民用涡扇发动机健康智能监控技术的研究
|
摘要
民用航空发动机的健康管理是民航管理和运营机构十分关注的热点问题，发动机状态监控、故障诊断和寿命预测等发动机健康管理关键技术，对减少运营和维修成本，有效避免重大事故的发生以及实现发动机视情维修意义重大。由于民航发动机结构复杂、部件繁杂，导致其故障现象与故障原因之间的映射关系复杂多变，特别是对于发动机气路故障，相关性能参数变化不明显，难以直观做出判断。本文对民用涡扇发动机的健康智能监控技术进行研究，主要研究内容和成果如下：
1．首次把QAR数据用于民航发动机的故障检测和故障分类诊断，将基于PCA和信息熵的方法用于民用涡扇发动机的气路健康监控。把PCA方法用于发动机的气路性能排队和评估发动机的气路健康。采用信息熵的方法分析故障征兆和故障原因之间的关系，探究引起发动机整体性能衰减的主要原因，为发动机的状态评估提供技术手段。
2．在发动机故障检测中，采用超平面支持向量机算法研究真实样本的分布特征，对发动机正常样本的分布特征进行学习，优化模型参数，确定最优分类边界，通过计算未知样本和支持向量的距离确定样本的类别归属。在检测模型中，参数变化对检测准确率影响较大，本文采用了验证法进行模型选择，研究表明样本检出率达到93.2%。
3．针对实际民航发动机故障样本少的特点，将支持向量机用于发动机故障分类诊断中，在二元分类器的基础上构造并实现了两种多分类支持向量机算法，通过仿真测试对比两种算法在故障分类诊断中的性能差异。同时对支持向量机三种核函数性能进行研究，包括核参数及模型参数变化对分类结果的影响，结果表明：径向基核函数稍优于其他核函数。
4．为综合评估发动机在翼寿命，采用系统工程中模糊层次分析法、均方根法来综合评定发动机的寿命。用航线、车间、试车台和工程管理数据等四个方面数据分析影响发动机寿命评估预测的因素，用层次分析法构造了发动机评估预测的指标体系，并以综合测评值作为发动机寿命预测指标，结果和实际相符较好。
5.根据民用发动机的特点，将改进的LS-SVM回归应用于航空发动机寿命预测，采用大修后发动机的试车数据，验证了LS-SVM回归预测发动机寿命的有效性，在工程实际中具有理论指导意义。
Civil aeroengine health management is a key issue for civil administrationauthorities and airlines, and engine condition mornitoring, fault diagnosis and lifepredication are key parts of civil aviation engine heath managment system, which arethe important means to reduce operation and maintenance costs and avoid seriousaccidents, then achieving on-condition maintenance. Because of the high complexsystem structures and enormous components, the aeroengine faults vary a lot as wellas the fault consequences and causes, especially in the gas-path fault which therelevant parameters change very slightly, thus it is hard to make an accurate diagnosisonly by working experiences. Civil aviation engine fault diagnosis and life predicationbased on intelligent technologies are studied in this dissertation, The main researchesare listed as follows:
1. QAR date are used for civil aeroengines fault detection amd fault diagnosis.PCA and information entropy method are employed to monitor aeroengine health.Thegaspath performance sort and health assessing are developed based on PCA,.andinformation entropy method is used to analyze relation between fault symptoms andcause.in order to develop the main cause of engine performance deterioration, then toassess engine health condition.
2. In fault detection, the Hyper-plane SVM is employed to train and test thenormal samples and make a data description, model parameters are selected todetermine best classification boundary, then to decide samples classification bycalculating distance between unknown samples and support vectors. Parameters aresensitive to accuracy in detection modle,so cross validation is used for modelselection. The research shows that the diagnostic accuracy reaches93.2%.
3. In fault diagnosis, the multi-classification algorithms are constructed andcompared by simulation samples based on the Least-square SVM because ofinsufficient real civil engine fault samples, The three types of kernel functions arealso studied, including the influence of function parameters and model parameters onthe classification results, and finally compared the results with Back PropagationNeural Network. The research shows that radial base kernel function gets betterresules than others.
4. A sythetical assess method according to mean square root method based onFuzzy AHP method is proposed to predict removal time for Aero-engines, in whichdate from airline,shop, test cell and other information are analyze to determine the main factors influencing engine life-on-wing by AHP. then remaining time of engineis forecasted by a new assessing parameter. The research shows that sythetical assessmethod is according with reality..
5) LS-SVM regression under Bayesian evidence framework is analysized and thecivil aviation engine life prediction model with error bars is built using the test celldata of overhauled engines. the results show the feasibility of prediction model.
1．首次把QAR数据用于民航发动机的故障检测和故障分类诊断，将基于PCA和信息熵的方法用于民用涡扇发动机的气路健康监控。把PCA方法用于发动机的气路性能排队和评估发动机的气路健康。采用信息熵的方法分析故障征兆和故障原因之间的关系，探究引起发动机整体性能衰减的主要原因，为发动机的状态评估提供技术手段。
2．在发动机故障检测中，采用超平面支持向量机算法研究真实样本的分布特征，对发动机正常样本的分布特征进行学习，优化模型参数，确定最优分类边界，通过计算未知样本和支持向量的距离确定样本的类别归属。在检测模型中，参数变化对检测准确率影响较大，本文采用了验证法进行模型选择，研究表明样本检出率达到93.2%。
3．针对实际民航发动机故障样本少的特点，将支持向量机用于发动机故障分类诊断中，在二元分类器的基础上构造并实现了两种多分类支持向量机算法，通过仿真测试对比两种算法在故障分类诊断中的性能差异。同时对支持向量机三种核函数性能进行研究，包括核参数及模型参数变化对分类结果的影响，结果表明：径向基核函数稍优于其他核函数。
4．为综合评估发动机在翼寿命，采用系统工程中模糊层次分析法、均方根法来综合评定发动机的寿命。用航线、车间、试车台和工程管理数据等四个方面数据分析影响发动机寿命评估预测的因素，用层次分析法构造了发动机评估预测的指标体系，并以综合测评值作为发动机寿命预测指标，结果和实际相符较好。
5.根据民用发动机的特点，将改进的LS-SVM回归应用于航空发动机寿命预测，采用大修后发动机的试车数据，验证了LS-SVM回归预测发动机寿命的有效性，在工程实际中具有理论指导意义。
Civil aeroengine health management is a key issue for civil administrationauthorities and airlines, and engine condition mornitoring, fault diagnosis and lifepredication are key parts of civil aviation engine heath managment system, which arethe important means to reduce operation and maintenance costs and avoid seriousaccidents, then achieving on-condition maintenance. Because of the high complexsystem structures and enormous components, the aeroengine faults vary a lot as wellas the fault consequences and causes, especially in the gas-path fault which therelevant parameters change very slightly, thus it is hard to make an accurate diagnosisonly by working experiences. Civil aviation engine fault diagnosis and life predicationbased on intelligent technologies are studied in this dissertation, The main researchesare listed as follows:
1. QAR date are used for civil aeroengines fault detection amd fault diagnosis.PCA and information entropy method are employed to monitor aeroengine health.Thegaspath performance sort and health assessing are developed based on PCA,.andinformation entropy method is used to analyze relation between fault symptoms andcause.in order to develop the main cause of engine performance deterioration, then toassess engine health condition.
2. In fault detection, the Hyper-plane SVM is employed to train and test thenormal samples and make a data description, model parameters are selected todetermine best classification boundary, then to decide samples classification bycalculating distance between unknown samples and support vectors. Parameters aresensitive to accuracy in detection modle,so cross validation is used for modelselection. The research shows that the diagnostic accuracy reaches93.2%.
3. In fault diagnosis, the multi-classification algorithms are constructed andcompared by simulation samples based on the Least-square SVM because ofinsufficient real civil engine fault samples, The three types of kernel functions arealso studied, including the influence of function parameters and model parameters onthe classification results, and finally compared the results with Back PropagationNeural Network. The research shows that radial base kernel function gets betterresules than others.
4. A sythetical assess method according to mean square root method based onFuzzy AHP method is proposed to predict removal time for Aero-engines, in whichdate from airline,shop, test cell and other information are analyze to determine the main factors influencing engine life-on-wing by AHP. then remaining time of engineis forecasted by a new assessing parameter. The research shows that sythetical assessmethod is according with reality..
5) LS-SVM regression under Bayesian evidence framework is analysized and thecivil aviation engine life prediction model with error bars is built using the test celldata of overhauled engines. the results show the feasibility of prediction model.
引文
[1] Tumer, I. and Bajwa, A. A Survey of Aircraft Engine Health MonitoringSystems.35th Joint Propulsion Conference.1999-6; AIAA-99-2528
[2] Pratt&Whitney. Engine Health Monitoring (EHM) Training Guide.USA：Pratt&Whitney Customer Training Center，2001
[3]范作民，孙春林，白杰．航空发动机状态诊断导论．科学出版社，2004,7：1~8
[4]瞿红春，林兆福.民用航空燃气涡轮发动机原理，兵器工业出版社，2006.12：
[5] Link C. Jaw. Recent Advancements in Aircraft Engine Health Management(EHM)Technologies and Recommendations for the Next Step. Proceedings ofTurbo Expo2005:50th ASME International Gas Turbine&AeroengineTechnical Congress,2005-06-09
[6] Jaw L.C. Friend R.，ICEMS：A platform for advanced condition-based healthmanagement，2001IEEE Aerospace Conference，Vol.6, Big Sky, Montana,USA，2001：2909-2914
[7]许春生.远程实时监控技术在飞机维修中的应用.中国民航学院学报，2003,3:6-9.
[8] Richard A. Johnson, Dean W. Wichern．实用多元统计分析．清华大学出版社，2010：334~343
[9]曾声奎,Pecht M G,吴际.故障预测与健康管理(PHM)技术的现状与发展.航空学报,2005,26(5):626-632.
[10]木志高,胡海峰,胡茑庆.武器装备故障预测及健康管理系统设计.兵工自动化,2006,25(3):20-21
[11]洪杰,张大钧,韩继斌.航空发动机关键件使用寿命监视系统设计.北京航空航天大学学报,2000,26(1):45-48.
[12]左洪福,张海军,戎翔.基于比例风险模型的航空发动机视情维修决策.航空动力学报,2006,21(4):716-721.
[13] Doel D.L.，TEMPER-A gas path analysis tool for commercial jet engines，Transactions of ASME，Journal of Engineering for GAS Turbines and Power，1994，116(1)：92-89
[14] Vapnik V N. Statistical Learning Theory[M]. New York：John Wiley，1998.
[15] Vapnik V N，张学工译.统计学习理论的本质[M].北京：清华大学出版社，2000
[16]瞿红春，刘杰，王太勇等，一种基于信息熵的航空发动机性能评估方法，机械科学与技术，2009.6（28）:701～704
[17]祁亨年.支持向量机及其应用研究综述.计算机工程，2004，30（10）：6-9.Doel, David L.，Assessment of Weighted-Least-Squares Based Gas PathAnalysis，ASME93-GT-119
[18]许建华，张学工，李衍达.支持向量机的新发展[J].控制与决策，2004，19（5）：481-484
[19]杜树新，吴铁军.模式识别中的支持向量方法[J].浙江大学学报（工学版），2003，37（5）：521-526
[20] Li.Y.G.，A gas turbine diagnostic approach with transient measurements，Journal of Power and Energy，2003，217（A2）：169-177
[21] Urban L. A.，Gas Path Analysis Applied to Turbine Engine ConditionMonitoring，AIAA72-1082
[22] Zedda M. Singh R.，Gas Turbine Engine and sensor Fault Diagnosis UsingOptimization Techniques，AIAA99-2842
[23] Bettocchi R, Spnia P.R.，Diagnosis of Gas Turbine Conditions by Means ofthe Inverse Cycle Calculation，ASME99-GT-185
[24] Davison C.R, Birk A.M，Steady State Performance Simulation of AuxiliaryPower Unit with Faults for Component Diagnosis，ASME2000-GT-623
[25]李应红，尉询楷，刘建勋，支持向量机的工程应用.北京：兵器工业出版社，2004
[26]郝英.基于智能技术的民航发动机故障诊断和寿命预测研究[D]：[博士学位论文].南京：南京航空航天大学能源与动力学院，2006
[27] Davison C.R, Birk A.M， Development of Fault Diagnosis and FailurePrediction Techniques for Small Gas Turbine Engines，ASME2001-GT-548
[28]李良敏，屈梁生基于遗传编程和支持向量机的故障诊断模型[J].西安交通大学学报，2004，38（3）：239-242
[29]李凌均，张周锁，何正嘉.支持向量机在机械故障诊断中的应用研究[J].计算机工程与应用，2002，（19）：19-21
[30]王华忠，张雪申，俞金寿.基于支持向量机的故障诊断方法[J].华东理工大学学报，2004，30（2）：179-181
[31] Sun bin, Zhang Jin, Zhang Shaoji，An Investigation of Artificial Network(NN)in Quantitative Diagnosis for Turbofan Engine，ASME2000-GT-32
[32] Zedda M, Singh R.，Fault Diagnosis of a Turbofan engine using neuralnetwork: a Quantitative Approach，AIAA98-3602
[33]杨俊，谢寿生，于东军.基于支持向量机的航空发动机故障诊断[J].机械科学与技术，2005，24（1）：123～126
[34]徐启华，师军.基于支持向量机的航空发动机故障诊断[J].航空动力学报，2005，20（2）：298-302
[35]陈恬孙健国杨蔚华等，自组织神经网络航空发动机气路故障诊断，航空学报，2003，24(1)：46-48
[36]黄向华孙健国，基于自联想网络的发动机传感器解析余度技术，航空动力学报，1999，14(4)：433-436
[37]刘杰，基于支持向量机的民用涡扇发动机故障诊断的研究[硕士学位论文]，中国民航大学，2009：35-55
[38] Tax D.，One-class classification，[PhD. dissertation]，Dutch，The graduateschool of ASCI，2001
[39] Chih-Chung Chang，Chih-Jen Lin. LIBSVM: a Library for Support VectorMachines[EB/OL].http://www.csie.ntu.edu.tw/~cjlin，2008-10
[40] Mika S., Sch lkpof B, Smola A, etc, Kernel PCA and de-nosing in featurespaces，In M.S.Kearns, S.A. Solla, D.A. Cohn. editors, Advances in NeuralInformation Processing Systems11：536-542，MIT Press,1999
[41] Suykens J A K，Vandewalle J. Least Squares Support Sector MachineClassifiers[J]. Neural Processing Letters，1999，9(3)：293-300S
[42] Zedda M, Singh R.，Fault Diagnosis of a Turbofan engine using neuralnetwork: a Quantitative Approach，AIAA98-3602
[43]叶志锋孙健国，用自联想网络处理发动机测量参数，数据采集与处理，2003，18(2)：218-221
[44]韩力群.人工神经网络理论、设计及应用[M].北京：化学工业出版社.2007
[45] DePold H. R, Gass F. D.，The Application of Expert System and NeuralNetworks to Gas Turbine Prognostics and Diagnostics，ASME98-GT-101
[46] Mackay D J C.，The evidence framework applied to classification networks，Neural Computation，1992，4(4)：720-736.
[47] Mackay D J C.，Probable network and plausible predictions-A review ofpractical Bayesian methods for supervised neural networks， NetworkComputation in Neural Systems,1995,6:469-505.
[48]边肇祺张学工，模式识别（第二版），北京，清华大学出版社,2000：284-303
[49] Tax D.，One-class classification，[PhD. dissertation]，Dutch，The graduateschool of ASCI，2001
[50] P kalska E., Paclik P.,Duin R.P.W.， A generalized kernel approach todissimilarity-based classification，Journal of Machine Learning Research，2001，2(2):175-211.
[51] P kalska E. Tax D. Duni R.P.W.，One-class LP classifier for dissimilarityrepresentations， Advances in Neural Information Processing Systems16(Sixteenth Annual NIPS Conference)，British Columbia, Canada，NIPS，2003：777-784
[52] Hargrave SM, Fleming PJ.，The Use of Cased-based Reasoning Technology toAid Fault Isolation In a Modern Gas Turbine Engine Design， ASME98-GT-61
[53] Campbell C.，An Introduction to Kernel Methods，Radial Basis FunctionNetworks: Design and Applications，2001:155-192
[54] Scholkopf B.，Statistical Learning and Kernel Methods，MSR-TR-2000-23
[55] Muller K.R., Mika S., R tsch G., Tsuda K., Schoelkopf B.，An introduction tokernel-based learning algorithms. IEEE Transactions on neural networks,2001,12(2):181-202
[56] Sch lkpof B, Smola A., Muller K.，Nonlinear components analysis as a kerneleigenvalue problem，Neural Computation，1998,10:1299-1319
[57] Mika S., Sch lkpof B, Smola A, etc, Kernel PCA and de-nosing in featurespaces，In M.S.Kearns, S.A. Solla, D.A. Cohn. editors, Advances in NeuralInformation Processing Systems11：536-542，MIT Press,1999
[58] Suykens J.，Nonlinear modeling and support vector machines，in Proc. of theIEEE International Conference on Instrumentation and MeasurementTechnology，Budapest, Hungary,2001：287-294.
[59] Sch lkpof B. Williamson R. Smola A.etc. Support vector method for noveltydetection，In S. A. Solla, T. K. Leen, and K.-R. Mller, editors, Advances inNeural Information Processing Systems12：582-588，MIT Press,2000
[60] Campbell C. Bennett K.P. A linear programming approach to noveltydetection，In T. K.Leen, T. G. Dietterich, and V. Tresp, editors, Advances inNeural Information Processing Systems13：395-401. MIT Press,2001.
[61] Tax D., Duin R. Data domain description by support vectors, In M.Verleysened Proceedings of ESANN99. Bressels: D.Facto Press,1999:251-256
[62] Tax D. Duin R. Outliers and data descriptions, In: R.L.Lagendijk, J.W.J.Heijnsdijk, A.D. Pimentel, M.H.F. Wilkinson eds., Proceedings of. ASCI2001.Delft: ASCI,2001:234-241.
[63] Suykens,J.A.K.,&Vandewalle,J Least squares support vector machineclassifiers. Neural Processing Letters,1999,9:293-300
[64]郝英孙健国杨国庆白杰，The application of support vector machines togas turbine performance diagnosis. Acta Aeronautica et Astronautica Sinica,2005,18(1):15-19.
[65]罗颖锋曾进，基于支持向量机的燃气轮机故障诊断，热能动力工程，2004,19（4）:354-357
[66] Hayton P., Schoelkopf B., Tarassenko L. et al.，Support vector NoveltyDetection Applied to Jet engine Vibration Spectra，Fourteenth Annual NeuralInformation Processing Systems (NIPS) Conference，2000:946-952
[67]郝英孙健国杨国庆白杰，基于支持向量机的民航发动机故障检测研究，航空学报，2005，26（4）：434-438
[68] Ryshetsky M, Ortmann S, Glester M.，Support Vector Approaches for EngineKnock Detection， IJCNN '99. International Joint Conference on NeuralNetworks,1999:969-974
[69] Kowk J T.，The evidence framework applied to support vector machines，IEEETransactions on Neural Networks,2000,11(5):1162-1173
[70] Kowk J T. Integrating the evidence framework and the support vector machine,In Proc. Of the European Symposium on Artificial Neural Networks (ESANN1999), Bruges, Belgium,1999:177-182
[71] Law M., Kwok J.T. Bayesian support vector regression, In Proceedings of theEighth International Workshop on Artificial Intelligence and Statistics, KeyWest, Florida,2001:239-244
[72] Gestel T., Suykens J. Lanckriet G. etc. Bayesian framework for least squaressupport vector machines classifiers, Gaussian process and kernel Fisherdiscriminant analysis, Neural Computation,2002,15（5）：1115-1148.
[73] Gestel T., Suykens J. Baestaens D. etc. Financial time series prediction usingleast squares support vector machines within evidence framework，IEEETransactions on Neural Networks，2001，12(4)：809-821.
[74] Yager R R. On the D-S framework and new combination rules. InformationSciences,1987,41(2):93-138
[75]孙全叶秀清顾伟康,一种新的基于证据理论的合成公式,电子学报,2000,28(8):117-119
[76]李弼程王波魏俊等，一种有效的证据理论合成公式，数据采集与处理，2002，17(1):33-36
[77] Roemer M. J.，Engine health monitoring system for advanced diagnosticmonitoring for gas turbine engines，AFRL-PR-WP-TR-1998-2120
[78]胡金海谢寿生，基于遗传算法的发动机性能监控与故障诊断，推进技术，2003，24（3）：198-200
[79]胡金海谢寿生骆广琦等，基于支持向量机方法的发动机性能趋势预测，推进技术，2005，26（3）：260-264
[80]胡金海谢寿生，表征某型发动机工作状况的特征参数研究，燃气涡轮试验与研究2005，18（1）：27-30
[81] Palmer C.A.，Combing Bayesian Belief Networks with Gas Path Analysis forTest Cell Diagnostics and Overhaull，ASME98-GT-168
[82]朱之丽,孟凡涛，模型辨识法诊断发动机故障的分析，航空学会第11届动力控制学术会议论文集，温州，2002：148-152
[83]宋金光许春生，基于遗传算法和BP网络的航空发动机拆换期望预测航空动力学报2003，18（5）：676-
[84] Pratt&Whintey，Engine health monitoring (EHM) training guide, USA，Pratt&Whintey Customer Training Center,2001
[85] Pratt&Whintey，Engine condition monitoring (ECM) II training guide, USA，Pratt&Whintey Customer Training Center,1997
[86] GE Aircraft Engine/CFMI, Eegnie condition monitoring, USA, GEAE/CFMI,2001
[87] Boeing, B737Aircraft Maintenance Manual (AMM), USA, Boeing,2001:ATA75-31-00:520-520,
[88]郝英，发动机起飞EGT裕度的估算，航空维修与工程，2004（2）：39-40
[89]许春生，民航发动机使用可靠性研究结题报告(该项目获国家科技进步二等奖)，中国民航学院，2000
[90] Zedda M. Singh R.，Gas Turbine Engine and sensor Fault Diagnosis UsingOptimization Techniques，AIAA99-2842
[91] Bettocchi R, Spnia P.R.，Diagnosis of Gas Turbine Conditions by Means ofthe Inverse Cycle Calculation，ASME99-GT-185
[92] Davison C.R, Birk A.M，Steady State Performance Simulation of AuxiliaryPower Unit with Faults for Component Diagnosis，ASME2000-GT-623
[93] Davison C.R, Birk A.M， Development of Fault Diagnosis and FailurePrediction Techniques for Small Gas Turbine Engines，ASME2001-GT-548
[94] Sun bin, Zhang Jin, Zhang Shaoji，An Investigation of Artificial Network(NN)in Quantitative Diagnosis for Turbofan Engine，ASME2000-GT-32
[95] Zedda M, Singh R.，Fault Diagnosis of a Turbofan engine using neuralnetwork: a Quantitative Approach，AIAA98-3602
[96] Mackay D J C.，The evidence framework applied to classification networks，Neural Computation，1992，4(4)：720-736.
[97] Mackay D J C.，Probable network and plausible predictions-A review ofpractical Bayesian methods for supervised neural networks， NetworkComputation in Neural Systems,1995,6:469-505.
[98] Tax D., Duin R. Data domain description by support vectors, In M.Verleysened Proceedings of ESANN99. Bressels: D.Facto Press,1999:251-256
[99] Tax D. Duin R. Outliers and data descriptions, In: R.L.Lagendijk, J.W.J.Heijnsdijk, A.D. Pimentel, M.H.F. Wilkinson eds., Proceedings of. ASCI2001.Delft: ASCI,2001:234-241.
[100] Suykens,J.A.K.,&Vandewalle,J Least squares support vector machineclassifiers. Neural Processing Letters,1999,9:293-300
[101] Sch lkpof B, Smola A., Muller K.，Nonlinear components analysis as a kerneleigenvalue problem，Neural Computation，1998,10:1299-1319
[102]屈梁生，张西宁，机械故障诊断理论，西安交通大学出版社，2009.12
[103]吴祈宗，系统工程，北京理工大学出版社，2008.7：63-73
[104]王帅,李林山，改进的层次分析法在发动机加权评估中的应用[J]，中国民航学院学报,2004,22(97)：107-113
[105]张维全，层次分析法与模糊理论在科研成果评价中的应用[J]，宁夏大学学报，2002，23(3)：230-233
[106] Manfred K.Algorithmic aero-engine life usage monotoring based on referenceanalysis of design mission[J]，MTU Aero Engines,2001,25(3):1268-1278
[107] Jurgen Broede, Hugo Pfoertner, Klaus Richter.The importance of testingforsuccessful life usage monitoring systems[J]. ArbeitslreisTelemeteie,1999,18(5):1112-1133
[108]高扬，牟德一，航空安全评估中的层次分析法-AHP[J]，中国民航学院学报，2000，10(3):38-41
[109]王帅,许春生，发动机机队状态排序技术[J]，航空维修与工程,2004，222(2):33-35
[110]刘浩广，蔡绍洪．信息熵及其随机性．贵州大学学报（自然科学版），2007，24（4）：350~351
[111]符向前，刘光临，蒋劲等．基于信息熵的机组运行劣化度综合指标[J]．电力系统自动化，2005，29（7）：75~78
[112]袁志发，周静芋．多元统计分析．科学出版社，2002，10:188~200
[113]徐晓敏．层次分析法的应用[J]．统计与决策，2008，1，156~158
[114] Roemer M. J.，Development of diagnostic and prognostic technologies foraerospace health management applications，2001IEEE Aerospace Conference,Vol.6, Big Sky, Montana, USA,2001：3139-3147
[115] Brothernton Tom. Prognosis of faults in gas turbine engines,2001IEEEAerospace Conference, Vol.6, Big Sky, Montana, USA,2001：163-171
[116] GE Aircraft Engine/CFMI, Eegnie condition monitoring, USA, GEAE/CFMI,2001
[117]中国民用航空总局令第41号，CCAR-121AA民用航空器运行适航管理规定
[S]，北京：航空工业出版社,1997
[118]王吉星.基于人工神经网络和遗传算法的民航发动机状态评估与故障诊断方法研究：[硕士学位论文].天津：中国民航学院机电学院，2004
[119]于文武，康力平.基于AHP的航空发动机在翼寿命预测[J]：航空器制造技术，2010（20）：48-50
[120] Gestel T V，Suykens J A K，et al. Benchmarking Least Squares SupportVector Machine Classifiers[J]. Machine Learning，2004，54：5-32
[121] Suykens J A K，Vandewalle J. Least Squares Support Sector MachineClassifiers[J]. Neural Processing Letters，1999，9(3)：293-300
[2] Pratt&Whitney. Engine Health Monitoring (EHM) Training Guide.USA：Pratt&Whitney Customer Training Center，2001
[3]范作民，孙春林，白杰．航空发动机状态诊断导论．科学出版社，2004,7：1~8
[4]瞿红春，林兆福.民用航空燃气涡轮发动机原理，兵器工业出版社，2006.12：
[5] Link C. Jaw. Recent Advancements in Aircraft Engine Health Management(EHM)Technologies and Recommendations for the Next Step. Proceedings ofTurbo Expo2005:50th ASME International Gas Turbine&AeroengineTechnical Congress,2005-06-09
[6] Jaw L.C. Friend R.，ICEMS：A platform for advanced condition-based healthmanagement，2001IEEE Aerospace Conference，Vol.6, Big Sky, Montana,USA，2001：2909-2914
[7]许春生.远程实时监控技术在飞机维修中的应用.中国民航学院学报，2003,3:6-9.
[8] Richard A. Johnson, Dean W. Wichern．实用多元统计分析．清华大学出版社，2010：334~343
[9]曾声奎,Pecht M G,吴际.故障预测与健康管理(PHM)技术的现状与发展.航空学报,2005,26(5):626-632.
[10]木志高,胡海峰,胡茑庆.武器装备故障预测及健康管理系统设计.兵工自动化,2006,25(3):20-21
[11]洪杰,张大钧,韩继斌.航空发动机关键件使用寿命监视系统设计.北京航空航天大学学报,2000,26(1):45-48.
[12]左洪福,张海军,戎翔.基于比例风险模型的航空发动机视情维修决策.航空动力学报,2006,21(4):716-721.
[13] Doel D.L.，TEMPER-A gas path analysis tool for commercial jet engines，Transactions of ASME，Journal of Engineering for GAS Turbines and Power，1994，116(1)：92-89
[14] Vapnik V N. Statistical Learning Theory[M]. New York：John Wiley，1998.
[15] Vapnik V N，张学工译.统计学习理论的本质[M].北京：清华大学出版社，2000
[16]瞿红春，刘杰，王太勇等，一种基于信息熵的航空发动机性能评估方法，机械科学与技术，2009.6（28）:701～704
[17]祁亨年.支持向量机及其应用研究综述.计算机工程，2004，30（10）：6-9.Doel, David L.，Assessment of Weighted-Least-Squares Based Gas PathAnalysis，ASME93-GT-119
[18]许建华，张学工，李衍达.支持向量机的新发展[J].控制与决策，2004，19（5）：481-484
[19]杜树新，吴铁军.模式识别中的支持向量方法[J].浙江大学学报（工学版），2003，37（5）：521-526
[20] Li.Y.G.，A gas turbine diagnostic approach with transient measurements，Journal of Power and Energy，2003，217（A2）：169-177
[21] Urban L. A.，Gas Path Analysis Applied to Turbine Engine ConditionMonitoring，AIAA72-1082
[22] Zedda M. Singh R.，Gas Turbine Engine and sensor Fault Diagnosis UsingOptimization Techniques，AIAA99-2842
[23] Bettocchi R, Spnia P.R.，Diagnosis of Gas Turbine Conditions by Means ofthe Inverse Cycle Calculation，ASME99-GT-185
[24] Davison C.R, Birk A.M，Steady State Performance Simulation of AuxiliaryPower Unit with Faults for Component Diagnosis，ASME2000-GT-623
[25]李应红，尉询楷，刘建勋，支持向量机的工程应用.北京：兵器工业出版社，2004
[26]郝英.基于智能技术的民航发动机故障诊断和寿命预测研究[D]：[博士学位论文].南京：南京航空航天大学能源与动力学院，2006
[27] Davison C.R, Birk A.M， Development of Fault Diagnosis and FailurePrediction Techniques for Small Gas Turbine Engines，ASME2001-GT-548
[28]李良敏，屈梁生基于遗传编程和支持向量机的故障诊断模型[J].西安交通大学学报，2004，38（3）：239-242
[29]李凌均，张周锁，何正嘉.支持向量机在机械故障诊断中的应用研究[J].计算机工程与应用，2002，（19）：19-21
[30]王华忠，张雪申，俞金寿.基于支持向量机的故障诊断方法[J].华东理工大学学报，2004，30（2）：179-181
[31] Sun bin, Zhang Jin, Zhang Shaoji，An Investigation of Artificial Network(NN)in Quantitative Diagnosis for Turbofan Engine，ASME2000-GT-32
[32] Zedda M, Singh R.，Fault Diagnosis of a Turbofan engine using neuralnetwork: a Quantitative Approach，AIAA98-3602
[33]杨俊，谢寿生，于东军.基于支持向量机的航空发动机故障诊断[J].机械科学与技术，2005，24（1）：123～126
[34]徐启华，师军.基于支持向量机的航空发动机故障诊断[J].航空动力学报，2005，20（2）：298-302
[35]陈恬孙健国杨蔚华等，自组织神经网络航空发动机气路故障诊断，航空学报，2003，24(1)：46-48
[36]黄向华孙健国，基于自联想网络的发动机传感器解析余度技术，航空动力学报，1999，14(4)：433-436
[37]刘杰，基于支持向量机的民用涡扇发动机故障诊断的研究[硕士学位论文]，中国民航大学，2009：35-55
[38] Tax D.，One-class classification，[PhD. dissertation]，Dutch，The graduateschool of ASCI，2001
[39] Chih-Chung Chang，Chih-Jen Lin. LIBSVM: a Library for Support VectorMachines[EB/OL].http://www.csie.ntu.edu.tw/~cjlin，2008-10
[40] Mika S., Sch lkpof B, Smola A, etc, Kernel PCA and de-nosing in featurespaces，In M.S.Kearns, S.A. Solla, D.A. Cohn. editors, Advances in NeuralInformation Processing Systems11：536-542，MIT Press,1999
[41] Suykens J A K，Vandewalle J. Least Squares Support Sector MachineClassifiers[J]. Neural Processing Letters，1999，9(3)：293-300S
[42] Zedda M, Singh R.，Fault Diagnosis of a Turbofan engine using neuralnetwork: a Quantitative Approach，AIAA98-3602
[43]叶志锋孙健国，用自联想网络处理发动机测量参数，数据采集与处理，2003，18(2)：218-221
[44]韩力群.人工神经网络理论、设计及应用[M].北京：化学工业出版社.2007
[45] DePold H. R, Gass F. D.，The Application of Expert System and NeuralNetworks to Gas Turbine Prognostics and Diagnostics，ASME98-GT-101
[46] Mackay D J C.，The evidence framework applied to classification networks，Neural Computation，1992，4(4)：720-736.
[47] Mackay D J C.，Probable network and plausible predictions-A review ofpractical Bayesian methods for supervised neural networks， NetworkComputation in Neural Systems,1995,6:469-505.
[48]边肇祺张学工，模式识别（第二版），北京，清华大学出版社,2000：284-303
[49] Tax D.，One-class classification，[PhD. dissertation]，Dutch，The graduateschool of ASCI，2001
[50] P kalska E., Paclik P.,Duin R.P.W.， A generalized kernel approach todissimilarity-based classification，Journal of Machine Learning Research，2001，2(2):175-211.
[51] P kalska E. Tax D. Duni R.P.W.，One-class LP classifier for dissimilarityrepresentations， Advances in Neural Information Processing Systems16(Sixteenth Annual NIPS Conference)，British Columbia, Canada，NIPS，2003：777-784
[52] Hargrave SM, Fleming PJ.，The Use of Cased-based Reasoning Technology toAid Fault Isolation In a Modern Gas Turbine Engine Design， ASME98-GT-61
[53] Campbell C.，An Introduction to Kernel Methods，Radial Basis FunctionNetworks: Design and Applications，2001:155-192
[54] Scholkopf B.，Statistical Learning and Kernel Methods，MSR-TR-2000-23
[55] Muller K.R., Mika S., R tsch G., Tsuda K., Schoelkopf B.，An introduction tokernel-based learning algorithms. IEEE Transactions on neural networks,2001,12(2):181-202
[56] Sch lkpof B, Smola A., Muller K.，Nonlinear components analysis as a kerneleigenvalue problem，Neural Computation，1998,10:1299-1319
[57] Mika S., Sch lkpof B, Smola A, etc, Kernel PCA and de-nosing in featurespaces，In M.S.Kearns, S.A. Solla, D.A. Cohn. editors, Advances in NeuralInformation Processing Systems11：536-542，MIT Press,1999
[58] Suykens J.，Nonlinear modeling and support vector machines，in Proc. of theIEEE International Conference on Instrumentation and MeasurementTechnology，Budapest, Hungary,2001：287-294.
[59] Sch lkpof B. Williamson R. Smola A.etc. Support vector method for noveltydetection，In S. A. Solla, T. K. Leen, and K.-R. Mller, editors, Advances inNeural Information Processing Systems12：582-588，MIT Press,2000
[60] Campbell C. Bennett K.P. A linear programming approach to noveltydetection，In T. K.Leen, T. G. Dietterich, and V. Tresp, editors, Advances inNeural Information Processing Systems13：395-401. MIT Press,2001.
[61] Tax D., Duin R. Data domain description by support vectors, In M.Verleysened Proceedings of ESANN99. Bressels: D.Facto Press,1999:251-256
[62] Tax D. Duin R. Outliers and data descriptions, In: R.L.Lagendijk, J.W.J.Heijnsdijk, A.D. Pimentel, M.H.F. Wilkinson eds., Proceedings of. ASCI2001.Delft: ASCI,2001:234-241.
[63] Suykens,J.A.K.,&Vandewalle,J Least squares support vector machineclassifiers. Neural Processing Letters,1999,9:293-300
[64]郝英孙健国杨国庆白杰，The application of support vector machines togas turbine performance diagnosis. Acta Aeronautica et Astronautica Sinica,2005,18(1):15-19.
[65]罗颖锋曾进，基于支持向量机的燃气轮机故障诊断，热能动力工程，2004,19（4）:354-357
[66] Hayton P., Schoelkopf B., Tarassenko L. et al.，Support vector NoveltyDetection Applied to Jet engine Vibration Spectra，Fourteenth Annual NeuralInformation Processing Systems (NIPS) Conference，2000:946-952
[67]郝英孙健国杨国庆白杰，基于支持向量机的民航发动机故障检测研究，航空学报，2005，26（4）：434-438
[68] Ryshetsky M, Ortmann S, Glester M.，Support Vector Approaches for EngineKnock Detection， IJCNN '99. International Joint Conference on NeuralNetworks,1999:969-974
[69] Kowk J T.，The evidence framework applied to support vector machines，IEEETransactions on Neural Networks,2000,11(5):1162-1173
[70] Kowk J T. Integrating the evidence framework and the support vector machine,In Proc. Of the European Symposium on Artificial Neural Networks (ESANN1999), Bruges, Belgium,1999:177-182
[71] Law M., Kwok J.T. Bayesian support vector regression, In Proceedings of theEighth International Workshop on Artificial Intelligence and Statistics, KeyWest, Florida,2001:239-244
[72] Gestel T., Suykens J. Lanckriet G. etc. Bayesian framework for least squaressupport vector machines classifiers, Gaussian process and kernel Fisherdiscriminant analysis, Neural Computation,2002,15（5）：1115-1148.
[73] Gestel T., Suykens J. Baestaens D. etc. Financial time series prediction usingleast squares support vector machines within evidence framework，IEEETransactions on Neural Networks，2001，12(4)：809-821.
[74] Yager R R. On the D-S framework and new combination rules. InformationSciences,1987,41(2):93-138
[75]孙全叶秀清顾伟康,一种新的基于证据理论的合成公式,电子学报,2000,28(8):117-119
[76]李弼程王波魏俊等，一种有效的证据理论合成公式，数据采集与处理，2002，17(1):33-36
[77] Roemer M. J.，Engine health monitoring system for advanced diagnosticmonitoring for gas turbine engines，AFRL-PR-WP-TR-1998-2120
[78]胡金海谢寿生，基于遗传算法的发动机性能监控与故障诊断，推进技术，2003，24（3）：198-200
[79]胡金海谢寿生骆广琦等，基于支持向量机方法的发动机性能趋势预测，推进技术，2005，26（3）：260-264
[80]胡金海谢寿生，表征某型发动机工作状况的特征参数研究，燃气涡轮试验与研究2005，18（1）：27-30
[81] Palmer C.A.，Combing Bayesian Belief Networks with Gas Path Analysis forTest Cell Diagnostics and Overhaull，ASME98-GT-168
[82]朱之丽,孟凡涛，模型辨识法诊断发动机故障的分析，航空学会第11届动力控制学术会议论文集，温州，2002：148-152
[83]宋金光许春生，基于遗传算法和BP网络的航空发动机拆换期望预测航空动力学报2003，18（5）：676-
[84] Pratt&Whintey，Engine health monitoring (EHM) training guide, USA，Pratt&Whintey Customer Training Center,2001
[85] Pratt&Whintey，Engine condition monitoring (ECM) II training guide, USA，Pratt&Whintey Customer Training Center,1997
[86] GE Aircraft Engine/CFMI, Eegnie condition monitoring, USA, GEAE/CFMI,2001
[87] Boeing, B737Aircraft Maintenance Manual (AMM), USA, Boeing,2001:ATA75-31-00:520-520,
[88]郝英，发动机起飞EGT裕度的估算，航空维修与工程，2004（2）：39-40
[89]许春生，民航发动机使用可靠性研究结题报告(该项目获国家科技进步二等奖)，中国民航学院，2000
[90] Zedda M. Singh R.，Gas Turbine Engine and sensor Fault Diagnosis UsingOptimization Techniques，AIAA99-2842
[91] Bettocchi R, Spnia P.R.，Diagnosis of Gas Turbine Conditions by Means ofthe Inverse Cycle Calculation，ASME99-GT-185
[92] Davison C.R, Birk A.M，Steady State Performance Simulation of AuxiliaryPower Unit with Faults for Component Diagnosis，ASME2000-GT-623
[93] Davison C.R, Birk A.M， Development of Fault Diagnosis and FailurePrediction Techniques for Small Gas Turbine Engines，ASME2001-GT-548
[94] Sun bin, Zhang Jin, Zhang Shaoji，An Investigation of Artificial Network(NN)in Quantitative Diagnosis for Turbofan Engine，ASME2000-GT-32
[95] Zedda M, Singh R.，Fault Diagnosis of a Turbofan engine using neuralnetwork: a Quantitative Approach，AIAA98-3602
[96] Mackay D J C.，The evidence framework applied to classification networks，Neural Computation，1992，4(4)：720-736.
[97] Mackay D J C.，Probable network and plausible predictions-A review ofpractical Bayesian methods for supervised neural networks， NetworkComputation in Neural Systems,1995,6:469-505.
[98] Tax D., Duin R. Data domain description by support vectors, In M.Verleysened Proceedings of ESANN99. Bressels: D.Facto Press,1999:251-256
[99] Tax D. Duin R. Outliers and data descriptions, In: R.L.Lagendijk, J.W.J.Heijnsdijk, A.D. Pimentel, M.H.F. Wilkinson eds., Proceedings of. ASCI2001.Delft: ASCI,2001:234-241.
[100] Suykens,J.A.K.,&Vandewalle,J Least squares support vector machineclassifiers. Neural Processing Letters,1999,9:293-300
[101] Sch lkpof B, Smola A., Muller K.，Nonlinear components analysis as a kerneleigenvalue problem，Neural Computation，1998,10:1299-1319
[102]屈梁生，张西宁，机械故障诊断理论，西安交通大学出版社，2009.12
[103]吴祈宗，系统工程，北京理工大学出版社，2008.7：63-73
[104]王帅,李林山，改进的层次分析法在发动机加权评估中的应用[J]，中国民航学院学报,2004,22(97)：107-113
[105]张维全，层次分析法与模糊理论在科研成果评价中的应用[J]，宁夏大学学报，2002，23(3)：230-233
[106] Manfred K.Algorithmic aero-engine life usage monotoring based on referenceanalysis of design mission[J]，MTU Aero Engines,2001,25(3):1268-1278
[107] Jurgen Broede, Hugo Pfoertner, Klaus Richter.The importance of testingforsuccessful life usage monitoring systems[J]. ArbeitslreisTelemeteie,1999,18(5):1112-1133
[108]高扬，牟德一，航空安全评估中的层次分析法-AHP[J]，中国民航学院学报，2000，10(3):38-41
[109]王帅,许春生，发动机机队状态排序技术[J]，航空维修与工程,2004，222(2):33-35
[110]刘浩广，蔡绍洪．信息熵及其随机性．贵州大学学报（自然科学版），2007，24（4）：350~351
[111]符向前，刘光临，蒋劲等．基于信息熵的机组运行劣化度综合指标[J]．电力系统自动化，2005，29（7）：75~78
[112]袁志发，周静芋．多元统计分析．科学出版社，2002，10:188~200
[113]徐晓敏．层次分析法的应用[J]．统计与决策，2008，1，156~158
[114] Roemer M. J.，Development of diagnostic and prognostic technologies foraerospace health management applications，2001IEEE Aerospace Conference,Vol.6, Big Sky, Montana, USA,2001：3139-3147
[115] Brothernton Tom. Prognosis of faults in gas turbine engines,2001IEEEAerospace Conference, Vol.6, Big Sky, Montana, USA,2001：163-171
[116] GE Aircraft Engine/CFMI, Eegnie condition monitoring, USA, GEAE/CFMI,2001
[117]中国民用航空总局令第41号，CCAR-121AA民用航空器运行适航管理规定
[S]，北京：航空工业出版社,1997
[118]王吉星.基于人工神经网络和遗传算法的民航发动机状态评估与故障诊断方法研究：[硕士学位论文].天津：中国民航学院机电学院，2004
[119]于文武，康力平.基于AHP的航空发动机在翼寿命预测[J]：航空器制造技术，2010（20）：48-50
[120] Gestel T V，Suykens J A K，et al. Benchmarking Least Squares SupportVector Machine Classifiers[J]. Machine Learning，2004，54：5-32
[121] Suykens J A K，Vandewalle J. Least Squares Support Sector MachineClassifiers[J]. Neural Processing Letters，1999，9(3)：293-300