机械设备运行故障预测方法综述
|
摘要
介绍了基于设备运行状态的故障预测方法,将基于设备运行状态的故障预测与维护过程归纳为数据获取、数据处理和设备剩余寿命预测三个步骤。从传感器检测的时间间隔和传感器的使用数量等方面阐述了数据的获取方法。归纳介绍了目前国内外常见的数据处理和分析技术。介绍了设备故障诊断、预测和有效寿命预测技术中常见的统计方法、人工智能方法和基于模型的预测方法。
The occurrence of mechanical equipment fault is inevitable.To reduce failure time and fault maintainance times of equipment,this paper introduced equipment operation condition based fault prognostic approach,and categorized the equipment fault prognosis based process into three steps: data aquisition,data process and equipment remain life prognosis.To gurantee the accurancy and comprehensiveness of the equipment operation condition monitoring data,this paper introduced the data aquisition approach from the aspect of sensor inspection time interval and sensor number;concluded the frequently applied data process and analysis technology over the world;introduced the frequently applied statistical approach,artificial intelligent approach and model based prognostic approach of equipment remain life prognositic technology.
The occurrence of mechanical equipment fault is inevitable.To reduce failure time and fault maintainance times of equipment,this paper introduced equipment operation condition based fault prognostic approach,and categorized the equipment fault prognosis based process into three steps: data aquisition,data process and equipment remain life prognosis.To gurantee the accurancy and comprehensiveness of the equipment operation condition monitoring data,this paper introduced the data aquisition approach from the aspect of sensor inspection time interval and sensor number;concluded the frequently applied data process and analysis technology over the world;introduced the frequently applied statistical approach,artificial intelligent approach and model based prognostic approach of equipment remain life prognositic technology.
引文
[1]John Moubray,Reliability-Centered Maintenance[M].2nd edn,Industrial Press,New York,1997.
[2]R.C.M.Yam,P.W.Tse,L.Li,P.Tu,Intelligent predictive de-cision support system for condition-based maintenance[J].Inter-nationalJournal of Advanced Manufacturing Technology,2001,(17):383–391.
[3]陈珊,王太勇,王国锋,等.机械设备智能诊断与预测维修系统[J].西南交通大学学报,2003,38(5):540-543.
[4]Alexandre Muller.On the concept of e-maintenance:Review and current research[J].Reliability Engineering&System Safety,2008,(93):1165-1187.
[5]J.Lee,R.Abujamra,A.K.S.Jardine,D.Lin,D.Banjevic,An integrated platform for diagnostics,prognostics and mainte-nance optimization[C],in:The IMS’2004International Con-ference on Advances in Maintenance and in Modeling,Simulation and Intelligent Monitoring of Degradations,Arles,France,2004.
[6]Andrew K.S.Jardine,A review on machinery diagnostics and prognostics implementing condition-based maintenance[J].Me-chanical Systems and Signal Processing,2006,(20):1483-1510.
[7]熊彦铭,李世玲,李军,等.多传感器时间控制系统的数据融合新算法[J].弹箭与制导学报,2012,32(1):171-174.
[8]陆宝春,张卫,孙宇.制造系统智能前端的研究[J].机械科学与技术,2004,23(9):1057-1059.
[9]S.Goldman,Vibration Spectrum Analysis:A Practical Approach[M],Industrial Press,New York,1999.
[10]A.H.Christer,W.Wang,A simple condition monitoring mod-el for a direct monitoring process[J].European Journal of Op-erationalResearch,1995,(82):258–269.
[11]W.Wang,Modelling condition monitoring intervals:A hybrid of simulation and analytical approaches[J].Journal of the Op-erational Research Society,2003,(54):273–282.
[12]R.Xu,C.Kwan,Robust isolation of sensor failures[J].AsianJournal of Control2003,(5):12–23.
[13]G.O.Allgood,B.R.Upadhyaya,A model-based high-frequen-cy matched filter arcing diagnostic system based on principal component analysis(PCA)clustering[C].Applications and Science of Computational Intelligence III,vol.4055,Belling-ham,2000,:430–440.
[14]陈后金,胡健,薛健.信号与系统[M].2版.北京:北方交通大学出版社,2003.
[15]Hong Thom Pham,Van Tung Tran,Bo-Suk Yang,A hybrid of nonlinear autoregressive model with exogenous input and autore-gressive moving average model for long-term machine state fore-casting[J].Exerpt Systems with Applications,2010,(37):3310-3317.
[16]姜浩,郭学东,张艳辉.基于时域分析的风载激励下桥梁结构动力特性识别[J].吉林大学学报(工学版),2011,41(5):1279-1283.
[17]Chin-Sheng Chen,Jian-Shiu Chen,Rotor fault diagnosis system based on sGA-based individual neural networks[J].Expert Systems with Applications,2011,(38):10822-10830.
[18]蒋培,温熙森,陈循.非高斯随机应力载荷频域疲劳寿命估计方法[J].机械工程学报,2006,42(2):51-56.
[19]Keith Worden,Wieslaw J.Staszewski,James J.Hensman,Natural computing for mechanical systems research:A tutorial overview[J].Mechanical Systems and Signal Processing,2011,(25):4-111.
[20]C.sidney Burrus,Ramesh A.Gopinath著.小波与小波变换导论[M].程正兴译.北京:机械工业出版社,2007.
[21]Hasan Ocak,Kenneth A.Loparo,Fred M.Discenzo,Online tracking of bearing wear using wavelet packet decomposition and probabilistic modeling:A method for bearing prognostics[J].Journal of Sound and Vibration,2007,(302):951-961.
[22]Baoping Tang,Wenyi Liu,Tao Song,Wind turbine fault diag-nosis based on Morlet wavelet transformation and Wigner-Ville distribution[J].Renewable Energy,2010,(35):2862-2866.
[23]别锋锋,王奉涛,吕凤霞.基于局域波时频图像处理技术的压缩机故障诊断[J].农业机械学报,2007,38(9):159-162.
[24]邰学勇,常胜利,沈曦,等.紫外图像处理在飞机引擎故障诊断中的研究[J].仪器仪表学报,2007,27(6):410-412.
[25]D.Banjevic,A.K.S.Jardine.Calculation of reliability func-tion and remaining useful life for a Markov failure time process[J].IMA journal of management mathematics,2006,17(2):115-130.
[26]K.B.Goode,J.Moore,B.J.Roylance,Plant machinery working life prediction method utilizing reliability and condition-monitoringdata[J],Proceedings of the Institution of Mechanical Engineers Part E—Journal of Process Mechanical Engineering,2000,(214):109–122.
[27]赵洪山,胡庆春,李志为.基于统计过程控制的风机齿轮箱故障预测[J].电力系统保护与控制,2012,40(13):67-73.
[28]Enrico Zio,Francesco Di Maio,A data-driven fuzzy approach for predicting the remaining useful life in dynamic failure sce-narios of a nuclear system[J],Reliability Engineering&System Safety,2010,(95):49-57.
[29]王太勇,汪文津,范胜波,等.基于人工神经网络的车削切屑形态预测动态建模及实时仿真[J].制造技术与机床,2005,(10):48-51.
[30]P.Wang,G.Vachtsevanos,Fault prognostics using dynamic wavelet neural networks[J].AI EDAM-Artificial Intelligence for Engineering Design Analysis and Manufacturing,2001,(15):349–365.
[31]凌维业,贾民平,许飞云.粗糙集神经网络故障诊断系统的优化方法研究[J].中国电机工程学报,2003,23(5):98-102.
[32]Jiangzhong Sun,Hongfu Zuo,Wenbin Wang,et al.Application of a state space modeling technique to system prognostics based on a health index for condition-based maintenance[J].Mechan-ical Systems and Signal Processing,2012,(28):585-596.
[33]Wahyu Caesarendra,Achmad Widodo,Bo-Suk Yang,Combi-nation of probability approach and support vector machine to-wards machine health prognostics[J].Probabilistic Engineering Mechanics,2011,(26):165-173.
[34]A.Ray,S.Tangirala,Stochastic modeling of fatigue crack dy-namics for on-line failure prognostics[J].IEEE Transactions on Control Systems Technology,1996,(4):443–451.
[35]C.H.Oppenheimer,K.A.Loparo,Physically based diagnosis and prognosis of cracked rotor shafts[C],Component and Sys-temsDiagnostics,Prognostics,and Health Management II,vol.4733,Bellingham,2002,122–132.
[2]R.C.M.Yam,P.W.Tse,L.Li,P.Tu,Intelligent predictive de-cision support system for condition-based maintenance[J].Inter-nationalJournal of Advanced Manufacturing Technology,2001,(17):383–391.
[3]陈珊,王太勇,王国锋,等.机械设备智能诊断与预测维修系统[J].西南交通大学学报,2003,38(5):540-543.
[4]Alexandre Muller.On the concept of e-maintenance:Review and current research[J].Reliability Engineering&System Safety,2008,(93):1165-1187.
[5]J.Lee,R.Abujamra,A.K.S.Jardine,D.Lin,D.Banjevic,An integrated platform for diagnostics,prognostics and mainte-nance optimization[C],in:The IMS’2004International Con-ference on Advances in Maintenance and in Modeling,Simulation and Intelligent Monitoring of Degradations,Arles,France,2004.
[6]Andrew K.S.Jardine,A review on machinery diagnostics and prognostics implementing condition-based maintenance[J].Me-chanical Systems and Signal Processing,2006,(20):1483-1510.
[7]熊彦铭,李世玲,李军,等.多传感器时间控制系统的数据融合新算法[J].弹箭与制导学报,2012,32(1):171-174.
[8]陆宝春,张卫,孙宇.制造系统智能前端的研究[J].机械科学与技术,2004,23(9):1057-1059.
[9]S.Goldman,Vibration Spectrum Analysis:A Practical Approach[M],Industrial Press,New York,1999.
[10]A.H.Christer,W.Wang,A simple condition monitoring mod-el for a direct monitoring process[J].European Journal of Op-erationalResearch,1995,(82):258–269.
[11]W.Wang,Modelling condition monitoring intervals:A hybrid of simulation and analytical approaches[J].Journal of the Op-erational Research Society,2003,(54):273–282.
[12]R.Xu,C.Kwan,Robust isolation of sensor failures[J].AsianJournal of Control2003,(5):12–23.
[13]G.O.Allgood,B.R.Upadhyaya,A model-based high-frequen-cy matched filter arcing diagnostic system based on principal component analysis(PCA)clustering[C].Applications and Science of Computational Intelligence III,vol.4055,Belling-ham,2000,:430–440.
[14]陈后金,胡健,薛健.信号与系统[M].2版.北京:北方交通大学出版社,2003.
[15]Hong Thom Pham,Van Tung Tran,Bo-Suk Yang,A hybrid of nonlinear autoregressive model with exogenous input and autore-gressive moving average model for long-term machine state fore-casting[J].Exerpt Systems with Applications,2010,(37):3310-3317.
[16]姜浩,郭学东,张艳辉.基于时域分析的风载激励下桥梁结构动力特性识别[J].吉林大学学报(工学版),2011,41(5):1279-1283.
[17]Chin-Sheng Chen,Jian-Shiu Chen,Rotor fault diagnosis system based on sGA-based individual neural networks[J].Expert Systems with Applications,2011,(38):10822-10830.
[18]蒋培,温熙森,陈循.非高斯随机应力载荷频域疲劳寿命估计方法[J].机械工程学报,2006,42(2):51-56.
[19]Keith Worden,Wieslaw J.Staszewski,James J.Hensman,Natural computing for mechanical systems research:A tutorial overview[J].Mechanical Systems and Signal Processing,2011,(25):4-111.
[20]C.sidney Burrus,Ramesh A.Gopinath著.小波与小波变换导论[M].程正兴译.北京:机械工业出版社,2007.
[21]Hasan Ocak,Kenneth A.Loparo,Fred M.Discenzo,Online tracking of bearing wear using wavelet packet decomposition and probabilistic modeling:A method for bearing prognostics[J].Journal of Sound and Vibration,2007,(302):951-961.
[22]Baoping Tang,Wenyi Liu,Tao Song,Wind turbine fault diag-nosis based on Morlet wavelet transformation and Wigner-Ville distribution[J].Renewable Energy,2010,(35):2862-2866.
[23]别锋锋,王奉涛,吕凤霞.基于局域波时频图像处理技术的压缩机故障诊断[J].农业机械学报,2007,38(9):159-162.
[24]邰学勇,常胜利,沈曦,等.紫外图像处理在飞机引擎故障诊断中的研究[J].仪器仪表学报,2007,27(6):410-412.
[25]D.Banjevic,A.K.S.Jardine.Calculation of reliability func-tion and remaining useful life for a Markov failure time process[J].IMA journal of management mathematics,2006,17(2):115-130.
[26]K.B.Goode,J.Moore,B.J.Roylance,Plant machinery working life prediction method utilizing reliability and condition-monitoringdata[J],Proceedings of the Institution of Mechanical Engineers Part E—Journal of Process Mechanical Engineering,2000,(214):109–122.
[27]赵洪山,胡庆春,李志为.基于统计过程控制的风机齿轮箱故障预测[J].电力系统保护与控制,2012,40(13):67-73.
[28]Enrico Zio,Francesco Di Maio,A data-driven fuzzy approach for predicting the remaining useful life in dynamic failure sce-narios of a nuclear system[J],Reliability Engineering&System Safety,2010,(95):49-57.
[29]王太勇,汪文津,范胜波,等.基于人工神经网络的车削切屑形态预测动态建模及实时仿真[J].制造技术与机床,2005,(10):48-51.
[30]P.Wang,G.Vachtsevanos,Fault prognostics using dynamic wavelet neural networks[J].AI EDAM-Artificial Intelligence for Engineering Design Analysis and Manufacturing,2001,(15):349–365.
[31]凌维业,贾民平,许飞云.粗糙集神经网络故障诊断系统的优化方法研究[J].中国电机工程学报,2003,23(5):98-102.
[32]Jiangzhong Sun,Hongfu Zuo,Wenbin Wang,et al.Application of a state space modeling technique to system prognostics based on a health index for condition-based maintenance[J].Mechan-ical Systems and Signal Processing,2012,(28):585-596.
[33]Wahyu Caesarendra,Achmad Widodo,Bo-Suk Yang,Combi-nation of probability approach and support vector machine to-wards machine health prognostics[J].Probabilistic Engineering Mechanics,2011,(26):165-173.
[34]A.Ray,S.Tangirala,Stochastic modeling of fatigue crack dy-namics for on-line failure prognostics[J].IEEE Transactions on Control Systems Technology,1996,(4):443–451.
[35]C.H.Oppenheimer,K.A.Loparo,Physically based diagnosis and prognosis of cracked rotor shafts[C],Component and Sys-temsDiagnostics,Prognostics,and Health Management II,vol.4733,Bellingham,2002,122–132.