基于改进神经网络的民机发动机故障诊断与性能预测研究
|
摘要
航空发动机是民机核心动力系统，对之实施有效的诊断和监控，是保障民机安全性、可靠性和经济性的重要技术途径。在发动机故障诊断研究领域，目标主体经常被抽象为一个典型复杂机械系统，由于该系统结构的复杂性、模型的严重非线性、诊断方法的多样性、测量综合误差对故障诊断的干扰影响等原因，造成了发动机故障诊断建模的复杂与困难。目前该领域研究热点包括诊断方法的有效性和全局性研究、诊断系统的实时性研究。前者旨在解决发动机故障诊断模型的性能问题，并将单一诊断方法的模型拓展为多诊断方法模型的集成应用。后者旨在将发动机故障的防范关口前移到实时节点，在传统航线检测、排查、航后排故的基础上引入基于智能诊断决策的故障预防和预防性维修。
本文在研究地空数据链（ACARS）和机载飞行数据记录设备（DFDR/QAR）中发动机状态数据译码的基础上，围绕航空发动机故障智能诊断与状态监控中若干关键的问题展开研究，本文的主要研究内容和创新点如下：
（1）ACARS所提供的实时信息量无法支撑发动机故障模型的在线训练和实时诊断，而快速存取记录器（QAR）中的数据，有信息完备和记录频率高的特点，因此，在基于智能算法的建模过程中，用ACARS与QAR数据共同构建样本空间。分析了两种数据源中数据帧结构可归类的特点，针对机载总线中发动机参数底层数据编码特征，提出了基于译码函数的发动机参数译码算法，译码过程具有较好的实时性和通用性，译码输出为发动机故障诊断和性能监控建模提供了基础数据支撑。
（2）发动机系统的复杂性决定了故障诊断方法的多样性，对于诊断决策而言，综合多种方法做出的决策输出比单一诊断决策具有更好的全局性。对发动机诊断过程中设计的多路信息源和多种诊断知识分别进行融合，针对多路信息源采用数据层融合策略，提出一种自适应加权融合估计算法，根据发动机参数特征迭代调整加权因子，实现参数的融合输出；针对多种诊断知识采用决策级融合策略，提出了一种基于HWA算子的诊断知识多属性决策融合方法，实现了分布式局部决策知识向全局决策知识的进化
（3）利用人工智能方法建立发动机故障诊断模型，可以突破传统数学理论建模、物理过程建模在处理非线性、非平稳性、不确定性复杂系统中的性能瓶颈，具有更好的逼近性能和泛化性能。针对所研究的故障诊断问题，提出了一种改进人工神经网络，利用蚁群算法优化了算法的初始权值向量的优化问题，避免了主观随机选择权值导致的收敛慢和训练振荡问题；模型的训练则引入Levenberg-Marquardt算法，利用其非线性寻优训练规则替代BP算法的梯度下降规则，减小训练过程中代价函数陷入局部极小点的机会，通过控制训练算法复杂度提高收敛速度。
（4）发动机故障预防的要点在于性能的预测，从大量运行数据中捕获用于表征发动机深层运行状态及趋势的信息。研究基于发动机EGT裕度控制的气路性能监控，在分析试车台和起飞过程EGTM的计算原理的基础上，明确其衰退原因，给出了提高EGTM的建议措施；用智能网络模型逼近发动机气路参数时序函数，给出了一种引入了附加参数的相空间重构方法，用粗糙集方法控制附加参数冗余属性，提出了基于区分矩阵的启发式最小约简算法。建模阶段采用动量法和学习率自适应调整相结合的策略，对发动机气路参数的发展趋势进行建模和预测，取得了具有较好的学习和泛化能力，对气路参数或其他类似的非线性动力系统的走势预测决策具有较好的效果。
（5）探索上述理论、方法的工程实现问题，通过在集成开发环境下构建了发动机故障诊断模块、气路性能监控模块、性能趋势预测模块，实现发动机故障诊断与性能监控原型系统，进行了工程实例测试应用。
Aeroengines are the only power resource of civil aircrafts in flight. To efficiently diagnose andmonitor their failures is important for safety, reliability and economical efficiency of civil aircrafts. Inengine fault diagnosis, a typical and complicated mechanical system can be abstracted from the target.Since the structureof the system is complicated, the diagnosis model is seriously nonlinear, and thediagnosis method is varied, the modeling of engine fault diagnosis becomes complex and difficult.Besides, the integrated errors of measurement can also affect the diagnosis result. So far, researchhotspots in the field of aeroengine fault diagnosis have included the following two aspects: theeffectiveness and global performance of diagnosis method, and the practical applicability of diagnosissystem. The former is to solve the problems of aeroengine fault diagnosis model, and to implementintegrated multi-method for fault diagnosis from single ones. The latter is to move the faultprecautionary point forward to a real-time node, and to introduce trouble-saving and preventivemaintenance into fault diagnosis on the basis of traditional route inspection and aviation accidentinvestigation.
Based on ACARSand data decoding of aeroengine state recorded by adigital flight-data recorder/quick access recorder(DFDR/QAR), several key problems are studied about aeroengine faultdiagnosis and state monitoring, which can be concluded as follows:
(1) The real-time information provided by ACARS cannot meet the requirements of engine faultmodel for on-line training and real-time diagnosing. However, the data recorded by QAR with a highfrequency is more complete. Therefore, in the modeling process based on function algorithm, amethod is proposed to build sample space using both ACARS and QAR data. Then, concerning datafrom these two sources, the classification characteristics of data frame structure are analyzed.Considering the underlying data coding features of aeroengine on airborne data bus, engine parameterdecoding algorithm is presented based on decoding function. And a real-time and general decodingprocess is realized. Its output can provide essential data for the modeling of aeroengine fault diagnosisand state monitoring.
(2)The complexity of the engine system determines the diversity of fault diagnosis.As diagnosisdecision is concerned, decision output obtained by integratingseveral methodsis global, comparedwiththat from single diagnosis decision. Multiplex information source and diagnosisknowledgedesigned duringthe engine fault diagnosis process are fused by different strategies,respectively.Formultiplex information source,a data-layer fusion strategy is adopted, and an adaptive weighted fusion estimation algorithm is proposed.According to the characteristics of engineparameters,the weighted factor is iteratively adjusted, thus realizing the integrated output ofparameters.For diagnosis knowledge, a decision-level fusion strategy is used, anda multiple attributedecision fusion methodbased onHWA operator is employed. Hence, the distributed local decisionknowledge is evolved to global decision knowledge.
(3)Using artificial neural method to establish engine fault diagnosis model can break through theperformance bottleneck of traditional mathematical and physical modeling in non-stationary,nonlinear, uncertain complex systems. The method has better approximation and generalizationperformance. Aiming at the fault diagnosis problems, an improved artificial neural networkisproposed,and the ant colony algorithm is used to optimize initial weight vectors in the traditionalalgorithm. Therefore, the disadvantages of slow convergence and training oscillationcan be avoided,which are resulted from subjective random weight determination.Furthermore, in the model training,Levenberg-Marquardt algorithm is introduced, whose nonlinear optimal training rules are used toreplace the gradient descent rules of BP algorithm to reduce the probability of cost function trappingin local minimumpoints during training process.So the convergence speed is improved bycontrollingthe complexity of training algorithm.
(4) The key of failure prevention for engines lies in performance prediction, which meansextracting typical information from large amount of operation data to analyze engines’ operationalstate and potential tendency. Therefore, pneumatic performance supervision is developed based onengine EGT margin control. The arithmetic principle for EGMT of testing and launching proceduresis analyzed to recognize the cause of EGMT regression. And the improvement suggestion is alsoprovided. Methods centering the theory of intelligent network are applied for developing pneumaticparameter timing function, including rough set to control redundancy, ant colony and LM algorithmsto train network weights. Momentum method and adaptive adjustment of learning rate are combinedtogether to predict engine pneumatic parameter tendency. Therefore, pneumatic parameters areequipped with good learning and generalizing ability. The proposed methods operate well in tendencyprediction for those nonlinear dynamic systems like pneumatic parameters.
(5) The implementation of the above theories and methods are realized in an integrateddeveloping environment. The prototype elaborates major functions related to engine failure andperformance supervision, including engine fault diagnosis, pneumatic performance supervision,performance tendency prediction. Practical testing is also launched.
本文在研究地空数据链（ACARS）和机载飞行数据记录设备（DFDR/QAR）中发动机状态数据译码的基础上，围绕航空发动机故障智能诊断与状态监控中若干关键的问题展开研究，本文的主要研究内容和创新点如下：
（1）ACARS所提供的实时信息量无法支撑发动机故障模型的在线训练和实时诊断，而快速存取记录器（QAR）中的数据，有信息完备和记录频率高的特点，因此，在基于智能算法的建模过程中，用ACARS与QAR数据共同构建样本空间。分析了两种数据源中数据帧结构可归类的特点，针对机载总线中发动机参数底层数据编码特征，提出了基于译码函数的发动机参数译码算法，译码过程具有较好的实时性和通用性，译码输出为发动机故障诊断和性能监控建模提供了基础数据支撑。
（2）发动机系统的复杂性决定了故障诊断方法的多样性，对于诊断决策而言，综合多种方法做出的决策输出比单一诊断决策具有更好的全局性。对发动机诊断过程中设计的多路信息源和多种诊断知识分别进行融合，针对多路信息源采用数据层融合策略，提出一种自适应加权融合估计算法，根据发动机参数特征迭代调整加权因子，实现参数的融合输出；针对多种诊断知识采用决策级融合策略，提出了一种基于HWA算子的诊断知识多属性决策融合方法，实现了分布式局部决策知识向全局决策知识的进化
（3）利用人工智能方法建立发动机故障诊断模型，可以突破传统数学理论建模、物理过程建模在处理非线性、非平稳性、不确定性复杂系统中的性能瓶颈，具有更好的逼近性能和泛化性能。针对所研究的故障诊断问题，提出了一种改进人工神经网络，利用蚁群算法优化了算法的初始权值向量的优化问题，避免了主观随机选择权值导致的收敛慢和训练振荡问题；模型的训练则引入Levenberg-Marquardt算法，利用其非线性寻优训练规则替代BP算法的梯度下降规则，减小训练过程中代价函数陷入局部极小点的机会，通过控制训练算法复杂度提高收敛速度。
（4）发动机故障预防的要点在于性能的预测，从大量运行数据中捕获用于表征发动机深层运行状态及趋势的信息。研究基于发动机EGT裕度控制的气路性能监控，在分析试车台和起飞过程EGTM的计算原理的基础上，明确其衰退原因，给出了提高EGTM的建议措施；用智能网络模型逼近发动机气路参数时序函数，给出了一种引入了附加参数的相空间重构方法，用粗糙集方法控制附加参数冗余属性，提出了基于区分矩阵的启发式最小约简算法。建模阶段采用动量法和学习率自适应调整相结合的策略，对发动机气路参数的发展趋势进行建模和预测，取得了具有较好的学习和泛化能力，对气路参数或其他类似的非线性动力系统的走势预测决策具有较好的效果。
（5）探索上述理论、方法的工程实现问题，通过在集成开发环境下构建了发动机故障诊断模块、气路性能监控模块、性能趋势预测模块，实现发动机故障诊断与性能监控原型系统，进行了工程实例测试应用。
Aeroengines are the only power resource of civil aircrafts in flight. To efficiently diagnose andmonitor their failures is important for safety, reliability and economical efficiency of civil aircrafts. Inengine fault diagnosis, a typical and complicated mechanical system can be abstracted from the target.Since the structureof the system is complicated, the diagnosis model is seriously nonlinear, and thediagnosis method is varied, the modeling of engine fault diagnosis becomes complex and difficult.Besides, the integrated errors of measurement can also affect the diagnosis result. So far, researchhotspots in the field of aeroengine fault diagnosis have included the following two aspects: theeffectiveness and global performance of diagnosis method, and the practical applicability of diagnosissystem. The former is to solve the problems of aeroengine fault diagnosis model, and to implementintegrated multi-method for fault diagnosis from single ones. The latter is to move the faultprecautionary point forward to a real-time node, and to introduce trouble-saving and preventivemaintenance into fault diagnosis on the basis of traditional route inspection and aviation accidentinvestigation.
Based on ACARSand data decoding of aeroengine state recorded by adigital flight-data recorder/quick access recorder(DFDR/QAR), several key problems are studied about aeroengine faultdiagnosis and state monitoring, which can be concluded as follows:
(1) The real-time information provided by ACARS cannot meet the requirements of engine faultmodel for on-line training and real-time diagnosing. However, the data recorded by QAR with a highfrequency is more complete. Therefore, in the modeling process based on function algorithm, amethod is proposed to build sample space using both ACARS and QAR data. Then, concerning datafrom these two sources, the classification characteristics of data frame structure are analyzed.Considering the underlying data coding features of aeroengine on airborne data bus, engine parameterdecoding algorithm is presented based on decoding function. And a real-time and general decodingprocess is realized. Its output can provide essential data for the modeling of aeroengine fault diagnosisand state monitoring.
(2)The complexity of the engine system determines the diversity of fault diagnosis.As diagnosisdecision is concerned, decision output obtained by integratingseveral methodsis global, comparedwiththat from single diagnosis decision. Multiplex information source and diagnosisknowledgedesigned duringthe engine fault diagnosis process are fused by different strategies,respectively.Formultiplex information source,a data-layer fusion strategy is adopted, and an adaptive weighted fusion estimation algorithm is proposed.According to the characteristics of engineparameters,the weighted factor is iteratively adjusted, thus realizing the integrated output ofparameters.For diagnosis knowledge, a decision-level fusion strategy is used, anda multiple attributedecision fusion methodbased onHWA operator is employed. Hence, the distributed local decisionknowledge is evolved to global decision knowledge.
(3)Using artificial neural method to establish engine fault diagnosis model can break through theperformance bottleneck of traditional mathematical and physical modeling in non-stationary,nonlinear, uncertain complex systems. The method has better approximation and generalizationperformance. Aiming at the fault diagnosis problems, an improved artificial neural networkisproposed,and the ant colony algorithm is used to optimize initial weight vectors in the traditionalalgorithm. Therefore, the disadvantages of slow convergence and training oscillationcan be avoided,which are resulted from subjective random weight determination.Furthermore, in the model training,Levenberg-Marquardt algorithm is introduced, whose nonlinear optimal training rules are used toreplace the gradient descent rules of BP algorithm to reduce the probability of cost function trappingin local minimumpoints during training process.So the convergence speed is improved bycontrollingthe complexity of training algorithm.
(4) The key of failure prevention for engines lies in performance prediction, which meansextracting typical information from large amount of operation data to analyze engines’ operationalstate and potential tendency. Therefore, pneumatic performance supervision is developed based onengine EGT margin control. The arithmetic principle for EGMT of testing and launching proceduresis analyzed to recognize the cause of EGMT regression. And the improvement suggestion is alsoprovided. Methods centering the theory of intelligent network are applied for developing pneumaticparameter timing function, including rough set to control redundancy, ant colony and LM algorithmsto train network weights. Momentum method and adaptive adjustment of learning rate are combinedtogether to predict engine pneumatic parameter tendency. Therefore, pneumatic parameters areequipped with good learning and generalizing ability. The proposed methods operate well in tendencyprediction for those nonlinear dynamic systems like pneumatic parameters.
(5) The implementation of the above theories and methods are realized in an integrateddeveloping environment. The prototype elaborates major functions related to engine failure andperformance supervision, including engine fault diagnosis, pneumatic performance supervision,performance tendency prediction. Practical testing is also launched.
引文
[1]吴建民,吴铭望,李国经.大型客机航空电子系统研发关键技术分析及建议[J].大型飞机关键技术高层论坛暨中国航空学会2007年学术年会论文集,2007,4(2):143-154.
[2]郑波.航空发动机故障诊断技术研究[J].航空计算技术,201036(2):21-26.
[3] Jonathan Litt, Donald L. simon, Claudia Meyer, NASA aviation safety program aircraftengine health management data mining tools roadmap, National Aeronautics and SpaceAdministration, Hanover2000.
[4]张风鸣,郑东良,吕振东,航空装备科学维修导论[M].北京:国防工业出版社,2006.
[5]常士基,现代民用航空维修工程管理[M].山西:山西科学技术出版社出版,2002.
[6]文宏. ACARS系统在飞机维修实践中的应用[J].江苏航空,2005,3(1):4-6.
[7]张天宏,左江福.民航发动机远程故障诊断若干关键技术研究[J].航空动力学报,2003,(1):134-139.
[8]南方航开发飞机远程诊断和实时跟踪系统[J].航空工程与维修,2002,(4):40-41.
[9] F. LU, J. HUANG, X. KONG. Rapid prototype design for turbo-fan engine fault diagnosis [J].Journal of Aerospace Power,2012,2:028.
[10] C.Z. Li, Y. Lei. Aircraft Engine Gas Path Fault Diagnosis Based on Neural Network [J].Applied Mechanics and Materials,2012,148:144-148.
[11] James D. Halderman, Advanced engine performance diagnosis [M].5th ed. Boston: PrenticeHall,2012.
[12]贾庆贤,张迎春,管宇.基于解析模型的非线性系统故障诊断方法综述[J].信息与控制,2012,41(3):356-364
[13]鲁峰,黄金泉,孔祥天.涡扇发动机故障诊断的快速原型设计[J].航空动力学报,2012,27(002):431-437.
[14]张鹏,基于卡尔曼滤波的航空发动机故障诊断技术研究[D],南京航空航天大学,2009.
[15]鲁峰,黄金泉,孔祥天.基于变权重最小二乘法的发动机气路故障诊断[J].航空动力学报,2011,26(10):2376-2381.
[16]南方航空公司,利用ACRDRTS实现实时跟踪飞机,2002.
[17] Z. S. Chen, Y. M. Yang, Z. Hu. Detecting and predicting early faults of complex rotatingmachinery based on cyclostationary time series model [J]. Journal of Vibration and Acoustics,Transactions of the ASME,2006,128:666-671.
[18] J. J. Chen, X. Chen, Research on Embedded Airborne Electronic Fault Diagnosis ExpertSystem [C], presented at the Proceedings of2nd International Conference on InformationEngineering&Computer Science (ICIECS), Wuhan,2010:332-337.
[19] Z.S. WANG, S.W. MA. Research on Early Fault Self-Recovery Monitoring of Aero-EngineRotor System [J]. Engineering,2010,2(1):60-64.
[20] J. Liu, Y. Liu, X. Zhao. The Achieving of Gas Turbine’s Gas Path Fault Criterion [J].Mechanical Engineering and Technology,2012:515-521.
[21] R. Mohammadi, E. Naderi, K. Khorasani, Fault diagnosis of gas turbine engines by usingdynamic neural networks [C], in Quality and Reliability (ICQR),2011IEEE InternationalConference on,2011:25-30.
[22] H.A. Nozari, H.D. Banadaki, M.A. Shoorehdeli, Model-based Fault Detection and IsolationUsing Neural Networks: An Industrial Gas Turbine Case Study [C], in Systems Engineering(ICSEng),201121st International Conference on,2011:26-31.
[23] J. Y. Qu, L. Y. Liang, A Production Rule Based Expert System for Electronic ControlAutomatic Transmission Fault Diagnosis [C], presented at the Proceedings of2009IEEEInternational Conference on Test&Automation,2009.
[24] Y. L. Chen, T. J. Zhang, Research on Application of Fuzzy Fault Tree Analysis Method in theMachinery Equipment Fault Diagnosis [C], presented at the Proceedings of2ndInternational Conference on Informatics in Control, Automation and Robotics,,Wuhan,2010,vol.6:84-87.
[25]胡昊磊,航空发动机视情维修管理中的下发预测技术研究,[D],南京航空航天大学,2009.
[26] D. Kodavade, S. Apte. A Universal Object Oriented Expert System Frame Work for FaultDiagnosis [J]. International Journal of Intelligence Science,2012,2(3):63-70.
[27] R. Jiang, J. Xie, Gas turbine gas path fault diagnosis technology based on the fuzzy Petri net[C], in Transportation, Mechanical, and Electrical Engineering (TMEE),2011InternationalConference on,2011:850-853.
[28] M. Karakose, I. Aydin, The Intelligent Fault Diagnosis Framework Based on Fuzzy Integral,[C], presented at the SPEEDAM2010International Symposium on Power Electronics,Electrical Drives, Automation and Motion, Pisa,2010,(1):14-16.
[29] S. Tyagi, D. Pandey, V. Kumar. Fuzzy Fault Tree Analysis for Fault Diagnosis of CannulaFault in Power Transformer [J]. Applied Mathematics,2011,2(11):1346-1355.
[30] L. Zhang, H. Ma, J. Deng, Reliability study of disengaging mechanism based on fault treeanalysis [C], in Quality, Reliability, Risk, Maintenance, and Safety Engineering(ICQR2MSE),2012International Conference on,2012:290-292.
[31]刘永建,朱剑英,曾捷.改进BP神经网络在发动机性能趋势分析和故障诊断中的应用[J].南京理工大学学报:自然科学版,2010,34(001):24-29.
[32]侯胜利,王威,胡金海.一种航空发动机性能监控的免疫神经网络模型[J].航空动力学报,2008,23(9):1748-1752.
[33] Koboyashi T, Simon DL. Hybrid neural network genetic-algorithm technique for aircraftengine performance diagnostics [J]. Journal of propulsion and power,2005,21(5):751~758.
[34] Joly R.B, Ogaji, Singh R. Gas-turbine diagnostics using artificial neural-networks for a highbypass ratio military turbofan engine [J]. Applied Energy,2004,78(4):397-418.
[35]马国岗.飞机发动机传感器信息融合技术应用研究[J].北京电力高等专科学校学报,2009,(4):162-163.
[36] J. Twycross, U. Aickelin. Information fusion in the immune system [J]. Information Fusion,2010,11(1):35-44.
[37] C. Stiller, F. Puente León, M. Kruse. Information fusion for automotive applications–Anoverview [J]. Information Fusion,2011,12(4):244-252.
[38]潘泉,于昕,程咏梅.信息融合理论的基本方法与进展[J].自动化学报,2003,29(4):600-617.
[39]韩崇昭,朱洪艳.多传感信息融合与自动化[J].自动化学报,2009,(S1):201-204.
[40] Boeing, AHM for Boeing [M],2000.
[41] Airbus, Airman for airbus [M],2000.
[42] M.Z. Osmanbhoy, S. Runo, P. Mallasch, Development of fault detection and reporting fornon-central maintenance aircraft [C], in Aerospace Conference,2010IEEE,2010:1-7.
[43]左洪福,发动机磨损状态监测与故障诊断技术[M].北京:航空工业出版社,1995.
[44]刘明,严建峰,李伟华.引入隐变量机制的航空发动机智能故障诊断系统[J].计算机测量与控制,2009,16(12):1770-1772.
[45]官颂,曲培树,董文会.航空发动机智能内窥故障诊断[J].辽宁工程技术大学学报:自然科学版,2009,28(006):981-984.
[46] F. Lu, J. Huang, Y. Xing. Fault Diagnostics for Turbo-Shaft Engine Sensors Based on aSimplified On-Board Model [J]. Sensors,2012,12(8):11061-11076.
[47] S.S. Tayarani-Bathaie, Z. Sadough, K. Khorasani, Dynamic Neural Network-based FaultDiagnosis of Gas Turbine Engines [C], in Modelling, Identification and Control/770:Advances in Computer Science and Engineering,2012.
[48]鲁峰,黄金泉,陈煜.航空发动机部件性能故障融合诊断方法研究[J].航空动力学报,2009,24(7):1649.
[49]金向阳.林琳.钟诗胜.航空发动机振动趋势预测的过程神经网络法[J].振动.测试与诊断,2011,31(3):331-334.
[50]田武刚,潘孟春,罗飞路.航空发动机叶片的内窥涡流集成化原位检测[J].国防科技大学学报,2009,31(005):101-105.
[51]陈立波,宋兰琪,陈果.航空发动机滑油综合监控中的磨损故障融合诊断研究[J].航空动力学报,2009,24(1):169-175.
[52]刘宏,雷勇,闫飞.航空发动机振动分析系统的开发及应用[J].噪声与振动控制,2009,29(1):110-113.
[53]张鹏,倪世宏,谢川.航空发动机振动监控新方法的研究[J].计算机工程与设计,2012,33(5):2027-2030.
[54]曲建岭,唐昌盛,肖辉雄.人工神经网络融合诊断航空发动机气路故障[J].航空动力学报,2009,23(11):2124-2127.
[55]蒋亮.李书明.郝英.航空发动机气路故障诊断研究现状[J].中国民航大学学报,2010,(z1):60-62.
[56]单晓明.宋云峰.黄金泉.基于神经网络和模糊逻辑的航空发动机状态监视[J].航空动力学报,2009,24(10):2356-2361.
[57] Z.Y. Li, H. Ji, H.L. Liu. Machining parameter optimization of aero-engine blade inelectrochemical machining based on BP neural network [J]. Advanced Materials Research,2010,121:893-899.
[58] S.H. Rui, F.M. Zhang, X.L. Xu. The Fault Detection of Aero-engine Based on the ImprovedAssociation Rules Mining [J]. Fire Control&Command Control,2011,9:051.
[59]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[J].航空动力学报,2009,23(12):2170-2176.
[60] A. Stranjak.P.S. Dutta.M. Ebden, A multi-agent simulation system for prediction andscheduling of aero engine overhaul [C], in Proceedings of the7th international jointconference on Autonomous agents and multiagent systems: industrial track,2008:81-88.
[61]肖苏,阳勇,方琳.航空涡轮喷气发动机整体技术现状及发展趋势简介[J].成都航空职业技术学院学报:综合版,2012,27(4):37-39.
[62]华成.徐光华.张庆.基于CBR的智能维修决策技术研究与应用[J].2009中国仪器仪表与测控技术大会论文集,2009,
[63]冯廷敏,基于状态监测的以可靠性为中心的智能维修系统,[D],北京:北京化工大学,2008.
[64]刘文彬.王庆锋.高金吉.以可靠性为中心的智能维修决策模型[J].北京工业大学学报,2012,5:006.
[65]王铮,李艳军.基于离散Hopfield网络的飞机发动机故障诊断的智能算法研究[J].科技信息,2010,(029):52-53.
[66]牛伟.王国庆.翟正军.航空发动机的多参数快速故障诊断模型[J].计算机应用研究,2011,28(12):4564-4575.
[67]梅晓川,陈亚莉.航空飞行器维修技术发展综述[J].航空发动机,2009,35(006):53-57.
[68] N. Papakostas.P. Papachatzakis.V. Xanthakis. An approach to operational aircraftmaintenance planning [J]. Decision Support Systems,2010,48(4):604-612.
[69]唐世明,飞机状态监控系统的研究与改进,[D],电子科技大学,2011.
[70] Z. Peng, Z. Shiwei, W. Yake, The research of aircraft fault diagnosis based on adaptive FPN[C], in Control and Decision Conference,2009. CCDC'09. Chinese,2009:5252-5255.
[71] H. Long, X. Wang, Application of aircraft fuel fault diagnostic expert system based on fuzzyneural network [C], in Information Engineering,2009. ICIE'09. WASE InternationalConference on,2009vol.2:202-205.
[72] L.J.W.C.Z. Yaxin. THE APPLICATION OF EXPERT SYSTEM IN AIRCRAFT FAULTDIAGNOSIS AND MAINTENANCE GUIDING SYSTEM [J]. Computer Applications andSoftware,2009,5:056.
[73] J.B. Cao, E.M. Guo, Y. Li. Design of Fault Diagnosis Expert System for Certain Type ofAircraft Electrical Power [J]. Advanced Materials Research,2012,466:1186-1190.
[74] Z. Yang, L. Qing, P. Lu, Integration of deep and shallow aircraft fault knowledge [C], inCommunication Software and Networks (ICCSN),2011IEEE3rd International Conferenceon,2011:320-324.
[75] D.L. Simon. An Integrated Architecture for On-Board Aircraft Engine Performance TrendMonitoring and Gas Path Fault Diagnostics [J].2010,
[76] H. Yu, Z. Wang, Y. Lu, Design of Remote Fault Diagnosis System on Aircraft [C], inInnovative Computing, Information and Control (ICICIC),2009Fourth InternationalConference on,2009:496-499.
[77] C. Hu, Aircraft fault diagnosis prognostics and health management based on flight recorder[C], in Prognostics and System Health Management (PHM),2012IEEE Conference on,2012:1-4.
[78] M. Cottrell.P. Gaubert.C. Eloy. Fault prediction in aircraft engines using self-organizing maps[J]. Advances in Self-Organizing Maps,2009:37-44.
[79] L. Wei, Prediction of the aircraft fault maintenance sorties based on least squares of linearregression [C], in System Science, Engineering Design and Manufacturing Informatization(ICSEM),20123rd International Conference on,2012vol.2:223-225.
[80] Z. Xuefeng, D. Jianqian, C. Jingjie, On fault prediction model for A320aircraft airconditioning system [C], in Information Networking and Automation (ICINA),2010International Conference on,2010vol.2: V2-231-V2-234.
[81]董亚伟,王杰.地空数据链在民航的应用与发展[J].大众科技,2012,(1):19-20.
[82]何桂萍,徐亚军. ADS-B数据链的比较及特性研究[J].中国民航飞行学院学报,2010,(004):3-6.
[83]蒋兴城,曹力,邓雪云.基于MSK的地空数据链通信调制解调方法[J].信息技术,2012,(8):5-8.
[84] R.J. Eckert, A.C. Prewett, System and method for wireless routing of data from an aircraft[P],ed: Google Patents,2010.
[85]史亚杰,李敬.民航机务维修系统安全风险监测[J].中国安全科学学报,2009,19(011):110-116.
[86]唐宇,王洪.民航机务维修差错评析[J].中国民航大学学报,2010,(z1):54-55.
[87]邓君香.民航机务高技能人才队伍建设[J].中国民用航空,2012,(3):65-67.
[88]刘槟,田玲玲.飞机维修的新理念——飞机健康管理[J].国际航空,2010,(011):80-82.
[89]范平,范玉青.突破技术趋同,波音再现竞争优势——对大型飞机研制技术的战略性分析[J].航空学报,2008,29(3):707-712.
[90]孙立.飞机实时数据的远程管理[J].航空维修与工程,2008,1:037.
[91]张宝珍.国外综合诊断,预测与健康管理技术的发展及应用[J].计算机测量与控制,2008,16(5):591-594.
[92] P. Goupil, A. Marcos, P. Goupil-Airbus. Advanced Diagnosis for Sustainable Flight Guidanceand Control: The European ADDSAFE Project [J]. SAE Technical Paper,2011:01-2804.
[93] D. Henry, J. Cieslak, A. Zolghadri, A Hinf/H-approach for Fault Diagnosis in ElectricalAircraft Flight Control Systems [C], in9th European Workshop on Advanced Control andDiagnosis,2011.
[94] M. O'Brien. IATA's Safety Audit for Ground Operations (ISAGO)[J]. International AirportReview,2008,12(5)
[95] J. Ma.M. Pedigo.L. Blackwell, The Line Operations Safety Audit Program: TransitioningFrom Flight Operations to Maintenance and Ramp Operations, DTIC Document2011.
[96] L.H. Kao, M. Stewart, K.H. Lee. Using structural equation modeling to predict cabin safetyoutcomes among Taiwanese airlines [J]. Transportation Research Part E: Logistics andTransportation Review,2009,45(2):357-365.
[97]肖宪波,俞力玲,王浩锋.基于BP神经网络和飞行参数的航段风险评价[J].中国民航大学学报,2011,29(001):35-38.
[98]路亚峰.张涛.张贤.机载电子设备故障诊断专家系统的设计与实现[J].电子测量技术,2010,(001):118-120.
[99]孙淑光,童震宇,韩雁飞.飞机ACARS报文航段识别专家系统的实现[J].交通信息与安全,2012,29(6):109-112.
[100] ARINC, ARINC Protocol Tutorial Manual [M]: Condor Engineering ARINC,1995.
[101] X.J.D.X.C. Li. Study on the Ground Air Data Link Technology Based on ARINC-618Protocol [J]. Civil Aircraft Design and Research,2011,4:007.
[102] ARINC, ARINC620Data link ground system standard and interface specification [M],1998.
[103] LM Parrilla, AL Rodriguez, A. Simon-Muela. Design of a Middleware Interface for ARINC429Data Bus [J]. Aerospace and Electronic Systems, IEEE Transactions on,2012,48(2):1136-1149.
[104]冯健朋,郭迎清.航空发动机状态监控系统研究[J].航空计算技术,20122:32-36.
[105]史秀宇. V2500发动机性能监控几起典型故障分析[J].航空维修与工程,2009,(4):59-60.
[106]马小骏,左洪福,刘昕.大型客机运行监控与健康管理系统设计[J].交通运输工程学报,2012,11(6):119-126.
[107]王仲生,赵鹏.基于多源信息融合的发动机转子早期故障识别[J].西北工业大学学报,2009,(003):326-329.
[108]李琼,信息融合技术在航空发动机智能监测中的应用研究,[D],南京航空航天大学,2011.
[109]李俊杰,王宏伟,李小波.航空装备视情维修决策研究[J].飞机设计,2011,31(5):77-80.
[110]张涛,航空发动机视情调度优化方法及系统开发,[D],南京航空航天大学,2009.
[111] LA Urban, A Gas Path Analysis Applied to Turbine Engine Condition Monitoring,AIAA1972.
[112] LA Urban. Parameter Selection for Multiple Fault Diagnostics of Gas turbine Engines [J].Journal of Engineering for Power,1975:225-230.
[113] L.A Urban, Gas Path Analysis Applied to Turbine Engine Condition Monitoring,1990.
[114] A. Shepherd,"Gas turbine engine comprising a tension stud," ed: EP Patent2,415,967,2012.
[115]叶斌,孙护国,蔡娜.航空发动机状态监控与故障诊断系统(EMS)研究[J].科技创新导报,2010,(004):5-6.
[116]李咏,杨晓飞,赵云强.油液分析技术在发动机磨损故障中的运用[J].实验科学与技术,2012,10(2):26-27.
[117]费逸伟.张子阳.谢寿生.基于在线油液颗粒检测的飞村发动机状态监控[J].航空维修与工程,2009,(004):66-68.
[118]谢小荣,江涛,杨小林.飞机发动机叶片榫槽爬波原位检测[J].无损检测,2012,1:114-118.
[119]单宁,史仪凯,刘霞.光纤法-珀传感器在飞机发动机叶片裂纹检测中的应用[J].无损检测,2009,31(3):206-207.
[120]张海兵,袁英民.某型发动机2级压气机叶片的涡流探伤方法[J].无损检测,2011,33(2):24-26.
[121]罗英.张德银.彭卫东.民航飞机主动红外热波成像检测技术应用进展[J].激光与红外,2011,41(7):718-723.
[122]刘罗曼.时间序列分析中指数平滑法的应用[J].沈阳师范大学学报:自然科学版,2009,27(004):416-418.
[123]齐驰,侯忠生.自适应单指数平滑法在短期交通流预测中的应用[J].控制理论与应用,2012,29(4):456-470.
[124]李林,黄柯棣,何芳.集中式多传感器融合系统中的时间配准研究[J].传感技术学报,2008,(11):2445-2449.
[125]许珉,刘凌波.基于三次样条函数的加Blackman-harris窗插值FFT算法[J].电力自动化设备,2009,29(2):59-63.
[126]翟旭升.胡金海.谢寿生.基于DSmT的航空发动机早期振动故障融合诊断方法[J].航空动力学报,2012,27(002):301-306.
[127]鲁峰,黄金泉,仇小杰.基于信息熵融合提取特征的发动机气路分析 [J].仪器仪表学报,2012,33(1):13-19.
[128]龚荣芳.关于多元函数极值判定方法的教学思考[J].中国科教创新导刊,2011,(17):97-97.
[129]陈东菊,范晋伟,雒驼. Daubechies小波在机床动态误差特征提取与辨识中的应用[J].北京工业大学学报,2012,38(10):239-246.
[130]张世强,吕杰能,蒋峥.关于相关系数的探讨[J].数学的实践与认识,2009,(019):102-107.
[131] E.C.Y. Peh, Y.C. Liang, Y.L. Guan. Cooperative spectrum sensing in cognitive radio networkswith weighted decision fusion schemes [J]. Wireless Communications, IEEE Transactions on,2010,9(12):3838-3847.
[132]汪新凡.混合加权集成算子及其在决策中的应用[J].湖南工业大学学报,2010,24(002):34-38.
[133]陈晓红,阳熹.一种基于三角模糊数的多属性群决策方法[J].系统工程与电子技术,2008,30(2):278-282.
[134] Q. Wu, R. Law. Fuzzy support vector regression machine with penalizing Gaussian noises ontriangular fuzzy number space [J]. Expert Systems with Applications,2010,37(12):7788-7795.
[135] I. Gonzalo-Fonrodona, M. Porras. Scaling power laws in the restoration of perception withincreasing stimulus in deficitary natural neural network [J]. Methods and Models in Artificialand Natural Computation. A Homage to Professor Mira’s Scientific Legacy,2009:174-183.
[136] M. Luko Evi Ius, H. Jaeger. Reservoir computing approaches to recurrent neural networktraining [J]. Computer Science Review,2009,3(3):127-149.
[137] L. Wang, K. Fu, Artificial neural networks [M]: Wiley Online Library,2009.
[138] S.S. Haykin, S.S. Haykin, S.S. Haykin, Neural networks and learning machines [M] vol.3:Prentice Hall,2009.
[139] G. Tayfur, Soft Computing in Water Resources Engineering: Artificial Neural Networks,Fuzzy Logic and Genetic Algorithms [M]: WIT Press/Computational Mechanics,2011.
[140] S. Kiranyaz, T. Ince, A. Yildirim. Evolutionary artificial neural networks bymulti-dimensional particle swarm optimization [J]. Neural Networks,2009,22(10):1448-1462.
[141] A. Krogh. What are artificial neural networks?[J]. Nature biotechnology,2008,26(2):195-197.
[142]刘廷毅.航空发动机研制全寿命管理研究及建议[J].航空发动机,2012,38(1):1-6.
[143]王俨剀,王理,廖明夫.航空发动机整机测振中的基本问题分析[J].航空发动机,2012,38(3):49-53.
[144] S. Goyal, G.K. Goyal. Artificial neuron based models for estimating shelf life of burfi [J].ARPN J. Sci. Tech,2012,2(6):536-540.
[145] K. Huang, L. Dai, S. Huang, Wind Prediction Based on Improved BP Artificial NeuralNetwork in Wind Farm [C], in Electrical and Control Engineering (ICECE),2010International Conference on,2010:2548-2551.
[146] Z. Liu, X. Meng. Integration of improved BPNN algorithm and multistage dynamic fuzzyjudgement and its application on ESMP evaluation [J]. Journal of computers,2009,4(1):69-76.
[147] Z. Xiao, S.J. Ye, B. Zhong. BP neural network with rough set for short term load forecasting[J]. Expert Systems with Applications,2009,36(1):273-279.
[148] Y. Huang, D. Sun, G. Xing, Criticality Evaluation for Spare Parts Based on BP NeuralNetwork [C], in Artificial Intelligence and Computational Intelligence (AICI),2010International Conference on,2010vol.1:204-206.
[149]邓万宇,郑庆华,陈琳.神经网络极速学习方法研究[J].计算机学报,2010,33(2):279-287.
[150]施彦,韩力群,神经网络设计方法与实例分析[M]:北京邮电大学出版社,2009.
[151]张泓,李爱平,刘雪梅.面向TSP求解的混合蚁群算法[J].计算机工程,2009,35(8)17-22.
[152]王书明,刘玉兰,王家映.蚁群算法[J].工程地球物理学报,2008,34(19):71-76.
[153]倪庆剑,邢汉承,张志政.蚁群算法及其应用研究进展[J].计算机应用与软件,2008,25(8):12-16.
[154] X. Li, J. Cao, D. Du. Comparison of Levenberg-Marquardt Method and Path FollowingInterior Point Method for the Solution of Optimal Power Flow Problem [J]. InternationalJournal of Emerging Electric Power Systems,2012,13(3):2-8..
[155] B.M. Wilamowski, H. Yu. Improved computation for Levenberg–Marquardt training [J].Neural Networks, IEEE Transactions on,2010,21(6):930-937.
[156] S. Basterrech, S. Mohammed, G. Rubino. Levenberg—Marquardt Training Algorithms forRandom Neural Networks [J]. The Computer Journal,2011,54(1):125-135.
[157] H. Mirzaee. Long-term prediction of chaotic time series with multi-step prediction horizonsby a neural network with Levenberg–Marquardt learning algorithm [J]. Chaos, Solitons&Fractals,2009,41(4):1975-1979.
[158]凌锦江,周志华.基于因果发现的神经网络集成方法[J].软件学报,2004,15(10)
[159] A. Azadeh, A. Maghsoudi, S. Sohrabkhani. An integrated artificial neural networks approachfor predicting global radiation [J]. Energy Conversion and Management,2009,50(6):1497-1505.
[160] D. elebi, D. Bayraktar. An integrated neural network and data envelopment analysis forsupplier evaluation under incomplete information [J]. Expert Systems with Applications,2008,35(4):1698-1710.
[161]张东波,黄辉先,王耀南.基于粗糙集约简的特征选择神经网络集成技术[J].控制与决策,2010,3:371-377.
[162]周志华,陈世福.神经网络集成[J].计算机学报,2002,25(1):1-8.
[163]吴建鑫,周志华,沈学华.一种选择性神经网络集成构造方法[J].计算机研究与发展,2000,37(9):1039-1044.
[164]唐伟,周志华.基于Bagging的选择性聚类集成[J].软件学报,2005,16(4):496-502.
[165]易承罡.基于ACARS的飞机实时监控系统研究[J].宁波大学学报(理工版),2011,24(1)：132-136.
[166]钟诗胜,雷达,丁刚.卷积和离散过程神经网络及其在航空发动机排气温度预测中的应用[J].航空学报,2012,33(003):438-445.
[167] A. Lapedes, R. Farber, Nonlinear signal processing using neural networks: Prediction andsystem modelling[C], IEEE international conference on neural networks, San Diego, CA,USA,21Jun1987.
[168] A. Lapedes, R. Farber, How neural nets work [C], in Neural information processing systems,1988:442-456.
[169] Z. Pawlak. Rough Sets [J]. International Journal of Computer and Information Sciences,1982,11:341-356.
[170] Z. Pawlak. Rough Set Theory and Its Application to Data Analysis [J]. Cybernetics andSystems,1998,29(9):661-668.
[171]夏红霞,王惠营.基于粗糙集的神经网络结构优化方法[J].计算机与数字工程,2010,38(5):49-51.
[172] H. Xu, D. Jiang, L. Liang, Application of Fuzzy-Rough Set theory and improved SMOalgorithm in aircraft engine vibration fault diagnosis [C], in Prognostics and System HealthManagement (PHM),2012IEEE Conference on NN,2012:1-6.
[173] L. Wang, YG Li, M.F.A. Ghafir. A Rough Set-based gas turbine fault classification approachusing enhanced fault signatures [J]. Proceedings of the Institution of Mechanical Engineers,Part A: Journal of Power and Energy,2011,225(8):1052-1065.
[174]苗夺谦. Rough Set理论中连续属性的离散化方法[J].自动化学报,2001,27(3):296-302.
[175]王海燕,盛昭瀚.混沌时间序列相空间重构参数的选取方法[J].东南大学学报,2000,30(5):113-117.
[176]陈铿,韩伯棠.混沌时间序列分析中的相空间重构技术综述[J].计算机科学,2005,32(4):67-70.
[177]张淑清,贾健,高敏.混沌时间序列重构相空间参数选取研究[J].物理学报,2010,59(3):1576-1582.
[2]郑波.航空发动机故障诊断技术研究[J].航空计算技术,201036(2):21-26.
[3] Jonathan Litt, Donald L. simon, Claudia Meyer, NASA aviation safety program aircraftengine health management data mining tools roadmap, National Aeronautics and SpaceAdministration, Hanover2000.
[4]张风鸣,郑东良,吕振东,航空装备科学维修导论[M].北京:国防工业出版社,2006.
[5]常士基,现代民用航空维修工程管理[M].山西:山西科学技术出版社出版,2002.
[6]文宏. ACARS系统在飞机维修实践中的应用[J].江苏航空,2005,3(1):4-6.
[7]张天宏,左江福.民航发动机远程故障诊断若干关键技术研究[J].航空动力学报,2003,(1):134-139.
[8]南方航开发飞机远程诊断和实时跟踪系统[J].航空工程与维修,2002,(4):40-41.
[9] F. LU, J. HUANG, X. KONG. Rapid prototype design for turbo-fan engine fault diagnosis [J].Journal of Aerospace Power,2012,2:028.
[10] C.Z. Li, Y. Lei. Aircraft Engine Gas Path Fault Diagnosis Based on Neural Network [J].Applied Mechanics and Materials,2012,148:144-148.
[11] James D. Halderman, Advanced engine performance diagnosis [M].5th ed. Boston: PrenticeHall,2012.
[12]贾庆贤,张迎春,管宇.基于解析模型的非线性系统故障诊断方法综述[J].信息与控制,2012,41(3):356-364
[13]鲁峰,黄金泉,孔祥天.涡扇发动机故障诊断的快速原型设计[J].航空动力学报,2012,27(002):431-437.
[14]张鹏,基于卡尔曼滤波的航空发动机故障诊断技术研究[D],南京航空航天大学,2009.
[15]鲁峰,黄金泉,孔祥天.基于变权重最小二乘法的发动机气路故障诊断[J].航空动力学报,2011,26(10):2376-2381.
[16]南方航空公司,利用ACRDRTS实现实时跟踪飞机,2002.
[17] Z. S. Chen, Y. M. Yang, Z. Hu. Detecting and predicting early faults of complex rotatingmachinery based on cyclostationary time series model [J]. Journal of Vibration and Acoustics,Transactions of the ASME,2006,128:666-671.
[18] J. J. Chen, X. Chen, Research on Embedded Airborne Electronic Fault Diagnosis ExpertSystem [C], presented at the Proceedings of2nd International Conference on InformationEngineering&Computer Science (ICIECS), Wuhan,2010:332-337.
[19] Z.S. WANG, S.W. MA. Research on Early Fault Self-Recovery Monitoring of Aero-EngineRotor System [J]. Engineering,2010,2(1):60-64.
[20] J. Liu, Y. Liu, X. Zhao. The Achieving of Gas Turbine’s Gas Path Fault Criterion [J].Mechanical Engineering and Technology,2012:515-521.
[21] R. Mohammadi, E. Naderi, K. Khorasani, Fault diagnosis of gas turbine engines by usingdynamic neural networks [C], in Quality and Reliability (ICQR),2011IEEE InternationalConference on,2011:25-30.
[22] H.A. Nozari, H.D. Banadaki, M.A. Shoorehdeli, Model-based Fault Detection and IsolationUsing Neural Networks: An Industrial Gas Turbine Case Study [C], in Systems Engineering(ICSEng),201121st International Conference on,2011:26-31.
[23] J. Y. Qu, L. Y. Liang, A Production Rule Based Expert System for Electronic ControlAutomatic Transmission Fault Diagnosis [C], presented at the Proceedings of2009IEEEInternational Conference on Test&Automation,2009.
[24] Y. L. Chen, T. J. Zhang, Research on Application of Fuzzy Fault Tree Analysis Method in theMachinery Equipment Fault Diagnosis [C], presented at the Proceedings of2ndInternational Conference on Informatics in Control, Automation and Robotics,,Wuhan,2010,vol.6:84-87.
[25]胡昊磊,航空发动机视情维修管理中的下发预测技术研究,[D],南京航空航天大学,2009.
[26] D. Kodavade, S. Apte. A Universal Object Oriented Expert System Frame Work for FaultDiagnosis [J]. International Journal of Intelligence Science,2012,2(3):63-70.
[27] R. Jiang, J. Xie, Gas turbine gas path fault diagnosis technology based on the fuzzy Petri net[C], in Transportation, Mechanical, and Electrical Engineering (TMEE),2011InternationalConference on,2011:850-853.
[28] M. Karakose, I. Aydin, The Intelligent Fault Diagnosis Framework Based on Fuzzy Integral,[C], presented at the SPEEDAM2010International Symposium on Power Electronics,Electrical Drives, Automation and Motion, Pisa,2010,(1):14-16.
[29] S. Tyagi, D. Pandey, V. Kumar. Fuzzy Fault Tree Analysis for Fault Diagnosis of CannulaFault in Power Transformer [J]. Applied Mathematics,2011,2(11):1346-1355.
[30] L. Zhang, H. Ma, J. Deng, Reliability study of disengaging mechanism based on fault treeanalysis [C], in Quality, Reliability, Risk, Maintenance, and Safety Engineering(ICQR2MSE),2012International Conference on,2012:290-292.
[31]刘永建,朱剑英,曾捷.改进BP神经网络在发动机性能趋势分析和故障诊断中的应用[J].南京理工大学学报:自然科学版,2010,34(001):24-29.
[32]侯胜利,王威,胡金海.一种航空发动机性能监控的免疫神经网络模型[J].航空动力学报,2008,23(9):1748-1752.
[33] Koboyashi T, Simon DL. Hybrid neural network genetic-algorithm technique for aircraftengine performance diagnostics [J]. Journal of propulsion and power,2005,21(5):751~758.
[34] Joly R.B, Ogaji, Singh R. Gas-turbine diagnostics using artificial neural-networks for a highbypass ratio military turbofan engine [J]. Applied Energy,2004,78(4):397-418.
[35]马国岗.飞机发动机传感器信息融合技术应用研究[J].北京电力高等专科学校学报,2009,(4):162-163.
[36] J. Twycross, U. Aickelin. Information fusion in the immune system [J]. Information Fusion,2010,11(1):35-44.
[37] C. Stiller, F. Puente León, M. Kruse. Information fusion for automotive applications–Anoverview [J]. Information Fusion,2011,12(4):244-252.
[38]潘泉,于昕,程咏梅.信息融合理论的基本方法与进展[J].自动化学报,2003,29(4):600-617.
[39]韩崇昭,朱洪艳.多传感信息融合与自动化[J].自动化学报,2009,(S1):201-204.
[40] Boeing, AHM for Boeing [M],2000.
[41] Airbus, Airman for airbus [M],2000.
[42] M.Z. Osmanbhoy, S. Runo, P. Mallasch, Development of fault detection and reporting fornon-central maintenance aircraft [C], in Aerospace Conference,2010IEEE,2010:1-7.
[43]左洪福,发动机磨损状态监测与故障诊断技术[M].北京:航空工业出版社,1995.
[44]刘明,严建峰,李伟华.引入隐变量机制的航空发动机智能故障诊断系统[J].计算机测量与控制,2009,16(12):1770-1772.
[45]官颂,曲培树,董文会.航空发动机智能内窥故障诊断[J].辽宁工程技术大学学报:自然科学版,2009,28(006):981-984.
[46] F. Lu, J. Huang, Y. Xing. Fault Diagnostics for Turbo-Shaft Engine Sensors Based on aSimplified On-Board Model [J]. Sensors,2012,12(8):11061-11076.
[47] S.S. Tayarani-Bathaie, Z. Sadough, K. Khorasani, Dynamic Neural Network-based FaultDiagnosis of Gas Turbine Engines [C], in Modelling, Identification and Control/770:Advances in Computer Science and Engineering,2012.
[48]鲁峰,黄金泉,陈煜.航空发动机部件性能故障融合诊断方法研究[J].航空动力学报,2009,24(7):1649.
[49]金向阳.林琳.钟诗胜.航空发动机振动趋势预测的过程神经网络法[J].振动.测试与诊断,2011,31(3):331-334.
[50]田武刚,潘孟春,罗飞路.航空发动机叶片的内窥涡流集成化原位检测[J].国防科技大学学报,2009,31(005):101-105.
[51]陈立波,宋兰琪,陈果.航空发动机滑油综合监控中的磨损故障融合诊断研究[J].航空动力学报,2009,24(1):169-175.
[52]刘宏,雷勇,闫飞.航空发动机振动分析系统的开发及应用[J].噪声与振动控制,2009,29(1):110-113.
[53]张鹏,倪世宏,谢川.航空发动机振动监控新方法的研究[J].计算机工程与设计,2012,33(5):2027-2030.
[54]曲建岭,唐昌盛,肖辉雄.人工神经网络融合诊断航空发动机气路故障[J].航空动力学报,2009,23(11):2124-2127.
[55]蒋亮.李书明.郝英.航空发动机气路故障诊断研究现状[J].中国民航大学学报,2010,(z1):60-62.
[56]单晓明.宋云峰.黄金泉.基于神经网络和模糊逻辑的航空发动机状态监视[J].航空动力学报,2009,24(10):2356-2361.
[57] Z.Y. Li, H. Ji, H.L. Liu. Machining parameter optimization of aero-engine blade inelectrochemical machining based on BP neural network [J]. Advanced Materials Research,2010,121:893-899.
[58] S.H. Rui, F.M. Zhang, X.L. Xu. The Fault Detection of Aero-engine Based on the ImprovedAssociation Rules Mining [J]. Fire Control&Command Control,2011,9:051.
[59]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[J].航空动力学报,2009,23(12):2170-2176.
[60] A. Stranjak.P.S. Dutta.M. Ebden, A multi-agent simulation system for prediction andscheduling of aero engine overhaul [C], in Proceedings of the7th international jointconference on Autonomous agents and multiagent systems: industrial track,2008:81-88.
[61]肖苏,阳勇,方琳.航空涡轮喷气发动机整体技术现状及发展趋势简介[J].成都航空职业技术学院学报:综合版,2012,27(4):37-39.
[62]华成.徐光华.张庆.基于CBR的智能维修决策技术研究与应用[J].2009中国仪器仪表与测控技术大会论文集,2009,
[63]冯廷敏,基于状态监测的以可靠性为中心的智能维修系统,[D],北京:北京化工大学,2008.
[64]刘文彬.王庆锋.高金吉.以可靠性为中心的智能维修决策模型[J].北京工业大学学报,2012,5:006.
[65]王铮,李艳军.基于离散Hopfield网络的飞机发动机故障诊断的智能算法研究[J].科技信息,2010,(029):52-53.
[66]牛伟.王国庆.翟正军.航空发动机的多参数快速故障诊断模型[J].计算机应用研究,2011,28(12):4564-4575.
[67]梅晓川,陈亚莉.航空飞行器维修技术发展综述[J].航空发动机,2009,35(006):53-57.
[68] N. Papakostas.P. Papachatzakis.V. Xanthakis. An approach to operational aircraftmaintenance planning [J]. Decision Support Systems,2010,48(4):604-612.
[69]唐世明,飞机状态监控系统的研究与改进,[D],电子科技大学,2011.
[70] Z. Peng, Z. Shiwei, W. Yake, The research of aircraft fault diagnosis based on adaptive FPN[C], in Control and Decision Conference,2009. CCDC'09. Chinese,2009:5252-5255.
[71] H. Long, X. Wang, Application of aircraft fuel fault diagnostic expert system based on fuzzyneural network [C], in Information Engineering,2009. ICIE'09. WASE InternationalConference on,2009vol.2:202-205.
[72] L.J.W.C.Z. Yaxin. THE APPLICATION OF EXPERT SYSTEM IN AIRCRAFT FAULTDIAGNOSIS AND MAINTENANCE GUIDING SYSTEM [J]. Computer Applications andSoftware,2009,5:056.
[73] J.B. Cao, E.M. Guo, Y. Li. Design of Fault Diagnosis Expert System for Certain Type ofAircraft Electrical Power [J]. Advanced Materials Research,2012,466:1186-1190.
[74] Z. Yang, L. Qing, P. Lu, Integration of deep and shallow aircraft fault knowledge [C], inCommunication Software and Networks (ICCSN),2011IEEE3rd International Conferenceon,2011:320-324.
[75] D.L. Simon. An Integrated Architecture for On-Board Aircraft Engine Performance TrendMonitoring and Gas Path Fault Diagnostics [J].2010,
[76] H. Yu, Z. Wang, Y. Lu, Design of Remote Fault Diagnosis System on Aircraft [C], inInnovative Computing, Information and Control (ICICIC),2009Fourth InternationalConference on,2009:496-499.
[77] C. Hu, Aircraft fault diagnosis prognostics and health management based on flight recorder[C], in Prognostics and System Health Management (PHM),2012IEEE Conference on,2012:1-4.
[78] M. Cottrell.P. Gaubert.C. Eloy. Fault prediction in aircraft engines using self-organizing maps[J]. Advances in Self-Organizing Maps,2009:37-44.
[79] L. Wei, Prediction of the aircraft fault maintenance sorties based on least squares of linearregression [C], in System Science, Engineering Design and Manufacturing Informatization(ICSEM),20123rd International Conference on,2012vol.2:223-225.
[80] Z. Xuefeng, D. Jianqian, C. Jingjie, On fault prediction model for A320aircraft airconditioning system [C], in Information Networking and Automation (ICINA),2010International Conference on,2010vol.2: V2-231-V2-234.
[81]董亚伟,王杰.地空数据链在民航的应用与发展[J].大众科技,2012,(1):19-20.
[82]何桂萍,徐亚军. ADS-B数据链的比较及特性研究[J].中国民航飞行学院学报,2010,(004):3-6.
[83]蒋兴城,曹力,邓雪云.基于MSK的地空数据链通信调制解调方法[J].信息技术,2012,(8):5-8.
[84] R.J. Eckert, A.C. Prewett, System and method for wireless routing of data from an aircraft[P],ed: Google Patents,2010.
[85]史亚杰,李敬.民航机务维修系统安全风险监测[J].中国安全科学学报,2009,19(011):110-116.
[86]唐宇,王洪.民航机务维修差错评析[J].中国民航大学学报,2010,(z1):54-55.
[87]邓君香.民航机务高技能人才队伍建设[J].中国民用航空,2012,(3):65-67.
[88]刘槟,田玲玲.飞机维修的新理念——飞机健康管理[J].国际航空,2010,(011):80-82.
[89]范平,范玉青.突破技术趋同,波音再现竞争优势——对大型飞机研制技术的战略性分析[J].航空学报,2008,29(3):707-712.
[90]孙立.飞机实时数据的远程管理[J].航空维修与工程,2008,1:037.
[91]张宝珍.国外综合诊断,预测与健康管理技术的发展及应用[J].计算机测量与控制,2008,16(5):591-594.
[92] P. Goupil, A. Marcos, P. Goupil-Airbus. Advanced Diagnosis for Sustainable Flight Guidanceand Control: The European ADDSAFE Project [J]. SAE Technical Paper,2011:01-2804.
[93] D. Henry, J. Cieslak, A. Zolghadri, A Hinf/H-approach for Fault Diagnosis in ElectricalAircraft Flight Control Systems [C], in9th European Workshop on Advanced Control andDiagnosis,2011.
[94] M. O'Brien. IATA's Safety Audit for Ground Operations (ISAGO)[J]. International AirportReview,2008,12(5)
[95] J. Ma.M. Pedigo.L. Blackwell, The Line Operations Safety Audit Program: TransitioningFrom Flight Operations to Maintenance and Ramp Operations, DTIC Document2011.
[96] L.H. Kao, M. Stewart, K.H. Lee. Using structural equation modeling to predict cabin safetyoutcomes among Taiwanese airlines [J]. Transportation Research Part E: Logistics andTransportation Review,2009,45(2):357-365.
[97]肖宪波,俞力玲,王浩锋.基于BP神经网络和飞行参数的航段风险评价[J].中国民航大学学报,2011,29(001):35-38.
[98]路亚峰.张涛.张贤.机载电子设备故障诊断专家系统的设计与实现[J].电子测量技术,2010,(001):118-120.
[99]孙淑光,童震宇,韩雁飞.飞机ACARS报文航段识别专家系统的实现[J].交通信息与安全,2012,29(6):109-112.
[100] ARINC, ARINC Protocol Tutorial Manual [M]: Condor Engineering ARINC,1995.
[101] X.J.D.X.C. Li. Study on the Ground Air Data Link Technology Based on ARINC-618Protocol [J]. Civil Aircraft Design and Research,2011,4:007.
[102] ARINC, ARINC620Data link ground system standard and interface specification [M],1998.
[103] LM Parrilla, AL Rodriguez, A. Simon-Muela. Design of a Middleware Interface for ARINC429Data Bus [J]. Aerospace and Electronic Systems, IEEE Transactions on,2012,48(2):1136-1149.
[104]冯健朋,郭迎清.航空发动机状态监控系统研究[J].航空计算技术,20122:32-36.
[105]史秀宇. V2500发动机性能监控几起典型故障分析[J].航空维修与工程,2009,(4):59-60.
[106]马小骏,左洪福,刘昕.大型客机运行监控与健康管理系统设计[J].交通运输工程学报,2012,11(6):119-126.
[107]王仲生,赵鹏.基于多源信息融合的发动机转子早期故障识别[J].西北工业大学学报,2009,(003):326-329.
[108]李琼,信息融合技术在航空发动机智能监测中的应用研究,[D],南京航空航天大学,2011.
[109]李俊杰,王宏伟,李小波.航空装备视情维修决策研究[J].飞机设计,2011,31(5):77-80.
[110]张涛,航空发动机视情调度优化方法及系统开发,[D],南京航空航天大学,2009.
[111] LA Urban, A Gas Path Analysis Applied to Turbine Engine Condition Monitoring,AIAA1972.
[112] LA Urban. Parameter Selection for Multiple Fault Diagnostics of Gas turbine Engines [J].Journal of Engineering for Power,1975:225-230.
[113] L.A Urban, Gas Path Analysis Applied to Turbine Engine Condition Monitoring,1990.
[114] A. Shepherd,"Gas turbine engine comprising a tension stud," ed: EP Patent2,415,967,2012.
[115]叶斌,孙护国,蔡娜.航空发动机状态监控与故障诊断系统(EMS)研究[J].科技创新导报,2010,(004):5-6.
[116]李咏,杨晓飞,赵云强.油液分析技术在发动机磨损故障中的运用[J].实验科学与技术,2012,10(2):26-27.
[117]费逸伟.张子阳.谢寿生.基于在线油液颗粒检测的飞村发动机状态监控[J].航空维修与工程,2009,(004):66-68.
[118]谢小荣,江涛,杨小林.飞机发动机叶片榫槽爬波原位检测[J].无损检测,2012,1:114-118.
[119]单宁,史仪凯,刘霞.光纤法-珀传感器在飞机发动机叶片裂纹检测中的应用[J].无损检测,2009,31(3):206-207.
[120]张海兵,袁英民.某型发动机2级压气机叶片的涡流探伤方法[J].无损检测,2011,33(2):24-26.
[121]罗英.张德银.彭卫东.民航飞机主动红外热波成像检测技术应用进展[J].激光与红外,2011,41(7):718-723.
[122]刘罗曼.时间序列分析中指数平滑法的应用[J].沈阳师范大学学报:自然科学版,2009,27(004):416-418.
[123]齐驰,侯忠生.自适应单指数平滑法在短期交通流预测中的应用[J].控制理论与应用,2012,29(4):456-470.
[124]李林,黄柯棣,何芳.集中式多传感器融合系统中的时间配准研究[J].传感技术学报,2008,(11):2445-2449.
[125]许珉,刘凌波.基于三次样条函数的加Blackman-harris窗插值FFT算法[J].电力自动化设备,2009,29(2):59-63.
[126]翟旭升.胡金海.谢寿生.基于DSmT的航空发动机早期振动故障融合诊断方法[J].航空动力学报,2012,27(002):301-306.
[127]鲁峰,黄金泉,仇小杰.基于信息熵融合提取特征的发动机气路分析 [J].仪器仪表学报,2012,33(1):13-19.
[128]龚荣芳.关于多元函数极值判定方法的教学思考[J].中国科教创新导刊,2011,(17):97-97.
[129]陈东菊,范晋伟,雒驼. Daubechies小波在机床动态误差特征提取与辨识中的应用[J].北京工业大学学报,2012,38(10):239-246.
[130]张世强,吕杰能,蒋峥.关于相关系数的探讨[J].数学的实践与认识,2009,(019):102-107.
[131] E.C.Y. Peh, Y.C. Liang, Y.L. Guan. Cooperative spectrum sensing in cognitive radio networkswith weighted decision fusion schemes [J]. Wireless Communications, IEEE Transactions on,2010,9(12):3838-3847.
[132]汪新凡.混合加权集成算子及其在决策中的应用[J].湖南工业大学学报,2010,24(002):34-38.
[133]陈晓红,阳熹.一种基于三角模糊数的多属性群决策方法[J].系统工程与电子技术,2008,30(2):278-282.
[134] Q. Wu, R. Law. Fuzzy support vector regression machine with penalizing Gaussian noises ontriangular fuzzy number space [J]. Expert Systems with Applications,2010,37(12):7788-7795.
[135] I. Gonzalo-Fonrodona, M. Porras. Scaling power laws in the restoration of perception withincreasing stimulus in deficitary natural neural network [J]. Methods and Models in Artificialand Natural Computation. A Homage to Professor Mira’s Scientific Legacy,2009:174-183.
[136] M. Luko Evi Ius, H. Jaeger. Reservoir computing approaches to recurrent neural networktraining [J]. Computer Science Review,2009,3(3):127-149.
[137] L. Wang, K. Fu, Artificial neural networks [M]: Wiley Online Library,2009.
[138] S.S. Haykin, S.S. Haykin, S.S. Haykin, Neural networks and learning machines [M] vol.3:Prentice Hall,2009.
[139] G. Tayfur, Soft Computing in Water Resources Engineering: Artificial Neural Networks,Fuzzy Logic and Genetic Algorithms [M]: WIT Press/Computational Mechanics,2011.
[140] S. Kiranyaz, T. Ince, A. Yildirim. Evolutionary artificial neural networks bymulti-dimensional particle swarm optimization [J]. Neural Networks,2009,22(10):1448-1462.
[141] A. Krogh. What are artificial neural networks?[J]. Nature biotechnology,2008,26(2):195-197.
[142]刘廷毅.航空发动机研制全寿命管理研究及建议[J].航空发动机,2012,38(1):1-6.
[143]王俨剀,王理,廖明夫.航空发动机整机测振中的基本问题分析[J].航空发动机,2012,38(3):49-53.
[144] S. Goyal, G.K. Goyal. Artificial neuron based models for estimating shelf life of burfi [J].ARPN J. Sci. Tech,2012,2(6):536-540.
[145] K. Huang, L. Dai, S. Huang, Wind Prediction Based on Improved BP Artificial NeuralNetwork in Wind Farm [C], in Electrical and Control Engineering (ICECE),2010International Conference on,2010:2548-2551.
[146] Z. Liu, X. Meng. Integration of improved BPNN algorithm and multistage dynamic fuzzyjudgement and its application on ESMP evaluation [J]. Journal of computers,2009,4(1):69-76.
[147] Z. Xiao, S.J. Ye, B. Zhong. BP neural network with rough set for short term load forecasting[J]. Expert Systems with Applications,2009,36(1):273-279.
[148] Y. Huang, D. Sun, G. Xing, Criticality Evaluation for Spare Parts Based on BP NeuralNetwork [C], in Artificial Intelligence and Computational Intelligence (AICI),2010International Conference on,2010vol.1:204-206.
[149]邓万宇,郑庆华,陈琳.神经网络极速学习方法研究[J].计算机学报,2010,33(2):279-287.
[150]施彦,韩力群,神经网络设计方法与实例分析[M]:北京邮电大学出版社,2009.
[151]张泓,李爱平,刘雪梅.面向TSP求解的混合蚁群算法[J].计算机工程,2009,35(8)17-22.
[152]王书明,刘玉兰,王家映.蚁群算法[J].工程地球物理学报,2008,34(19):71-76.
[153]倪庆剑,邢汉承,张志政.蚁群算法及其应用研究进展[J].计算机应用与软件,2008,25(8):12-16.
[154] X. Li, J. Cao, D. Du. Comparison of Levenberg-Marquardt Method and Path FollowingInterior Point Method for the Solution of Optimal Power Flow Problem [J]. InternationalJournal of Emerging Electric Power Systems,2012,13(3):2-8..
[155] B.M. Wilamowski, H. Yu. Improved computation for Levenberg–Marquardt training [J].Neural Networks, IEEE Transactions on,2010,21(6):930-937.
[156] S. Basterrech, S. Mohammed, G. Rubino. Levenberg—Marquardt Training Algorithms forRandom Neural Networks [J]. The Computer Journal,2011,54(1):125-135.
[157] H. Mirzaee. Long-term prediction of chaotic time series with multi-step prediction horizonsby a neural network with Levenberg–Marquardt learning algorithm [J]. Chaos, Solitons&Fractals,2009,41(4):1975-1979.
[158]凌锦江,周志华.基于因果发现的神经网络集成方法[J].软件学报,2004,15(10)
[159] A. Azadeh, A. Maghsoudi, S. Sohrabkhani. An integrated artificial neural networks approachfor predicting global radiation [J]. Energy Conversion and Management,2009,50(6):1497-1505.
[160] D. elebi, D. Bayraktar. An integrated neural network and data envelopment analysis forsupplier evaluation under incomplete information [J]. Expert Systems with Applications,2008,35(4):1698-1710.
[161]张东波,黄辉先,王耀南.基于粗糙集约简的特征选择神经网络集成技术[J].控制与决策,2010,3:371-377.
[162]周志华,陈世福.神经网络集成[J].计算机学报,2002,25(1):1-8.
[163]吴建鑫,周志华,沈学华.一种选择性神经网络集成构造方法[J].计算机研究与发展,2000,37(9):1039-1044.
[164]唐伟,周志华.基于Bagging的选择性聚类集成[J].软件学报,2005,16(4):496-502.
[165]易承罡.基于ACARS的飞机实时监控系统研究[J].宁波大学学报(理工版),2011,24(1)：132-136.
[166]钟诗胜,雷达,丁刚.卷积和离散过程神经网络及其在航空发动机排气温度预测中的应用[J].航空学报,2012,33(003):438-445.
[167] A. Lapedes, R. Farber, Nonlinear signal processing using neural networks: Prediction andsystem modelling[C], IEEE international conference on neural networks, San Diego, CA,USA,21Jun1987.
[168] A. Lapedes, R. Farber, How neural nets work [C], in Neural information processing systems,1988:442-456.
[169] Z. Pawlak. Rough Sets [J]. International Journal of Computer and Information Sciences,1982,11:341-356.
[170] Z. Pawlak. Rough Set Theory and Its Application to Data Analysis [J]. Cybernetics andSystems,1998,29(9):661-668.
[171]夏红霞,王惠营.基于粗糙集的神经网络结构优化方法[J].计算机与数字工程,2010,38(5):49-51.
[172] H. Xu, D. Jiang, L. Liang, Application of Fuzzy-Rough Set theory and improved SMOalgorithm in aircraft engine vibration fault diagnosis [C], in Prognostics and System HealthManagement (PHM),2012IEEE Conference on NN,2012:1-6.
[173] L. Wang, YG Li, M.F.A. Ghafir. A Rough Set-based gas turbine fault classification approachusing enhanced fault signatures [J]. Proceedings of the Institution of Mechanical Engineers,Part A: Journal of Power and Energy,2011,225(8):1052-1065.
[174]苗夺谦. Rough Set理论中连续属性的离散化方法[J].自动化学报,2001,27(3):296-302.
[175]王海燕,盛昭瀚.混沌时间序列相空间重构参数的选取方法[J].东南大学学报,2000,30(5):113-117.
[176]陈铿,韩伯棠.混沌时间序列分析中的相空间重构技术综述[J].计算机科学,2005,32(4):67-70.
[177]张淑清,贾健,高敏.混沌时间序列重构相空间参数选取研究[J].物理学报,2010,59(3):1576-1582.