基于全矢谱的故障预测关键技术研究
|
摘要
随着科学技术和工业技术的飞速发展,各种设备的自动化程度越来越高,功能也愈加完善,设备的复杂程度也越来越高,对提取的与设备状态有关的信号的准确度要求也越来越高。实践表明,传统的单通道信号分析技术已经不能满足工业现场对设备状态检测与故障诊断高准确性、高可靠性的要求。针对旋转机械单源振动信号包含信息不完整的缺陷,基于数据融合思想的全信息数据处理及故障诊断技术应运而生。其中基于数据层融合技术的全矢谱分析技术能够全面地表达转子振动的强度和频谱结构,并且其图谱表现形式与传统频谱分析方法相兼容,与其它全信息技术相比,具有独特的优势。
在设备状态预测领域,针对旋转机械单源振动信号包含信息不完整的缺陷,基于数据融合思想,将全矢谱技术分别与时间序列自回归AR(n)模型、基于最小二乘参数估计的线性拟合模型、简单滑动平均预测模型、指数平滑预测模型等预测技术相结合,提出了基于全矢谱技术的时间序列自回归AR(n)模型、基于全矢谱技术的线性拟和、基于全矢谱技术的简单滑动平均、基于全矢谱技术的指数平滑法预测方法,分别给出其计算方法及参数优化算法并加以分析比较。结果表明,基于全矢谱的预测方法相比传统单通道预测方法在各个频段上预测精度一致性更高,能够更加全面、准确地反映设备运行状态的发展趋势,是一种准确、有效、实用的旋转机械状态预测方法。
本文以全矢谱的预测理论为基础,以构建设备点检预测系统为目标,在Windows操作系统平台下,利用Visual C++程序开发工具以及SQL Server 2000数据库工具建立了基于全矢谱技术的设备状态预测系统,实现了历史数据的波形、频谱显示及预测分析。这对设备状态预测以及故障早期预测在工程实际中的实现以及全信息预测技术在工程实际中的应用有着非常重要的意义。
As science and technology and the rapid development of industrial technology, a variety of increasingly high degree of automation equipment, its function has become even more perfect, which increasing the complexity in the monitoring equipment, increasingly high demands on the accuracy of testing and fault diagnosis of signals. Practice has shown that the traditional single-channel signal analysis techniques cannot meet the requirements of high accuracy and high reliability. For the defects of incomplete information of single source vibration signals of rotating machinery, full information data processing and fault diagnosis technology came into being which based on data fusion. The technique of vector spectrum which based on the data level fusion can fully express vibration strength and frequency structure, and its expression pattern is compatible with the traditional method of spectrum analysis, has an unparalleled advantage.
In the field of equipment status forecast, for the defects of incomplete information of single source vibration signals of rotating machinery, based on the method of data fusion, combing the vector spectrum technology with the time sequence autoregressive AR(n) model, parameter estimation based on least squares linear regression model, simple sliding smoothing forecasting model, exponential smoothing forecasting models combining prediction, proposed the time sequence autoregressive AR(n) model forecast method based on vector spectrum technology, the linear fitting forecast method based on vector spectrum technology, the simple moving average forecast method based on vector spectrum technology, the exponential smoothing forecast method based on vector spectrum technology, respectively give computational method and parameter optimization algorithms and to compare them. The results show that the spectrum prediction method based on vector spectrum technology has higher prediction accuracy in each frequency bands which can comprehensively and accurately reflect the state of the development trend of mechanical operation, is an accurate, effective, practical prediction method of rotating machinery.
This article based on the prediction theory of vector spectrum technology, to the goal of building an equipment of inspection forecasting system, in the Windows operating system platform, using the Visual C++ programs development tools and SQL Server 2000 database tools to build an equipment condition forecasting system based on vector spectrum technology which realize the historical data, waveform, spectrum display, and prediction analysis. This work has a very important significance to the prediction of the equipment state and early prediction of the realization in engineering practice and full information forecasting techniques in practical application of engineering.
在设备状态预测领域,针对旋转机械单源振动信号包含信息不完整的缺陷,基于数据融合思想,将全矢谱技术分别与时间序列自回归AR(n)模型、基于最小二乘参数估计的线性拟合模型、简单滑动平均预测模型、指数平滑预测模型等预测技术相结合,提出了基于全矢谱技术的时间序列自回归AR(n)模型、基于全矢谱技术的线性拟和、基于全矢谱技术的简单滑动平均、基于全矢谱技术的指数平滑法预测方法,分别给出其计算方法及参数优化算法并加以分析比较。结果表明,基于全矢谱的预测方法相比传统单通道预测方法在各个频段上预测精度一致性更高,能够更加全面、准确地反映设备运行状态的发展趋势,是一种准确、有效、实用的旋转机械状态预测方法。
本文以全矢谱的预测理论为基础,以构建设备点检预测系统为目标,在Windows操作系统平台下,利用Visual C++程序开发工具以及SQL Server 2000数据库工具建立了基于全矢谱技术的设备状态预测系统,实现了历史数据的波形、频谱显示及预测分析。这对设备状态预测以及故障早期预测在工程实际中的实现以及全信息预测技术在工程实际中的应用有着非常重要的意义。
As science and technology and the rapid development of industrial technology, a variety of increasingly high degree of automation equipment, its function has become even more perfect, which increasing the complexity in the monitoring equipment, increasingly high demands on the accuracy of testing and fault diagnosis of signals. Practice has shown that the traditional single-channel signal analysis techniques cannot meet the requirements of high accuracy and high reliability. For the defects of incomplete information of single source vibration signals of rotating machinery, full information data processing and fault diagnosis technology came into being which based on data fusion. The technique of vector spectrum which based on the data level fusion can fully express vibration strength and frequency structure, and its expression pattern is compatible with the traditional method of spectrum analysis, has an unparalleled advantage.
In the field of equipment status forecast, for the defects of incomplete information of single source vibration signals of rotating machinery, based on the method of data fusion, combing the vector spectrum technology with the time sequence autoregressive AR(n) model, parameter estimation based on least squares linear regression model, simple sliding smoothing forecasting model, exponential smoothing forecasting models combining prediction, proposed the time sequence autoregressive AR(n) model forecast method based on vector spectrum technology, the linear fitting forecast method based on vector spectrum technology, the simple moving average forecast method based on vector spectrum technology, the exponential smoothing forecast method based on vector spectrum technology, respectively give computational method and parameter optimization algorithms and to compare them. The results show that the spectrum prediction method based on vector spectrum technology has higher prediction accuracy in each frequency bands which can comprehensively and accurately reflect the state of the development trend of mechanical operation, is an accurate, effective, practical prediction method of rotating machinery.
This article based on the prediction theory of vector spectrum technology, to the goal of building an equipment of inspection forecasting system, in the Windows operating system platform, using the Visual C++ programs development tools and SQL Server 2000 database tools to build an equipment condition forecasting system based on vector spectrum technology which realize the historical data, waveform, spectrum display, and prediction analysis. This work has a very important significance to the prediction of the equipment state and early prediction of the realization in engineering practice and full information forecasting techniques in practical application of engineering.
引文
[1]钟秉林,黄仁.机械故障诊断学(第3版)[M].北京：机械工业出版社,2006,1～2
[2]王江萍.机械设备故障诊断技术及应用[M].西安：西北工业大学出版社,2001,8～11
[3]张正松,傅尚新,冯冠平等.旋转机械振动监测及故障诊断[M].北京：机械工业出版社,1991,1～3
[4]屈梁生,何正嘉.机械故障诊断学[M].上海：上海科学技术出版社,1996
[5]张瑞林.机械设备故障诊断技术的现状与发展趋势[J].振动工程学报,1998,Vol.11(s)：1～5
[6]李国华,张永忠.机械故障诊断[M]．北京：化工工业出版社,1999,120～133
[7]Dcollacott R A.Mechanical Fault Diagnosis and Condition Monitoring[J]. London:Chapman and Hall,1977
[8]陈大禧,朱铁光.大型回转机械诊断现场实用技术[M]．北京：机械工业出版社,2002,6.242～244
[9]韩捷,石来德.全矢谱技术及工程应用[M]．北京：机械工业出版社,2008
[10]薛子云,杨江天,朱衡君.机械故障预测模型综述[J].机械强度2006,Vol.28(s)：60～65
[11]蒋瑜,杨雪,阮启明.机械设备故障规律及运行趋势预测方法综述[J].机电一体化,2001,(3)：14～17
[12]潘红宇.时间序列分析[M].北京：对外经济贸易大学出版社,2006.41～47
[13]徐大江.预测模型参数的指数平滑估计法及其应用的进一步研究[J].系统工程理论与实践,1999, Vol.19 (2):1～7
[14]张树京,齐立心.时间序列分析简明教程[M].北京：北方交通大学出版社,2003：1～2
[15]戴中华.基于时序分析的风机故障预测的研究[D].[硕士学位论文].长沙：中南大学,2006
[16]Granpe D.Time series analysis:Identification and adptive filtering[M].Malabar:Krieger. Pub.co,1989
[17]陈仲生,杨拥民,胡政.基于几乎周期时变AR模型的故障早期预报[J].机械工程学报,2005, Vol.41 (1):184～188
[18]杨叔子,吴雅,轩建平,等.时间序列分析的工程应用(上册)[M].华中科技大学出版社2007,6.50～52
[19]刘思峰,郭天榜,党耀国.灰色系统理论及其应用(第2版)[M].北京：科学出版社,1999
[20]靳春梅,樊灵,邱阳,等.灰色理论在旋转机械故障诊断与预报中的应用[J].应用力学学报,2000, Vol.17 (3):74～79
[21]杨江天,岳维亮.灰色模型在机械故障预测中的应用[J].机械强度,2001, Vol.23 (3): 277～279
[22]赵荣珍,孟凡明,张优云.机械振动趋势的灰色预测模型研究[J].机械科学与技术,2004,Vol.23 (3):256～259
[23]Zhang Siyu, Ganesan R.Multivariable trend analysis for system monitoring through self-organizing neural networks Trans of the ASME[J].Journal of Dynamic Systems, Measurement, and Control,1997, Vol.119 (2):223～228
[24]C.A.Kulikowski.Artificial Intelligence Methods And Systems for Medical Consultation[J]. IEEE Trans.On pattern analysis and Machine Intelligence,1980, PAMI-2(5):465～476
[25]Mohamed A.Awadallah, Medhat, M Morcos.Application of AI Tools in Fault Diagnosis of Electrical Machines and Drives—An Overview[J].IEEE Trans.On Energy Conversion, June 2003,52(4):1076～1098
[26]叶强,夏哲雷,卫力.基于神经网络趋势分析[J].中国计量学院学报,2000, Vol.2 (11):177-181
[27]Nahvi H, Esfahanian M. Fault identification in rotating machinery using artificial neural networks. Proceedings of the Institution of Mechanical Engineers, Part C:Journal of Mechanical Engineering Science,2005, Vol.219 (2):141～158.
[28]杜耀武,蒋伟康.基于人工神经网络的大型机械系统的剩余寿命预报模型[J].机械强度,1997, Vol.19 (1):5～8
[29]Venkasubramanian Venkat, Chan King. A neural network methodology for process fault diagnosis. Journal of AIChE.1989, Vol.35(12):1993～2002
[30]Timo S, Heikki N K, Hannu K.Neural networks in process fault diagnosis[J].IEEE Trans.on SMC,1991, Vol.21(4):815～825
[31]肖健华,樊可清,吴今培.应用于故障诊断的SVM理论研究[J].振动、测试与诊断,2001,Vol.21(4)：258～262
[32]边肇祺,张学工.模式识别[M](第二版)．北京：清华大学出版社,2000
[33]李凌均,张周锁,何正嘉.基于支持向量机的机械设备状态趋势预测研究[J].西安交通大学学报,2004, Vol.38 (3):230～233
[34]Chen B J, Chang M W, Lin C J.Load forecasting using support vector machines:a study on EUNITE competition 2001 [J].Taiwan:Department of Computer Science and Information Engineering, Taiwan University,2002:1～11
[35]杨俊燕,张优云,赵荣珍.支持向量机在机械设备振动信号趋势分析中的应用[J].西安交通大学学报,2005, Vol.39 (9):950～953
[36]关慧玲,韩捷.设备故障诊断专家系统原理及实践[M].北京：机械工业出版社,2000
[37]Ali M. Gupta V.An expert system for fault diagnosis in a space shuttle main engine[J]. AIAA-90-1990
[38]J.L.Alty and M.J.Coombs.Expert Systems Concepts and Examples[M].Ncc Pubilications, England,1982
[39]Jan Maciej Koscielny. Michal Bartys Diagnostic models of industrial processes[J]. International Journal of COMADEM,2005, Vol.8 (2):23～29
[40]陈敏泽,周东华.动态系统的故障预报技术[J].控制理论与应用,2003, Vol.20 (6):819～ 823
[41]H. O. Peitgen, Chaos and Fractals.New Frontiers of Science[J].Springer-Verlag, New York, 1992
[42]Llias J, Waltz E. Multisonsor data fusion. AltechHouse, Norwood, Massachusetts,1990
[43]BachSCbmid N, Pennacchi P, Vania A. Diagnostic significance of orbit shape analysis and its application to improve machine fault detection[J]. Journal of the Brazilian Society of Mechanical Sciences and Engineering,2004, Vol.26(2):200～208
[44]朱大奇,刘永安.故障诊断的信息融合方法[J].控制与决策,2007,12：1321～1326
[45]Qu Langsheng, Chen Yaodong, Liu Xing. The holospectrum-A new method for rotor surveillance and diagnosis[J]. Mechanical Systems and Signal Processing,1989, Vol.7(3): 255～267
[46]Don Southwick. Using Full Spectrum Plots[J].Orblt,1993,14:19～21
[47]韩捷,关惠玲,梁川等.矢谱：一种实用的旋转机械故障诊断分析方法[J].机械强度,1998,Vol.20 (3):212～215
[48]屈梁生,史东锋.全息谱十年：回顾与展望[J].振动、测试与诊断,1998, Vol.18(4):235～242
[49]杜永祚,秦志英.旋转机械动态信号全息谱分析[J].振动、测试与诊断,2002, Vol.22(2):81～88
[50]Qu Langsheng, Liu Xing, Chen Yaodong. Discovering the Holospectrum[J].Noise & Vibration Worldwide,1989, Vol.7(3):255～267
[51]Don Southwick. Using Full Spectrum Plots Part2[J].Orblt.1994,6:11～15
[52]Bon Bently. How to handle(and some cases of)forward and reverse orbits [J].Orblt,1995,9: 4-5
[53]Goldman P, Muszyka A. Application of full spectrum to rotating machinery diagnostics [J].Orbit,1999,1:17～21
[54]韩捷,石来德,董辛曼.旋转机械虚拟探头融合检测技术研究[J].中国振动工程学报,2007, Vol.5 (2),204～209
[55]韩捷,毕果,郝伟.旋转机械空间域矢谱分析方法与应用[J].机械强度,2004, Vol.26 (6):605～608
[56]韩捷,石来德.全谱分析技术及其在故障诊断中的应用[J].郑州大学学报(工学版),2002,Vol.23 (3):44～47
[57]佟德纯.工程信号处理及应用[M].上海：上海交通大学出版社,1989
[58]胡广书.现代信号处理教程[M].北京：清华大学出版社,2004
[59]Davis J M.Augmenting experience-based diagnosis with casual reasoning[J].Int. Journal of Intelligent system.1989, Vol.2(1):1～32
[60]D.Logan, J.Mathew.Using the Correlation Dimension for Vibration Fault Diagnosis of Rolling Element Bearing-1[J].Basic Concepts.Mechanical System and Signal Processing, 1996, Vol.10(3):241～250
[61]MUSZYNSKA Agnes.BENTLY, ALEX Petchenev.Vibration response of rotor supported in one rigid and one poorly lubricated fluid filmbearing[J].ORBIT,1996,17(3):7～9
[62]Beaty R F.Differentiating rotor response due to radial rubbing[J].ASME J.Vibration Acoustics, Stress, Reliability in Design.1985, Vol.107(1):151～160
[63]张文.转子动力学理论基础[M]．北京：科学出版社,1990：132～142
[64]钟一谔,何衍宗.转子动力学[M].北京：清华大学出版社,1987：165～172
[65]韩捷,石来德.旋转机械的全信息能量谱分析方法研究[J].机械强度2003, Vol.25 (4):364～368
[66]谢凯,韩捷.基于复调制的细化全矢谱分析研究[J].机械强度,2008, Vol.30(2),184～188
[67]韩捷,董辛旻,等.旋转机械同源信息倒频谱分析与应用[J].机械强度,2005, Vol.27 (4):452～455
[68]冯彩红,韩捷,李凌均.全信息小波包分析及其在旋转机械故障诊断中的应用[J].机械强度,2006, Vol.28 (5):639～642
[69]董辛旻,韩捷,石来德.非平稳短时矢谱研究及应用[J].计算机工程,2005, Vol.27 (4):452～455
[70]周宇.基于全信息技术的非平稳信号的Wigner分布及应用[D].[硕士学位论文].郑州：郑州大学,2007
[71]李中原,韩捷,雷文平,等.基于矢双谱分析的旋转机械故障诊断研究[J].汽轮机技术,2006, Vol.48(6):430～432
[72]周宇,韩捷,李志农,等.分数阶Fourier变换在滚动轴承故障诊断中的应用[J].煤矿机械,2007, Vol.28(6):112～115
[73]李军伟,韩捷,李志农,等．小波变换域双谱分析及其在滚动轴承故障诊断中的应用[J].振动与冲击,2006, Vol.25 (5):92～95
[74]韩捷,张瑞林.旋转机械故障机理及诊断技术[M]．北京：机械工业出版社,1997,63～68
[75]杜奕,卢德唐,李道伦,等.一种快速的时间序列线性拟合算法[J].中国科学技术大学学报,2007, Vol.37 (3):310～314
[76]黄玉春,黄载绿,黄本雄,等.基于FFT滑动平均极大似然发的正弦信号频率估计[J].电子与信息学报,2008, Vol.30 (4):831～834
[77]冯金巧,杨兆升,张林,等.一种自适应指数平滑动态预测模型[J].吉林大学学报(工学版),2007, Vol.37 (6):1284～1287
[78]吴德会.基于动态指数平滑模型的小批量制造过程质量预测[J].农业机械学报,2008,Vol.39 (8):164～168
[79]Day I J. Prediction of compressor performance in rotating stall[J].Engineer for Power,1978
[80]Rojas.Guzman, Carlos, Kramer, Mark A. Remote diagnosis and monitoring of complex industrial systems using a genetic algorithm approach[J].IEEE International sysmposium on Industrial Electronics,1994:363～367
[81]Caldwell N H M, Breton B C, Holburn D M.Remote instrument diagnosis on the internet[J]. IEEE Intelligent Systems,1998, Vol.13(3):70～76
[82]陈晓娜.推行设备点检制的实践与认识[J].机械管理与开发,2008, Vol.23 (3):104～105
[83]梁川,韩捷.基于数据库的便携式数据采集和管理系统[J].郑州大学学报,2002,Vol.23(4):14～16
[84]王志英.以点检制为核心的设备管理新模式[J].设备管理与维修2009,(11)：14～15
[85]Martin Fowler.Patterns of Enterprise Application Architecture[J]. Boston:Addison-Wesley, 2003
[86]信江艳,董洁.企业资产管理系统(EAM)设计与实施[M]．北京：中国铁道出版社,2005
[87]杨友东,汪琛琛.Visual C++程序设计全程指南[M].北京：电子工业出版社,2009
[88]张海涛,韩捷,李志农,等.基于全矢谱分析的故障诊断系统的开发[J].煤矿机械,2007,28(3)：185～188
[89]Futter D N.Techniques for condition monitoring of large gearboxes in the power industry [J]. INSIGHT,1995, Vol.37(8):591～594
[90]Ding Lipei, Guo Xiaosong, Zhu ZhiVirtual.Test System Based on Visual C++. ICEMI'2007 Proceedings of 2007 8th International Conference on Electronic Measurement & Instrument, 2007, Vol.2
[91]徐东方,邓飞其.基于多传感器数据融合的智能故障诊断系统[J].仪器仪表学报,2004,Vol.25 (4):404～406
[92]Bogler P L.Shafer-dempster reasoning with applications to multisensory target identification system [J].IEEE Trans.on Systems, Man and Cybernetics,1987, Vol.17(3):968～977
[93]关慧玲,张优云.转子系统振动幅度的监测[J].机械强度,2000，Vol.22(3)：180～183
[94]刘红岩.数据库技术及应用[M]．北京：清华大学出版社,2007
[95]王丽雅,董辛旻,韩捷.基于SQL Server的设备远程诊断数据库安全[J].中国设备工程,2003(4)：40～41
[96]徐枫,马国之,刘良旭.基于ADO技术的数据库访问研究与实现[J].计算机工程与设计,2004, Vol.25 (1):107～110
[97]David Sceppa.ADO编程技术[M]．北京：清华大学出版社,2001
[98]N. Narayanan, N. Viswanadham. Methodology for Knowledge acquisition and Reasoning in Failure Analysis of System[J]. Transacting on System, Man and Cybernetics,1987, Vol.17(2):274～288
[99]陈燕.组合预测方法研究及其软件系统设计与开发[D].[硕士学位论文].哈尔滨：东北农业大学,2007
[100]李洪雷,管群.基于VC的时间序列分析法的应用研究[J].计算机仿真,2009, Vol.26(7)：113～117
[101]Joentgen A, Mikenina L, Weber R, et al.Automatic fault detection in gearboxes by dynamic fuzzy data analysis[J]. Fuzzy Sets and Systems,1999, Vol.105(1):123～132
[2]王江萍.机械设备故障诊断技术及应用[M].西安：西北工业大学出版社,2001,8～11
[3]张正松,傅尚新,冯冠平等.旋转机械振动监测及故障诊断[M].北京：机械工业出版社,1991,1～3
[4]屈梁生,何正嘉.机械故障诊断学[M].上海：上海科学技术出版社,1996
[5]张瑞林.机械设备故障诊断技术的现状与发展趋势[J].振动工程学报,1998,Vol.11(s)：1～5
[6]李国华,张永忠.机械故障诊断[M]．北京：化工工业出版社,1999,120～133
[7]Dcollacott R A.Mechanical Fault Diagnosis and Condition Monitoring[J]. London:Chapman and Hall,1977
[8]陈大禧,朱铁光.大型回转机械诊断现场实用技术[M]．北京：机械工业出版社,2002,6.242～244
[9]韩捷,石来德.全矢谱技术及工程应用[M]．北京：机械工业出版社,2008
[10]薛子云,杨江天,朱衡君.机械故障预测模型综述[J].机械强度2006,Vol.28(s)：60～65
[11]蒋瑜,杨雪,阮启明.机械设备故障规律及运行趋势预测方法综述[J].机电一体化,2001,(3)：14～17
[12]潘红宇.时间序列分析[M].北京：对外经济贸易大学出版社,2006.41～47
[13]徐大江.预测模型参数的指数平滑估计法及其应用的进一步研究[J].系统工程理论与实践,1999, Vol.19 (2):1～7
[14]张树京,齐立心.时间序列分析简明教程[M].北京：北方交通大学出版社,2003：1～2
[15]戴中华.基于时序分析的风机故障预测的研究[D].[硕士学位论文].长沙：中南大学,2006
[16]Granpe D.Time series analysis:Identification and adptive filtering[M].Malabar:Krieger. Pub.co,1989
[17]陈仲生,杨拥民,胡政.基于几乎周期时变AR模型的故障早期预报[J].机械工程学报,2005, Vol.41 (1):184～188
[18]杨叔子,吴雅,轩建平,等.时间序列分析的工程应用(上册)[M].华中科技大学出版社2007,6.50～52
[19]刘思峰,郭天榜,党耀国.灰色系统理论及其应用(第2版)[M].北京：科学出版社,1999
[20]靳春梅,樊灵,邱阳,等.灰色理论在旋转机械故障诊断与预报中的应用[J].应用力学学报,2000, Vol.17 (3):74～79
[21]杨江天,岳维亮.灰色模型在机械故障预测中的应用[J].机械强度,2001, Vol.23 (3): 277～279
[22]赵荣珍,孟凡明,张优云.机械振动趋势的灰色预测模型研究[J].机械科学与技术,2004,Vol.23 (3):256～259
[23]Zhang Siyu, Ganesan R.Multivariable trend analysis for system monitoring through self-organizing neural networks Trans of the ASME[J].Journal of Dynamic Systems, Measurement, and Control,1997, Vol.119 (2):223～228
[24]C.A.Kulikowski.Artificial Intelligence Methods And Systems for Medical Consultation[J]. IEEE Trans.On pattern analysis and Machine Intelligence,1980, PAMI-2(5):465～476
[25]Mohamed A.Awadallah, Medhat, M Morcos.Application of AI Tools in Fault Diagnosis of Electrical Machines and Drives—An Overview[J].IEEE Trans.On Energy Conversion, June 2003,52(4):1076～1098
[26]叶强,夏哲雷,卫力.基于神经网络趋势分析[J].中国计量学院学报,2000, Vol.2 (11):177-181
[27]Nahvi H, Esfahanian M. Fault identification in rotating machinery using artificial neural networks. Proceedings of the Institution of Mechanical Engineers, Part C:Journal of Mechanical Engineering Science,2005, Vol.219 (2):141～158.
[28]杜耀武,蒋伟康.基于人工神经网络的大型机械系统的剩余寿命预报模型[J].机械强度,1997, Vol.19 (1):5～8
[29]Venkasubramanian Venkat, Chan King. A neural network methodology for process fault diagnosis. Journal of AIChE.1989, Vol.35(12):1993～2002
[30]Timo S, Heikki N K, Hannu K.Neural networks in process fault diagnosis[J].IEEE Trans.on SMC,1991, Vol.21(4):815～825
[31]肖健华,樊可清,吴今培.应用于故障诊断的SVM理论研究[J].振动、测试与诊断,2001,Vol.21(4)：258～262
[32]边肇祺,张学工.模式识别[M](第二版)．北京：清华大学出版社,2000
[33]李凌均,张周锁,何正嘉.基于支持向量机的机械设备状态趋势预测研究[J].西安交通大学学报,2004, Vol.38 (3):230～233
[34]Chen B J, Chang M W, Lin C J.Load forecasting using support vector machines:a study on EUNITE competition 2001 [J].Taiwan:Department of Computer Science and Information Engineering, Taiwan University,2002:1～11
[35]杨俊燕,张优云,赵荣珍.支持向量机在机械设备振动信号趋势分析中的应用[J].西安交通大学学报,2005, Vol.39 (9):950～953
[36]关慧玲,韩捷.设备故障诊断专家系统原理及实践[M].北京：机械工业出版社,2000
[37]Ali M. Gupta V.An expert system for fault diagnosis in a space shuttle main engine[J]. AIAA-90-1990
[38]J.L.Alty and M.J.Coombs.Expert Systems Concepts and Examples[M].Ncc Pubilications, England,1982
[39]Jan Maciej Koscielny. Michal Bartys Diagnostic models of industrial processes[J]. International Journal of COMADEM,2005, Vol.8 (2):23～29
[40]陈敏泽,周东华.动态系统的故障预报技术[J].控制理论与应用,2003, Vol.20 (6):819～ 823
[41]H. O. Peitgen, Chaos and Fractals.New Frontiers of Science[J].Springer-Verlag, New York, 1992
[42]Llias J, Waltz E. Multisonsor data fusion. AltechHouse, Norwood, Massachusetts,1990
[43]BachSCbmid N, Pennacchi P, Vania A. Diagnostic significance of orbit shape analysis and its application to improve machine fault detection[J]. Journal of the Brazilian Society of Mechanical Sciences and Engineering,2004, Vol.26(2):200～208
[44]朱大奇,刘永安.故障诊断的信息融合方法[J].控制与决策,2007,12：1321～1326
[45]Qu Langsheng, Chen Yaodong, Liu Xing. The holospectrum-A new method for rotor surveillance and diagnosis[J]. Mechanical Systems and Signal Processing,1989, Vol.7(3): 255～267
[46]Don Southwick. Using Full Spectrum Plots[J].Orblt,1993,14:19～21
[47]韩捷,关惠玲,梁川等.矢谱：一种实用的旋转机械故障诊断分析方法[J].机械强度,1998,Vol.20 (3):212～215
[48]屈梁生,史东锋.全息谱十年：回顾与展望[J].振动、测试与诊断,1998, Vol.18(4):235～242
[49]杜永祚,秦志英.旋转机械动态信号全息谱分析[J].振动、测试与诊断,2002, Vol.22(2):81～88
[50]Qu Langsheng, Liu Xing, Chen Yaodong. Discovering the Holospectrum[J].Noise & Vibration Worldwide,1989, Vol.7(3):255～267
[51]Don Southwick. Using Full Spectrum Plots Part2[J].Orblt.1994,6:11～15
[52]Bon Bently. How to handle(and some cases of)forward and reverse orbits [J].Orblt,1995,9: 4-5
[53]Goldman P, Muszyka A. Application of full spectrum to rotating machinery diagnostics [J].Orbit,1999,1:17～21
[54]韩捷,石来德,董辛曼.旋转机械虚拟探头融合检测技术研究[J].中国振动工程学报,2007, Vol.5 (2),204～209
[55]韩捷,毕果,郝伟.旋转机械空间域矢谱分析方法与应用[J].机械强度,2004, Vol.26 (6):605～608
[56]韩捷,石来德.全谱分析技术及其在故障诊断中的应用[J].郑州大学学报(工学版),2002,Vol.23 (3):44～47
[57]佟德纯.工程信号处理及应用[M].上海：上海交通大学出版社,1989
[58]胡广书.现代信号处理教程[M].北京：清华大学出版社,2004
[59]Davis J M.Augmenting experience-based diagnosis with casual reasoning[J].Int. Journal of Intelligent system.1989, Vol.2(1):1～32
[60]D.Logan, J.Mathew.Using the Correlation Dimension for Vibration Fault Diagnosis of Rolling Element Bearing-1[J].Basic Concepts.Mechanical System and Signal Processing, 1996, Vol.10(3):241～250
[61]MUSZYNSKA Agnes.BENTLY, ALEX Petchenev.Vibration response of rotor supported in one rigid and one poorly lubricated fluid filmbearing[J].ORBIT,1996,17(3):7～9
[62]Beaty R F.Differentiating rotor response due to radial rubbing[J].ASME J.Vibration Acoustics, Stress, Reliability in Design.1985, Vol.107(1):151～160
[63]张文.转子动力学理论基础[M]．北京：科学出版社,1990：132～142
[64]钟一谔,何衍宗.转子动力学[M].北京：清华大学出版社,1987：165～172
[65]韩捷,石来德.旋转机械的全信息能量谱分析方法研究[J].机械强度2003, Vol.25 (4):364～368
[66]谢凯,韩捷.基于复调制的细化全矢谱分析研究[J].机械强度,2008, Vol.30(2),184～188
[67]韩捷,董辛旻,等.旋转机械同源信息倒频谱分析与应用[J].机械强度,2005, Vol.27 (4):452～455
[68]冯彩红,韩捷,李凌均.全信息小波包分析及其在旋转机械故障诊断中的应用[J].机械强度,2006, Vol.28 (5):639～642
[69]董辛旻,韩捷,石来德.非平稳短时矢谱研究及应用[J].计算机工程,2005, Vol.27 (4):452～455
[70]周宇.基于全信息技术的非平稳信号的Wigner分布及应用[D].[硕士学位论文].郑州：郑州大学,2007
[71]李中原,韩捷,雷文平,等.基于矢双谱分析的旋转机械故障诊断研究[J].汽轮机技术,2006, Vol.48(6):430～432
[72]周宇,韩捷,李志农,等.分数阶Fourier变换在滚动轴承故障诊断中的应用[J].煤矿机械,2007, Vol.28(6):112～115
[73]李军伟,韩捷,李志农,等．小波变换域双谱分析及其在滚动轴承故障诊断中的应用[J].振动与冲击,2006, Vol.25 (5):92～95
[74]韩捷,张瑞林.旋转机械故障机理及诊断技术[M]．北京：机械工业出版社,1997,63～68
[75]杜奕,卢德唐,李道伦,等.一种快速的时间序列线性拟合算法[J].中国科学技术大学学报,2007, Vol.37 (3):310～314
[76]黄玉春,黄载绿,黄本雄,等.基于FFT滑动平均极大似然发的正弦信号频率估计[J].电子与信息学报,2008, Vol.30 (4):831～834
[77]冯金巧,杨兆升,张林,等.一种自适应指数平滑动态预测模型[J].吉林大学学报(工学版),2007, Vol.37 (6):1284～1287
[78]吴德会.基于动态指数平滑模型的小批量制造过程质量预测[J].农业机械学报,2008,Vol.39 (8):164～168
[79]Day I J. Prediction of compressor performance in rotating stall[J].Engineer for Power,1978
[80]Rojas.Guzman, Carlos, Kramer, Mark A. Remote diagnosis and monitoring of complex industrial systems using a genetic algorithm approach[J].IEEE International sysmposium on Industrial Electronics,1994:363～367
[81]Caldwell N H M, Breton B C, Holburn D M.Remote instrument diagnosis on the internet[J]. IEEE Intelligent Systems,1998, Vol.13(3):70～76
[82]陈晓娜.推行设备点检制的实践与认识[J].机械管理与开发,2008, Vol.23 (3):104～105
[83]梁川,韩捷.基于数据库的便携式数据采集和管理系统[J].郑州大学学报,2002,Vol.23(4):14～16
[84]王志英.以点检制为核心的设备管理新模式[J].设备管理与维修2009,(11)：14～15
[85]Martin Fowler.Patterns of Enterprise Application Architecture[J]. Boston:Addison-Wesley, 2003
[86]信江艳,董洁.企业资产管理系统(EAM)设计与实施[M]．北京：中国铁道出版社,2005
[87]杨友东,汪琛琛.Visual C++程序设计全程指南[M].北京：电子工业出版社,2009
[88]张海涛,韩捷,李志农,等.基于全矢谱分析的故障诊断系统的开发[J].煤矿机械,2007,28(3)：185～188
[89]Futter D N.Techniques for condition monitoring of large gearboxes in the power industry [J]. INSIGHT,1995, Vol.37(8):591～594
[90]Ding Lipei, Guo Xiaosong, Zhu ZhiVirtual.Test System Based on Visual C++. ICEMI'2007 Proceedings of 2007 8th International Conference on Electronic Measurement & Instrument, 2007, Vol.2
[91]徐东方,邓飞其.基于多传感器数据融合的智能故障诊断系统[J].仪器仪表学报,2004,Vol.25 (4):404～406
[92]Bogler P L.Shafer-dempster reasoning with applications to multisensory target identification system [J].IEEE Trans.on Systems, Man and Cybernetics,1987, Vol.17(3):968～977
[93]关慧玲,张优云.转子系统振动幅度的监测[J].机械强度,2000，Vol.22(3)：180～183
[94]刘红岩.数据库技术及应用[M]．北京：清华大学出版社,2007
[95]王丽雅,董辛旻,韩捷.基于SQL Server的设备远程诊断数据库安全[J].中国设备工程,2003(4)：40～41
[96]徐枫,马国之,刘良旭.基于ADO技术的数据库访问研究与实现[J].计算机工程与设计,2004, Vol.25 (1):107～110
[97]David Sceppa.ADO编程技术[M]．北京：清华大学出版社,2001
[98]N. Narayanan, N. Viswanadham. Methodology for Knowledge acquisition and Reasoning in Failure Analysis of System[J]. Transacting on System, Man and Cybernetics,1987, Vol.17(2):274～288
[99]陈燕.组合预测方法研究及其软件系统设计与开发[D].[硕士学位论文].哈尔滨：东北农业大学,2007
[100]李洪雷,管群.基于VC的时间序列分析法的应用研究[J].计算机仿真,2009, Vol.26(7)：113～117
[101]Joentgen A, Mikenina L, Weber R, et al.Automatic fault detection in gearboxes by dynamic fuzzy data analysis[J]. Fuzzy Sets and Systems,1999, Vol.105(1):123～132