航空发动机磨损故障智能诊断若干关键技术研究
|
摘要
航空发动机结构极复杂，工作在高温、高速的恶劣条件下，极易发生各种机械故障。据统计，在造成各类飞行事故的诸因素中，发动机故障原因所占比例一般在25％～30％，而航空发动机转子系统及传动系统中的齿轮和轴承磨损失效是航空发动机研制和使用过程中所出现的主要故障。由此可见，及时有效地诊断和预测出航空发动机的磨损故障，对于提高飞行安全，降低发动机维修成本，实施航空发动机视情维修，具有重要意义。然而，由于航空发动机的复杂性，各种磨损数据与磨损故障之间是一种模糊的、非线性、不确定的关系，传统方法已经不能满足磨损故障诊断的要求。鉴于此，本文将现代人工智能和模式识别技术引入航空发动机磨损故障诊断，围绕航空发动机磨损故障智能诊断若干关键技术进行研究，主要内容如下：
1）不局限于正态分布假设的磨损界限值的制定。抛弃了传统油样数据正态分布假设，提出了基于支持向量机的磨损界限值制定方法。利用支持向量机从大量的油样分析数据中估计出概率密度函数，再依据估计出的概率密度函数得到航空发动机磨损界限值。该方法利用了支持向量机全局最优、良好泛化能力，以及解的稀疏性等优越性能，与传统统计方法相比，更具科学性和合理性。最后本文应用实际的航空发动机油样光谱数据对方法进行了验证分析，表明了方法的正确有效性。
2）磨损趋势的组合预测方法。对油样分析数据进行数学建模，外推出未来发展趋势，对于航空发动机磨损状态的预测，尽早对故障的发展趋势进行预测和评估，从而避免重大事故的发生和及时安排维修工作，具有重要意义。鉴于此，本文提出基于最小二乘支持向量机的组合预测方法，首先利用灰色预测模型，神经网络预测模型和AR预测模型进行单项预测，然后利用最小二乘支持向量机方法实现组合预测，同时利用粒子群算法对支持向量机参数进行了优化。该方法解决了单一预测模型的信息源不广泛性，对模型设定形式敏感等问题。最后，利用实际的航空发动机油样光谱数据对方法进行了验证，表明了本文组合预测方法较单一预测模型方法大大提高了预测精度。
3）磨损故障诊断知识规则的自动提取。为了解决目前航空发动机磨损故障智能诊断专家系统普遍存在知识获取能力弱，知识更新困难，知识适应性差等方面的缺陷，本文提出了基于支持向量机的数据挖掘技术，利用支持向量机进行了磨损规则的自动获取研究。在该方法中，首先利用遗传算法对样本数据特征进行选取，然后将特征选取后的数据样本映射到一个高维特征空间中，得到样本的最优分类超平面以及支持向量，利用支持向量机聚类算法得到样本的聚类分配矩阵，最后在聚类分配矩阵的基础上构建超矩形，得到超矩形规则，并利用规则合并、维数约简、区间延伸等方法对超矩形规则进行了简化。针对样本严重不平衡问题，本文采用过抽样算法中典型的SMOTE算法对故障样本进行重采样之后再进行规则提取，取得了良好的效果。同时，开发了专家系统与国外著名数据挖掘开源软件Weka的接口技术，利用Weka软件的数据挖掘算法实现了航空发动机磨损故障诊断专家系统的知识自动获取。最后，利用实际的航空发动机故障数据进行了验证，表明了本文方法的正确有效性。
4）基于多Agent的磨损故障融合诊断方法。该方法综合运用各油样分析方法的冗余性和互补性，有效地利用各种油样分析方法的特点和优势以提高诊断精度。该多Agent诊断系统主要包括颗粒计数Agent、理化分析Agent、铁谱分析Agent、光谱分析Agent、总控Agent、调度Agent、通信Agent、融合诊断Agent、油样数据和知识规则库以及人机智能界面。本文根据飞机发动机磨损故障诊断的实际情况，给出了各Agent诊断规则，并用具体的油样分析数据进行了验证，表明了多Agent融合诊断的有效性。
5）最后本文将所研究的若干智能方法运用于与成都飞机工业（集团）有限责任公司以及北京航空工程技术研究中心合作开发的航空发动机磨损故障诊断专家系统中，实现磨损界限值制定、磨损趋势预测、融合诊断以及专家系统的知识自动获取。应用结果表明，本文的研究工作大大提升了航空发动机磨损故障智能诊断专家系统的智能化和自动化水平。
Aero-engine has extremely complex structure, and easily has broken down all kinds ofmechanical failure working in harsh conditions of high temperature and high speed. According tosome statistics, in the factors that cause various types of flight accident, the proportion of the enginefailure reason is generally in the range of25%to30%. Moreover, the gear and bearing wear failurein the aero-engine rotor system and transmission system is the main fault occurred in the study andapplication. Therefore, it is critical to diagnose and predict the aircraft engine wear fault timely andeffectively in order to elevate the flight safety, lower the engine maintenance cost, implementaero-engine condition based maintenance. However, because of the complexity of the aero-engine,the relationships between the various wear data and the wear failure is fuzzy, nonlinear and uncertainrelationship, and the traditional methods can't meet the requirements of the wear fault diagnosis. Inview of this, this paper introduces the modern artificial intelligence and pattern recognitiontechnology into the aero-engine wear fault diagnosis and has commenced the study on some pivotalproblems about aero-engine wear fault intelligent diagnosis. Now the summary of main workingcontents in this paper is as follows:
(1) The establishment of the wear threshold that is not limited to the normal distributionassumption. The establishment of the wear threshold based on Support Vector Machine is proposedwith abandoning the traditional normal distribution assumption of the sample data. The probabilitydensity is estimated from a large number of oil samples by using Support Vector Machine, and thenthe wear threshold is obtained according to the probability density. This method takes advantage ofserious advantages of Support Vector Machine such as the global optimal solutions, goodgeneralization ability, and the sparse solution. This method is more scientific and reasonable incontrast to the traditional statistical methods. Lastly, the verification analysis is done by using theactual Aero-engine spectroscopic data, and the results suggest the correctness and effectiveness ofthe method.
(2) Combinational Forecast Method of the wear trend. It is critical to estimate the futuredevelopment trend through making Mathematical Modeling for oil sample data in order to predictthe aircraft engine wear trend, and forecast and evaluate the development trend of the fault as earlyas possible, so as to prevent major accidents and schedule maintenance work in time. In view of this,this paper proposed the combinational forecast method based on Least Square Support VectorMachine. The first step is using AR model、GM(1,1) model and BP neural network model to predictindividually, and the next step is combination forecast based on LSSVM, at the same timeoptimizing the parameters of SVM method by using particle swarm algorithm. This method solvessome issues such as comprehensive information of the single forecasting model, and sensitive to themodel form setting. Lastly, the verification analysis is done by using the actual Aero-enginespectroscopic data, and the results show that, compared with the individual forecast methods, thecombinational forecast method has greatly improved the prediction precision.
(3) Automatic extraction of wear fault diagnosis knowledge rules. In order to solve the defectsof the current aircraft engine wear fault intelligent diagnosis expert system, such as the weakness ofcapability of knowledge acquisition, the difficulty of knowledge updating, poor adaptability of knowledge, and so on. In this paper, a data mining approach based on SVM is proposed to extractwear rules automatically. In this method, the first step is to choose the features of the sample data byusing Genetic Algorithm for improving the comprehensibility of the knowledge rules. Then the SVCalgorithm is adopted to get the Clustering Distribution Matrix of the sample data whose featureshave been chosen. Finally, hyper-rectangle rules are constructed on the base of the ClusteringDistribution Matrix. In order to make the rules more concise, and easier to be explained,hyper-rectangle rules are simplified further by using rules combination, dimension reduction andinterval extension. In addition, the SMOTE algorithm is adopted to resample fault samples in orderto solve the serious imbalance problem of samples. Meanwhile, the interface between the foreignwell-known open source software in data mining called Weka and expert system was researched,and the data mining method in Weka is used to extract knowledge automatically from aircraft enginewearing fault data. Lastly, the verification analysis is done by using the actual Aero-enginespectroscopic data, and the results suggest the correctness and effectiveness of the method.
(4) Engine wear fault fusion diagnosis method based on Multi-Agent. This method improvesdiagnostic accuracy by using of characteristics and advantage and comprehensive use of redundancyand complementarity of various oil analysis methods. The Multi-Agent diagnosis System isconstituted by Particle Count Agent, Physicochemical Analysis Agent, Ferrograph Analysis Agent,Spectrometric Analysis Agent, General Control Agent, Scheduling Agent, Communication Agent,Fusion Diagnosis Agent sample data and knowledge rule database, and man-machine intelligentinterface. In this paper, according to the actual situation of aero-engine wear fault diagnosis, eachagent diagnosis rules are given. At last, the test results of the specific oil analysis data show theeffectiveness of the multi-agent fusion diagnosis.
(5) Finally, the intelligent methods of this paper researched are applied to the developedaero-engine wear fault diagnosis expert system cooperated with Chengdu aircraft industrial (group)co., LTD and the Institute of Airforce Equipment. The establishment of the wear threshold, the weartrend, fusion diagnosis and automatic extraction of wear fault diagnosis knowledge rules are realized.The application results show that the work researched has greatly increased the intelligent andautomation level of the aero-engine wear fault intelligent diagnosis expert system.
1）不局限于正态分布假设的磨损界限值的制定。抛弃了传统油样数据正态分布假设，提出了基于支持向量机的磨损界限值制定方法。利用支持向量机从大量的油样分析数据中估计出概率密度函数，再依据估计出的概率密度函数得到航空发动机磨损界限值。该方法利用了支持向量机全局最优、良好泛化能力，以及解的稀疏性等优越性能，与传统统计方法相比，更具科学性和合理性。最后本文应用实际的航空发动机油样光谱数据对方法进行了验证分析，表明了方法的正确有效性。
2）磨损趋势的组合预测方法。对油样分析数据进行数学建模，外推出未来发展趋势，对于航空发动机磨损状态的预测，尽早对故障的发展趋势进行预测和评估，从而避免重大事故的发生和及时安排维修工作，具有重要意义。鉴于此，本文提出基于最小二乘支持向量机的组合预测方法，首先利用灰色预测模型，神经网络预测模型和AR预测模型进行单项预测，然后利用最小二乘支持向量机方法实现组合预测，同时利用粒子群算法对支持向量机参数进行了优化。该方法解决了单一预测模型的信息源不广泛性，对模型设定形式敏感等问题。最后，利用实际的航空发动机油样光谱数据对方法进行了验证，表明了本文组合预测方法较单一预测模型方法大大提高了预测精度。
3）磨损故障诊断知识规则的自动提取。为了解决目前航空发动机磨损故障智能诊断专家系统普遍存在知识获取能力弱，知识更新困难，知识适应性差等方面的缺陷，本文提出了基于支持向量机的数据挖掘技术，利用支持向量机进行了磨损规则的自动获取研究。在该方法中，首先利用遗传算法对样本数据特征进行选取，然后将特征选取后的数据样本映射到一个高维特征空间中，得到样本的最优分类超平面以及支持向量，利用支持向量机聚类算法得到样本的聚类分配矩阵，最后在聚类分配矩阵的基础上构建超矩形，得到超矩形规则，并利用规则合并、维数约简、区间延伸等方法对超矩形规则进行了简化。针对样本严重不平衡问题，本文采用过抽样算法中典型的SMOTE算法对故障样本进行重采样之后再进行规则提取，取得了良好的效果。同时，开发了专家系统与国外著名数据挖掘开源软件Weka的接口技术，利用Weka软件的数据挖掘算法实现了航空发动机磨损故障诊断专家系统的知识自动获取。最后，利用实际的航空发动机故障数据进行了验证，表明了本文方法的正确有效性。
4）基于多Agent的磨损故障融合诊断方法。该方法综合运用各油样分析方法的冗余性和互补性，有效地利用各种油样分析方法的特点和优势以提高诊断精度。该多Agent诊断系统主要包括颗粒计数Agent、理化分析Agent、铁谱分析Agent、光谱分析Agent、总控Agent、调度Agent、通信Agent、融合诊断Agent、油样数据和知识规则库以及人机智能界面。本文根据飞机发动机磨损故障诊断的实际情况，给出了各Agent诊断规则，并用具体的油样分析数据进行了验证，表明了多Agent融合诊断的有效性。
5）最后本文将所研究的若干智能方法运用于与成都飞机工业（集团）有限责任公司以及北京航空工程技术研究中心合作开发的航空发动机磨损故障诊断专家系统中，实现磨损界限值制定、磨损趋势预测、融合诊断以及专家系统的知识自动获取。应用结果表明，本文的研究工作大大提升了航空发动机磨损故障智能诊断专家系统的智能化和自动化水平。
Aero-engine has extremely complex structure, and easily has broken down all kinds ofmechanical failure working in harsh conditions of high temperature and high speed. According tosome statistics, in the factors that cause various types of flight accident, the proportion of the enginefailure reason is generally in the range of25%to30%. Moreover, the gear and bearing wear failurein the aero-engine rotor system and transmission system is the main fault occurred in the study andapplication. Therefore, it is critical to diagnose and predict the aircraft engine wear fault timely andeffectively in order to elevate the flight safety, lower the engine maintenance cost, implementaero-engine condition based maintenance. However, because of the complexity of the aero-engine,the relationships between the various wear data and the wear failure is fuzzy, nonlinear and uncertainrelationship, and the traditional methods can't meet the requirements of the wear fault diagnosis. Inview of this, this paper introduces the modern artificial intelligence and pattern recognitiontechnology into the aero-engine wear fault diagnosis and has commenced the study on some pivotalproblems about aero-engine wear fault intelligent diagnosis. Now the summary of main workingcontents in this paper is as follows:
(1) The establishment of the wear threshold that is not limited to the normal distributionassumption. The establishment of the wear threshold based on Support Vector Machine is proposedwith abandoning the traditional normal distribution assumption of the sample data. The probabilitydensity is estimated from a large number of oil samples by using Support Vector Machine, and thenthe wear threshold is obtained according to the probability density. This method takes advantage ofserious advantages of Support Vector Machine such as the global optimal solutions, goodgeneralization ability, and the sparse solution. This method is more scientific and reasonable incontrast to the traditional statistical methods. Lastly, the verification analysis is done by using theactual Aero-engine spectroscopic data, and the results suggest the correctness and effectiveness ofthe method.
(2) Combinational Forecast Method of the wear trend. It is critical to estimate the futuredevelopment trend through making Mathematical Modeling for oil sample data in order to predictthe aircraft engine wear trend, and forecast and evaluate the development trend of the fault as earlyas possible, so as to prevent major accidents and schedule maintenance work in time. In view of this,this paper proposed the combinational forecast method based on Least Square Support VectorMachine. The first step is using AR model、GM(1,1) model and BP neural network model to predictindividually, and the next step is combination forecast based on LSSVM, at the same timeoptimizing the parameters of SVM method by using particle swarm algorithm. This method solvessome issues such as comprehensive information of the single forecasting model, and sensitive to themodel form setting. Lastly, the verification analysis is done by using the actual Aero-enginespectroscopic data, and the results show that, compared with the individual forecast methods, thecombinational forecast method has greatly improved the prediction precision.
(3) Automatic extraction of wear fault diagnosis knowledge rules. In order to solve the defectsof the current aircraft engine wear fault intelligent diagnosis expert system, such as the weakness ofcapability of knowledge acquisition, the difficulty of knowledge updating, poor adaptability of knowledge, and so on. In this paper, a data mining approach based on SVM is proposed to extractwear rules automatically. In this method, the first step is to choose the features of the sample data byusing Genetic Algorithm for improving the comprehensibility of the knowledge rules. Then the SVCalgorithm is adopted to get the Clustering Distribution Matrix of the sample data whose featureshave been chosen. Finally, hyper-rectangle rules are constructed on the base of the ClusteringDistribution Matrix. In order to make the rules more concise, and easier to be explained,hyper-rectangle rules are simplified further by using rules combination, dimension reduction andinterval extension. In addition, the SMOTE algorithm is adopted to resample fault samples in orderto solve the serious imbalance problem of samples. Meanwhile, the interface between the foreignwell-known open source software in data mining called Weka and expert system was researched,and the data mining method in Weka is used to extract knowledge automatically from aircraft enginewearing fault data. Lastly, the verification analysis is done by using the actual Aero-enginespectroscopic data, and the results suggest the correctness and effectiveness of the method.
(4) Engine wear fault fusion diagnosis method based on Multi-Agent. This method improvesdiagnostic accuracy by using of characteristics and advantage and comprehensive use of redundancyand complementarity of various oil analysis methods. The Multi-Agent diagnosis System isconstituted by Particle Count Agent, Physicochemical Analysis Agent, Ferrograph Analysis Agent,Spectrometric Analysis Agent, General Control Agent, Scheduling Agent, Communication Agent,Fusion Diagnosis Agent sample data and knowledge rule database, and man-machine intelligentinterface. In this paper, according to the actual situation of aero-engine wear fault diagnosis, eachagent diagnosis rules are given. At last, the test results of the specific oil analysis data show theeffectiveness of the multi-agent fusion diagnosis.
(5) Finally, the intelligent methods of this paper researched are applied to the developedaero-engine wear fault diagnosis expert system cooperated with Chengdu aircraft industrial (group)co., LTD and the Institute of Airforce Equipment. The establishment of the wear threshold, the weartrend, fusion diagnosis and automatic extraction of wear fault diagnosis knowledge rules are realized.The application results show that the work researched has greatly increased the intelligent andautomation level of the aero-engine wear fault intelligent diagnosis expert system.
引文
[1]屈梁生,何正嘉.机诫故障诊断学.上海:上海科学技术大学出版社,1986.
[2]邝朴生.现代机器故障诊断学.北京:农业出版社,1991.
[3]钟秉林,黄仁.机械故障诊断学.北京:机械工业出版社,1997.
[4]丁玉兰,石来德.机械设备故障诊断技术.上海:上海科学技术文献出版社,1994.
[5]范作民.航空发动机状态诊断.天津:天津科技翻译出版公司,1990.
[6]陈长征,白秉三.设备故障诊断技术研究进展.洛阳工业大学学报，2000,4(22):349~352
[7]陈克兴,李川奇.设备状态监视与故障诊断技术.北京:科技文献出版社,1991.
[8]屈梁生,张海军.机械诊断中的几个基本问题.中国机械工程,2000, l(1l):211~216.
[9]李炜,伦椒娴.设备故障诊断技术的现状及其发展.甘肃工业大学学报,1998,2(24):66~69.
[10]虞和济,傅润兰.故障诊断的数学力学基础.北京:冶金工业出版社,1991.
[11]吴今培.智能故障诊断技术的发展与展望.振动、测试与诊断,1999,2(19):79~86.
[12]左洪福.发动机磨损状态监测与故障诊断技术.北京:航空工业出版社,1995.
[13]陈果.航空器检测与诊断技术导论.北京:中国民航出版社,2007.
[14]陈果,李爱.航空器检测与诊断技术导论.北京:航空工业出版社,2012.
[15]吴振峰.基于磨粒分析和信息融合的发动机磨损故障诊断技术研究[博士学位论文].南京:南京航空航天大学,2001.
[16] Doel, David L. Assessment of weighted-Least-Squares Based Gas Path Analysis. Journal ofEngineering for Gas Turbines and Power,2009,116(2):366-373.
[17] Doel David L. Temper-A Gas Path Analysis Tool for Commercial Jet Engines. Transactions ofthe ASME Journal of Engineering for Gas Turbines and Power,1994,116(1):82-89.
[18]范作民,孙春林,林兆福.发动机故障方程的建立与故障因子的引入.中国民航学院学报,1994,12(1):1-14.
[19]陈大光.多状态气路分析法诊断发动机故障的分析.航空动力学报,1994,9(4):339-343.
[20]严寒松.航空发动机故障诊断[博士学位论文].南京:南京航空航天大学,1996.
[21]钱建阳.航空发动机气路智能故障诊断[博士学位论文].南京:南京航空航天大学,2000.
[22]杨建国,孙扬,郑严.基于小波和模糊神经网络的涡喷发动机故障诊断.推进技术,2001,22(2):114-117.
[23]左洪福.发动机磨损状态监测与故障诊断技术.北京:航空工业出版社,1995:63~149.
[24] Chen Guo.3D Measurement and Stereo Reconstruction for Aeroengine Interior Damage.Chinese Journal of Aeronautics.2004,17(3):149-151.
[25]杨叔子,史铁林.基于知识的诊断推理.北京:清华大学出版社,1993.
[26]高济.基于知识的软件智能化技术.浙江:浙江大学出版社,2002.
[27] Sorsa T, Koivo H N, Koivisto H. Neural networks in process fault diagnosis. IEEE Transactionson Systems, Man, and Cybernetics,1991,21(4):815~824.
[28] Bernieri A, A puzzo M D, Sansone L, et al. A neural network approach for identification andfault diagnosis on dynamic systems. IEEE Transactions on Instrumentation and Measurement,1994,43(6):867~873.
[29] Tang T H, Lin X, Li J R, et al. A new fuzzy neural network approach for intelligent monitoringsystem. Proceedings of IFAC Transportation Systems Conference,1997:691-696.
[30] Varma A, Roddy N. ICARUS: design and deployment of a case-based reasoning system forlocomotive diagnostics. Engineering Applications of Artificial Intelligence,1999,12(6):681-690.
[31] Palshikar G K, Khemani D. Diagnosing dynamic systems using trace patterns. PatternRecognition Letters,1999,20(7):741-753.
[32] Kassidas A, Taylor P A, MacGregor J F. Off line diagnosis of deterministic faults in continuousdynamic multivariable processes using speech recognition methods. Journal of Process Control,1998,8(5-6):381~393.
[33] Foret M P, G lasgow J I. Combining casebased and model based reasoning for the diagnosis ofcomplex devices. Applied Intelligence,1997,7(1):57-78.
[34]丘雪棠.润滑油液在线颗粒传感器试验研究[硕士学位论文].广州:华南理工大学,2011.
[35] Muir D M, Howe B. In-line oil debris monitor (ODM) for the advanced tactical fighter engine.SAE Paper961308, May1996.
[36] Hughes I, Muir D. On-line oil debris monitor for aircraft for engines. JOAP Conference,November,1994.
[37] Higgins P D, Crow J T. Advances in commercial engine lube debris monitoring. SAE Technical1997,1-4:972603.
[38] Byington C S, Schalcosky D C. Advances in real time oil Analysis. Practicing Oil AnalysisMagazine,2000,11(2):28-34.
[39] Powrie H E G, Fisher C E. Engine-health monitoring: towards total prognostics. IEEEAeropsace Conference Proceedings, March,1999,3(6-13):11-20.
[40] Powrie H E G. Use of electrostatic technology for aero engine oil system monitoring.Proceedings of IEEE Aerospace Conference,2000:57-71.
[41] Powrie H E G, Wood R J K, Harvey T J, et al. Electrostatic charge generation associated withmachinery component deterioration. Proceedings of IEEE Aerospace Conference, Big Sky,Montana, March2002,6:2927-2934.
[42]李应红,尉询楷,刘建勋.支持向量机的工程应用.北京:民兵工业出版社,2004.
[43]李应红,付全俊.航空发动机试车故障诊断专家系统.航空学会动力控制学术交流会,1989.9.
[44]贾智伟,李应红,雷晓犇.基于模糊综合函数的故障诊断[J].系统工程与电子技术,2004,26(3):416-417.
[45]尉询楷,李应红等.基于支持向量机的航空发动机辨识模型.航空动力学报,2004.10,19(5):684-688.
[46]尉询楷,李应红等.基于支持向量机的航空发动机滑油监控分析.航空动力学报,2004.6,19(3):392-397.
[47]尉询楷,陆波等.支持向量机在航空发动机故障诊断中的应用.航空动力学报,2004.12,19(6):844-848.
[48]石荣德,赵廷弟等.故障诊断专家系统.北京航空航天大学学报,1995.10,21(4):7-12.
[49]左洪福,吴振峰等. DMAS智能化铁谱分析系统及其应用.江苏航空,1999(3-4):60-64.
[50]陈果,左洪福.基于知识规则的发动机磨损故障诊断专家系统.航空动力学报,2004,19(1):23-29.
[51]陈果,左洪福.基于神经网络的多种油样分析技术融合诊断.摩擦学学报,2003,23(5):431-434.
[52]陈果.基于神经网络和D-S证据理论的发动机磨损故障融合诊断.航空动力学报,2005,20(2):303-308.
[53]陈果.用结构自适应神经网络预测航空发动机性能趋势.航空学报,2007,28(3):535-539.
[54]周志华,何佳洲,尹旭日等.一种基于统计的神经网络规则抽取方法.软件学报,2001,12(2):263-269.
[55]陈果,宋兰琪,陈立波,张占纲.基于粗糙集理论的航空发动机滑油光谱诊断专家系统知识获取方法研究.机械科学与技术,2007,26(7):898-901.
[56] Paw lak Z. Rough set. International Journal of Information and Computer Science,1982,11(5):341-356.
[57]王国胤. Rough集理论与知识获取.西安交通大学出版社,2001.
[58]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(12),23(12):2170-2176.
[59] Saito K, Nakano R. Medical diagnostic expert system based on PDP model. Proceedings of theIEEE International Conference on Neural Networks. New York: IEEE Press,1988:255-262.
[60] Fu L M. Rule learning by searching on adapts nets. Proceedings of the9th National Conferenceon Arificial Intelligence. Anaheim, CA: AAAI Press,1991:590-595.
[61]虞和济,韩庆大,李沈等.设备故障诊断工程.北京:冶金工业出版社,2001.
[62]陈果.航空发动机磨损故障的智能融合诊断.2005,16(4):299-306.
[63] Ramesh R, Bruce C W, Matthew S. Evolution of Propulsion Controls and Health Monitoring atPratt and Whitney, AIAA-2003-2645.4.
[64] Takahisa K, A. Hybrid Neural Network Genetic Algorithm Technique for Aircraft EnginePerformance Diagnostics. NASA/TM-2001-211088.
[65]赵方,谢友柏,柏子游.油液分析多技术集成的特征与信息融合.摩擦学学报,1998,18(1):45-52.
[66]严新平,谢友柏,潇汉良.摩擦学故障诊断种类的D-S信息融合研究.摩擦学学报,1999,19(2):145-150.
[67]陈果.基于神经网络和D-S证据理论的发动机磨损故障融合诊断.航空动力学报,2005.4,20(2):303-308.
[68]陈果,左洪福,杨新.基于神经网络的多种油样分析技术融合诊断.摩擦学学报,2003.9,23(5):431-434.
[69]叶志锋.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.
[70] Chen G, Yang Y W, Zuo H F. Intelligent Fusion for Aeroengine Wear Fault Diagnosis.Transactions of Nanjing University of Aeronautics&Astronautics,2006,23(4):297-303.
[71]陈恬，孙健国，郝英.基于神经网络和证据融合理论的航空发动机气路故障诊断.航空学报,2006,27(6):1014-1017.
[72]王松,褚福磊,何永勇等.基于信息融合技术的发动机故障诊断的研究.内燃机学报,2003,21(5):374-378.
[73]夏勇,张振仁,陈卫昌等.机械设备故障诊断的复杂性理论.机械学报,2001,28(5):3-5.
[74]尉询楷,李应红等.基于支持向量机的信息融合诊断方法.系统工程与电子技术.2005.9,27(9):1665-1668.
[75]葛世荣,朱华.摩擦学复杂系统及其问题的量化研究方法.摩擦学学报,2002,22(5):405-408.
[76]干敏梁,左洪福,杨忠,江涌.时序建模方法在滑油光谱分析中的应用.光谱学与光谱分析,2000,20(1):64-67.
[77]陈志英.航空发动机滑油监视与诊断系统软件研制.推进技术,1998,19(5):52-55.
[78]任国全,张英堂,吕建刚,张培林.润滑油磨粒浓度预测模型研究.润滑与密封,1999,4:45-47.
[79]严新平,谢友柏,李晓峰,萧汉梁.一种柴油机磨损的预测模型与试验研究.摩擦学学报,1996,16(4):358-366.
[80]梁华,杨明忠,陆培德.用人工神经网络预测摩擦学系统磨损趋势.摩擦学学报,1996,16(3):267-271.
[81]吴明赞,陈森发.用灰色系统模型进行船舶柴油机磨损趋势分析.系统工程理论与实践,2001,(8):102-105.
[82]张来斌,刘守道,王朝晖.柴油机整体性能预测的灰色神经网络方法. Oil Field Equipment,2001,30(5):1-4.
[83]张红,龚玉.磨损趋势预测的GM模型应用.机械设计与研究.2001,17(1):69-70.
[84]马智峰,李晓峰.柴油机磨损趋势预测.润滑与密封,2000,1:54-56.
[85]朱新河,严志军,刘一梅等.船舶柴油机缸套磨损量灰色预测方法研究.大连海事大学学报,2000,26(1):2-4.
[86]吴晓兵,常明,李晓雷,徐春龙等.光谱油料分析故障诊断对柴油机的应用研究.车用发动机,1999,(3):55-58.
[87] Chang Hanbao, Zhang Yusheng, Chen Lingen. Gray forecast of Diesel engine performancebased on wear. Applied Thermal Engineering. Applied Thermal Engineering,2003,(23):2285-2292.
[88] Zhang hong, Li Zhuguo, Chen Zhaoneng. Application of grey modeling method to fitting andforecasting wear trend of marine diesel engine. Tribology International,2003,(36):753-756.
[89]杨叔子,吴雅.时间序列分析的工程应用.武汉:华中理工大学出版社,1991.
[90] Box G E P, Jenkins M. Time series analysis forecasting and control. Holden-Day Inc.1976.
[91](美)约翰内特著.应用线性回归模型,张勇等译.北京:中国统计出版社,1990.
[92]邓聚龙.灰色理论及其预测.武汉:华中理工大学出版社,1987.
[93] Lapedes A, Farber. Nonlinear signal processing using neural network: Prediction and systemmodeling. Technical Report LA-UR-87-2662, Los Alamos National Laboratory. Los Alamos.NM,1987.
[94] Werbos P J. Generation of backpropagation with application to a recurrent gas market model.Neural Network,1988,(1):339-356.
[95] Varfis A, Versino C. Univariate economic time series forecasting by connectionist methods.Proceedings of the IEEE International Joint Conference on Neural Networks,1990,342-345.
[96] Bates J M, Granger C W J. Combination of forecasts. Journal of Operational ResearchQuarterly,1969(20):451-468.
[97]唐小我.组合预测误差信息矩阵研究.电子科技大学学报,1992,21(4):448~454.
[98]马永开,唐小我,杨桂元.非负权重最优组合预测方法的基本理论研究.运筹与管理,1997,6(2):1~8.
[99]陈华友,侯定丕.基于预测有效度的优性组合预测模型的研究.中国科学技术大学学报,2002,32(2):172~180.
[100]王应明.基于相关性的组合预测方法研究.预测,2002,21(2):58~62.
[101]李柱国.机械润滑与诊断.北京:化学工业出版社,2005.
[102]任国全,张培林,张英堂.装备油液智能监控原理.北京:国防工业出版社,2006.
[103]万耀青,郑长松,马彪.原子发射光谱仪作油液分析故障诊断的界限值问题.机械强度,2006,28(4):485～488.
[104]张永国,张子阳,费逸伟.航空发动机润滑油光谱分析界限值动态调整问题研究.润滑与密封,2009(6),34(6):89-93.
[105] Sabuncuoglu, Yilmaz, Oskaylar. Input DataAnalysis for Simulation Using Neural Networks. InProceedings of the Advances in Simulation’92Symposium, A.R.Kaylan and T.I. ren(eds.), pp137-150,1992.
[106] Akbay, Ruchti, Carlson. Using Neural Networks for Selecting Input Probability Distributions.Proceed-ings of ANNIE’92,1992.
[107] Aydin, zkan. D ylym Turunun Belirlenmesinde Yapay Sinir A larynyn Kullanylmasy.Proceedings of the First Turkish Symposium on Intelligent Manufacturing Systems, pp176-184,1996.
[108] Yilmaz, Sabuncuoglu. Probability Distribution Selection Using Neural Networks. Proceedingsof the European Simulation Multiconference’97,1997.
[109]朱家元,张恒喜,张喜斌.基于智能复合结构的可靠性分布模式自动识别.航空学报,2003.5,24(3):207-211.
[110]王文清.机械装备光谱油样分析故障诊断中界限值制定与知识库建立的研究与应用(硕士学位论文).北京:北京理工大学,1994.
[111] Weston, J. Gammerman, A. Stitson, M. O. Vapnick, V. Vovk, V. Watkins, C. Support VectorDensity Estimation Advances in Kernel Methods. MIT Press,1999.
[112]边肇祺,张学工等.模式识别(第二版).北京:清华大学出版社,2000.
[113] Gad Miller, David Horn. Probability Density Estimation Using Entropy Maximization. NeuralComputation,1998,10:1925-1938.
[114] Schlkopf B, Smola A. Learning with kernels: support vector machines, regularization,optimization and beyond. Cambridge, MA: MIT Press,2002.
[115] Gunnar Ratsch, Sebastian Mika Constructing BoostingAlgorithms from SVMs: AnApplication to One–Class Clasificatin. IEEE Transactions on Pattern Analysis and MachineIntelligence, September2002,9(24):111~115.
[116] S.Mukheree, V.Vapnik. Multivariate density estimation an svm approach. AIMemo1653,Vassachusetts Institute of Technology,1999.
[117] Parzen E. On the estimation of a probability density function and its mode. Ann Mathstatist,1962,33:1065-1076.
[118]吕金虎,陆君安,陈士乐.混沌时间序列分析及其应用.武汉:武汉大学出版社,2002.
[119] Giles C L, Lawre S, Tsoi A C. Nosiy Time Series Prediction Using Recurrent NeuralNetworks and Grammatical Inference. Machine Learning,2001,44(1):335-356.
[120] Tsai R S. Analsysis of Financial Time Series. John Wiley&Sons,2002.
[121]韩敏.混沌时间序列预测理论与方法.北京:中国水利水电出版社,2007.
[122] Jan G, Gooijer D, Hyndman R J.25Years of Time Series Forecasting. International Journal ofForecasting,2006,22(3):443-473.
[123]范剑青,姚琦伟.非线性时间序列—建模、预报及应用.北京:高等教育出版社,2005.
[124] Winters P R. Forecasting Sales by Exponentially Weighted Moving Averages. JournalManagement Science,1960,(6):324-342.
[125] Box G E P, Jenkins J. Time Series Analysis: Forecasting and Control. SanFrancisco,Holden-Day,1976.
[126] Granger C W J, Terasvirta T. Modeling Nonlinear Economic Relationships. New York,Oxford University Press,1993.
[127] Granger C W J, Anderson A P. An Introduction to Bilinear Time Series Models. Gottingen,Vandenhoeck and Ruprecht,1978.
[128] Bollerslev T. Generalised Autoregressive Conditional Heteroscedasticity. Journal ofEconometrics,1986,(31):307-327.
[129] Tong H, Lim K S. Threshold Autoregression Limit Cycles and Cyclical Data. Journal ofRoyal Statistical Society, Series B,1980,(42):245-292.
[130] Martin C. Nonlinear Prediction of Chaotic Time Series. Physica D: Nonlinear Phenomena,1989,35(3):335-356.
[131] E. Bonabeau, M. Dorigo, G. Theraulaz. Inspiration for optimization from social insectbehavior. Nature,2000,406(6):39-442.
[132] E. Bonabeau, M.Dorigo, G. Theraulaz. Swarm intelligence from natural to artificial systems.New York: Oxford Univ. Press,1999.
[133] J.Kennedy, R.C.Eberhart. Particle swarm optimization. Proceeding IEEE InternationalConference on Neural Networks.1995:1942-1948.
[134]杨维,李岐强.粒子群优化算法综述.中国工程科学,2004,6(5):87-92.
[135] R.C.E. Scrhart, Y. Sh. Evolving Artificial Neural Networks. Proceeding of InternationalConference on Neural Networks and Brain. Piscataway NJ IEEE Press,1998:5-13.
[136]张选平,杜玉平,秦国强,覃征.一种动态改变惯性权的自适应粒子群算法.西安交通大学学报.2005.10,39(10):1039-1042.
[137]张文善,雷英杰,冯有前. Matlab在时间序列分析中的应用.西安:西安电子科技大学出版社,2007.
[138]吴怀宇.时间序列分析与综合.武汉:武汉大学出版社,2004.
[139]董长虹. Matlab神经网络与应用.长沙:国防科技大学出版社,2007.
[140] JiaWei Han, Micheline Kamber. Data mining: concepts and techniques. San Francisco:Morgan Kaufmann Publishers,2001.
[141] Mannila H. Data Mining: Machine Learning, Statistics, and Databases. Eight InternationalConference on Scientific and Statistical Database Management, Stockholm June18-20,1996.
[142] Ziarko W.. Discovery through Rough Set Theory. Communications of the ACM, Vol.42,No.11,55-57, November1999.
[143] Agrawal R., Mannila H., Srikant R., Toivonen H., Verkamo A. I.. Fast Discovery ofAssociation Rules. Chapter12in Usama M. Fayyad, Gregory Piatetsky-Shapiro, PadhraicSmyth, and Ramasamy Uthurusamy,editors, Adcances in Knowledge Discovery and DataMining,307-328, AAAI Press,1996.
[144] Fu L.. Knowledge Discovery Based on Neural Networks. Communications of the ACM,42(11):47-50, November1999.
[145] Quinlan, J.R. Inducction of Decision Trees. Machine Learning,1:81-106,1986.
[146] H.Nunez, C. Angulo, and A. Catala,“Rule-Extraction from Support Vector Machines”. Proc.European Symp. Artificial Neural Networks, pp.107-112,2002.
[147] Fu L. Knowledge Discovery Based on Neural Networks. Communications of the ACM,42(11):47-50, November1999.
[148]张英.基于支持向量机的过程工业数据挖掘技术研究[博士学位论文].浙江:浙江大学,2005.
[149] Y. Zhang, Z. Li, Y. Tang, K. Cui. DRC-BK: Mining Classification Rules with Help of SVM.LNAI3056, H. Dai, R. Srikant, and C. Zhang, eds. pp.191-195, Springer,2004.
[150] Jack L B，Nandi A K．Feature selection for ANNs using genetic algorithms in conditionmonitoring. ESANN'1999Proceedings-European Symposium on Artificial Neural Networks,Bruges(Belgium),1999:313～318.
[151] Weiss G.M. Mining with rarity: A unifying framework. SIGKDD Explorations,2004,6(1):7-19.
[152] Chawla N., Bowyer K., Hall L., et al. Smote: Synthetic Minority Over-Sampling Technique.Artificial Intelligence and Reseach,2002,16:321-357.
[153] Michael Egmont-Petersen, Jan L Talmon. Assessing the Importance of Feature for Multi-layerPerceptrons. Neural Network,1998,11(4):623~635.
[154]高仁祥,张世英,刘豹.基于神经网络的变量选择方法.系统工程学报,1998,13(2):32~37.
[155]肖建华.智能模式识别方法.广州:华南理工大学出版社,2006.
[156] Law M H C, et al. Simultaneous Feature Selection and Clustering Using Mixture Model.IEEE Transaction on Pattern Analysis and Machine Intelligence,2004,26(9):1154~1166.
[157]张莉,孙钢,郭军.基于K-均值聚类的无监督的特征选择方法.计算机应用研究,2005,3:23~24.
[158] Ludmila Ilieva Kuncheva. Fuzzy Rough Sets Application to feature selection. Fuzzy Sets andSystems,1992,51(2):147~153.
[159] L. B. Jack, A. K. Nandi. Feature Selection for ANNs using Genetic Algorithms in ConditionMonitoring. ESANN’1999proceedings-European Symposium on Artificial Neural Networks,Bruges(Belgium),1999:313~318.
[160]史东锋,屈梁生.遗传算法在故障特征选择中的应用研究.振动、测试与诊断,2000,20(3):171~176.
[161]王新峰,邱静,刘冠军.基于特征相关性和冗余性分析的机械故障特征选择研究.中国机械工程,2006,17(4):379~382.
[162]章新华.一种特征选择的动态规划方法.自动化学报,1998,24(5):675~680.
[163] Ben-Hur A. Hom D, Sidgelman H.T. Support vector clustering. Journal of machine learningresearch,125-137,2001.
[164]屈俊峰.决策树的节点属性选择和修剪方法研究[硕士学位论文].中国地质大学,2006.
[165]赵蕊.基于Weka平台的决策树算法设计与实现[硕士学位论文].中南大学,2007.
[166]孟晓明,陈慧萍,张涛.基于Weka平台的web事物聚类算法的研究.计算机工程与设计,2009,30(6):1332-1338.
[167]付友. Weka软件分析解析[硕士学位论文.北京交通大学,2006.
[168]贺石中.液压设备的润滑磨损故障及监测诊断.液压气动与密封,2004,(5):23-24.
[169]夏志新,张虎.液压系统污染控制技术现状及发展.液压气动与密封,2000,(1):32-39.
[170]樊庆和,韩维.铁谱分析技术在飞机液压系统故障分析中的应用.液压与气动,2007,(5):59-61.
[171]樊庆和,贾忠湖. FAS-2C光谱仪在飞机液压系统故障分析中的应用.液压与气动,2002,(9):23-6.
[172]张强.飞机液压系统磨损综合监控专家系统研究[硕士学位论文].南京:南京航空航天大学,2008.
[173] Wooldridge M J, Jennings N R. Intelligent Agents: Theory and Practice. KnowledgeEngineering Review,1995,10(2):115–52.
[174] Liu Jiming.多智能体原理与技术.北京:清华大学出版社,2003.
[175] Boloni L, Marinescu D C. Agent Surgery: The Case for Mutable Agents. Proc. of theHeterogeneous Computing Workshop,1999.
[176]肖小锋,蔡金燕,马飒飒.基于多Agent的智能监测与诊断技术.计算机工程,2005,31(16):165-167.
[177] M. Minsky. Socity of Mind. Simon&Schuster,1986.
[178] Michael Woodrige, Nicholas Jennings. Formalizing the cooperative problem solvingprocesss.Reading in Agents.430-440.
[179] Kai G. Architecture and Design of a Diagnostic Information Fusion System. ArtificialIntelligence for Engineering Design, Analysis and Manufacturing,2001,15:335～338.
[180]陈果.一种磨损故障融合诊断新方法及其应用.机械科学与技术,2009,(9):1157-1161.
[2]邝朴生.现代机器故障诊断学.北京:农业出版社,1991.
[3]钟秉林,黄仁.机械故障诊断学.北京:机械工业出版社,1997.
[4]丁玉兰,石来德.机械设备故障诊断技术.上海:上海科学技术文献出版社,1994.
[5]范作民.航空发动机状态诊断.天津:天津科技翻译出版公司,1990.
[6]陈长征,白秉三.设备故障诊断技术研究进展.洛阳工业大学学报，2000,4(22):349~352
[7]陈克兴,李川奇.设备状态监视与故障诊断技术.北京:科技文献出版社,1991.
[8]屈梁生,张海军.机械诊断中的几个基本问题.中国机械工程,2000, l(1l):211~216.
[9]李炜,伦椒娴.设备故障诊断技术的现状及其发展.甘肃工业大学学报,1998,2(24):66~69.
[10]虞和济,傅润兰.故障诊断的数学力学基础.北京:冶金工业出版社,1991.
[11]吴今培.智能故障诊断技术的发展与展望.振动、测试与诊断,1999,2(19):79~86.
[12]左洪福.发动机磨损状态监测与故障诊断技术.北京:航空工业出版社,1995.
[13]陈果.航空器检测与诊断技术导论.北京:中国民航出版社,2007.
[14]陈果,李爱.航空器检测与诊断技术导论.北京:航空工业出版社,2012.
[15]吴振峰.基于磨粒分析和信息融合的发动机磨损故障诊断技术研究[博士学位论文].南京:南京航空航天大学,2001.
[16] Doel, David L. Assessment of weighted-Least-Squares Based Gas Path Analysis. Journal ofEngineering for Gas Turbines and Power,2009,116(2):366-373.
[17] Doel David L. Temper-A Gas Path Analysis Tool for Commercial Jet Engines. Transactions ofthe ASME Journal of Engineering for Gas Turbines and Power,1994,116(1):82-89.
[18]范作民,孙春林,林兆福.发动机故障方程的建立与故障因子的引入.中国民航学院学报,1994,12(1):1-14.
[19]陈大光.多状态气路分析法诊断发动机故障的分析.航空动力学报,1994,9(4):339-343.
[20]严寒松.航空发动机故障诊断[博士学位论文].南京:南京航空航天大学,1996.
[21]钱建阳.航空发动机气路智能故障诊断[博士学位论文].南京:南京航空航天大学,2000.
[22]杨建国,孙扬,郑严.基于小波和模糊神经网络的涡喷发动机故障诊断.推进技术,2001,22(2):114-117.
[23]左洪福.发动机磨损状态监测与故障诊断技术.北京:航空工业出版社,1995:63~149.
[24] Chen Guo.3D Measurement and Stereo Reconstruction for Aeroengine Interior Damage.Chinese Journal of Aeronautics.2004,17(3):149-151.
[25]杨叔子,史铁林.基于知识的诊断推理.北京:清华大学出版社,1993.
[26]高济.基于知识的软件智能化技术.浙江:浙江大学出版社,2002.
[27] Sorsa T, Koivo H N, Koivisto H. Neural networks in process fault diagnosis. IEEE Transactionson Systems, Man, and Cybernetics,1991,21(4):815~824.
[28] Bernieri A, A puzzo M D, Sansone L, et al. A neural network approach for identification andfault diagnosis on dynamic systems. IEEE Transactions on Instrumentation and Measurement,1994,43(6):867~873.
[29] Tang T H, Lin X, Li J R, et al. A new fuzzy neural network approach for intelligent monitoringsystem. Proceedings of IFAC Transportation Systems Conference,1997:691-696.
[30] Varma A, Roddy N. ICARUS: design and deployment of a case-based reasoning system forlocomotive diagnostics. Engineering Applications of Artificial Intelligence,1999,12(6):681-690.
[31] Palshikar G K, Khemani D. Diagnosing dynamic systems using trace patterns. PatternRecognition Letters,1999,20(7):741-753.
[32] Kassidas A, Taylor P A, MacGregor J F. Off line diagnosis of deterministic faults in continuousdynamic multivariable processes using speech recognition methods. Journal of Process Control,1998,8(5-6):381~393.
[33] Foret M P, G lasgow J I. Combining casebased and model based reasoning for the diagnosis ofcomplex devices. Applied Intelligence,1997,7(1):57-78.
[34]丘雪棠.润滑油液在线颗粒传感器试验研究[硕士学位论文].广州:华南理工大学,2011.
[35] Muir D M, Howe B. In-line oil debris monitor (ODM) for the advanced tactical fighter engine.SAE Paper961308, May1996.
[36] Hughes I, Muir D. On-line oil debris monitor for aircraft for engines. JOAP Conference,November,1994.
[37] Higgins P D, Crow J T. Advances in commercial engine lube debris monitoring. SAE Technical1997,1-4:972603.
[38] Byington C S, Schalcosky D C. Advances in real time oil Analysis. Practicing Oil AnalysisMagazine,2000,11(2):28-34.
[39] Powrie H E G, Fisher C E. Engine-health monitoring: towards total prognostics. IEEEAeropsace Conference Proceedings, March,1999,3(6-13):11-20.
[40] Powrie H E G. Use of electrostatic technology for aero engine oil system monitoring.Proceedings of IEEE Aerospace Conference,2000:57-71.
[41] Powrie H E G, Wood R J K, Harvey T J, et al. Electrostatic charge generation associated withmachinery component deterioration. Proceedings of IEEE Aerospace Conference, Big Sky,Montana, March2002,6:2927-2934.
[42]李应红,尉询楷,刘建勋.支持向量机的工程应用.北京:民兵工业出版社,2004.
[43]李应红,付全俊.航空发动机试车故障诊断专家系统.航空学会动力控制学术交流会,1989.9.
[44]贾智伟,李应红,雷晓犇.基于模糊综合函数的故障诊断[J].系统工程与电子技术,2004,26(3):416-417.
[45]尉询楷,李应红等.基于支持向量机的航空发动机辨识模型.航空动力学报,2004.10,19(5):684-688.
[46]尉询楷,李应红等.基于支持向量机的航空发动机滑油监控分析.航空动力学报,2004.6,19(3):392-397.
[47]尉询楷,陆波等.支持向量机在航空发动机故障诊断中的应用.航空动力学报,2004.12,19(6):844-848.
[48]石荣德,赵廷弟等.故障诊断专家系统.北京航空航天大学学报,1995.10,21(4):7-12.
[49]左洪福,吴振峰等. DMAS智能化铁谱分析系统及其应用.江苏航空,1999(3-4):60-64.
[50]陈果,左洪福.基于知识规则的发动机磨损故障诊断专家系统.航空动力学报,2004,19(1):23-29.
[51]陈果,左洪福.基于神经网络的多种油样分析技术融合诊断.摩擦学学报,2003,23(5):431-434.
[52]陈果.基于神经网络和D-S证据理论的发动机磨损故障融合诊断.航空动力学报,2005,20(2):303-308.
[53]陈果.用结构自适应神经网络预测航空发动机性能趋势.航空学报,2007,28(3):535-539.
[54]周志华,何佳洲,尹旭日等.一种基于统计的神经网络规则抽取方法.软件学报,2001,12(2):263-269.
[55]陈果,宋兰琪,陈立波,张占纲.基于粗糙集理论的航空发动机滑油光谱诊断专家系统知识获取方法研究.机械科学与技术,2007,26(7):898-901.
[56] Paw lak Z. Rough set. International Journal of Information and Computer Science,1982,11(5):341-356.
[57]王国胤. Rough集理论与知识获取.西安交通大学出版社,2001.
[58]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(12),23(12):2170-2176.
[59] Saito K, Nakano R. Medical diagnostic expert system based on PDP model. Proceedings of theIEEE International Conference on Neural Networks. New York: IEEE Press,1988:255-262.
[60] Fu L M. Rule learning by searching on adapts nets. Proceedings of the9th National Conferenceon Arificial Intelligence. Anaheim, CA: AAAI Press,1991:590-595.
[61]虞和济,韩庆大,李沈等.设备故障诊断工程.北京:冶金工业出版社,2001.
[62]陈果.航空发动机磨损故障的智能融合诊断.2005,16(4):299-306.
[63] Ramesh R, Bruce C W, Matthew S. Evolution of Propulsion Controls and Health Monitoring atPratt and Whitney, AIAA-2003-2645.4.
[64] Takahisa K, A. Hybrid Neural Network Genetic Algorithm Technique for Aircraft EnginePerformance Diagnostics. NASA/TM-2001-211088.
[65]赵方,谢友柏,柏子游.油液分析多技术集成的特征与信息融合.摩擦学学报,1998,18(1):45-52.
[66]严新平,谢友柏,潇汉良.摩擦学故障诊断种类的D-S信息融合研究.摩擦学学报,1999,19(2):145-150.
[67]陈果.基于神经网络和D-S证据理论的发动机磨损故障融合诊断.航空动力学报,2005.4,20(2):303-308.
[68]陈果,左洪福,杨新.基于神经网络的多种油样分析技术融合诊断.摩擦学学报,2003.9,23(5):431-434.
[69]叶志锋.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.
[70] Chen G, Yang Y W, Zuo H F. Intelligent Fusion for Aeroengine Wear Fault Diagnosis.Transactions of Nanjing University of Aeronautics&Astronautics,2006,23(4):297-303.
[71]陈恬，孙健国，郝英.基于神经网络和证据融合理论的航空发动机气路故障诊断.航空学报,2006,27(6):1014-1017.
[72]王松,褚福磊,何永勇等.基于信息融合技术的发动机故障诊断的研究.内燃机学报,2003,21(5):374-378.
[73]夏勇,张振仁,陈卫昌等.机械设备故障诊断的复杂性理论.机械学报,2001,28(5):3-5.
[74]尉询楷,李应红等.基于支持向量机的信息融合诊断方法.系统工程与电子技术.2005.9,27(9):1665-1668.
[75]葛世荣,朱华.摩擦学复杂系统及其问题的量化研究方法.摩擦学学报,2002,22(5):405-408.
[76]干敏梁,左洪福,杨忠,江涌.时序建模方法在滑油光谱分析中的应用.光谱学与光谱分析,2000,20(1):64-67.
[77]陈志英.航空发动机滑油监视与诊断系统软件研制.推进技术,1998,19(5):52-55.
[78]任国全,张英堂,吕建刚,张培林.润滑油磨粒浓度预测模型研究.润滑与密封,1999,4:45-47.
[79]严新平,谢友柏,李晓峰,萧汉梁.一种柴油机磨损的预测模型与试验研究.摩擦学学报,1996,16(4):358-366.
[80]梁华,杨明忠,陆培德.用人工神经网络预测摩擦学系统磨损趋势.摩擦学学报,1996,16(3):267-271.
[81]吴明赞,陈森发.用灰色系统模型进行船舶柴油机磨损趋势分析.系统工程理论与实践,2001,(8):102-105.
[82]张来斌,刘守道,王朝晖.柴油机整体性能预测的灰色神经网络方法. Oil Field Equipment,2001,30(5):1-4.
[83]张红,龚玉.磨损趋势预测的GM模型应用.机械设计与研究.2001,17(1):69-70.
[84]马智峰,李晓峰.柴油机磨损趋势预测.润滑与密封,2000,1:54-56.
[85]朱新河,严志军,刘一梅等.船舶柴油机缸套磨损量灰色预测方法研究.大连海事大学学报,2000,26(1):2-4.
[86]吴晓兵,常明,李晓雷,徐春龙等.光谱油料分析故障诊断对柴油机的应用研究.车用发动机,1999,(3):55-58.
[87] Chang Hanbao, Zhang Yusheng, Chen Lingen. Gray forecast of Diesel engine performancebased on wear. Applied Thermal Engineering. Applied Thermal Engineering,2003,(23):2285-2292.
[88] Zhang hong, Li Zhuguo, Chen Zhaoneng. Application of grey modeling method to fitting andforecasting wear trend of marine diesel engine. Tribology International,2003,(36):753-756.
[89]杨叔子,吴雅.时间序列分析的工程应用.武汉:华中理工大学出版社,1991.
[90] Box G E P, Jenkins M. Time series analysis forecasting and control. Holden-Day Inc.1976.
[91](美)约翰内特著.应用线性回归模型,张勇等译.北京:中国统计出版社,1990.
[92]邓聚龙.灰色理论及其预测.武汉:华中理工大学出版社,1987.
[93] Lapedes A, Farber. Nonlinear signal processing using neural network: Prediction and systemmodeling. Technical Report LA-UR-87-2662, Los Alamos National Laboratory. Los Alamos.NM,1987.
[94] Werbos P J. Generation of backpropagation with application to a recurrent gas market model.Neural Network,1988,(1):339-356.
[95] Varfis A, Versino C. Univariate economic time series forecasting by connectionist methods.Proceedings of the IEEE International Joint Conference on Neural Networks,1990,342-345.
[96] Bates J M, Granger C W J. Combination of forecasts. Journal of Operational ResearchQuarterly,1969(20):451-468.
[97]唐小我.组合预测误差信息矩阵研究.电子科技大学学报,1992,21(4):448~454.
[98]马永开,唐小我,杨桂元.非负权重最优组合预测方法的基本理论研究.运筹与管理,1997,6(2):1~8.
[99]陈华友,侯定丕.基于预测有效度的优性组合预测模型的研究.中国科学技术大学学报,2002,32(2):172~180.
[100]王应明.基于相关性的组合预测方法研究.预测,2002,21(2):58~62.
[101]李柱国.机械润滑与诊断.北京:化学工业出版社,2005.
[102]任国全,张培林,张英堂.装备油液智能监控原理.北京:国防工业出版社,2006.
[103]万耀青,郑长松,马彪.原子发射光谱仪作油液分析故障诊断的界限值问题.机械强度,2006,28(4):485～488.
[104]张永国,张子阳,费逸伟.航空发动机润滑油光谱分析界限值动态调整问题研究.润滑与密封,2009(6),34(6):89-93.
[105] Sabuncuoglu, Yilmaz, Oskaylar. Input DataAnalysis for Simulation Using Neural Networks. InProceedings of the Advances in Simulation’92Symposium, A.R.Kaylan and T.I. ren(eds.), pp137-150,1992.
[106] Akbay, Ruchti, Carlson. Using Neural Networks for Selecting Input Probability Distributions.Proceed-ings of ANNIE’92,1992.
[107] Aydin, zkan. D ylym Turunun Belirlenmesinde Yapay Sinir A larynyn Kullanylmasy.Proceedings of the First Turkish Symposium on Intelligent Manufacturing Systems, pp176-184,1996.
[108] Yilmaz, Sabuncuoglu. Probability Distribution Selection Using Neural Networks. Proceedingsof the European Simulation Multiconference’97,1997.
[109]朱家元,张恒喜,张喜斌.基于智能复合结构的可靠性分布模式自动识别.航空学报,2003.5,24(3):207-211.
[110]王文清.机械装备光谱油样分析故障诊断中界限值制定与知识库建立的研究与应用(硕士学位论文).北京:北京理工大学,1994.
[111] Weston, J. Gammerman, A. Stitson, M. O. Vapnick, V. Vovk, V. Watkins, C. Support VectorDensity Estimation Advances in Kernel Methods. MIT Press,1999.
[112]边肇祺,张学工等.模式识别(第二版).北京:清华大学出版社,2000.
[113] Gad Miller, David Horn. Probability Density Estimation Using Entropy Maximization. NeuralComputation,1998,10:1925-1938.
[114] Schlkopf B, Smola A. Learning with kernels: support vector machines, regularization,optimization and beyond. Cambridge, MA: MIT Press,2002.
[115] Gunnar Ratsch, Sebastian Mika Constructing BoostingAlgorithms from SVMs: AnApplication to One–Class Clasificatin. IEEE Transactions on Pattern Analysis and MachineIntelligence, September2002,9(24):111~115.
[116] S.Mukheree, V.Vapnik. Multivariate density estimation an svm approach. AIMemo1653,Vassachusetts Institute of Technology,1999.
[117] Parzen E. On the estimation of a probability density function and its mode. Ann Mathstatist,1962,33:1065-1076.
[118]吕金虎,陆君安,陈士乐.混沌时间序列分析及其应用.武汉:武汉大学出版社,2002.
[119] Giles C L, Lawre S, Tsoi A C. Nosiy Time Series Prediction Using Recurrent NeuralNetworks and Grammatical Inference. Machine Learning,2001,44(1):335-356.
[120] Tsai R S. Analsysis of Financial Time Series. John Wiley&Sons,2002.
[121]韩敏.混沌时间序列预测理论与方法.北京:中国水利水电出版社,2007.
[122] Jan G, Gooijer D, Hyndman R J.25Years of Time Series Forecasting. International Journal ofForecasting,2006,22(3):443-473.
[123]范剑青,姚琦伟.非线性时间序列—建模、预报及应用.北京:高等教育出版社,2005.
[124] Winters P R. Forecasting Sales by Exponentially Weighted Moving Averages. JournalManagement Science,1960,(6):324-342.
[125] Box G E P, Jenkins J. Time Series Analysis: Forecasting and Control. SanFrancisco,Holden-Day,1976.
[126] Granger C W J, Terasvirta T. Modeling Nonlinear Economic Relationships. New York,Oxford University Press,1993.
[127] Granger C W J, Anderson A P. An Introduction to Bilinear Time Series Models. Gottingen,Vandenhoeck and Ruprecht,1978.
[128] Bollerslev T. Generalised Autoregressive Conditional Heteroscedasticity. Journal ofEconometrics,1986,(31):307-327.
[129] Tong H, Lim K S. Threshold Autoregression Limit Cycles and Cyclical Data. Journal ofRoyal Statistical Society, Series B,1980,(42):245-292.
[130] Martin C. Nonlinear Prediction of Chaotic Time Series. Physica D: Nonlinear Phenomena,1989,35(3):335-356.
[131] E. Bonabeau, M. Dorigo, G. Theraulaz. Inspiration for optimization from social insectbehavior. Nature,2000,406(6):39-442.
[132] E. Bonabeau, M.Dorigo, G. Theraulaz. Swarm intelligence from natural to artificial systems.New York: Oxford Univ. Press,1999.
[133] J.Kennedy, R.C.Eberhart. Particle swarm optimization. Proceeding IEEE InternationalConference on Neural Networks.1995:1942-1948.
[134]杨维,李岐强.粒子群优化算法综述.中国工程科学,2004,6(5):87-92.
[135] R.C.E. Scrhart, Y. Sh. Evolving Artificial Neural Networks. Proceeding of InternationalConference on Neural Networks and Brain. Piscataway NJ IEEE Press,1998:5-13.
[136]张选平,杜玉平,秦国强,覃征.一种动态改变惯性权的自适应粒子群算法.西安交通大学学报.2005.10,39(10):1039-1042.
[137]张文善,雷英杰,冯有前. Matlab在时间序列分析中的应用.西安:西安电子科技大学出版社,2007.
[138]吴怀宇.时间序列分析与综合.武汉:武汉大学出版社,2004.
[139]董长虹. Matlab神经网络与应用.长沙:国防科技大学出版社,2007.
[140] JiaWei Han, Micheline Kamber. Data mining: concepts and techniques. San Francisco:Morgan Kaufmann Publishers,2001.
[141] Mannila H. Data Mining: Machine Learning, Statistics, and Databases. Eight InternationalConference on Scientific and Statistical Database Management, Stockholm June18-20,1996.
[142] Ziarko W.. Discovery through Rough Set Theory. Communications of the ACM, Vol.42,No.11,55-57, November1999.
[143] Agrawal R., Mannila H., Srikant R., Toivonen H., Verkamo A. I.. Fast Discovery ofAssociation Rules. Chapter12in Usama M. Fayyad, Gregory Piatetsky-Shapiro, PadhraicSmyth, and Ramasamy Uthurusamy,editors, Adcances in Knowledge Discovery and DataMining,307-328, AAAI Press,1996.
[144] Fu L.. Knowledge Discovery Based on Neural Networks. Communications of the ACM,42(11):47-50, November1999.
[145] Quinlan, J.R. Inducction of Decision Trees. Machine Learning,1:81-106,1986.
[146] H.Nunez, C. Angulo, and A. Catala,“Rule-Extraction from Support Vector Machines”. Proc.European Symp. Artificial Neural Networks, pp.107-112,2002.
[147] Fu L. Knowledge Discovery Based on Neural Networks. Communications of the ACM,42(11):47-50, November1999.
[148]张英.基于支持向量机的过程工业数据挖掘技术研究[博士学位论文].浙江:浙江大学,2005.
[149] Y. Zhang, Z. Li, Y. Tang, K. Cui. DRC-BK: Mining Classification Rules with Help of SVM.LNAI3056, H. Dai, R. Srikant, and C. Zhang, eds. pp.191-195, Springer,2004.
[150] Jack L B，Nandi A K．Feature selection for ANNs using genetic algorithms in conditionmonitoring. ESANN'1999Proceedings-European Symposium on Artificial Neural Networks,Bruges(Belgium),1999:313～318.
[151] Weiss G.M. Mining with rarity: A unifying framework. SIGKDD Explorations,2004,6(1):7-19.
[152] Chawla N., Bowyer K., Hall L., et al. Smote: Synthetic Minority Over-Sampling Technique.Artificial Intelligence and Reseach,2002,16:321-357.
[153] Michael Egmont-Petersen, Jan L Talmon. Assessing the Importance of Feature for Multi-layerPerceptrons. Neural Network,1998,11(4):623~635.
[154]高仁祥,张世英,刘豹.基于神经网络的变量选择方法.系统工程学报,1998,13(2):32~37.
[155]肖建华.智能模式识别方法.广州:华南理工大学出版社,2006.
[156] Law M H C, et al. Simultaneous Feature Selection and Clustering Using Mixture Model.IEEE Transaction on Pattern Analysis and Machine Intelligence,2004,26(9):1154~1166.
[157]张莉,孙钢,郭军.基于K-均值聚类的无监督的特征选择方法.计算机应用研究,2005,3:23~24.
[158] Ludmila Ilieva Kuncheva. Fuzzy Rough Sets Application to feature selection. Fuzzy Sets andSystems,1992,51(2):147~153.
[159] L. B. Jack, A. K. Nandi. Feature Selection for ANNs using Genetic Algorithms in ConditionMonitoring. ESANN’1999proceedings-European Symposium on Artificial Neural Networks,Bruges(Belgium),1999:313~318.
[160]史东锋,屈梁生.遗传算法在故障特征选择中的应用研究.振动、测试与诊断,2000,20(3):171~176.
[161]王新峰,邱静,刘冠军.基于特征相关性和冗余性分析的机械故障特征选择研究.中国机械工程,2006,17(4):379~382.
[162]章新华.一种特征选择的动态规划方法.自动化学报,1998,24(5):675~680.
[163] Ben-Hur A. Hom D, Sidgelman H.T. Support vector clustering. Journal of machine learningresearch,125-137,2001.
[164]屈俊峰.决策树的节点属性选择和修剪方法研究[硕士学位论文].中国地质大学,2006.
[165]赵蕊.基于Weka平台的决策树算法设计与实现[硕士学位论文].中南大学,2007.
[166]孟晓明,陈慧萍,张涛.基于Weka平台的web事物聚类算法的研究.计算机工程与设计,2009,30(6):1332-1338.
[167]付友. Weka软件分析解析[硕士学位论文.北京交通大学,2006.
[168]贺石中.液压设备的润滑磨损故障及监测诊断.液压气动与密封,2004,(5):23-24.
[169]夏志新,张虎.液压系统污染控制技术现状及发展.液压气动与密封,2000,(1):32-39.
[170]樊庆和,韩维.铁谱分析技术在飞机液压系统故障分析中的应用.液压与气动,2007,(5):59-61.
[171]樊庆和,贾忠湖. FAS-2C光谱仪在飞机液压系统故障分析中的应用.液压与气动,2002,(9):23-6.
[172]张强.飞机液压系统磨损综合监控专家系统研究[硕士学位论文].南京:南京航空航天大学,2008.
[173] Wooldridge M J, Jennings N R. Intelligent Agents: Theory and Practice. KnowledgeEngineering Review,1995,10(2):115–52.
[174] Liu Jiming.多智能体原理与技术.北京:清华大学出版社,2003.
[175] Boloni L, Marinescu D C. Agent Surgery: The Case for Mutable Agents. Proc. of theHeterogeneous Computing Workshop,1999.
[176]肖小锋,蔡金燕,马飒飒.基于多Agent的智能监测与诊断技术.计算机工程,2005,31(16):165-167.
[177] M. Minsky. Socity of Mind. Simon&Schuster,1986.
[178] Michael Woodrige, Nicholas Jennings. Formalizing the cooperative problem solvingprocesss.Reading in Agents.430-440.
[179] Kai G. Architecture and Design of a Diagnostic Information Fusion System. ArtificialIntelligence for Engineering Design, Analysis and Manufacturing,2001,15:335～338.
[180]陈果.一种磨损故障融合诊断新方法及其应用.机械科学与技术,2009,(9):1157-1161.