飞机液压系统磨损综合监控专家系统研究
|
摘要
飞机液压系统是飞机的重要组成部分,主要是给飞机操纵系统、起落架系统和反推装置等提供操纵动力。飞机液压系统故障将影响飞机的正常运行,严重时将导致灾难性的飞行事故。因此,及时地对飞机液压系统的状态进行综合监测,对于正确作出维修决策,防范事故于未然,适时进行液压系统的修理和维护具有重要意义。但是由于油样分析方法有信息种类多、信息的表征各异、信息的离散性和随机性、定量和定性信息交叉、信息的冗余性、不确定性、不一致性和不完整性等特点,难于通过单一方法确定液压系统的故障。鉴于此,本文进行了飞机液压系统综合监测专家系统研究。
(1)阐述了飞机典型的液压系统,包括能源子系统、襟翼收放系统、减速板、货舱门及弹性门等的工作原理;介绍了油样颗粒计数分析、铁谱分析、光谱分析和理化性能分析等主要的油样分析方法以及在液压系统污染监控中的应用;
(2)提出液压系统综合监测的案例推理方法。专家系统首先通过在各子案例库中搜索得到各子相似度,然后再综合各子相似度,通过计算得到总相似度,最后按总相似度对相关案例进行排序,便于维修人员进行决策。
(3)提出了一种飞机液压系统状态监控的多智体协同诊断方法,该方法能够综合运用各油样分析方法的冗余性和互补性,实现多油样分析方法的综合诊断,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。专家系统由污染分析Agent、理化分析Agent、铁谱分析Agent、光谱分析Agent及综合诊断Agent构成,综合诊断Agent负责控制和管理其他Agent进行协同诊断。本文根据飞机液压系统诊断的实际情况,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,表明了多智体协同诊断的有效性。
(4)由于严重磨损趋势具有随时间递增的特点,因此利用灰色系统理论能够对磨损的发展趋势进行准确预测。本文利用GM(1,1)模型对飞机液压系统磨损趋势进行了预测分析,并列举算例进行了验证分析。
(5)利用Microsoft Visual C++6.0语言和Microsoft Access 2000数据库开发了飞机液压系统综合监控专家系统AHMES(Aircraft Hydraulic System Monitoring Expert System)。构建了系统的整体架构,实现了多智体协同诊断、案例综合诊断以及灰色预测等功能,并进行了验证和分析,表明了专家系统的诊断有效性。
Aircraft hydraulic system is the important composing part, and it mainly offers controlling power for airplane control system, landing gear system and thrust reverser etc. The faults of the aircraft hydraulic system will affect the normal operation of the aircraft, and it even lead to the disastrous aviation accidents. Therefore, it is very important to integratedly monitor the operation condition of the aircraft hydraulic system in time, give maintaining decision-making so as to prevent future faults and timely repair and maintain the hydraulic system. But because the oil sample analysis methods have the characteristics, such as indeterminacy, inconsistency, randomicity and redundancy, it is difficult to determine the faults of aircraft hydraulic system by using single method. So, in this paper, an aircraft hydraulic system integrated monitoring expert system is studied.
(1)The working principles of the typical aircraft hydraulic systems which include energy sources subsystem, flag control system, drag plate, cargo cabin door and elastic door etc are expounded; Further, the main oil sample analysis methods of Particle Counting Analysis, Ferrograph Analysis, Spectrometric Analysis and physicochemical Analysis etc and their application in hydraulic system contamination monitoring are introduced.
(2)A case-based reasoning method of hydraulic system is developed. Firstly, the expert system searches and obtains the sub- comparability in every sub-case database; afterward, it integrates all sub- comparabilities to compute and obtain the total comparability; finally, according to the total comparability obtained, it sorts the correlative cases so that the maintaining personnel make decision-making easily.
(3)A Multi-agent collaborative diagnosis method for monitoring the conditions of aircraft hydraulic system is put forward. This method can synthetically use the redundancy and complementary of every oil sample analysis methods, achieve integrated diagnosis of many oil sample analysis methods and effectively use the characteristics and advantages of every oil sample analysis methods to improve diagnosis precision. The expert system is composed of contamination analysis agent, physicochemical analysis agent, ferrograph analysis agent, spectrometric analysis agent and integrated diagnostic agen which is charge of controlling and managing other agents for collaborative diagnosis. In this paper, according to the actual situation of aircraft hydraulic system diagnosis, every agent diagnosis rules are given, and the test results of specific data of the oil samples show the effectiveness of the multi-agent collaborative diagnosis.
(4)Because the trend of wear increases with time lapsing, the grey system theories can accurately forecast the growing trend of the wear. This paper uses the model of GM(1,1) to forecast and analyze the wear trend of aircraft hydraulic system, and enumerates computing examples to validate the analysis results.
(5)In this paper, an Aircraft Hydraulic System Integrated Monitoring Expert System is developed by using the development tools of Microsoft Visual C++6.0 language and Microsoft ACCESS 2000database. The whole structure of the system is constructed, and the functions of multi-agent collaborative diagnosis, case integrated diagnosis and grey forecasting etc are realized. Finally, the validation and analysis are carried out and the results show the validity of the diagnosis of the expert system.
(1)阐述了飞机典型的液压系统,包括能源子系统、襟翼收放系统、减速板、货舱门及弹性门等的工作原理;介绍了油样颗粒计数分析、铁谱分析、光谱分析和理化性能分析等主要的油样分析方法以及在液压系统污染监控中的应用;
(2)提出液压系统综合监测的案例推理方法。专家系统首先通过在各子案例库中搜索得到各子相似度,然后再综合各子相似度,通过计算得到总相似度,最后按总相似度对相关案例进行排序,便于维修人员进行决策。
(3)提出了一种飞机液压系统状态监控的多智体协同诊断方法,该方法能够综合运用各油样分析方法的冗余性和互补性,实现多油样分析方法的综合诊断,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。专家系统由污染分析Agent、理化分析Agent、铁谱分析Agent、光谱分析Agent及综合诊断Agent构成,综合诊断Agent负责控制和管理其他Agent进行协同诊断。本文根据飞机液压系统诊断的实际情况,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,表明了多智体协同诊断的有效性。
(4)由于严重磨损趋势具有随时间递增的特点,因此利用灰色系统理论能够对磨损的发展趋势进行准确预测。本文利用GM(1,1)模型对飞机液压系统磨损趋势进行了预测分析,并列举算例进行了验证分析。
(5)利用Microsoft Visual C++6.0语言和Microsoft Access 2000数据库开发了飞机液压系统综合监控专家系统AHMES(Aircraft Hydraulic System Monitoring Expert System)。构建了系统的整体架构,实现了多智体协同诊断、案例综合诊断以及灰色预测等功能,并进行了验证和分析,表明了专家系统的诊断有效性。
Aircraft hydraulic system is the important composing part, and it mainly offers controlling power for airplane control system, landing gear system and thrust reverser etc. The faults of the aircraft hydraulic system will affect the normal operation of the aircraft, and it even lead to the disastrous aviation accidents. Therefore, it is very important to integratedly monitor the operation condition of the aircraft hydraulic system in time, give maintaining decision-making so as to prevent future faults and timely repair and maintain the hydraulic system. But because the oil sample analysis methods have the characteristics, such as indeterminacy, inconsistency, randomicity and redundancy, it is difficult to determine the faults of aircraft hydraulic system by using single method. So, in this paper, an aircraft hydraulic system integrated monitoring expert system is studied.
(1)The working principles of the typical aircraft hydraulic systems which include energy sources subsystem, flag control system, drag plate, cargo cabin door and elastic door etc are expounded; Further, the main oil sample analysis methods of Particle Counting Analysis, Ferrograph Analysis, Spectrometric Analysis and physicochemical Analysis etc and their application in hydraulic system contamination monitoring are introduced.
(2)A case-based reasoning method of hydraulic system is developed. Firstly, the expert system searches and obtains the sub- comparability in every sub-case database; afterward, it integrates all sub- comparabilities to compute and obtain the total comparability; finally, according to the total comparability obtained, it sorts the correlative cases so that the maintaining personnel make decision-making easily.
(3)A Multi-agent collaborative diagnosis method for monitoring the conditions of aircraft hydraulic system is put forward. This method can synthetically use the redundancy and complementary of every oil sample analysis methods, achieve integrated diagnosis of many oil sample analysis methods and effectively use the characteristics and advantages of every oil sample analysis methods to improve diagnosis precision. The expert system is composed of contamination analysis agent, physicochemical analysis agent, ferrograph analysis agent, spectrometric analysis agent and integrated diagnostic agen which is charge of controlling and managing other agents for collaborative diagnosis. In this paper, according to the actual situation of aircraft hydraulic system diagnosis, every agent diagnosis rules are given, and the test results of specific data of the oil samples show the effectiveness of the multi-agent collaborative diagnosis.
(4)Because the trend of wear increases with time lapsing, the grey system theories can accurately forecast the growing trend of the wear. This paper uses the model of GM(1,1) to forecast and analyze the wear trend of aircraft hydraulic system, and enumerates computing examples to validate the analysis results.
(5)In this paper, an Aircraft Hydraulic System Integrated Monitoring Expert System is developed by using the development tools of Microsoft Visual C++6.0 language and Microsoft ACCESS 2000database. The whole structure of the system is constructed, and the functions of multi-agent collaborative diagnosis, case integrated diagnosis and grey forecasting etc are realized. Finally, the validation and analysis are carried out and the results show the validity of the diagnosis of the expert system.
引文
[1]贾瑞清,王炉平.液压污染控制技术的研究现状及重点展望[J].液压气动与密封, 2004, (1): 15-17.
[2]窦培明,潘玉田,胡双启.液压系统常见故障分析及处理方法探讨[J].机械管理开发, 2006, (1):79–80.
[3]党育哲.基于油液检测的污染磨损故障诊断[J].液压与气动, 2005, (12): 70-72.
[4]贺石中.液压设备的润滑磨损故障及监测诊断[J].液压气动与密封, 2004 (5): 23–24.
[5]夏志新,张虎.液压系统污染控制技术现状及发展[J].液压气动与密封, 2000, (1): 32–39.
[6]李雅武,乜庆海,杨沛.液压系统常见的故障诊断及处理[J].汽轮机技术, 2005, 47(1): 73–75.
[7]陈新响,李文华,李振中,魏德宝,王国有,周学军.液压系统主要故障分析及对策[J].液压气动与密封, 2007, (2): 6–7.
[8]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[J].液压与气动, 2002(9): 23–26.
[9]陈林强.液压系统常见故障的成因及其预防与排除[J].液压与气动, 2003, (7): 52-53.
[10]任国全,张培林,房立青,韩守红.基于油液光谱分析的发动机故障诊断专家系统研究[J].润滑与密封, 2001, (6): 57–59.
[11]宋兰琪,毛美娟,陈立波.航空发动机滑油光谱故障诊断专家系统[J].航空发动机, 1999, (1): 45–49.
[12]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[J].机械强度, 2006, 28(4): 485– 488.
[13]赵春华,严新平.油液监测智能化的关键技术探讨[J].润滑与密封, 2004, (4): 48-52.
[14]《飞机设计手册》总编委会.飞机设计手册(12)[M],北京:航空工业出版社, 2003.
[15]唐有才.飞机液压系统污染及控制[J].机床与液压, 2002, (3): 206– 208.
[16]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[J].液压与气动, 2007, (5): 59–61.
[17]刘延俊.液压系统使用与维修[M],北京:化学工业出版社, 2006. 7.
[18]黄志坚,袁周.液压设备故障诊断与监测实用技术[M],北京:机械工业出版社, 2005.10.
[19]张利平.液压控制系统与设计[M],北京:化学工业出版社, 2006.7.
[20]陈果.航空器检测与诊断技术导论[M].北京:中国民航出版社, 2007.
[21]李柱国.机械润滑与诊断[M],北京:化学工业出版社, 2005.05.
[22]程瑞琪,崔建军.内燃机车机油光谱数据特征分析与故障诊断[J].机械科学与技术, 2000, 19(2): 289-294.
[23]高经纬,张培林,张英堂,任国全.某型柴油机磨损特点及油液光谱分析诊断研究[J].内燃机学报, 2004, 22(6): 571-576.
[24]霍宇翔.基于光谱油料分析的磨损状态监测[博士学位论文].北京:清华大学, 1993.
[25]马璐.柴油机光谱油料分析故障诊断与专家系统的研究与实践[博士学位论文].北京:北京理工大学, 1993.
[26]高经纬,张培林,任国全,李兵.油液光谱分析比例模型的建立[J].内燃机工程, 2004, 25(6): 34–37.
[27]高经纬,张培林,任国全,李峰.油液光谱分析故障诊断专家系统知识库的设计与实现[J].润滑与密封, 2004, (3): 96–97.
[28]宋兰琪,汤道宇,陈立波,毛美娟.基于油液光谱分析的发动故障诊断专家系统研究[J].航空学报, 2000, 21(5): 453–457.
[29]李韶辉,付集新,张冶.船舶机械油液检测光谱分析的特征参数研究[J].润滑与密封, 2004, (11): 92–93.
[30]傅建平,张培林,李国章,廖振强.基于光谱信息融合的发动机磨损状态监测[J].机械工程学院学报, 2005, 17(1): 14–16.
[31]郑长松,马彪,万耀青,周凯.油品对定型产品台架寿命试验的研究与应用[J].中国机械工程, 2006, 17(9): 975–978.
[32]吴今培,肖健华.智能故障诊断与专家系统[M].北京:科学出版社, 1997.
[33]张荣梅.智能决策支持系统研究开发及应用[M].北京:冶金工业出版社, 2003.
[34]杨善林,倪志伟.机器学习与智能决策支持系统[M].北京:科学出版社, 2004.
[35] Dutta S. Integrating Case-based and Rule-based Reasoning: The possibilistic Connection In Proceedings of the Six Conference on Uncertainty in Artificial Intelligence, 1990-07.
[36] Kolodner J, Mark W. Case-based reasoning[J]. IEEE EXPERT, 1992, 7(5): 5–6.
[37] Feret M P, Glasrow J I. Hybrid cased based reasoning for diagnosis of complex Devices[A]. Proc of 11th National Conf on Artificial Intelligence[C]. Washington: AAAI Press, 1993. 168-178.
[38] Karen Ketler. Case–based reasoning: an introduction, Expert Systems with Applications, 1993, 6: 3–8.
[39] B.C. Jcng. T. P. Liaing. Fuzzy indexing and retrieval in case–based systems. Expert Systems with Applications, 1995, l1: 135–142.
[40] Diederich J, Ruhmann I, and May M. KRITON: A Knowledge– Acquisition Tool for Expert Systems, Int. J. Man– Machine Studies, 1987, 26: 29–40.
[41] Fink P K and Lusth J C. A Second Generation Expert Systems for Diagnosis and Repair of Mechanical Devices, SAE Inern. Congress and Exposition, 1986.
[42] Gupta U G. How case-based reasoning solves new problems[J]. Interfaces, 1994, 24(6): 110-119.
[43] Burkhard H D. Sinilarity and distance in case-based reasoning[J]. Foudamenta Informaticae, 2001, 47: 201–215.
[44] Waton I. Applying Case-based Reasoning: Thechniques for Enterprises System[M]. Morgan Kaufmman Publisher, California, 1997.
[45] Aamodt A, Plaza E. Case-based resoning: foundational issues, methodological variations and system approaches[J]. AI Communications, 1994, 7(1): 39–59.
[46] Watson I. Case-based reasoning is a methodology not a technology[J]. Knowledge-based systems. 1999, 12.
[47] Mantaras R L, Plaza E. Case-based reasoning: an overview[J]. AI Communications, 1997, 10: 21–29.
[48] Joseph Garratano. Expert Systems Principles and Programming[M]. China Machine Press.
[49]王遵彤,刘战强,万熠,艾兴.相似度及基于实例推理在高速切削数据库中的应用[J].机械科学与技术, 2003, 22(3): 431–.434.
[50]肖小锋,蔡金燕,马飒飒.基于多Agent的智能监测与诊断技术[J].计算机工程, 2005, 31(16): 165-167.
[51] [加]Jiming Liu.多智能体原理与技术[M].北京:清华大学出版社, 2003.
[52] Boloni L, Marinescu D C. Agent Surgery: The Case for Mutable Agents[C]//Proc. of the Heterogeneous Computing Workshop. 1999.
[53] Franklin S, Graesser A. Is It An Agent or Just A Program?: A Taxonomy for Autonomous Agents[C]. Proceedings of the 3rd International Workshop on Agent Theories, Architectures, and Languages. Springer-Verlag. 1996
[54] Bell,J. Changing attitudes. In Wooldridge, M. and Jennings, N.R., editors, Intelligent Agents: Theories, Architectures, and Languages (LNAI Volume 890), Springer-Verlag: Heidelberg, Germany, 1995: 40-55.
[55] Castelfranchi, C. Social power. In Demazeau, Y. and Muller, J.-P., editors, Decentralized AI–Proceedings of the First European Workshop on Modelling Autonomous Agents in Multi-Agent Worlds (MAAMAW-89), Elsevier Science Publishers B.V.: Amsterdam, The Netherlands, 1990: 49–62.
[56] Castelfranchi, C. Guarantees for autonomy in cognitive agent architecture. In Wooldridge, M. and Jennings, N. R., editors, Intelligent Agents: Theories, Architectures, and Languages(LNAI Volume 890), Springer-Verlag: Heidelberg, Germany, 1995: 56-70.
[57] Castelfranchi C, Miceli M, Cesta A. Dependence relations among autonomous agents. In Werner, E. and Demazeau, Y., editors, Decentralized AI 3– Proceedings of the Third European Workshop on Modelling Autonomous Agents and Multi-Agent Worlds (MAAMAW-91), Elsevier Science Publishers B. V.: Amsterdam, The Netherlands, 1992: 215-231.
[58] Connah, D. and Wavish, P. An experiment in cooperation. In Demazeau, Y. and Muller, J.–P., editors, Decentralized AI– Proceedings of the First European Workshop on Modelling Autonomous Agents in Multi-Agent World (MAAMAW-89), Elsevier Science Publishers B.V.: Amsterdam, The Netherlands, 1990: 197–214.
[59] Wooldridge M J, Jennings N R. Intelligent Agents: Theory and Practice. Knowledge Engineering Review, 1995, 10(2): 115–152.
[60]万耀青,郑长松,马彪.油液分析故障诊断中的信息融合问题[J].机械设计, 2004(9): 1–3.
[61]陈志伟,米东,徐章遂,刘斌.基于灰色理论和时间序列模型的润滑油中磨粒含量预测分析[J].润滑与密封, 2007, 32(5):147-149.
[62]杨江天,岳维亮.灰色模型在机械故障预测中的应用[J].机械强度, 2001, 23(3): 277-279.
[63]赵荣珍,孟凡明,张优云,王成栋.机械振动趋势的灰色预测模型研究[J].机械科学与技术, 2004, 23(3): 256-259.
[64]沈凌,阮锋,陈承泽.基于灰色预测的冲压机油液贴谱定量分析的研究[J].液压与气动, 2007, (8): 26-28.
[65]陈庆斌,秦树人.灰色预测法在机械测试中的应用[J].中国测试技术, 2007, 33(5): 10-13.
[66]邓聚龙.灰色系统基本方法[M].武汉:华中理工大学出版社, 1987.
[67] Chen C K, Tien T L. A new forecasting method for time continuous model of dynamic system [J]. Applied Mathematics and Computation, 1996, 80: 225– 244.
[68] Chen C K, Tien T L. Anew forecasting method for discrete dynamic system [J]. Applied Mathematics and Computation, 1997, 86: 61–84.
[69] Tseng F M, Yu H C, Tzeng G H. Applied hybrid grey model to forecast seasonal time series[J]. Technological Forecasting and Social Change, 2001, 67: 291–302.
[70] ZHANG Zhenhui, SHI Guohong., Application of grey prophecy in operation state and tendency of facilities. Journal of Southeast University, 1998, 28 (4): 83–87 (In chinese).
[71] DENG Jolong, Grey system theory, Wuhan: Huazhong Science and Technology University Press, 1990 (In chinese)
[72] Mechanical systems integrity management a new direction for SOAP. DOD JOAP naval air station. Pensacola, Floride, 1990
[73]安智平.大型数据库技术在油液状态监测方面的应用[博士学位论文].西安:西安交通大学, 2000.
[74]黄碧华,裘崇伟.柴油机磨损状态监测及故障诊断专家系统知识库建立的研究[J].摩擦学学报, 1994, 14(4): 352–359.
[75]朱道庆,董本才,杨玉梅.机械磨损的元素含量分析方法在机械故障诊断中的应用[J].润滑与密封, 2003, (6): 98–100.
[76]蔡增杰,赖威.军用飞机液压系统污染监测[J].液压与气动, 2001, (8): 6–7.
[77]唐俊杰.液压油与液压系统故障[J].液压气动与密封, 2005, (5): 25–26.
[78]周健,姚志刚.船舶装备油液分析应用专家系统[J].润滑与密封, 2002, (1): 54–55.
[79]吴青,陈定方.基于油液监测的故障诊断专家系统[J].交通与计算机, 1996, 14(2): 11–14.
[2]窦培明,潘玉田,胡双启.液压系统常见故障分析及处理方法探讨[J].机械管理开发, 2006, (1):79–80.
[3]党育哲.基于油液检测的污染磨损故障诊断[J].液压与气动, 2005, (12): 70-72.
[4]贺石中.液压设备的润滑磨损故障及监测诊断[J].液压气动与密封, 2004 (5): 23–24.
[5]夏志新,张虎.液压系统污染控制技术现状及发展[J].液压气动与密封, 2000, (1): 32–39.
[6]李雅武,乜庆海,杨沛.液压系统常见的故障诊断及处理[J].汽轮机技术, 2005, 47(1): 73–75.
[7]陈新响,李文华,李振中,魏德宝,王国有,周学军.液压系统主要故障分析及对策[J].液压气动与密封, 2007, (2): 6–7.
[8]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[J].液压与气动, 2002(9): 23–26.
[9]陈林强.液压系统常见故障的成因及其预防与排除[J].液压与气动, 2003, (7): 52-53.
[10]任国全,张培林,房立青,韩守红.基于油液光谱分析的发动机故障诊断专家系统研究[J].润滑与密封, 2001, (6): 57–59.
[11]宋兰琪,毛美娟,陈立波.航空发动机滑油光谱故障诊断专家系统[J].航空发动机, 1999, (1): 45–49.
[12]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[J].机械强度, 2006, 28(4): 485– 488.
[13]赵春华,严新平.油液监测智能化的关键技术探讨[J].润滑与密封, 2004, (4): 48-52.
[14]《飞机设计手册》总编委会.飞机设计手册(12)[M],北京:航空工业出版社, 2003.
[15]唐有才.飞机液压系统污染及控制[J].机床与液压, 2002, (3): 206– 208.
[16]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[J].液压与气动, 2007, (5): 59–61.
[17]刘延俊.液压系统使用与维修[M],北京:化学工业出版社, 2006. 7.
[18]黄志坚,袁周.液压设备故障诊断与监测实用技术[M],北京:机械工业出版社, 2005.10.
[19]张利平.液压控制系统与设计[M],北京:化学工业出版社, 2006.7.
[20]陈果.航空器检测与诊断技术导论[M].北京:中国民航出版社, 2007.
[21]李柱国.机械润滑与诊断[M],北京:化学工业出版社, 2005.05.
[22]程瑞琪,崔建军.内燃机车机油光谱数据特征分析与故障诊断[J].机械科学与技术, 2000, 19(2): 289-294.
[23]高经纬,张培林,张英堂,任国全.某型柴油机磨损特点及油液光谱分析诊断研究[J].内燃机学报, 2004, 22(6): 571-576.
[24]霍宇翔.基于光谱油料分析的磨损状态监测[博士学位论文].北京:清华大学, 1993.
[25]马璐.柴油机光谱油料分析故障诊断与专家系统的研究与实践[博士学位论文].北京:北京理工大学, 1993.
[26]高经纬,张培林,任国全,李兵.油液光谱分析比例模型的建立[J].内燃机工程, 2004, 25(6): 34–37.
[27]高经纬,张培林,任国全,李峰.油液光谱分析故障诊断专家系统知识库的设计与实现[J].润滑与密封, 2004, (3): 96–97.
[28]宋兰琪,汤道宇,陈立波,毛美娟.基于油液光谱分析的发动故障诊断专家系统研究[J].航空学报, 2000, 21(5): 453–457.
[29]李韶辉,付集新,张冶.船舶机械油液检测光谱分析的特征参数研究[J].润滑与密封, 2004, (11): 92–93.
[30]傅建平,张培林,李国章,廖振强.基于光谱信息融合的发动机磨损状态监测[J].机械工程学院学报, 2005, 17(1): 14–16.
[31]郑长松,马彪,万耀青,周凯.油品对定型产品台架寿命试验的研究与应用[J].中国机械工程, 2006, 17(9): 975–978.
[32]吴今培,肖健华.智能故障诊断与专家系统[M].北京:科学出版社, 1997.
[33]张荣梅.智能决策支持系统研究开发及应用[M].北京:冶金工业出版社, 2003.
[34]杨善林,倪志伟.机器学习与智能决策支持系统[M].北京:科学出版社, 2004.
[35] Dutta S. Integrating Case-based and Rule-based Reasoning: The possibilistic Connection In Proceedings of the Six Conference on Uncertainty in Artificial Intelligence, 1990-07.
[36] Kolodner J, Mark W. Case-based reasoning[J]. IEEE EXPERT, 1992, 7(5): 5–6.
[37] Feret M P, Glasrow J I. Hybrid cased based reasoning for diagnosis of complex Devices[A]. Proc of 11th National Conf on Artificial Intelligence[C]. Washington: AAAI Press, 1993. 168-178.
[38] Karen Ketler. Case–based reasoning: an introduction, Expert Systems with Applications, 1993, 6: 3–8.
[39] B.C. Jcng. T. P. Liaing. Fuzzy indexing and retrieval in case–based systems. Expert Systems with Applications, 1995, l1: 135–142.
[40] Diederich J, Ruhmann I, and May M. KRITON: A Knowledge– Acquisition Tool for Expert Systems, Int. J. Man– Machine Studies, 1987, 26: 29–40.
[41] Fink P K and Lusth J C. A Second Generation Expert Systems for Diagnosis and Repair of Mechanical Devices, SAE Inern. Congress and Exposition, 1986.
[42] Gupta U G. How case-based reasoning solves new problems[J]. Interfaces, 1994, 24(6): 110-119.
[43] Burkhard H D. Sinilarity and distance in case-based reasoning[J]. Foudamenta Informaticae, 2001, 47: 201–215.
[44] Waton I. Applying Case-based Reasoning: Thechniques for Enterprises System[M]. Morgan Kaufmman Publisher, California, 1997.
[45] Aamodt A, Plaza E. Case-based resoning: foundational issues, methodological variations and system approaches[J]. AI Communications, 1994, 7(1): 39–59.
[46] Watson I. Case-based reasoning is a methodology not a technology[J]. Knowledge-based systems. 1999, 12.
[47] Mantaras R L, Plaza E. Case-based reasoning: an overview[J]. AI Communications, 1997, 10: 21–29.
[48] Joseph Garratano. Expert Systems Principles and Programming[M]. China Machine Press.
[49]王遵彤,刘战强,万熠,艾兴.相似度及基于实例推理在高速切削数据库中的应用[J].机械科学与技术, 2003, 22(3): 431–.434.
[50]肖小锋,蔡金燕,马飒飒.基于多Agent的智能监测与诊断技术[J].计算机工程, 2005, 31(16): 165-167.
[51] [加]Jiming Liu.多智能体原理与技术[M].北京:清华大学出版社, 2003.
[52] Boloni L, Marinescu D C. Agent Surgery: The Case for Mutable Agents[C]//Proc. of the Heterogeneous Computing Workshop. 1999.
[53] Franklin S, Graesser A. Is It An Agent or Just A Program?: A Taxonomy for Autonomous Agents[C]. Proceedings of the 3rd International Workshop on Agent Theories, Architectures, and Languages. Springer-Verlag. 1996
[54] Bell,J. Changing attitudes. In Wooldridge, M. and Jennings, N.R., editors, Intelligent Agents: Theories, Architectures, and Languages (LNAI Volume 890), Springer-Verlag: Heidelberg, Germany, 1995: 40-55.
[55] Castelfranchi, C. Social power. In Demazeau, Y. and Muller, J.-P., editors, Decentralized AI–Proceedings of the First European Workshop on Modelling Autonomous Agents in Multi-Agent Worlds (MAAMAW-89), Elsevier Science Publishers B.V.: Amsterdam, The Netherlands, 1990: 49–62.
[56] Castelfranchi, C. Guarantees for autonomy in cognitive agent architecture. In Wooldridge, M. and Jennings, N. R., editors, Intelligent Agents: Theories, Architectures, and Languages(LNAI Volume 890), Springer-Verlag: Heidelberg, Germany, 1995: 56-70.
[57] Castelfranchi C, Miceli M, Cesta A. Dependence relations among autonomous agents. In Werner, E. and Demazeau, Y., editors, Decentralized AI 3– Proceedings of the Third European Workshop on Modelling Autonomous Agents and Multi-Agent Worlds (MAAMAW-91), Elsevier Science Publishers B. V.: Amsterdam, The Netherlands, 1992: 215-231.
[58] Connah, D. and Wavish, P. An experiment in cooperation. In Demazeau, Y. and Muller, J.–P., editors, Decentralized AI– Proceedings of the First European Workshop on Modelling Autonomous Agents in Multi-Agent World (MAAMAW-89), Elsevier Science Publishers B.V.: Amsterdam, The Netherlands, 1990: 197–214.
[59] Wooldridge M J, Jennings N R. Intelligent Agents: Theory and Practice. Knowledge Engineering Review, 1995, 10(2): 115–152.
[60]万耀青,郑长松,马彪.油液分析故障诊断中的信息融合问题[J].机械设计, 2004(9): 1–3.
[61]陈志伟,米东,徐章遂,刘斌.基于灰色理论和时间序列模型的润滑油中磨粒含量预测分析[J].润滑与密封, 2007, 32(5):147-149.
[62]杨江天,岳维亮.灰色模型在机械故障预测中的应用[J].机械强度, 2001, 23(3): 277-279.
[63]赵荣珍,孟凡明,张优云,王成栋.机械振动趋势的灰色预测模型研究[J].机械科学与技术, 2004, 23(3): 256-259.
[64]沈凌,阮锋,陈承泽.基于灰色预测的冲压机油液贴谱定量分析的研究[J].液压与气动, 2007, (8): 26-28.
[65]陈庆斌,秦树人.灰色预测法在机械测试中的应用[J].中国测试技术, 2007, 33(5): 10-13.
[66]邓聚龙.灰色系统基本方法[M].武汉:华中理工大学出版社, 1987.
[67] Chen C K, Tien T L. A new forecasting method for time continuous model of dynamic system [J]. Applied Mathematics and Computation, 1996, 80: 225– 244.
[68] Chen C K, Tien T L. Anew forecasting method for discrete dynamic system [J]. Applied Mathematics and Computation, 1997, 86: 61–84.
[69] Tseng F M, Yu H C, Tzeng G H. Applied hybrid grey model to forecast seasonal time series[J]. Technological Forecasting and Social Change, 2001, 67: 291–302.
[70] ZHANG Zhenhui, SHI Guohong., Application of grey prophecy in operation state and tendency of facilities. Journal of Southeast University, 1998, 28 (4): 83–87 (In chinese).
[71] DENG Jolong, Grey system theory, Wuhan: Huazhong Science and Technology University Press, 1990 (In chinese)
[72] Mechanical systems integrity management a new direction for SOAP. DOD JOAP naval air station. Pensacola, Floride, 1990
[73]安智平.大型数据库技术在油液状态监测方面的应用[博士学位论文].西安:西安交通大学, 2000.
[74]黄碧华,裘崇伟.柴油机磨损状态监测及故障诊断专家系统知识库建立的研究[J].摩擦学学报, 1994, 14(4): 352–359.
[75]朱道庆,董本才,杨玉梅.机械磨损的元素含量分析方法在机械故障诊断中的应用[J].润滑与密封, 2003, (6): 98–100.
[76]蔡增杰,赖威.军用飞机液压系统污染监测[J].液压与气动, 2001, (8): 6–7.
[77]唐俊杰.液压油与液压系统故障[J].液压气动与密封, 2005, (5): 25–26.
[78]周健,姚志刚.船舶装备油液分析应用专家系统[J].润滑与密封, 2002, (1): 54–55.
[79]吴青,陈定方.基于油液监测的故障诊断专家系统[J].交通与计算机, 1996, 14(2): 11–14.