面向多故障诊断的分层架构及其实现
|
摘要
多故障并发时,故障征兆表现复杂,并非多个单故障征兆的简单叠加,而且故障振动信号往往具有非稳态性,加大了多故障诊断的难度。为此,提出了一个面向多故障诊断的分层架构。联合应用互信息最大化准则与灰色关联分析,对待诊断的多故障与潜在的单故障模式之间的关联特性进行定量评价,据此建立候选故障集合;在此基础上,分别提取候选故障与多故障模式的小波变换能量矩特征,用于自组织映射网络的训练与测试;借助自组织映射网络的拓扑映射能力,在特征空间对耦合特征解耦分离的同时实现多故障模式的判别。实验结果表明,所提方法应用于多故障诊断是有效的。而且,它可以在多故障并发情况下对所识别出的各个单故障的严重程度进行排序,有利于制定合理的维修决策。
When multiple faults arise simultaneously in a machine,their fault symptoms are quite complicated,not simple superposition of symptoms of multiple single faults.Moreover,faulty vibration signals often show themselves nonstationary.All these make multi-faults diagnosis difficult.In this paper,a hierarchical architecture for multi-faults diagnosis was proposed.Based on combined of mutual information maximization and gray relation analysis,relational characteristics between multi-faults to be recognized and single potential faults were quantitatively evaluated to obtain a set of candidate faults.Then wavelet transformation energy moments were extracted from the candidate faults and the multi-faults.They were used for training and testing a self-organizing map network.Finally,coupled features were decoupled and separated in feature space by the self-organizing map network with powerful performance on topologically mapping.At the same time,multi-faults was recognized.Experimental results show that the proposed architecture is effective on multi-faults diagnosis.It is capable of sorting the recognized single faults according to their severity,under concurrency of multiple faults,which helps making a reasonable maintenance decision.
When multiple faults arise simultaneously in a machine,their fault symptoms are quite complicated,not simple superposition of symptoms of multiple single faults.Moreover,faulty vibration signals often show themselves nonstationary.All these make multi-faults diagnosis difficult.In this paper,a hierarchical architecture for multi-faults diagnosis was proposed.Based on combined of mutual information maximization and gray relation analysis,relational characteristics between multi-faults to be recognized and single potential faults were quantitatively evaluated to obtain a set of candidate faults.Then wavelet transformation energy moments were extracted from the candidate faults and the multi-faults.They were used for training and testing a self-organizing map network.Finally,coupled features were decoupled and separated in feature space by the self-organizing map network with powerful performance on topologically mapping.At the same time,multi-faults was recognized.Experimental results show that the proposed architecture is effective on multi-faults diagnosis.It is capable of sorting the recognized single faults according to their severity,under concurrency of multiple faults,which helps making a reasonable maintenance decision.
引文
[1]王国彪,何正嘉,陈雪峰,等.机械故障诊断基础研究“何去何从”[J].机械工程学报,2012,49(1):63-72.WANG G B,HE ZH J,CHEN X F,et al.Basic research on machinery fault diagnosis-what is the prescription[J].Journal of Mechanical Engineering,2012,49(1):63-72.
[2]PATEL T H,DARPE A K.Coupled bending-torsional vibration analysis of rotor with rub and crack[J].Journal of Sound and Vibration,2009,326(3):740-752.
[3]PATEL T H,DARPE A K.Vibration response of a cracked rotor in presence of rotor-stator rub[J].Journal of Sound and Vibration,2008,317(3):841-865.
[4]JIAO W D,QIAN S X,CHANG Y P,et al.Research on vibration response of a multi-faulted rotor system using LMD-based time-frequency representation[J].Eurasip Journal on Advances in Signal Processing,2012(1):73-83.
[5]焦卫东,蒋永华,施继忠,等.一种旋转机械系统耦合故障诊断的新方法[J].仪器仪表学报,2016,37(7):1449-1456.JIAO W D,JIANG Y H,SHI J ZH,et al.New approach for diagnosis on coupled faults of rotating machine system[J].Chinese Journal of Scientific Instrument,2016,37(7):1449-1456.
[6]黄为勇,王义,田秀玲,等.一种基于SVR的发动机多模式故障诊断方法[J].仪器仪表学报,2015,36(9):2112-2119.HUANG W Y,WANG Y,TIAN X L,et al.Multi-mode engine fault diagnosis method based on SVR[J].Chinese Journal of Scientific Instrument,2015,36(9):2112-2119.
[7]姜媛媛,王友仁,吴讳,等.基于小波包能量谱和ELM的光伏逆变器多故障在线诊断[J].仪器仪表学报,2015,36(9):2145-2152.JIANG Y Y,WANG Y R,WU H,et al.Online multiple fault diagnosis for PV inverter based on wavelet packet energy spectrum and extreme learning machine[J].Chinese Journal of Scientific Instrument,2015,36(9):2145-2152.
[8]谢骏遥,王金江,赵锐,等.迁移因子分析在齿轮箱变工况故障诊断中的应用[J].电子测量与仪器学报,2016,30(4):534-541.XIE J Y,WANG J J,ZHAO R,et al.Application of transfer factor analysis in gearbox fault diagnosis under various working condition[J].Journal of Electronic Measurement and Instrumentation,2016,30(4):534-541.
[9]徐元博,蔡宗琰.三点对称差分能量算子与经验小波变换在轴承故障诊断中的应用[J].电子测量与仪器学报,2017,31(8):1247-1256.XU Y B,CAI Z Y.Application of demodulation energy operator of symmetrical differencing and empirical wavelet transform in bearing fault diagnosis[J].Journal of Electronic Measurement and Instrumentation,2017,31(8):1247-1256.
[10]许爱华,闫俊泉,伍旭灿,等.基于VMD和MP算法的旋转机械故障特征提取[J].国外电子测量技术,2017,36(8):11-17.XU AI H,YAN J Q,WU X C,et al.Rotating machinery fault feature extraction based on VMD and MP algorithm[J].Foreign Electronic Measurement Technology,2017,36(8):11-17.
[11]范晓鹏,蔡铁峰,朱枫.实现人眼灰度感知信息最大化的图像增强算法[J].计算机辅助设计与图形学学报,2015,27(10):1900-1906.FAN X P,CAI T F,ZHU F.Image enhancement algorithm for achieving maximum of perceived grayscale information of human visual system[J].Journal of Computer-Aided Design&Computer Graphics,2015,27(10):1900-1906.
[12]朱霞,陈仁文,夏桦康,等.基于文化粒子群的图像配准优化算法[J].兵工学报,2015,36(6):1033-1039.ZHU X,CHEN R W,XIA H K,et al.A novel image registration based on cultural particle swarm optimization algorithm[J].Acta Armamentarii,2015,36(6):1033-1039.
[13]赵永宁,叶林.区域风电场短期风电功率预测的最大相关-最小冗余数值天气预报特征选取策略[J].中国电机工程学报,2015,35(23):5985-5994.ZHAO Y N,YE L.A numerical weather prediction feature selection approach based on minimal-redundancymaximal-relevance strategy for short-term regional wind power prediction[J].Proceedings of the CSEE,2015,35(23):5985-5994.
[14]刘明才.小波分析及其应用[M].第2版.北京:清华大学出版社,2013.LIU M C.Wavelet analysis and its application[M].The2nd Edition.Beijing:Tsinghua University Press,2013.
[15]程军圣,罗颂荣,杨斌,等.LMD能量矩和变量预测模型模式识别在轴承故障智能诊断中的应用[J].振动工程学报,2013,26(5):571-757.CHENG J SH,LUO S R,YANG B,et al.LMD energy moment and variable predictive model based class discriminate and their application in intelligent fault diagnosis of roller bearing[J].Journal of Vibration Engineering,2013,26(5):751-757.
[16]KOHONEN T.The self-organizing map[J].Proceedings of the IEEE,1990,78(9):1464-1480.
[17]RIVERA D,SANDOVAL M,GODOY A.Exploring soil databases:A self-organizing map approach[J].Soil Use and Management,2015,31(1):121-131.
[18]PIERPAOLO D,GIOVANNI L D,MASSARI R.Selforganizing maps for imprecise data[J].Fuzzy Sets and Systems,2014,237(2):63-89.
[19]EZEQUIEL L R,ANTONIO D R.Grid topologies for the self-organizing map[J].Neural Networks,2014,56(8):35-48.
[2]PATEL T H,DARPE A K.Coupled bending-torsional vibration analysis of rotor with rub and crack[J].Journal of Sound and Vibration,2009,326(3):740-752.
[3]PATEL T H,DARPE A K.Vibration response of a cracked rotor in presence of rotor-stator rub[J].Journal of Sound and Vibration,2008,317(3):841-865.
[4]JIAO W D,QIAN S X,CHANG Y P,et al.Research on vibration response of a multi-faulted rotor system using LMD-based time-frequency representation[J].Eurasip Journal on Advances in Signal Processing,2012(1):73-83.
[5]焦卫东,蒋永华,施继忠,等.一种旋转机械系统耦合故障诊断的新方法[J].仪器仪表学报,2016,37(7):1449-1456.JIAO W D,JIANG Y H,SHI J ZH,et al.New approach for diagnosis on coupled faults of rotating machine system[J].Chinese Journal of Scientific Instrument,2016,37(7):1449-1456.
[6]黄为勇,王义,田秀玲,等.一种基于SVR的发动机多模式故障诊断方法[J].仪器仪表学报,2015,36(9):2112-2119.HUANG W Y,WANG Y,TIAN X L,et al.Multi-mode engine fault diagnosis method based on SVR[J].Chinese Journal of Scientific Instrument,2015,36(9):2112-2119.
[7]姜媛媛,王友仁,吴讳,等.基于小波包能量谱和ELM的光伏逆变器多故障在线诊断[J].仪器仪表学报,2015,36(9):2145-2152.JIANG Y Y,WANG Y R,WU H,et al.Online multiple fault diagnosis for PV inverter based on wavelet packet energy spectrum and extreme learning machine[J].Chinese Journal of Scientific Instrument,2015,36(9):2145-2152.
[8]谢骏遥,王金江,赵锐,等.迁移因子分析在齿轮箱变工况故障诊断中的应用[J].电子测量与仪器学报,2016,30(4):534-541.XIE J Y,WANG J J,ZHAO R,et al.Application of transfer factor analysis in gearbox fault diagnosis under various working condition[J].Journal of Electronic Measurement and Instrumentation,2016,30(4):534-541.
[9]徐元博,蔡宗琰.三点对称差分能量算子与经验小波变换在轴承故障诊断中的应用[J].电子测量与仪器学报,2017,31(8):1247-1256.XU Y B,CAI Z Y.Application of demodulation energy operator of symmetrical differencing and empirical wavelet transform in bearing fault diagnosis[J].Journal of Electronic Measurement and Instrumentation,2017,31(8):1247-1256.
[10]许爱华,闫俊泉,伍旭灿,等.基于VMD和MP算法的旋转机械故障特征提取[J].国外电子测量技术,2017,36(8):11-17.XU AI H,YAN J Q,WU X C,et al.Rotating machinery fault feature extraction based on VMD and MP algorithm[J].Foreign Electronic Measurement Technology,2017,36(8):11-17.
[11]范晓鹏,蔡铁峰,朱枫.实现人眼灰度感知信息最大化的图像增强算法[J].计算机辅助设计与图形学学报,2015,27(10):1900-1906.FAN X P,CAI T F,ZHU F.Image enhancement algorithm for achieving maximum of perceived grayscale information of human visual system[J].Journal of Computer-Aided Design&Computer Graphics,2015,27(10):1900-1906.
[12]朱霞,陈仁文,夏桦康,等.基于文化粒子群的图像配准优化算法[J].兵工学报,2015,36(6):1033-1039.ZHU X,CHEN R W,XIA H K,et al.A novel image registration based on cultural particle swarm optimization algorithm[J].Acta Armamentarii,2015,36(6):1033-1039.
[13]赵永宁,叶林.区域风电场短期风电功率预测的最大相关-最小冗余数值天气预报特征选取策略[J].中国电机工程学报,2015,35(23):5985-5994.ZHAO Y N,YE L.A numerical weather prediction feature selection approach based on minimal-redundancymaximal-relevance strategy for short-term regional wind power prediction[J].Proceedings of the CSEE,2015,35(23):5985-5994.
[14]刘明才.小波分析及其应用[M].第2版.北京:清华大学出版社,2013.LIU M C.Wavelet analysis and its application[M].The2nd Edition.Beijing:Tsinghua University Press,2013.
[15]程军圣,罗颂荣,杨斌,等.LMD能量矩和变量预测模型模式识别在轴承故障智能诊断中的应用[J].振动工程学报,2013,26(5):571-757.CHENG J SH,LUO S R,YANG B,et al.LMD energy moment and variable predictive model based class discriminate and their application in intelligent fault diagnosis of roller bearing[J].Journal of Vibration Engineering,2013,26(5):751-757.
[16]KOHONEN T.The self-organizing map[J].Proceedings of the IEEE,1990,78(9):1464-1480.
[17]RIVERA D,SANDOVAL M,GODOY A.Exploring soil databases:A self-organizing map approach[J].Soil Use and Management,2015,31(1):121-131.
[18]PIERPAOLO D,GIOVANNI L D,MASSARI R.Selforganizing maps for imprecise data[J].Fuzzy Sets and Systems,2014,237(2):63-89.
[19]EZEQUIEL L R,ANTONIO D R.Grid topologies for the self-organizing map[J].Neural Networks,2014,56(8):35-48.