摘要
航空发动机静电监测技术是一种具有预测能力的在线监测技术,它能有效地解决航空发动机气路高温部件难以实现在线监测的问题,提高发动机PHM能力,有助于先进维修思想的引入和先进维修方式的实施,从而增加视情维修在航空发动机维修保障方式中所占的比例,确保安全和经济效益兼顾。静电监测技术主要通过静电传感器监测发动机气路中的静电荷,借助于信号处理算法和智能模型对气路部件性能和工作状态进行预估。本文首先分析了气路荷电颗粒的形成机理、气路电荷水平的组成及影响因素,介绍了静电监测系统构成及基本原理,然后针对静电监测的关键技术展开了研究:
(1)传感器技术研究
设计了适合于气路高温环境的静电传感器;针对通过解析方法或实验方法难以获得静电传感器灵敏空间分布的问题,基于点电荷的思想建立了棒状传感器的测量模型,采用有限元的方法对静电传感器感应探极的灵敏度空间进行了数值求解,通过数据拟合的方法获得了感应探极的空间灵敏度的分布函数,并对探极空间灵敏度分布的影响因素进行了分析;针对微弱静电感应信号的检测问题,分析了检测电路中噪声来源并给出了相应的解决方案,设计了可以嵌入传感器内部的前置放大器;研究了静电传感器输出信号的频率特性以及影响因素,并通过模拟实验对理论分析的结论进行验证;
(2)静电监测信号降噪方法研究
针对小波阈值滤波方法不能有效去除脉冲噪声,阈值选取对降噪效果影响较大的问题,综合考虑了静电监测信号的噪声构成和能量分布特点,研究了中值滤波与基于Birge-Massart策略的小波分层阈值滤波方法相结合的滤波方法,取得了较好的效果;此外,研究了基于独立分量分析的静电监测信号降噪方法,提出了采用经验模态分解的方法构造与原始信号中噪声总体相近的参考噪声信号,解决了基于ICA降噪过程中出现的欠定问题;通过模拟信号和实测信号验证,表明了研究的两种降噪方法均能有效地提高监测信号的信噪比.
(3)信号特征提取及异常颗粒识别方法研究
依据单颗粒和多颗粒信号的频谱差异,提出了基于信号频谱峰值的重采样预处理方法,并采用小波分解的方法抽取了信号在相对频段内的能量分布特征。基于静电监测信号的特征参数,提出了一种用于异常颗粒识别知识获取的粗糙集神经网络模型,针对模型中离散处理环节,基于属性重要度和决策表不相容度,采自组织神经网络对连续属性进行离散处理;针对神经网络结构优化问题,研究了基于遗传算法的神经网络结构自适应模型,有效地提高了网络泛化能力;通过训练后的神经网络产生比原始数据包含更多预知信息的数据样本,用于规则提取,为异常颗粒识别提供了一种有效的方法。
最后建立了航空发动机气路环境模拟实验平台,并通过该实验平台对静电监测技术的可行性、传感器特性、获取的知识规则等进行了实验验证,通过典型工况的模拟实验,获得了气路静电信号特征参数变化的规律,为气路中辨别异常颗粒提供了参考依据。
Electrostatic monitoring technology is one of the tools with prediction ability that can be used to effectively resolve the problem of real time and on-line monitoring of the heat components of aero-engine. It can improve PHM capabilities of aero-engine, and promote the introduction of advanced maintenance strategy and the implementation of advanced maintenance methods, and increase the proportion of the conditioned based maintenance in the maintenance support, improving the safety while decreasing the maintenance cost. Electrostatic monitoring technology is to monitor the electrostatic charge in exhaust gas of aero-engine via electrostatic sensor, and make performance and state prediction of gas path competent by means of signal processing algorithms and intelligent decision model. Firstly, the formation mechanism of charged particles, the composition and influencing factors of charge level are analyzed, and then the key technologies for electrostatic monitoring are researched in the thesis as follows:
(1) Sensor technology
An electrostatic sensor is designed to meet the requirement of gas path monitoring under high temperature. The sensitivity distribution of electrostatic sensor probe is hard to obtain by Analytical method and experimental method. Aiming at this problem, based on point charge principle the mathematic model of electrostatic field generated by a club-shaped probe is established. Numerical solution method based on finite element is proposed to obtain sensitivity distribution of the sensor probe. The distribution function of sensitivity is obtained by data fitting method, then the effect of structure parameters and material characteristics on the sensing fielding are explored detailedly; Aiming at problems of weak electrostatic induction signal detection, the noise sources of detection circuit are discussed and the relevant solutions are proposed, a preamplifier embedded in sensor is designed. The temporal frequency characteristic of the sensor output signal and influence factors are investigated theoretically and experimentally.
(2) Noise reduction method for electrostatic monitoring signal
The de-noise effect is not good when wavelet threshold filtering is applied to process the electrostatic inducing signal, Based on comprehensive consideration of energy distribution and noise composition, a de-noise method combining with the median filter method and Birge-Massart threshold wavelet method is researched in this thesis and the better filter effect is obtained by experiment. Moreover, A de-noise method for electrostatic monitoring signal based on Independent Component Analysis is researched. A construction method of reference noise signal based on Empirical Mode Decomposition is proposed to construct reference noise signal similar with overall noise in original signal and solve the underdetermined problem while de-noising by Independent Component Analysis method. The experimental result of simulated signal and measured singal shows the two methods can increase the signal-to-noise ratio effectively.
(3) Character extraction and abnormal particles distinguishing method
According to the difference of frequency spectrum of induced by single particle and multi-particles, a pretreatment method based on frequency spectrum characteristics is applied to resample signal, then extract energy distribution characteristic in relative frequency range via wavelet decomposition method.A knowledge acquirement model based on rough sets theory and neural network is proposed in this thesis. Based on the importance of attribute and the consistency of decision table, SOM neural network is employed to discretize continuous data.In order to improve neural network’s generalization ability. A structure auto-adaptive Neural Network model based on genetic algorithm is proposed to optimize structure parameter of Neural Network, then Neural Network matching the training requirement is employed to generate more samples containing foreknowledge, which are used to extract rules. The model provides an effective method for distinguishing abnormal particle.
Lastly, an experimental platform is set up to simulate aero-engine gas path environment, and experimentize study on the electrostatic monitoring technology, electrostatic sensor, and rule extraction model via the experimental platform. The relationship between change law of characteristic parameters and varied conditions is obtained by typical simulated work condition experiment and provides a reference for distinguishing the abnormal particles.
引文
[1] Smith C.T. USAF Condition Based Maintenance Plus(CBM+) Initative. Air Force Logistics Management Agency.2003.
[2] Cutter D M, Thompson O R, Logistics Management Inst Mclean V A. Condition-Based Maintenance Plus Select Program Survey.Defense Technical Information Center,2005.
[3] Kacprzynski G J, Roemer M J, Hess A J, et al. Health Management System Design: Development, Simulation and Cost/Benefit Optimization. Proceeding of IEEE, Naval Air Warfare Center Aircraft Div Patuxent River MD, 2002(6): 3065-3072.
[4] Roemer M J, Kacprzynski G J, Orsagh R F. Assessment of data and knowledge fusion strategies for prognostics and health management. Proceedings of IEEE Aerospace Conference, 2001(6): 62979-62988.
[5] Mathur A. Data mining of aviation data for advancing health management. Proceedings of SPIE, the International Society for Optical Engineering, 2002(4733): 61-71.
[6] Hess A, Calvello G, Dabney T. PHM a key enabler for the JSF autonomic logistics support concept. Proceedings of Aerospace Conference, IEEE, 2004(6): 3543-3550
[7] Hess A, Fila L, Propulsion N, et al. The Joint Strike Fighter (JSF) PHM concept: Potential impact on aging aircraft problems. Proceedings of Aerospace Conference,IEEE, 2002(6): 3021-3026
[8] Ferrell B L, Syst L, Worth F. Air vehicle prognostics and health management. Proceedings of Aerospace Conference, IEEE, 2000(6): 145-146.
[9] DOD. Condition Based Maintenance Plus (CBM+) Guidebook. 2007
[10] Inspector General Dept of Defense Arlington V A. Logistics: Condition Based Maintenance-Plus (D-2003-125).Defense Technical Information Center,2003.
[11] Navarra K, Lawton R, Hearrell N. An Enterprise Strategy for Implementing Conditioned-Based Maintenance Plus (CBM+) Research in the USAF. IEEE AC paper, 2007: 1-7.
[12]张宝珍.预测与健康管理技术的发展及应用.测控技术,2008, 27(2):5-7.
[13]张宝珍. 21世纪的保障方案-JSF的自主式后勤.航空维修与工程, 2003(1): 27-30.
[14]张宝珍,曾天翔.先进的故障预测与状态管理技术.测控技术, 2003, 22(11): 4-6.
[15]曾声奎, Pecht M,吴际.故障预测与健康管理技术(PHM)的现状与发展.航空学报, 2005, 26(5): 627-632.
[16]徐萍,康锐.预测与状态管理系统(PHM)技术研究.测控技术,2004,23(012): 58-60.
[17] Novis A, Powrie H. PHM sensor Implementation in the real world-a status report. Proceedings of IEEE Aerospace Conference, USA, IEEE, 2006(3): 1-9.
[18]孙博,康锐,谢劲松.故障预测与健康管理系统研究和应用现状综述.系统工程与电子技术, 2007, 29(10): 1762-1767.
[19]范作民,孙春林,白杰.航空发动机故障诊断导论.北京:科学出版社, 2004.
[20]孔瑞莲.航空发动机可靠性工程.北京:航空工业出版社, 1996.
[21] Carter T J. Common failures in gas turbine blades. Engineering Failure Analysis, 2005, 12(2):237-247.
[22] Bhaumik S K, Bhaskaran T A, Rangaraju R, et al. Failure of turbine rotor blisk of an aircraft engine. Engineering Failure Analysis,2002,9(3):287-301.
[23]叶志峰.基于模型和神经网络的发动机故障诊断. [博士学位论文],南京,南京航空航天大学, 2003.
[24]毛景立,李鸣,林健.某型涡轮轴发动机稳态气路故障诊断方法.航空动力学报, 2002, 17 (1): 69-74.
[25]郝英,孙健国,白杰.航空燃气涡轮发动机气路故障诊断现状与展望.航空动力学报, 2003, 18(6): 753-760.
[26] Courses E, Surveys T. Use of electrostatic technology for aero engine oil system monitoring. Proceeding of Aerospace Conference, IEEE, 2000(6): 57-71.
[27] Jackson T, Austin J, Fletcher M, et al. Distributed health monitoring for aero-engines on the GRID: DAME. Proceeding of Aerospace Conference, IEEE, 2005: 3738-3747.
[28] Gayme D, Menon S, Ball C, et al. Fault detection and diagnosis in turbine engines using fuzzy logic. North American Fuzzy Information Processing, 2003: 341-346.
[29] Sangha M S, Yu D L, Gomm J B. On-board monitoring and diagnosis for spark ignition engine air path via adaptive neural networks. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering,2006,220(11):1641-1655.
[30] Romessis C, Mathioudakis K. Bayesian network approach for gas path fault diagnosis. Journal of Engineering for Gas Turbines and Power,2006,128(1):64-72.
[31] Vodopianov V, Nikitin V. A New approach to GPA-System for Gas turbine Engine. The 39th AIAA/ASME/SAE/ASEE Joint Propulsion Conference and Exhibit, Huntsville, Alabama, AIAA, 2003: 4986.
[32] Doel D L. TEMPER—a gas-path analysis tool for commercial jet engines. Journal ofEngineering for Gas Turbines and Power,1994,116(1):82-89.
[33]陈果,李成刚,王德友.航空发动机转子-滚动轴承-支承-机匣耦合系统的碰摩故障分析与验证.航空动力学报, 2008, 23(7): 1304-1311.
[34] Adiletta G, Guido a R, Rossi C. Nonlinear dynamics of a rigid unbalanced rotor in journal bearings. Part II: Experimental analysis. Nonlinear Dynamics,1997,14(2):157-189.
[35]陈果.航空发动机内部损伤的三维测量与重建.航空学报, 2004, 17(3): 149-151.
[36] Li Y G. A gas turbine diagnostic approach with transient measurements. Proceedings of the Institution of Mechanical Engineers, Part A: Journal of Power and Energy,2003,217(2):169-177.
[37] Hall D L, Mcmullen S a H. Mathematical techniques in multisensor data fusion.Artech House,2004.
[38]李长有,石鹤,姚红宇.孔探图像特点研究.航空维修与工程, 2006, 239(5): 38-40.
[39] Powrie H E G, Fisher C E. Engine Health Monitoring Towards Total Prognostics. IEEE Aerospace Applications Conference Proceedings, CA,USA, IEEE, 1999(3): 11-20.
[40] Couch R P, Rossbach D R. Sensing Incipient Engine Failure with Electrostatic Probes. Instrumentation for Airbreathing propulsion. Proceedings of the Symposium, Monterey, 1972: 515-529.
[41] Couch R P, Rossbach D R. Sensing Jet Engine Performance and Incipient Failure with Electrostatic Probes,1972.
[42] Mitchell J E. Exploding Wire Simulation of Jet-Engine Gas-Path Microdistresses. [Master thesis], Air Force Inst of Tech Wright-Patterson AFB OHIO School of Engineering, 1975.
[43] Dunn R W. The Electrostatic Sensing of Simulated MA-1A Gas Path Distresses. [Master thesis], Air Force Inst of Tech Wright-Patterson AFB OHIO School of Engineering, 1976.
[44] Gifford W E. A method for analysis of electrostatic probe signals relating to jet-engine microdistresses. [Master thesis], Air Force Inst of Tech Wright-Patterson AFB OHIO School of Engineering, 1976.
[45] Couch R P. Detecting abnormal turbine engine deterioration using electrostatic methods. Journal of Aircraft,1978,15(10):692-695.
[46] Powrie H E G, K.Mcnicholas. Gas path condition monitoring during accelerated mission testing of a demonstrator engine. The 33rd AIAA/ ASME / SAE/ASEE Joint Propulsion Conference and Exhibit, Seattle,WA,USA, AIAA, 1997: 2904.
[47] Powrie H E G, Fisher C E. Monitoring of Foreign Objects Ingested into the Intake of a Gas Turbine Aero-Engine. International Conference on Condition Monitoring Proceedings, UK:University of Wales Swansea, 1999: 175-190.
[48] Fisher C E. Gas path debris monitoring-A 21st century PHM tool IEEE Aerospace Conference Proceedings, Montana, USA, IEEE 2000(6): 441-448.
[49] Powrie H, Novis A. Gas path debris monitoring for F-35 joint strike fighter propulsion system PHM. Proceedings of IEEE Aerospace Conference, Montana, USA, IEEE, 2006(2): 1-8
[50] Powrie H E G. Electrostatic Charge Generation Associated with Machinery Component Generation. Proceedings of IEEE Aerospace Conference, Montana, USA, IEEE, 2002: 2927-2934.
[51] Morris S, Wood R J K, Harvey T J. Use of Electrostatic Charge Monitoring for Early Detection of Adhesive Wear in Oil Lubricated Contacts. Transactions of the ASME, 2002: 288-296.
[52] Vatazhin A, Lebedev A, Likhter V, et al. Turbulent air-steam jets with a condensed dispersed phase: Theory, experiment, numerical modeling. Journal of Aerosol Science,1995,26(1):71-93.
[53] Vatazhin A B, Likhter V A, Sepp V A, et al. Effect of an electric field on the nitrogen oxide emission and structure of a laminar propane diffusion flame. Fluid dynamics, 1995, 30 (2): 166-174.
[54] Vatazhin A B, Golentsov D A, Likhter V A, et al. Aircraft engine state nonobstructive electrostatic monitoring theoretical and laboratory modelling. Journal of Electrostiacs, 1997, 40 (41):711-716.
[55] Vatazhin A B, Ulybyshev K E. Model of electric current formation in aircraft jet engine ducts. Izv. Ros. Akad. Nauk, Mekh. Zhidk. Gaza,2000:139.
[56] Vatazhin A B, Ulybyshev K E. Diffusion and Electrical Processes in the Turbulent Boundary Layer and in the Neighborhood of the Stagnation Point. Fluid dynamics,2001,36(3):429-436.
[57] Vatazhin A B, Starik a M, Kholshchevnikova E K. Electric charging of soot particles in aircraft engine exhaust plumes. Fluid dynamics,2004,39(3):384-392.
[58] Yan Y, Byrne B, Woodhead S, et al. Velocity measurement of pneumatically conveyed solids using electrodynamic sensors. Measurement Science And technology,1995,6:515-537.
[59] Yan Y. Mass flow measurement of bulk solids in pneumatic pipelines. Measurement Science And technology,1996,7:1687-1706.
[60] Gajewski J. Continuous non-contact measurement of electric charges of solid particles in pipes of pneumatic transport. Part I: Physical and mathematical models of a method. Conference Record of the 1989 IEEE/IAS Annual Meeting., San Diego, CA. USA, 1989: 1958-1963.
[61] Gajewski J B. Non-contact electrostatic flow probes for measuring the flow rate and charge inthe two-phase gas–solids flows. Chemical Engineering Science,2006,61(7):2262-2270.
[62] Yan Y. Mass flow measurement of pneumatically conveyed solids. [Ph.D thesis], University of Teesside,U.K, 1992.
[63] Ma J, Yan Y. Design and evaluation of electrostatic sensors for the measurement of velocity of pneumatically conveyed solids. Flow Measurement and Instrumentation,2000,11(3):195-204.
[64] Murnane S N, Barnes R N, Woodhead S R, et al. Electrostatic modelling and measurement of airborne particleconcentration. IEEE Transactions on Instrumentation and Measurement,1996, 45(2):488-492.
[65]张朴,孔力,刘文中,等.气固两相流静电传感器特性的研究.华中科技大学学报,2004, 32(2): 32-34.
[66]许传龙,汤光华,黄键,等.基于静电传感器空间滤波效应的颗粒速度测量.化工学报,2007, 58(1):67-74.
[67]金喜平,李序.静电传感器在煤粉质量流量测量中的研究与应用.沈阳工业大学学报, 2001,23(4): 312-314.
[68]许传龙.气固两相流颗粒荷电及流动参数检测方法研究. [博士学位论文],南京,东南大学, 2005.
[69]金锋,王师.电容式气-固两相流浓度传感器的优化设计.清华大学学报,2002,42 (3): 380-382.
[70]蒋泰毅,熊友辉.气固两相流速度及质量流量的静电测量法研究.华中科技大学学报, 2005,33(1): 93-95.
[71]范玮,严传俊.燃烧学.西安:西北工业大学出版社,2005.
[72]刘尚合.静电放电及危害防护.北京:北京邮电大学出版社,2004.
[73]吴筱敏,周龙保,汪映.离子电流法检测发动机失火和爆震的研究.西安交通大学学报,2002,36(9)895-898.
[74]金如山.航空燃气轮机燃烧室.北京:宇航出版社,1988.
[75]张宝铭,林文荻.静电防护技术手册.北京:电子工业出版社,2000.
[76] Wilhelm S, Haverkamp H, Sorokin A,et al. Detection of very large ions in aircraft gas turbine engine combustor exhaust: charged small soot particles? Atmospheric Environment,2004,38 (27): 4561-4569.
[77]许世海,刘治中.烃火焰中的离子及其对燃烧进程的影响.燃烧科学与技术,1995, 1(4): 347-353.
[78] Vinckier C, Gardner M P, Bayes K D. A study of some primary and secondary chemi-ionization reactions in hydrocarbon oxidations. The 16th Symposium on Combustion (International),Pittsburgh, 1977: 881-889.
[79] Calcote H F, Keil D G. The role of ions in soot formation. Pure Appl. Chem,1990,62:815-824.
[80] Balthasar M, Mauss F, Wang H. A computational study of the thermal ionization of soot particles and its effect on their growth in laminar premixed flames. Combustion and Flame,2002,129(1-2):204-216.
[81] Keil D G. Ionization and soot formation in premixed flames. Twentieth Symposium on Combustion, Pittsburgh, The combusiton Institute, 1984: 1129.
[82] Sorokin A, Vancassel X, Mirabel P. Emission of ions and charged soot particles by aircraft engines. Atmospheric Chemistry and Physics,2003,3(2):325-334.
[83] Sorokin A, Arnold F. Organic positive ions in aircraft gas-turbine engine exhaust. Atmospheric Environment,2006,40(32):6077-6087.
[84] Sorokin A, Arnold F. Electrically charged small soot particles in the exhaust of an aircraft gas-turbine engine combustor:comparison of model and experiment. Atmospheric Environment,2004,38(17):2611-2618.
[85] Gysel M, Nyeki S, Weingartner E, et al. Properties of jet engine combustion particles during the PartEmis experiment: Hygroscopicity at subsaturated conditions. Geophys. Res. Lett,2003,30(11):1566-1569.
[86] Petzold A, Stein C, Nyeki S, et al. Properties of jet engine combustion particles during the PartEmis experiment: Microphysics and chemistry. Geophys. Res. Lett,2003,30(13):1719-1722.
[87] Petzold A, Fiebig M, Fritzsche L, et al. Particle Emissions from Aircraft Engines–An Overview of the European Project PartEmis. European Conference on Aviation, Atmosphere, and Climate (AAC), Proceedings of an International Conference, 2003: 41-51.
[88]任俊,沈健,卢寿慈.颗粒分散科学与技术.北京:化学工业出版社,2005.
[89]田裕鹏,姚恩涛,李开宇.传感器原理.北京:科学出版社,2007.
[90]张祖寿.导体达到静电平衡所需时间的数量级估计.物理与工程,2003,12(2): 20-21.
[91]阚伟,董群,王东军,等.气固两相流固体质量流量测量技术.计量技术,2007(12): 36-39.
[92]蔡圣善,朱耘,徐建军.电动力学.北京:高等教育出版社,2002.
[93] Vatazhin a V, Golentsov D A, Likhter V A, et al. Noncontact electrostatic engine diagnostics: Theoretical and laboratory simulation. Fluid dynamics,1997,32(2):223-232.
[94]许传龙,王式民,孔明,等.静电传感器空间灵敏度特性研究.计量学报, 2006, 27(4): 335-338.
[95]龚曙光. ANSYS工程应用实例解析.北京:机械工业出版社, 2003.
[96]金建铭.电磁场有限元方法.西安:西安电子科技大学出版社, 2001.
[97]吴新杰,张建成.形态滤波和空间滤波在两相流速度测量中的应用传感技术学报, 2007, 27(9): 2124～2127.
[98] Ator J T. Image velocity sensing by optical correlation. Applied Optics,1966,5(8):1325-1331.
[99]戴逸松.微弱信号检测方法及仪器.北京:国防工业出版社, 1994.
[100]梁廷贵.现代集成电路实用手册集成运算放大器电压比较器分册.北京:科学技术文献出版社, 2002.
[101]第七机械工业部.电子元器件优选手册.北京:知识出版社, 1978.
[102]梁瑞林.贴片式电子元件.北京:科学出版社, 2008.
[103] Yang L, Judd M D, Bennoch C J. Denoising UHF signal for PD detection in transformers based on wavelet technique. Electrical Insulation and Dielectric Phenomena, 2004. CEIDP'04. , 2004: 166-169.
[104] Abramovich F, Silverman B W. Wavelet decomposition approaches to statistical inverse problems. Biometrika,1998,85(1):115-129.
[105]黄宜军,汪金友.小波分析在微弱信号测量中的应用研究.计量学报, 2007, 28(2): 163-166.
[106] Lin J, Qu L. Feature extraction based on Morlet wavelet and its application for mechanical fault diagnosis. Journal of Sound and Vibration,2000,234(1):135-148.
[107] Chang C S, Jin J, Kumar S, et al. Denoising of partial discharge signals in wavelet packets domain. IEE Proceedings-Science, Measurement and Technology,2005,152(3):129-140.
[108] Daubechies I. The wavelet transform, time-frequency localization and signal analysis. IEEE transactions on information theory,1990,36(5):961-1005.
[109] Ma X, Zhou C, Kemp I J. Wavelets for the analysis and compression of partial discharge data. 2001: 329-334.
[110] Mallat S G. A theory for multiresolution signal decomposition: the waveletrepresentation. IEEE transactions on pattern analysis and machine intelligence,1989,11(7):674-693.
[111] Mallat S, Zhong S. Characterization of signals from multiscale edges. IEEE transactions on pattern analysis and machine intelligence,1992,14(7):710-732.
[112] Pasti L, Walczak B, Massart D L, et al. Optimization of signal denoising in discrete wavelet transform. Chemometrics and intelligent laboratory systems,1999,48(1):21-34.
[113] Donoho D L, Johnstone I M. Ideal Spatial Adaptation via Wavelet Shrinkage. Biometrika To appear,1992,81(3):425-455.
[114] Donoho D L. De-noise via soft threshold. IEEE Transform, Information Theory, 1995, 41(3):613-627.
[115] Li T, Li Q, Zhu S, et al. A survey on wavelet applications in data mining. ACM SIGKDD Explorations Newsletter,2002,4(2):49-68.
[116] Akay M, Coll D, Hanover N H. Wavelet applications in medicine. IEEE spectrum,1997, 34(5):50-56.
[117] Peng Z K, Chu F L. Application of the wavelet transform in machine condition monitoring and fault diagnostics: a review with bibliography. Mechanical Systems and Signal Processing,2004, 18(2):199-221.
[118] Lalitha E M, Satish L. Wavelet analysis for classification of multi-source PD patterns. IEEE Transactions on Dielectrics and Electrical insulation,2000,7(1):40-47.
[119]文振华,左洪福,李耀华.气路颗粒静电监测技术及实验.航空动力学报, 2008, 23 (12): 2321-2326.
[120]刘丽梅,孙玉荣,李莉.中值滤波技术发展研究.云南师范大学学报, 2004, 24(1): 23-27.
[121]黄庆华,冯焕清.一种快速有效的图像脉冲噪声滤除方法.计算机工程与应用, 2002, 38(17): 113-114.
[122]胡旺,李志蜀,黄奇.基于粗糙集和多向差分图像的去噪方法.小型微型计算机系统, 2006, 27(12): 2341-2345.
[123] Ma X, Zhou C, Kemp I J. Automated wavelet selection and thresholding for PD detection. Electrical Insulation Magazine, IEEE, 2002(18): 37-45.
[124] Bingham E, Hyvarinen A. A fast fixed-point algorithm for independent component analysis of complex valued signals. International Journal of Neural Systems,2000,10(1):1-8.
[125] Hyvarinen A. The fixed-point algorithm and maximum likelihood estimation for independent component analysis. Neural Processing Letters,1999,10(1):1-5.
[126] Hyvarinen A, Shimizu S. A quasi-stochastic gradient algorithm for variance-dependent component analysis. Lecture Notes in Computer Science,2006,4132:211-220.
[127]张贤达.现代信号处理.北京:清华大学出版社, 2002.
[128]史习智.盲信号处理-理论与实践.上海:上海交通大学出版社, 2008.
[129]吴小培,周荷琴.采用独立分量分析方法消除信号中的工频干扰.中国科学技术大学学报, 2000, 30(6): 671-676.
[130] Huang N E, Shen Z, Long S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proceedings-Royal Society of Londona, 1998(454): 903-995.
[131]公茂盛,谢礼立. HHT方法在地震工程中的应用之初步探讨.世界地震工程, 2003, 19(3): 39-43.
[132]孙仁,沈海东,鲁传敬,等. HHT方法在脉搏波信号分析中的应用.医用生物力学, 2006, 21(2): 87-93.
[133]胡劲松,杨世锡,吴昭同,等.基于经验模态分解的旋转机械振动信号滤波技术研究.振动、测试与诊断, 2003, 23(2): 96-98.
[134] Lapini G, Zippo M, Tirone G. The Use of Electrostatic Charge Measurements as an Early Warning of Distress in Heavy-duty Gas Turbines. Proceedings of ASME Turbo Expo, 2001.
[135]牛培峰,张君.小波分析技术在汽轮机故障诊断中的应用.动力工程, 2007, 27(1): 76-80.
[136]周志华,陈世福.神经网络规则抽取.计算机研究与发展, 2002, 39(4): 398-405.
[137]文振华,陈果.基于DS证据理论的航空发动机磨损故障智能融合诊断方法.机械科学与技术, 2005, 24(9): 1018-1021.
[138] Pawlak Z. Rough sets. International Journal of Parallel Programming,1982,11(5): 341-356.
[139] Pawlak Z. Rough sets: Theoretical aspects of reasoning about data.Kluwer Academic Print on Demand,1991.
[140] Haykin S. Neural networks: a comprehensive foundation.Prentice Hall,2008.
[141]魏海坤,神经网络结构设计的理论与方法.北京:国防工业出版社, 2005.
[142] Nguyen S H, Skowron A. Quantization of real value attributes: Rough set and boolean reasoning approach. Bulletin of International Rough Set Society,1997,1(1):5–16.
[143] Susmaga R. Analyzing discretizations of continuous attributes given a monotonic discrimination function. Intelligent data analysis,1997,1(3):157-179.
[144]李兴生,李德毅.一种基于云模型的决策表连续属性离散化方法.模式识别与人工智能, 2003, 16(1): 33-38.
[145] Roy A, Pal S K. Fuzzy discretization of feature space for a rough set classifier. Pattern Recognition Letters,2003,24(6):895-902.
[146]翁敬农.数据挖掘教程.北京:清华大学出版社,2003.
[147]苗夺谦. Rough Set理论中连续属性的离散化方法.自动化学报, 2001, 27(3): 296-302.
[148]田学全,舒兰.基于自组织特征映射的属性离散化方法四川师范大学学报, 2005, 28(4): 432-435.
[149]文振华,左洪福.基于粗糙集-集成神经网络的航空发动机磨损故障诊断方法.中国机械工程, 2007, 18(21): 2580-2584.
[150]张鸿宾.训练多层网络的样本数问题.自动化学报, 1993, 19(1): 71-77.
[151]张乃尧,阎平凡.神经网络与模糊控制.北京:清华大学出版社, 1998.
[152] Geman S, Bienenstock E, Doursat R. Neural networks and the bias/variance dilemma. Neural computation,1992,4(1):1-58.
[153] Kwok T Y, Yeung D Y. Constructive algorithms for structure learning in feed forward neural networks for regression problems. IEEE Transactions on Neural Networks, 1997(8): 630-645.
[154] Kolen J F, Pollack J B. Back propagation is sensitive to initial conditions. Complex Systems,1990,4(3):269-280.
[155] Patridge D. Network generalization differences quantified. Neural Networks,1996,9 (2): 263-271.
[156] Abu-Mostafa Y S. Learning from hints in neural networks. Journal of Complexity,1990,6 (2) : 192-198.
[157] Wang C, Venkatesh S S, Judd J S. Optimal stopping and effective machine complexity in learning. IEEE international Symposium On Information Theory ,IEEE,1995: 169-169.
[158]文振华.智能诊断专家系统知识获取方法研究及应用. [硕士学位论文],南京,南京航空航天大学, 2006.
[159]褚蕾蕾,陈绥阳,周梦.计算智能的数学基础.北京:科学出版社, 2002.
[160]张立明.人工神经网络的模型及其应用.上海:复旦大学出版社, 1993.
[161] Chen Y Q, Thomas D W, Nixon M S. Generating-shrinking algorithm for learning arbitrary classification. Neural Networks,1994,7(9):1477-1489.
[162]陈果,宋兰琪,陈立波.基于神经网络规则提取的航空发动机磨损故障诊断知识获取.航空动力学报, 2008, 23(12): 2170-2176.
[163]王国胤. Rough集理论与知识获取.西安:西安交通大学出版社,2001.
[164] Grzymala-Busse J W, Hu M. A comparison of several approaches to missing attribute values in data mining. Lecture Notes in Computer Science,2001:378-385.
[165]常犁云,王国胤.一种基于Rough Set理论的属性约简及规则提取方法.软件学报,1999, 10(11): 1206-1211.
[166]吴福保,李奇.基于粗集理论知识表达系统的一种归纳学习方法.控制与决策,1999,14 (3): 206-211.
[167]周洁,袁镇福,岑可法,等.光信号互相关测量两相流中颗粒流动速度的研究.中国电机工程学报, 2003, 3(1): 185-188.