基于VMD分解和支持向量机的水电机组振动故障诊断
|
摘要
针对传统方法难以精确提取水电机组非平稳振动信号的故障特征,首先引入变分模态分解(variational modal decomposition,VMD)将水电机组非平稳振动信号分解为一系列中心频段互不重叠的IMF分量,进而采取能量法提取各IMF分量的故障特征,最后将提取的故障特征向量输入到本文建立的基于遗传算法优化支持向量机的故障诊断模型中,实现故障模式的识别与诊断。将该方法应用于实际水电机组故障振动信号的处理中,仿真结果表明,该方法能够有效识别机组的异常状况,具有较高的故障诊断正确率。
As it is difficult to extract the fault characteristics of the nonstationary vibration signal of the hydropower unit accurately with the traditional method, this paper firstly introduces the Variational Modal Decomposition(VMD) to decompose the nonstationary vibration signal into a series of IMF components that do not overlap each other. Second, the energy extraction method is used to extract the fault feature of each IMF component. Finally, the fault feature vector extracted is input into the fault diagnosis model based on genetic algorithm optimization support vector machine(SVM) which is established in this paper, and the fault pattern recognition and diagnosis are thus realized. The method is applied to the treatment of faulty vibration signals of an actual hydropower unit, and the simulation results show that the proposed method can effectively identify the abnormal condition of the unit and have high fault diagnosis accuracy.
As it is difficult to extract the fault characteristics of the nonstationary vibration signal of the hydropower unit accurately with the traditional method, this paper firstly introduces the Variational Modal Decomposition(VMD) to decompose the nonstationary vibration signal into a series of IMF components that do not overlap each other. Second, the energy extraction method is used to extract the fault feature of each IMF component. Finally, the fault feature vector extracted is input into the fault diagnosis model based on genetic algorithm optimization support vector machine(SVM) which is established in this paper, and the fault pattern recognition and diagnosis are thus realized. The method is applied to the treatment of faulty vibration signals of an actual hydropower unit, and the simulation results show that the proposed method can effectively identify the abnormal condition of the unit and have high fault diagnosis accuracy.
引文
[1]张孝远,张新萍,苏保平.基于最小最大核K均值聚类算法的水电机组振动故障诊断[J].电力系统保护与控制,2015,43(5):27-34.ZHANG Xiaoyuan,ZHANG Xinping,SU Baoping.Fault diagnosis of hydroelectric generating set based on minimal maximum K maximum clustering algorithm[J].Power System Protection and Control,2015,43(5):27-34.
[2]李超顺,周建中,肖剑,等.基于引力搜索核聚类算法的水电机组振动故障诊断[J].中国电机工程学报,2013,33(2):98-104.LI Chaoshun,ZHOU Jianzhong,XIAO Jian,et al.Fault diagnosis of hydroelectric generating set based on gravity search kernel clustering algorithm[J].Chinese Journal of Electrical Engineering,2013,33(2):98-104.
[3]贾嵘,李涛涛,夏洲,等.基于随机共振和经验模态分解的水力发电机组振动故障诊断[J].水利学报,2017,48(3):334-340.JIA Rong,LI Taotao,XIA Zhou,et al.Fault diagnosis of hydroelectric generating set based on stochastic resonance and empirical mode decomposition[J].Journal of Hydraulic Engineering,2017,48(3):334-340.
[4]ZHANG X,ZHOU J,GUO J,et al.Vibrant fault diagnosis for hydroelectric generator units with a new combination of rough sets and support vector machine[J].Expert Systems With Applications,2012,39(3):2621-2628.
[5]何洋洋,贾嵘,李辉,等.基于随机共振和多维度排列熵的水电机组振动故障诊断[J].水力发电学报,2015,34(12):123-130.HE Yangyang,JIA Rong,LI Hui,et al.Fault diagnosis of hydroelectric generating units based on stochastic resonance and multi-dimensional permutation entropy[J].Jounal of Hydroelectric Engineering,2015,34(12):123-130.
[6]杨永锋.经验模态分解在振动分析中的应用[M].北京:国防工业出版社,2013.
[7]桂中华,韩凤琴.小波包特征熵神经网络在尾水管故障诊断中的应用[J].中国电机工程学报,2005,25(4):99-102.GUI Zhonghua,HAN Fengqin.Application of wavelet packet feature entropy neural network in fault diagnosis of draft pipe[J].Chinese Journal of Electrical Engineering,2005,25(4):99-102.
[8]张克危,林雯婷.小波变换及其在水轮机水压脉动信号处理中的应用[J].大电机技术,2002(6):47-53.ZHANG Kewei,LIN Wenting.Wavelet transform and its application in hydraulic pulsating signal processing of hydraulic turbine[J].Large Electric Machine Technology,2002(6):47-53.
[9]康守强,王玉静,杨广学,等.基于经验模态分解和超球多类支持向量机的滚动轴承故障诊断方法[J].中国电机工程学报,2011,31(14):96-102.KANG Shouqiang,WANG Yujing,YANG Guangxue,et al.Fault diagnosis method of rolling bearing based onempirical mode decomposition and hypersphere support vector machine[J].Chinese Journal of Electrical Engineering,2011,31(14):96-102.
[10]马富齐,贾嵘,武桦,等.基于复数据的EMD在水导轴承故障诊断中的应用[J].水力发电学报,2017,36(2):75-82.MA Fuqi,JIA Rong,WU Hua,et al.Application of EMD based on complex data in fault diagnosis of aqueduct bearing[J].Journal of Hydroelectric Engineering,2017,36(2):75-82.
[11]李辉,李欣同,贾嵘,等.基于经验模态分解和支持向量机的水电机组振动故障诊断[J].水力发电学报,2016,35(12):105-111.LI Hui,LI Xintong,JIA Rong,et al.Fault diagnosis of hydroelectric generating set based on empirical mode decomposition and support vector machine[J].Journal of Hydroelectric Engineering,2016,35(12):105-111.
[12]Dragomiretskiy K,Zosso D.Variational mode decomposition[J].IEEE Transactions on Signal Processing,2014,62(3):531-544.
[13]马增强,李亚超,刘政,等.基于变分模态分解和Teager能量算子的滚动轴承故障特征提取[J].振动与冲击,2016,35(13):134-139.MA Zengqiang,LI Yachao,LIU Zheng,et al.Fault extraction of rolling bearing based on variational modal decomposition and Teager Energy Operator[J].Journal of Vibration and Shock,2016,35(13):134-139.
[14]WANG Y,Markert R,Xiang J,et al.Research on variational mode decomposition and its application in detecting rubimpact fault of the rotor system[J].Mechanical Systems&Signal Processing,2015,60:243-251.
[15]党建,何洋洋,贾嵘,等.水轮发电机组非平稳振动信号的检测与故障诊断[J].水利学报,2016,47(2):173-179.DANG Jian,HE Yangyang,JIA Rong,et al.Detection for non-stationary vibration signaland fault diagnosis of hydropower unit[J].Jounal of Hydraulic Engineering,2016,47(2):173-179.
[16]武英杰.基于变分模态分解的风电机组传动系统故障诊断研究[D].北京:华北电力大学,2016.
[2]李超顺,周建中,肖剑,等.基于引力搜索核聚类算法的水电机组振动故障诊断[J].中国电机工程学报,2013,33(2):98-104.LI Chaoshun,ZHOU Jianzhong,XIAO Jian,et al.Fault diagnosis of hydroelectric generating set based on gravity search kernel clustering algorithm[J].Chinese Journal of Electrical Engineering,2013,33(2):98-104.
[3]贾嵘,李涛涛,夏洲,等.基于随机共振和经验模态分解的水力发电机组振动故障诊断[J].水利学报,2017,48(3):334-340.JIA Rong,LI Taotao,XIA Zhou,et al.Fault diagnosis of hydroelectric generating set based on stochastic resonance and empirical mode decomposition[J].Journal of Hydraulic Engineering,2017,48(3):334-340.
[4]ZHANG X,ZHOU J,GUO J,et al.Vibrant fault diagnosis for hydroelectric generator units with a new combination of rough sets and support vector machine[J].Expert Systems With Applications,2012,39(3):2621-2628.
[5]何洋洋,贾嵘,李辉,等.基于随机共振和多维度排列熵的水电机组振动故障诊断[J].水力发电学报,2015,34(12):123-130.HE Yangyang,JIA Rong,LI Hui,et al.Fault diagnosis of hydroelectric generating units based on stochastic resonance and multi-dimensional permutation entropy[J].Jounal of Hydroelectric Engineering,2015,34(12):123-130.
[6]杨永锋.经验模态分解在振动分析中的应用[M].北京:国防工业出版社,2013.
[7]桂中华,韩凤琴.小波包特征熵神经网络在尾水管故障诊断中的应用[J].中国电机工程学报,2005,25(4):99-102.GUI Zhonghua,HAN Fengqin.Application of wavelet packet feature entropy neural network in fault diagnosis of draft pipe[J].Chinese Journal of Electrical Engineering,2005,25(4):99-102.
[8]张克危,林雯婷.小波变换及其在水轮机水压脉动信号处理中的应用[J].大电机技术,2002(6):47-53.ZHANG Kewei,LIN Wenting.Wavelet transform and its application in hydraulic pulsating signal processing of hydraulic turbine[J].Large Electric Machine Technology,2002(6):47-53.
[9]康守强,王玉静,杨广学,等.基于经验模态分解和超球多类支持向量机的滚动轴承故障诊断方法[J].中国电机工程学报,2011,31(14):96-102.KANG Shouqiang,WANG Yujing,YANG Guangxue,et al.Fault diagnosis method of rolling bearing based onempirical mode decomposition and hypersphere support vector machine[J].Chinese Journal of Electrical Engineering,2011,31(14):96-102.
[10]马富齐,贾嵘,武桦,等.基于复数据的EMD在水导轴承故障诊断中的应用[J].水力发电学报,2017,36(2):75-82.MA Fuqi,JIA Rong,WU Hua,et al.Application of EMD based on complex data in fault diagnosis of aqueduct bearing[J].Journal of Hydroelectric Engineering,2017,36(2):75-82.
[11]李辉,李欣同,贾嵘,等.基于经验模态分解和支持向量机的水电机组振动故障诊断[J].水力发电学报,2016,35(12):105-111.LI Hui,LI Xintong,JIA Rong,et al.Fault diagnosis of hydroelectric generating set based on empirical mode decomposition and support vector machine[J].Journal of Hydroelectric Engineering,2016,35(12):105-111.
[12]Dragomiretskiy K,Zosso D.Variational mode decomposition[J].IEEE Transactions on Signal Processing,2014,62(3):531-544.
[13]马增强,李亚超,刘政,等.基于变分模态分解和Teager能量算子的滚动轴承故障特征提取[J].振动与冲击,2016,35(13):134-139.MA Zengqiang,LI Yachao,LIU Zheng,et al.Fault extraction of rolling bearing based on variational modal decomposition and Teager Energy Operator[J].Journal of Vibration and Shock,2016,35(13):134-139.
[14]WANG Y,Markert R,Xiang J,et al.Research on variational mode decomposition and its application in detecting rubimpact fault of the rotor system[J].Mechanical Systems&Signal Processing,2015,60:243-251.
[15]党建,何洋洋,贾嵘,等.水轮发电机组非平稳振动信号的检测与故障诊断[J].水利学报,2016,47(2):173-179.DANG Jian,HE Yangyang,JIA Rong,et al.Detection for non-stationary vibration signaland fault diagnosis of hydropower unit[J].Jounal of Hydraulic Engineering,2016,47(2):173-179.
[16]武英杰.基于变分模态分解的风电机组传动系统故障诊断研究[D].北京:华北电力大学,2016.