障诊断方法[J].工程科学学报,2015(S1):72-77.JIANG Wanlu,ZHENG Zhi,HU HaoSong.Fault diagnosis of ball bearing based vector machine on EEMD morphological spectrum and support[J].Chinese Journal of Engineering,2015(S1):72-77(In Chinese).
[13] 秦波,吴庆朝,张娟娟,等.基于PSO优化SVM的转炉炼钢用氧量预测研究[J].测控技术,2014,33(12):121-124.QIN Bo,WU QingChao,ZHANG JuanJuan.Blowing oxygen volume prediction of BOF steelmaking based on PSO-SVM.Measurement and Control Technology,2014,33(12):121-124(In Chinese).