基于Logistic回归模型的旋转机械健康状态评估研究
|
摘要
近年来,随着现代工业的发展,大型系统需求量不断增加,且这些系统本身还不断向大功率、大容量、高速度、高效率和复杂化等方面发展。如何维护好这些系统、确保工作过程的安全性和可靠性、避免事故发生、使其发挥最大的作用,已成为现代企业管理的重要目标之一。应用先进的故障诊断技术可以及时发现系统故障,避免和预防恶性事故发生,降低企业维修成本。因此,研究设备健康状态评估技术对于现代企业具有重要的经济意义和实用价值。
本文主要针对Logistic回归在旋转机械设备的状态评估中的应用进行了研究,应用Logistic回归模型分析设备运行状态与历史数据概率分布之间的关系,用设备当前数据与设备历史状态数据之间的差异相似性来评估旋转机械设备状态的健康程度,并用实验数据验证该方法的可行性。研究了旋转机械设备运行状态评估系统的设计与构架。本文结构如下:
第一章首先论述了设备运行健康状态评估研究的背景及意义,回顾了传统状态监、故障诊断及健康评估的方法,指出各种方法的优缺点。进而分析了大型旋转机械实时状态监测以及流程工业智能维修技术与设备健康状态评估的联系。确立了本论文的研究题目:基于Logistic回归的设备健康状态评估系统研究。
第二章对Logistic回归理论的算法进行了研究。包括Logistic回归理论,Logistic回归模型估计,Logistic回归模型评价及统计检验,以及logistic回归系数的确定方法。
第三章研究基于Logistic回归模型的设备运行健康状态评估,提出用logistic回归模型计算设备状态故障发生的概率来评估设备状态的健康程度。分析旋转机械不同故障特征提取的方法,以及讨论如何选取Logistic回归模型的特征参数作为设备状态健康度的指标。
第四章实验数据分析验证。利用轴承转子实验台,监测其正常和多种故障状态的振动值,确定设备运行状态。设计实验方案,完成振动信号的采集,并针对信号进行时域和频域的特征提取,利用Logistic回归模型对该设备进行健康评估。研究了基于Logistic回归模型的设备健康状态评估系统的架构。
第五章对本论文所做的工作以及需进一步改进提高的方面进行了总结,并对本研究方向进行了展望。
In the recent year, more and more large-scale systems are needed for the development of modern industry. These systems themselves keep developing towards the directions of high-power, high-capability, high-speed, high-efficiency and becoming more and more complex. How to effectively maintain these systems, to enhance their security and reliability, to avoid abnormal events and to take their full advantages has become one of the most significant causes of modern management. The application of advanced fault diagnosis techniques can help to identify the system fault, to avoid and prevent the occurrence of vicious accident and to minimize the cost of maintenance. As a result, the research of condition health assessment techniques is very significant for modern enterprises both in economic and practical value.
In this paper, the logistic regression arithmetic is introduced to analyze the relationship between operating state and probability distribution of historical data. The health state of rotating machinery condition can be assessed by comparability and difference between current and historical data. Experimental case shows that this method is feasible and effective using in the condition health assessment of machinery. The main content of this paper is as follows.
Firstly the significance and background of this paper is introduced in Chapter 1. The traditional method of condition monitoring, fault diagnosis and health assessment of machinery are expatiated on afterwards, and the benefits and shortcoming are also pointed out. Then the relationship among the real-time condition monitoring of rotating machinery, the intelligent maintenance technology of process industry and the condition health assessment is summarized. And then the development trend of condition health assessment and prediction technology is analyzed in this chapter at home and abroad. In the end, the research's target of the paper is put forward and the topic content and structure of the paper is summarized.
The arithmetic of Logistic Regression is studied in Chapter 2. The theory of Logistic Regression arithmetic, the model estimation of Logistic Regression, the model assessment and statistical test of Logistic Regression, and method of deciding the coefficient of Logistic Regression are putting forward.
The method of condition health assessment of rotating machinery based on Logistic Regression is studied in Chapter 3. To begin with, the method of Logistic Regression is put forward to analyse and assess the health degree of running condition of rotating machinery. Moreover, various fault extraction methods of rotating machinery are analyzed in this chapter, and how to choose the feature parameter of Logistic Regression as the index of health degree is also discussed.
A process of experimental analysis and validity of the condition health assessment system of rotating machinery based on Logistic Regression using the Bearing Rotating Test Bed is expatiated in Chapter 4. Firstly, an experimental plan is designed, including collecting the vibration signal, feature extracting in both time domain and frequency domain, using Logistic Regression system to assess the bearing's health condition. Secondly the frame of the condition health assessment system of rotating machine based on Logistic Regression is discussed.
本文主要针对Logistic回归在旋转机械设备的状态评估中的应用进行了研究,应用Logistic回归模型分析设备运行状态与历史数据概率分布之间的关系,用设备当前数据与设备历史状态数据之间的差异相似性来评估旋转机械设备状态的健康程度,并用实验数据验证该方法的可行性。研究了旋转机械设备运行状态评估系统的设计与构架。本文结构如下:
第一章首先论述了设备运行健康状态评估研究的背景及意义,回顾了传统状态监、故障诊断及健康评估的方法,指出各种方法的优缺点。进而分析了大型旋转机械实时状态监测以及流程工业智能维修技术与设备健康状态评估的联系。确立了本论文的研究题目:基于Logistic回归的设备健康状态评估系统研究。
第二章对Logistic回归理论的算法进行了研究。包括Logistic回归理论,Logistic回归模型估计,Logistic回归模型评价及统计检验,以及logistic回归系数的确定方法。
第三章研究基于Logistic回归模型的设备运行健康状态评估,提出用logistic回归模型计算设备状态故障发生的概率来评估设备状态的健康程度。分析旋转机械不同故障特征提取的方法,以及讨论如何选取Logistic回归模型的特征参数作为设备状态健康度的指标。
第四章实验数据分析验证。利用轴承转子实验台,监测其正常和多种故障状态的振动值,确定设备运行状态。设计实验方案,完成振动信号的采集,并针对信号进行时域和频域的特征提取,利用Logistic回归模型对该设备进行健康评估。研究了基于Logistic回归模型的设备健康状态评估系统的架构。
第五章对本论文所做的工作以及需进一步改进提高的方面进行了总结,并对本研究方向进行了展望。
In the recent year, more and more large-scale systems are needed for the development of modern industry. These systems themselves keep developing towards the directions of high-power, high-capability, high-speed, high-efficiency and becoming more and more complex. How to effectively maintain these systems, to enhance their security and reliability, to avoid abnormal events and to take their full advantages has become one of the most significant causes of modern management. The application of advanced fault diagnosis techniques can help to identify the system fault, to avoid and prevent the occurrence of vicious accident and to minimize the cost of maintenance. As a result, the research of condition health assessment techniques is very significant for modern enterprises both in economic and practical value.
In this paper, the logistic regression arithmetic is introduced to analyze the relationship between operating state and probability distribution of historical data. The health state of rotating machinery condition can be assessed by comparability and difference between current and historical data. Experimental case shows that this method is feasible and effective using in the condition health assessment of machinery. The main content of this paper is as follows.
Firstly the significance and background of this paper is introduced in Chapter 1. The traditional method of condition monitoring, fault diagnosis and health assessment of machinery are expatiated on afterwards, and the benefits and shortcoming are also pointed out. Then the relationship among the real-time condition monitoring of rotating machinery, the intelligent maintenance technology of process industry and the condition health assessment is summarized. And then the development trend of condition health assessment and prediction technology is analyzed in this chapter at home and abroad. In the end, the research's target of the paper is put forward and the topic content and structure of the paper is summarized.
The arithmetic of Logistic Regression is studied in Chapter 2. The theory of Logistic Regression arithmetic, the model estimation of Logistic Regression, the model assessment and statistical test of Logistic Regression, and method of deciding the coefficient of Logistic Regression are putting forward.
The method of condition health assessment of rotating machinery based on Logistic Regression is studied in Chapter 3. To begin with, the method of Logistic Regression is put forward to analyse and assess the health degree of running condition of rotating machinery. Moreover, various fault extraction methods of rotating machinery are analyzed in this chapter, and how to choose the feature parameter of Logistic Regression as the index of health degree is also discussed.
A process of experimental analysis and validity of the condition health assessment system of rotating machinery based on Logistic Regression using the Bearing Rotating Test Bed is expatiated in Chapter 4. Firstly, an experimental plan is designed, including collecting the vibration signal, feature extracting in both time domain and frequency domain, using Logistic Regression system to assess the bearing's health condition. Secondly the frame of the condition health assessment system of rotating machine based on Logistic Regression is discussed.
引文
[1]高金吉.装备系统故障自愈原理研究[J].中国工程科学,2005,5(7):1-6
[2]Gao Jinji.Risk Based Dynamic Intelligent Maintenance and Fault Self-recovery Engineering for Process Industry.[CD].Proceedings of The 4th World Congress on Maintenance.Haikou,December,2008.
[3]高金吉,王维民,江志农.高速透平机械轴位移故障自愈调控系统研究[J].机械科学与技术,2005.11(24):30-33
[4]高金吉.设备诊断工程文集[C].辽宁:中国石化机电仪研修中心,1997
[5]高金吉.机泵群实时监测网络和故障诊断专家系统[J].中国工程科学,2001,9(3):41-47
[6]Bowerman,O'Connell.Forecasting and Time Series:An applied approach[M].北京:机械工业出版社,2003.7(影印版)
[7]LUKS,Sakes R.Failure prediction for an on-line maintenance system in a passion shock environment[J].IEEE Trans on Systems,Man,and Cybernetics,1979(6):356-362
[8]Dr.Robert Milne,Mr Ed.Bain,Dr.Mike Drummond.Predicting faults with real-time diagnosis.Proceedings of the 30th Conference on decision and control,Brighton,England.December 1991.IEEE,1991.pp.2598-2603
[9]Taghi M.Khoshgoftaar,Abhijit S.Pandya,Hemant B.More.A neural network approach for software development faults.IEEE,1992.pp.83-89
[10]E.D.Gadzheva,L.H.Raykovska.Nullator-norator approach for diagnosis and fault prediction in analog circuits.Supported by the Bulgarian National Founadation "Scientific Investigations",1993,pp.53-56
[11]B.Lennox,P.Rutherford,G.A.Montague etc.A novel fault prediction technique using model degradation analysis.Processing of the American Control conference.1995.Seattle,3274-3278
[12]V.K.Devabhaktuni,M.Yagoub,Q.J.Zhang.A robust algorithm for automatic development of neural network models for microwave applications.IEEE MTT International Microwave Symp.Digest,(Phoenix,AZ),pp.2087-2090,May 2001.
[13]Vijay Devabhaktuni,Mustapha C.E.Yagoub,Qi-Jun Zhang,A robust algorithm for automatic development of neural network models for microwave applications.IEEE Trans.Microwave Theory Tech.,vol.49,pp.2282-2291,December 2001.
[14]Tai-con Chen,Da-jian Han,Francis T.K.Au etc.Acceleration of Levenberg-Marquardt Training of Neural Networks with Variable Decay Rate.Proceedings of the International Joint Conference on Neural Networks,2003,vol.3,pp.1873- 1878,July 2003.
[15]Mie Mie Thet Thwin,Tong-Seng Quah.Application of neural network for predicting software development faults using object-oriented design metrics.Proceedings of the 9th International conference on neural information processing(ICONIP-02) Vol.5,IEEE,2002.Pp.2312-2316
[16]Ali A.Ghorbani,Virendrakumar C.Bhavsar,Incremental communication for Multilayer neural networks:error analysis,IEEE transactions on neural networks,Vol,9,No.1,pp.68-82,January 1998.
[17]Shing chiang tan,Chee peng lim.condition monitoring and fault prediction via an adaptive neural network.IEEE.2000.Pp.13-17
[18]Mohammad Tanvir Islam,and Yoichi Okabe,A brief discussion on moderatism based local gradient learning rules,Proceedings.Seventh International Symposium on Signal Processing and Its Applications,IEEE,2003,vol.2,pp.239- 242,2003
[19]J.A.Prieto,A.Rueda,I.Grout,etc.An Approach to Realistic Fault Prediction and Layout Design for Testability in Analog Circuits.Design Automation and Test in Europe.Num.1.Paris.IEEE Computer SOC.1998.Pp.905-909
[20]D S Henderson,Lothian,and J Priest.PC monitoring and fault prediction for small hydroelectric plants.Power station maintenance:Profitability Through Reliability,30March-1 April 1998.Conference Publication No.452,IEE,1998.pp.28-32
[21]Casoetto N,Djurdjanovic D,Mayor,D,Lee,J and Ni,J,Multi-sensor Process Performance Assessment Through the Use of Autoregressive Modeling and Feature Maps,MSE.[J] Journal of Manufacturing Systems,Vol.22,No.1,pp.64-72,2003
[22]Yuan S,Ge M,Qiu H,Lee J,Xu Y.Intelligent Diagnosis in Electromechanical Operations Systems.Proceedings of 2004 IEEE International Conference on Robotics and Automation,New Orleans,2004,p.2267-2272
[23]Runqing Huang,Lifeng Xi,Xinglin Li,C.Richard Liu,Hal Qiu,Jay Lee.Residual Life Predictions for Ball Bearings Based on Self-organizing Map and Back Propagation Neural Network Methods[J].Mechanical System and Signal Processing,2006,1
[24]Djurdjanovic D,Ni J,Lee J.Time-frequency Based Sensor Fusion in the Assessment and Monitoring of Machine Performance Degradation.The proceedings of 2002 ASME International Mechanical Engineering Congress and Exposition.And Proceeding of ASME IMEC&E 2002,New Orleans,LA.Paper number IMECE 2002-32032;2002
[25]Yan Jihong,Lee Jay.Degradation Assessment and Fault Modes Classification Using Logistic Regression[J].Journal of Manufacturing Science and Engineering,Transactions of the ASME,v 127,n 4,November,2005,p 912-914
[26]Yan Jihong,Koc Muammer,Lee Jay.A Prognostic Algorithm for Machine Performance Assessment and Its Application.Production Planning and Control,v 15,n 8,December,2004,p 796-801
[27]Lucy Y.Pao,Michael Kalandros.Covariance Control for Multi-sensor Systems.IEEE Transactions on aerospace and electronic systems.Vol.38,No.4.October 2002.pp.1138-1156.
[28]Michael Kalandros,Lucy Y.Pao.Controlling Target Estimate Covriance in Centralized Multisensor Systems.Proceedings of the American Control Conference.Philadel phia,Pennsylvanis.June.1998.2749-2753
[29]Kim S.D,Morcos M.M,Diagnosis of Useful Life for ACSR Conductors Using A Fuzzy Interference System.IEEE Power Engineering Review,v 22,n 5,May,2002,p 61-64
[30]Roemer M.J,Kacprznski G.J,Orsagh R.F,Assessment of Data and Knowledge Fusion Strategies for Prognostics and Health Management.IEEE Aerospace Conference Proceedings,v 6,2001,p62979-62988
[31]Roemer M.J,Kacprznski G.J,Advanced Diagnostics and Prognostics for Gas Turbine Engine Risk Assessment.IEEE Aerospace Conference Proceedings,v 6,2000,p 345-354
[32]Taghi M.Khoshgoftaar,Naeem Seliya.Tree-Based Software Quality Estimation Models For Fault Prediction.Proceeding of the 8th IEEE Symposium on Software Metrics,2002.IEEE.Computer Society.02.pp.203-214
[33]Taghi M.Khoshgoftaar,Bojan Cukic,Naeem Seliya:Predicting Fault-Prone Modules in Embedded Systems Using Analogy-Based Classification Models.International Journal of Software Engineering and Knowledge Engineering.2002.12(2):201-221
[34]Allen P.Nikora,John C.Munson.Developing Fault Prediction for Evolving Software Systems.Proceeding of the 9th international software metrics symposium.2003.
[35]M Cavacece.A Introini,Analysis of Damage of Ball Bearings of Aeronautical Transmissions by Auto-Power Spectrum and Cross-power Spectrum[J].Journal of Vibration and Acoustics,Transactions of the ASME,Vol.124,April 2002,p 180-185
[36]Ocak Hasan,Loparo Kenneth A.HMM-based Fault Detection and Diagnosis Scheme for Rolling Element Bearings[J].Journal of Vibration and Acoustics.Transactions of the ASME,v 127,n 4,August,2005,p 299-306
[37]Samanta B,Al-Balushi K.R,Al-Araimi,S.A.Artificial Neural Networks and Support Vector Machines with Genetic Algorithm for Bearing Fault Detection[J].Engineering Applications of Artificial Intelligence,v 16,n 7-8,October/December,2003,p657-665
[38]程惠涛,黄文虎,姜兴渭.基于灰色模型的故障预报技术及其在空间推进系统上的应用[J].推进技术,1998,No.3,Vol(19):74-77
[39]李勇,孙艳萍,孙海波,宋景东.用于故障预测的BP网络模型及改进[J].东北电力学院学报,1999年第1期:27-32
[40]黄景德,王兴贵,王祖光.反后坐装置漏气故障分析模糊评价[J].润滑与密封.2000,No.6.pp.61-64
[41]黄景德,王兴贵,王祖光.动态模糊综合评判法及其在故障预测中的应用[J].模糊系统与数学,2001年第4期:96-99
[42]黄景德,崔山宝,王兴贵等.正向推理型故障模糊预测系统的知识表示与推理.计算机工程.2001,27(2).pp.78-79
[43]黄景德,王兴贵,王祖光.基于模糊评判的故障预测系统研究[J].电子机械工程,2001年第6期:42-44
[44]HUANG Jin-de,WANG Qiang.Design method of fault fuzzy forecast system based on knowledge[J].Comouter automated measurement & control,2001,9(5):26-27.
[45]王宗川,黄景德,王兴贵等.基于虚拟样机的机械装备故障仿真预测技术研究[J].计算机测量与控制,2002,Vol.10,No.12.Pp.192-194
[46]黄景德,黄春庆,王兴贵等.故障模糊预测系统开发环境的思想及其实现[J].系统仿真学报.2001,13(4).pp.485-487
[47]秦俊奇,曹立军,王兴贵,黄景德.基于动态模糊综合评判的故障预测方法[J].计算机工程,2005 Vol.31,No.12.Pp.172-174
[48]陈举华,郭毅之.GM模糊优化方法在小子样机械系统故障预测中的应用,2002,Vol(13),No.19.pp.1658-1660
[49]高俊峰,刘树林,王日新.反面选择算法在转动设备故障预测中的应用[J].石油机械,2002,Vol(30),No.6.pp.33-35
[50]张红,李柱国,陈兆能.舰船柴油机磨损趋势预测的灰色模型方法[J].内燃机学报,2002,4:362-364
[51]孙才新,毕为民等.灰色预测参数模型新模式及其在电气绝缘故障预测中的应用[J].控制理论与应用,2003,Vol(20),No.5.pp.797-801
[52]吴为麟,朱宁.复杂性测度分析在电力电子电路故障预测中的应用[J].电子与信息学报,2003,Vol(25),No.5,.pp.677-682
[53]徐小力.旋转机械的遗传算法优化神经网络预测模型[J].机械工程学报,2003,2:140-141
[54]赵海东,缪旭东,吕世聘.基于神经网络的军用飞机故障预报系统研究[J].系统工程与电子技术.2003.025(007).pp.894-896
[55]汪梅.基于神经网络的三相电缆故障预测定位系统[J].西安科技学院学报,2004,Vol(24),No.2.pp.225-227,239
[56]李凌均,张周锁,何正嘉.基于支持向量机的机械设备状态预测研究[J].西安交通大学学报,2004,3:230-231
[57]赵荣珍,孟凡明,张优云,王成栋.机械振动趋势的灰色预测模型研究[J].机械科学于技术,2004,3:256-258
[58]郭明,谢磊,王树青.基于模型的多尺度间歇过程性能监控[J].系统工程理论与实践.2004(1):97-102
[59]李骥,张洪钺.基于预测滤波器的故障诊断方法研究[J].中国科学E辑.2004,34(12).pp.1375-1392
[60]Martin,D.Early.Warning of Bank Failure[J].Journal of Banking and Finance.1977,7:249-276
[61]James A.Ohlson.Financial Ratios and the Probabilistic Prediction of Bankruptcy[J].Journal of Accounting Research.1980,18(1):109-131
[62]Gangadharrao Soundaryarao Maddala.Limited-Dependent and Qualitative Variables in Econometrics[J].Cambridge University Press,1986:173-215
[63]DuoglasM.Baets,Dnoald著,韦博成,万方焕,朱宏图译.非线性回归分析及其应用[M].北京:中国统计出版社,1997.
[64]Aldrieh John,Forrest D.Nelson.Linear Probability,Logit,and Probit Models[M].Newbury Park,CA:Sage Publications.1984.
[65]Long,J.Scott.Regression Models for Categorical and Limited Dependent Variables[M].Thousand Oaks,California:Sage Publication.
[66]李志荣,侯洪海,曾亚宏.转子不平衡的故障特征[J].洛阳工学院学报,1999,20(1):54-57
[67]韩延良.离心机不平衡故障的早期诊断[J].振动测试与诊断,1992,12(1):50-51
[68]屈粱生,何正矗.机械故障诊断学[M].上海:上海科学技术出版杜,1986.80-82
[69]王殿武,张敬伟.不对中故障的分析与诊断技巧[J].设备管理与维修,2005,10(8):32-34
[70]伍洋.用状态监测判断不对中故障[J].技术与应用,2004,3(10):47-48
[71]庄表中,黄志强.振动分析基础[M].北京:北京科学出版社,1985.118-120
[72]窦卫东.汽轮发动机组转子油膜涡动原因分析[J].电力学报,2003,18(1):40-45
[2]Gao Jinji.Risk Based Dynamic Intelligent Maintenance and Fault Self-recovery Engineering for Process Industry.[CD].Proceedings of The 4th World Congress on Maintenance.Haikou,December,2008.
[3]高金吉,王维民,江志农.高速透平机械轴位移故障自愈调控系统研究[J].机械科学与技术,2005.11(24):30-33
[4]高金吉.设备诊断工程文集[C].辽宁:中国石化机电仪研修中心,1997
[5]高金吉.机泵群实时监测网络和故障诊断专家系统[J].中国工程科学,2001,9(3):41-47
[6]Bowerman,O'Connell.Forecasting and Time Series:An applied approach[M].北京:机械工业出版社,2003.7(影印版)
[7]LUKS,Sakes R.Failure prediction for an on-line maintenance system in a passion shock environment[J].IEEE Trans on Systems,Man,and Cybernetics,1979(6):356-362
[8]Dr.Robert Milne,Mr Ed.Bain,Dr.Mike Drummond.Predicting faults with real-time diagnosis.Proceedings of the 30th Conference on decision and control,Brighton,England.December 1991.IEEE,1991.pp.2598-2603
[9]Taghi M.Khoshgoftaar,Abhijit S.Pandya,Hemant B.More.A neural network approach for software development faults.IEEE,1992.pp.83-89
[10]E.D.Gadzheva,L.H.Raykovska.Nullator-norator approach for diagnosis and fault prediction in analog circuits.Supported by the Bulgarian National Founadation "Scientific Investigations",1993,pp.53-56
[11]B.Lennox,P.Rutherford,G.A.Montague etc.A novel fault prediction technique using model degradation analysis.Processing of the American Control conference.1995.Seattle,3274-3278
[12]V.K.Devabhaktuni,M.Yagoub,Q.J.Zhang.A robust algorithm for automatic development of neural network models for microwave applications.IEEE MTT International Microwave Symp.Digest,(Phoenix,AZ),pp.2087-2090,May 2001.
[13]Vijay Devabhaktuni,Mustapha C.E.Yagoub,Qi-Jun Zhang,A robust algorithm for automatic development of neural network models for microwave applications.IEEE Trans.Microwave Theory Tech.,vol.49,pp.2282-2291,December 2001.
[14]Tai-con Chen,Da-jian Han,Francis T.K.Au etc.Acceleration of Levenberg-Marquardt Training of Neural Networks with Variable Decay Rate.Proceedings of the International Joint Conference on Neural Networks,2003,vol.3,pp.1873- 1878,July 2003.
[15]Mie Mie Thet Thwin,Tong-Seng Quah.Application of neural network for predicting software development faults using object-oriented design metrics.Proceedings of the 9th International conference on neural information processing(ICONIP-02) Vol.5,IEEE,2002.Pp.2312-2316
[16]Ali A.Ghorbani,Virendrakumar C.Bhavsar,Incremental communication for Multilayer neural networks:error analysis,IEEE transactions on neural networks,Vol,9,No.1,pp.68-82,January 1998.
[17]Shing chiang tan,Chee peng lim.condition monitoring and fault prediction via an adaptive neural network.IEEE.2000.Pp.13-17
[18]Mohammad Tanvir Islam,and Yoichi Okabe,A brief discussion on moderatism based local gradient learning rules,Proceedings.Seventh International Symposium on Signal Processing and Its Applications,IEEE,2003,vol.2,pp.239- 242,2003
[19]J.A.Prieto,A.Rueda,I.Grout,etc.An Approach to Realistic Fault Prediction and Layout Design for Testability in Analog Circuits.Design Automation and Test in Europe.Num.1.Paris.IEEE Computer SOC.1998.Pp.905-909
[20]D S Henderson,Lothian,and J Priest.PC monitoring and fault prediction for small hydroelectric plants.Power station maintenance:Profitability Through Reliability,30March-1 April 1998.Conference Publication No.452,IEE,1998.pp.28-32
[21]Casoetto N,Djurdjanovic D,Mayor,D,Lee,J and Ni,J,Multi-sensor Process Performance Assessment Through the Use of Autoregressive Modeling and Feature Maps,MSE.[J] Journal of Manufacturing Systems,Vol.22,No.1,pp.64-72,2003
[22]Yuan S,Ge M,Qiu H,Lee J,Xu Y.Intelligent Diagnosis in Electromechanical Operations Systems.Proceedings of 2004 IEEE International Conference on Robotics and Automation,New Orleans,2004,p.2267-2272
[23]Runqing Huang,Lifeng Xi,Xinglin Li,C.Richard Liu,Hal Qiu,Jay Lee.Residual Life Predictions for Ball Bearings Based on Self-organizing Map and Back Propagation Neural Network Methods[J].Mechanical System and Signal Processing,2006,1
[24]Djurdjanovic D,Ni J,Lee J.Time-frequency Based Sensor Fusion in the Assessment and Monitoring of Machine Performance Degradation.The proceedings of 2002 ASME International Mechanical Engineering Congress and Exposition.And Proceeding of ASME IMEC&E 2002,New Orleans,LA.Paper number IMECE 2002-32032;2002
[25]Yan Jihong,Lee Jay.Degradation Assessment and Fault Modes Classification Using Logistic Regression[J].Journal of Manufacturing Science and Engineering,Transactions of the ASME,v 127,n 4,November,2005,p 912-914
[26]Yan Jihong,Koc Muammer,Lee Jay.A Prognostic Algorithm for Machine Performance Assessment and Its Application.Production Planning and Control,v 15,n 8,December,2004,p 796-801
[27]Lucy Y.Pao,Michael Kalandros.Covariance Control for Multi-sensor Systems.IEEE Transactions on aerospace and electronic systems.Vol.38,No.4.October 2002.pp.1138-1156.
[28]Michael Kalandros,Lucy Y.Pao.Controlling Target Estimate Covriance in Centralized Multisensor Systems.Proceedings of the American Control Conference.Philadel phia,Pennsylvanis.June.1998.2749-2753
[29]Kim S.D,Morcos M.M,Diagnosis of Useful Life for ACSR Conductors Using A Fuzzy Interference System.IEEE Power Engineering Review,v 22,n 5,May,2002,p 61-64
[30]Roemer M.J,Kacprznski G.J,Orsagh R.F,Assessment of Data and Knowledge Fusion Strategies for Prognostics and Health Management.IEEE Aerospace Conference Proceedings,v 6,2001,p62979-62988
[31]Roemer M.J,Kacprznski G.J,Advanced Diagnostics and Prognostics for Gas Turbine Engine Risk Assessment.IEEE Aerospace Conference Proceedings,v 6,2000,p 345-354
[32]Taghi M.Khoshgoftaar,Naeem Seliya.Tree-Based Software Quality Estimation Models For Fault Prediction.Proceeding of the 8th IEEE Symposium on Software Metrics,2002.IEEE.Computer Society.02.pp.203-214
[33]Taghi M.Khoshgoftaar,Bojan Cukic,Naeem Seliya:Predicting Fault-Prone Modules in Embedded Systems Using Analogy-Based Classification Models.International Journal of Software Engineering and Knowledge Engineering.2002.12(2):201-221
[34]Allen P.Nikora,John C.Munson.Developing Fault Prediction for Evolving Software Systems.Proceeding of the 9th international software metrics symposium.2003.
[35]M Cavacece.A Introini,Analysis of Damage of Ball Bearings of Aeronautical Transmissions by Auto-Power Spectrum and Cross-power Spectrum[J].Journal of Vibration and Acoustics,Transactions of the ASME,Vol.124,April 2002,p 180-185
[36]Ocak Hasan,Loparo Kenneth A.HMM-based Fault Detection and Diagnosis Scheme for Rolling Element Bearings[J].Journal of Vibration and Acoustics.Transactions of the ASME,v 127,n 4,August,2005,p 299-306
[37]Samanta B,Al-Balushi K.R,Al-Araimi,S.A.Artificial Neural Networks and Support Vector Machines with Genetic Algorithm for Bearing Fault Detection[J].Engineering Applications of Artificial Intelligence,v 16,n 7-8,October/December,2003,p657-665
[38]程惠涛,黄文虎,姜兴渭.基于灰色模型的故障预报技术及其在空间推进系统上的应用[J].推进技术,1998,No.3,Vol(19):74-77
[39]李勇,孙艳萍,孙海波,宋景东.用于故障预测的BP网络模型及改进[J].东北电力学院学报,1999年第1期:27-32
[40]黄景德,王兴贵,王祖光.反后坐装置漏气故障分析模糊评价[J].润滑与密封.2000,No.6.pp.61-64
[41]黄景德,王兴贵,王祖光.动态模糊综合评判法及其在故障预测中的应用[J].模糊系统与数学,2001年第4期:96-99
[42]黄景德,崔山宝,王兴贵等.正向推理型故障模糊预测系统的知识表示与推理.计算机工程.2001,27(2).pp.78-79
[43]黄景德,王兴贵,王祖光.基于模糊评判的故障预测系统研究[J].电子机械工程,2001年第6期:42-44
[44]HUANG Jin-de,WANG Qiang.Design method of fault fuzzy forecast system based on knowledge[J].Comouter automated measurement & control,2001,9(5):26-27.
[45]王宗川,黄景德,王兴贵等.基于虚拟样机的机械装备故障仿真预测技术研究[J].计算机测量与控制,2002,Vol.10,No.12.Pp.192-194
[46]黄景德,黄春庆,王兴贵等.故障模糊预测系统开发环境的思想及其实现[J].系统仿真学报.2001,13(4).pp.485-487
[47]秦俊奇,曹立军,王兴贵,黄景德.基于动态模糊综合评判的故障预测方法[J].计算机工程,2005 Vol.31,No.12.Pp.172-174
[48]陈举华,郭毅之.GM模糊优化方法在小子样机械系统故障预测中的应用,2002,Vol(13),No.19.pp.1658-1660
[49]高俊峰,刘树林,王日新.反面选择算法在转动设备故障预测中的应用[J].石油机械,2002,Vol(30),No.6.pp.33-35
[50]张红,李柱国,陈兆能.舰船柴油机磨损趋势预测的灰色模型方法[J].内燃机学报,2002,4:362-364
[51]孙才新,毕为民等.灰色预测参数模型新模式及其在电气绝缘故障预测中的应用[J].控制理论与应用,2003,Vol(20),No.5.pp.797-801
[52]吴为麟,朱宁.复杂性测度分析在电力电子电路故障预测中的应用[J].电子与信息学报,2003,Vol(25),No.5,.pp.677-682
[53]徐小力.旋转机械的遗传算法优化神经网络预测模型[J].机械工程学报,2003,2:140-141
[54]赵海东,缪旭东,吕世聘.基于神经网络的军用飞机故障预报系统研究[J].系统工程与电子技术.2003.025(007).pp.894-896
[55]汪梅.基于神经网络的三相电缆故障预测定位系统[J].西安科技学院学报,2004,Vol(24),No.2.pp.225-227,239
[56]李凌均,张周锁,何正嘉.基于支持向量机的机械设备状态预测研究[J].西安交通大学学报,2004,3:230-231
[57]赵荣珍,孟凡明,张优云,王成栋.机械振动趋势的灰色预测模型研究[J].机械科学于技术,2004,3:256-258
[58]郭明,谢磊,王树青.基于模型的多尺度间歇过程性能监控[J].系统工程理论与实践.2004(1):97-102
[59]李骥,张洪钺.基于预测滤波器的故障诊断方法研究[J].中国科学E辑.2004,34(12).pp.1375-1392
[60]Martin,D.Early.Warning of Bank Failure[J].Journal of Banking and Finance.1977,7:249-276
[61]James A.Ohlson.Financial Ratios and the Probabilistic Prediction of Bankruptcy[J].Journal of Accounting Research.1980,18(1):109-131
[62]Gangadharrao Soundaryarao Maddala.Limited-Dependent and Qualitative Variables in Econometrics[J].Cambridge University Press,1986:173-215
[63]DuoglasM.Baets,Dnoald著,韦博成,万方焕,朱宏图译.非线性回归分析及其应用[M].北京:中国统计出版社,1997.
[64]Aldrieh John,Forrest D.Nelson.Linear Probability,Logit,and Probit Models[M].Newbury Park,CA:Sage Publications.1984.
[65]Long,J.Scott.Regression Models for Categorical and Limited Dependent Variables[M].Thousand Oaks,California:Sage Publication.
[66]李志荣,侯洪海,曾亚宏.转子不平衡的故障特征[J].洛阳工学院学报,1999,20(1):54-57
[67]韩延良.离心机不平衡故障的早期诊断[J].振动测试与诊断,1992,12(1):50-51
[68]屈粱生,何正矗.机械故障诊断学[M].上海:上海科学技术出版杜,1986.80-82
[69]王殿武,张敬伟.不对中故障的分析与诊断技巧[J].设备管理与维修,2005,10(8):32-34
[70]伍洋.用状态监测判断不对中故障[J].技术与应用,2004,3(10):47-48
[71]庄表中,黄志强.振动分析基础[M].北京:北京科学出版社,1985.118-120
[72]窦卫东.汽轮发动机组转子油膜涡动原因分析[J].电力学报,2003,18(1):40-45