无绝缘轨道电路故障诊断方法研究
|
摘要
无绝缘轨道电路是中国列车运行控制系统的基础设备,是一种典型的安全苛求系统,且是影响铁路运输效率的关键因素。然而,目前轨道电路的故障诊断技术及维护手段尚不能满足我国铁路运输事业发展的迫切需求,其中存在的一些“惯性故障”甚至成为铁路安全生产的突出薄弱环节,开展轨道电路故障诊断方法的系统研究具有重要意义。
论文以我国铁路系统广泛应用的ZPW-2000A无绝缘轨道电路为研究对象。首先,基于二端口网络理论建立了轨道电路空闲状态时的等效电路模型,并通过轨道电路模拟盘实验数据和实际监测数据验证了模型的正确性；然后,总结了空闲状态时轨道电路存在的典型故障模式,分析了故障模式与各监测参量间的相互影响关系。对被占用状态时的轨道电路做了类似的工作。特别地,本文基于电接触理论对导致分路不良发生的关键因素——轮轨接触电阻进行了建模分析,从理论层面对分路不良的发生机理进行了解释。
在上述分析基础上,论文重点研究了轨道电路空闲状态时典型故障模式的故障诊断方法。首先,提出了以空闲状态时轨道电路地面监测数据为观测量,以支持向量机和基于组合法的多分类策略为主要方法的故障诊断方法,并给出了诊断输出结果的概率化表示方法和考虑误判损失时诊断结果的修正方法。针对上述方法无法实现补偿电容故障精确定位的不足,进一步提出了以被占用状态时轨道电路车载监测数据(感应电压)为观测量,以集合经验模式分解和相空间重构理论为主要方法的补偿电容故障诊断方法。论文通过仿真数据、模拟盘实验数据以及现场实际监测数据对上述诊断算法的性能进行了验证,结果表明本文所提出的方法对轨道电路的典型故障模式具有很好的诊断效果,对外界干扰因素具有良好的免疫能力,具有实践应用价值和理论创新意义。
论文通过以下创新性工作,对轨道电路故障诊断方法体系进行了拓展与丰富：
(1)基于符号有向图、独立分量分析及线性拟合相结合的方法,给出了无绝缘轨道电路故障模式与监测参量间影响关系的特性总结,为故障诊断方法研究提供了必要的先验知识。
(2)提出了一种基于电接触理论的轮轨接触电阻建模方法,定量研究了轮轨接触电阻的变化机理以及与各影响因素间的关系。在理论层面对分路不良的发生机理进行了解释,为分路不良的预测和处理提供了研究基础。
(3)提出了一种以空闲状态时轨道电路地面监测数据为观测量,以支持向量机和基于组合法的多分类策略为关键算法的轨道电路故障诊断方法,算法扩展性能好,泛化能力强。
(4)提出了一种基于Sigmoid函数模型和扩展的Bradley-Terry模型的诊断输出结果的概率化表示方法,提高了诊断结果表达的科学性。
(5)提出了一种以被占用状态时轨道电路车载监测数据为观测量,以集合经验模式分解和相空间重构理论为关键算法的补偿电容故障诊断方法,算法能够有效诊断补偿电容的早期故障,且对外界干扰因素具有较强的免疫能力。
A jointless track circuit is the fundamental infrastructure in Chinese Train Control System, it is a typical safety critical system and is a key issue affecting the efficiency of railway transport. However, fault diagnosis and maintenance methods for track circuits cannot meet the urgent needs of the development of railway transport in China, some "inertia faults" even become prominent weaknesses in production of railway safety. It is significantly important to carry out systematic research on fault diagnosis for track circuits.
In this paper, the ZPW-2000A jointless track circuit is used as the study object which is widely used in China railway system. An equivalent circuit model of an unoccupied track circuit is established based on two-port network theory, the correctness of the model is validated using experiment data based on track circuit physical mode and real data based on Signal Centralized System, then the main fault modes are summarized and relationships between fault modes and monitoring variables are investigated. Similar work is done for a track circuit under occupied condition. In particular, the wheel-rail contact resistance which is a key factor to cause shunt disfunction of a track circuit is modeled and investigated using Electrical Contact Theory, then the mechanism of shunt disfunction is analyzed in the view of theory.
Based on these results, fault diagnosis methods for typical fault modes for the unoccupied track circuit are studied. Firstly, a fault diagnosis method which combines Support Vector Machine and Combination-based multi-class strategy is proposed, a multi-class probability estimation algorithm and an amendment algorithm considering the loss for misclassification for diagnosis results are presented. Furthermore, In order to obtain the information of the location of faulty compensation capacitor, that cannot be got from the above method, a fault diagnosis method for compensation capacitors is proposed which is based on Ensemble Empirical Mode Decomposition and Phase Space Reconstruction Theory, in which the signal from on-board monitoring system for an occupied track circuit is used as the analyzed object. Three different sources of data: simulated data based on track circuit model, experiment data based on track circuit physical model and real data from monitoring system are used to test the preference of the diagnosis methods, Experiments'results show that the fault models can be well diagnosed using the approach, and the preference is not sensitive to interference.
The innovations of the dissertation are as follows:
(1) The study investigates the relationships between fault models and monitoring variables of a jointless track circuit which combines Signed Directed Graph, Independent Component Analysis and linear fit method and so on, this work provides the necessary prior knowledge for fault diagnosis research.
(2) The study proposes a wheel-rail contact resistance model based on Electrical Contact Theory, based on the model the variation mechanism of the wheel-rail contact resistance and relationship between the resistance and influence factors are investigated quantitatively, this work provides a theoretical basis for the prediction and elimination of shunt disfunction.
(3) The study proposes a fault diagnosis method for track circuits based on Support Vector Machine and Combination-based multi-class stratagem, in which the signal from ground monitoring system for an unoccupied track circuit is used as analyzed object. The adaptability and generalization ability of this method can comply with the requirements of maintenance.
(4) The study proposes a multi-class probability estimation algorithm for diagnosis results using Sigmoid function model and generalized Bradley-Terry model, in doing so, the expression of diagnosis results is more reasonable.
(5) The study proposes a fault diagnosis method for compensation capacitors in track circuit based on Ensemble Empirical Mode Decomposition and Phase Space Reconstruction theory, in which the signal from on-board monitoring system for an occupied track circuit is used as analyzed object. This method is effective for incipient fault of a compensation capacitor, and is not sensitive to interference.
论文以我国铁路系统广泛应用的ZPW-2000A无绝缘轨道电路为研究对象。首先,基于二端口网络理论建立了轨道电路空闲状态时的等效电路模型,并通过轨道电路模拟盘实验数据和实际监测数据验证了模型的正确性；然后,总结了空闲状态时轨道电路存在的典型故障模式,分析了故障模式与各监测参量间的相互影响关系。对被占用状态时的轨道电路做了类似的工作。特别地,本文基于电接触理论对导致分路不良发生的关键因素——轮轨接触电阻进行了建模分析,从理论层面对分路不良的发生机理进行了解释。
在上述分析基础上,论文重点研究了轨道电路空闲状态时典型故障模式的故障诊断方法。首先,提出了以空闲状态时轨道电路地面监测数据为观测量,以支持向量机和基于组合法的多分类策略为主要方法的故障诊断方法,并给出了诊断输出结果的概率化表示方法和考虑误判损失时诊断结果的修正方法。针对上述方法无法实现补偿电容故障精确定位的不足,进一步提出了以被占用状态时轨道电路车载监测数据(感应电压)为观测量,以集合经验模式分解和相空间重构理论为主要方法的补偿电容故障诊断方法。论文通过仿真数据、模拟盘实验数据以及现场实际监测数据对上述诊断算法的性能进行了验证,结果表明本文所提出的方法对轨道电路的典型故障模式具有很好的诊断效果,对外界干扰因素具有良好的免疫能力,具有实践应用价值和理论创新意义。
论文通过以下创新性工作,对轨道电路故障诊断方法体系进行了拓展与丰富：
(1)基于符号有向图、独立分量分析及线性拟合相结合的方法,给出了无绝缘轨道电路故障模式与监测参量间影响关系的特性总结,为故障诊断方法研究提供了必要的先验知识。
(2)提出了一种基于电接触理论的轮轨接触电阻建模方法,定量研究了轮轨接触电阻的变化机理以及与各影响因素间的关系。在理论层面对分路不良的发生机理进行了解释,为分路不良的预测和处理提供了研究基础。
(3)提出了一种以空闲状态时轨道电路地面监测数据为观测量,以支持向量机和基于组合法的多分类策略为关键算法的轨道电路故障诊断方法,算法扩展性能好,泛化能力强。
(4)提出了一种基于Sigmoid函数模型和扩展的Bradley-Terry模型的诊断输出结果的概率化表示方法,提高了诊断结果表达的科学性。
(5)提出了一种以被占用状态时轨道电路车载监测数据为观测量,以集合经验模式分解和相空间重构理论为关键算法的补偿电容故障诊断方法,算法能够有效诊断补偿电容的早期故障,且对外界干扰因素具有较强的免疫能力。
A jointless track circuit is the fundamental infrastructure in Chinese Train Control System, it is a typical safety critical system and is a key issue affecting the efficiency of railway transport. However, fault diagnosis and maintenance methods for track circuits cannot meet the urgent needs of the development of railway transport in China, some "inertia faults" even become prominent weaknesses in production of railway safety. It is significantly important to carry out systematic research on fault diagnosis for track circuits.
In this paper, the ZPW-2000A jointless track circuit is used as the study object which is widely used in China railway system. An equivalent circuit model of an unoccupied track circuit is established based on two-port network theory, the correctness of the model is validated using experiment data based on track circuit physical mode and real data based on Signal Centralized System, then the main fault modes are summarized and relationships between fault modes and monitoring variables are investigated. Similar work is done for a track circuit under occupied condition. In particular, the wheel-rail contact resistance which is a key factor to cause shunt disfunction of a track circuit is modeled and investigated using Electrical Contact Theory, then the mechanism of shunt disfunction is analyzed in the view of theory.
Based on these results, fault diagnosis methods for typical fault modes for the unoccupied track circuit are studied. Firstly, a fault diagnosis method which combines Support Vector Machine and Combination-based multi-class strategy is proposed, a multi-class probability estimation algorithm and an amendment algorithm considering the loss for misclassification for diagnosis results are presented. Furthermore, In order to obtain the information of the location of faulty compensation capacitor, that cannot be got from the above method, a fault diagnosis method for compensation capacitors is proposed which is based on Ensemble Empirical Mode Decomposition and Phase Space Reconstruction Theory, in which the signal from on-board monitoring system for an occupied track circuit is used as the analyzed object. Three different sources of data: simulated data based on track circuit model, experiment data based on track circuit physical model and real data from monitoring system are used to test the preference of the diagnosis methods, Experiments'results show that the fault models can be well diagnosed using the approach, and the preference is not sensitive to interference.
The innovations of the dissertation are as follows:
(1) The study investigates the relationships between fault models and monitoring variables of a jointless track circuit which combines Signed Directed Graph, Independent Component Analysis and linear fit method and so on, this work provides the necessary prior knowledge for fault diagnosis research.
(2) The study proposes a wheel-rail contact resistance model based on Electrical Contact Theory, based on the model the variation mechanism of the wheel-rail contact resistance and relationship between the resistance and influence factors are investigated quantitatively, this work provides a theoretical basis for the prediction and elimination of shunt disfunction.
(3) The study proposes a fault diagnosis method for track circuits based on Support Vector Machine and Combination-based multi-class stratagem, in which the signal from ground monitoring system for an unoccupied track circuit is used as analyzed object. The adaptability and generalization ability of this method can comply with the requirements of maintenance.
(4) The study proposes a multi-class probability estimation algorithm for diagnosis results using Sigmoid function model and generalized Bradley-Terry model, in doing so, the expression of diagnosis results is more reasonable.
(5) The study proposes a fault diagnosis method for compensation capacitors in track circuit based on Ensemble Empirical Mode Decomposition and Phase Space Reconstruction theory, in which the signal from on-board monitoring system for an occupied track circuit is used as analyzed object. This method is effective for incipient fault of a compensation capacitor, and is not sensitive to interference.
引文
[1]国家铁路局.2008年10月国家批准《中长期铁路网规划(2008年调整)》[OL].http://www.nra.gov.cn/zggstl/wggstlghqk/2008/201312/t20131227_4084.html.2014.
[2]新华网. 中国高铁总里程达11028公里占世界一半[0L].http://news.xinhuanet.com/fortune/2014-03/05/c 119626642.htm.2014.
[3]人民网.中国高铁总里程将翻番,铁路革命令中国前行[0L].http://scitech.people.com.cn/n/2014/2306/c1007-24543679.html,2014.
[4]宁滨,唐涛,李开成,董海荣.高速列车运行控制系统[M].北京：科学出版社.2012：5-32.
[5]《当代中国铁路信号(2006-2010)》编辑委员会.当代中国铁路信号(2006-2010)[M].北京：中国铁道出版社.2013：1-58,454-508.
[6]傅世善.傅世善铁路信号论文选集[M].北京：中国铁道出版社.2012：293-300.
[7]中华人民共和国铁道部.CTCS-3级列控系统系统标准规范系列-CTCS-3级列控系统功能需求规范[S].北京：中国铁道出版社.2009：1-12.
[8]汪希时.智能铁路运输系统ITS-R[M].北京：中国铁道出版社.2004：1-40.
[9]赵自信.ZPW--2000A无绝缘移频自动闭塞系统的技术综述.铁路通信信号工程技术[J]2003,A01：12-19.
[10]铁道部铁运函(2003)196号.关于规范ZPW-2000自动闭塞上道管理工作的通知[S].2003.
[11]铁道部运输局运基信号(2003)240号.关于加强ZPW-2000自动闭塞上道管理的实施意见[S].2003.
[12]黄赞武,魏学业,李绍斌.轨道电路故障预测与健康管理体系结构设计[M].计算机工程.2012,38(20)：232-235.
[13]袁成华,皇甫开春,陈延国,董龙.铁路信号设备故障分析与处理[M].北京：中国铁道出版社.2011：245-280.
[14]罗海涛.国外无绝缘轨道电路及列车自动控制系统[R],专题情报资料88-8.铁道部科学技术情报研究所.1988(9).
[15]阿.米.布列也夫尤.阿.克拉夫错夫,阿.付.希师良柯夫合著,孙铭甫译.轨道电路的分析与综合[M].北京：中国铁道出版社.1981：67-83.
[16]朱淇昌,胡同光,司徒镇国.轨道电路及其研究(上)[J].铁道研究通讯.1953(1)：33-38.
[17]《当代中国铁路信号(1986-1990)》编辑委员会.当代中国铁路信号(1986-1990)[M].北京：中国铁道出版社.1993：1-37.
[18]《当代中国铁路信号(1991-1995)》编辑委员会.当代中国铁路信号(1991-1995)[M].北京：中国铁道出版社.1997：1-35.
[19]《当代中国铁路信号(1996-2000)》编辑委员会当代中国铁路信号(1996-2000)[M].北京：中国铁道出版社.2002：1-45.
[20]李德垂,杨奎芳.轨道电路参数模拟装置的研制[J].铁道通信信号,1997.33(5)：12-15.
[21]费锡康.无绝缘轨道电路原理及分析[M].北京：中国铁道出版社.1993：17-60.
[22]赵会兵.轨道电路系统数字仿真的研究[D].北京.北京交通大学.1998：1-18.
[23]毛广智,解学书.S型电气绝缘节的建模与分析[J].清华大学学报(自然科学版).2004.44(10)：1364-1367.
[24]仝百祥UM71 (ZPW-2000A)型无绝缘移频轨道电路绝缘节窜码原因分析[J].铁道通信信号.2009.45(9)：5-8.
[25]刘朝英,莫志松.京津城际高速铁路信号系统集成[M].北京：中国铁道出版社.2010：325-332.
[26]大秦重载铁路电务技术与应用编辑委员会.大秦重载铁路电务技术与应用[M].北京：中国铁道出版社.2009：473-481.
[27]徐啸明.列控地面系统设备[M].北京：中国铁道出版社.2007：106-133.
[28]李文海.ZPW-2000A移频自动闭塞系统原理、维护和故障处理[M].北京：中国铁道出版社.2010：57-66.
[29]中华人民共和国铁道部.中华人民共和国铁道部信号维护规则技术标准[M].北京：中国铁道出版社.2008：7-23.
[30]赵林海,穆建成.基于AOK-TFR的轨道电路故障诊断方法[J].西南交通大学学报.2011.46(1)：84-91.
[31]邱宽明等编著,袁湘鄂,刘大为审.JT1-CZ2000型机车信号车载系统[M].北京：中国铁道出版社.2007.
[32]孟景辉,谢保锋,高利民.基于线性拟合的区间轨道电路传输特性[J].中国铁道科学.2011.32(1)：112-117.
[33]Li Liang, Wei Dong, Yindong Ji, Zengke Zhang. An improved parameter identification approach for piecewise affine model[J]. Control Engineering Practice,2013.21(1):54-64.
[34]杨世武,魏学业,范博,蒋大明.基于数据的轨道电路故障诊断的混合算法[J].北京交通大学学报.2012.36(2)：40-46.
[35]谢保锋,林涛,鲁恩斌.基于数据融合的轨道电路工作状态综合分析系统[J].中国铁路.2011(6)：54-58.
[36]袁孝均.轨道电路分路不良问题研究[J].铁路通信信号.2007.43(4)：11-14.
[37]北京全路通信信号研究设计院有限公司.解决区间ZPW-2000A轨道电路分路不良海南东环、郑西线阶段试验报告[R].2011.12：2-40.
[38]#12
[39]H.Q.科拉列克著武正贵,杨易民,罗海涛译.轨道电路[M].人民铁道出版社.1966.
[40] Hill R. J., S. Brillante, P. J. Leonard. Electromagnetic field modelling for transmission line distributed parameters of railway track[J]. Electric Power Applications, IEE Proceedings,1999. 146(1):53-59.
[41] Hill R. J., S. Brillante, C. R. De Souza, P. J. Leonard. Electrical material data for railway track transmission line parameter studies[J]. IEE Proceedings:Electric Power Applications,1999. 146(1):60-68.
[42] Hill R. J., M. L. Berova. Computer modelling and simulation of jointless audio-frequency track circuit[C]. Proceedings of the 4th International Conference on Computer Aided Design, Manufacture and Operation in the Railway and Other Mass Transit Systems. Part 1 (of 2),1994. Madrid, Spain:515-522.
[43] Fessant F, P Aknin, F Vilette, M Antoni. Modelisation electrique du circuit de voie, element du systeme de transmission voie-machine des TGV[J]. Revue 3,2001.27:46-52.
[44]Mariscotti A., M. Ruscelli, M. Vanti. Modeling of audiofrequency track circuits for validation, tuning, and conducted interference prediction. [J] Intelligent Transportation Systems, IEEE Transactions on,2010.11(1):52-60.
[45]Kim Min-Seok, Jong-Woo Lee. A study on the distance between the track circuits using identical frequency in railway track circuit system[J]. Transactions of the Korean Institute of Electrical Engineers,2009.58(11):2168-2174.
[46]Chen J., C. Roberts, P. Weston. Fault detection and diagnosis for railway track circuits using neuro-fuzzy systems[J]. Control Engineering Practice,2008.16(5):585-596.
[47]Chen J., C. Roberts. Effective condition monitoring of line side assets[C]. IET International Conference on Railway Condition Monitoring,2006. Birmingham, United kingdom: Institution of Engineering and Technology,78-83.
[48]Oukhellou L., A. Debiolles, T. Denoeux, P. Aknin. Fault diagnosis in railway track circuits using Dempster-Shafer classifier fusion[C]. Engineering Applications of Artificial Intelligence,2010. 23(1):117-128.
[49]Come E, L Oukhellou, T Denoeux, P Aknin. Independent Factor Analysis with mixing constraints in a semi-supervised framework:Application to railway device fault diagnosis[C]. International Conference on Artificial Neural Networks(ICICANN).2009:416-425.
[50]Come E., L. Oukhellou, T. Denoeux, P. Aknin. Learning from partially supervised data using mixture models and belief functions[J]. Pattern Recognition,2009.42(3):334-348.
[51]Nagase K., T. Nomura, J. Hirama. Influence of contact condition between rails and wheels upon track circuit shunting (1st report quantitative evaluation of factors that cause inadequate track circuit shunting) [J]. Transactions of the Japan Society of Mechanical Engineers, Part C,1997. 63(616):4187-4194.
[52]Yusuke Wakabayashi, Nakagawa Daisuke, Hirama Junji. Influence of contact condition between rails and wheels upon track circuit shunting (2nd Report, measuring methods and results of track circuit shunting resistance of running train's wheelset) [J]. Transactions of the Japan Society of Mechanical Engineers. PartC,2002.68(672):2402-2409.
[53]Wakabayashi Yusuke, Daisuke Nakagawa, Tomoya Kitagawa, Junji Hirama, Kazuhiko Nagase. Influence of contact condition between rails and wheels upon track circuit shunting (3rd report, electric resonance phenomena by track circuit shunting of running train's wheelset) [J]. Transactions of the Japan Society of Mechanical Engineers, Part C,2002.68(674):3023-3028.
[54]Hirama Junji, Yusuke Wakabayashi, Tomoya Kitagawa, Kazuhiko Nagase. Influence of contact condition between rails and wheels upon track circuit shunting (4th report, result of continuously measured shunting resistance of the running wheelsets) [J]. Transactions of the Japan Society of Mechanical Engineers, Part C,2005.71(4):1263-1268.
[55]Lewis R., J. Masing. Static wheel/rail contact isolation due to track contamination[J]. Proceedings of the Institution of Mechanical Engineers Part F-Journal of Rail and Rapid Transit, 2006.220(1):43-53.
[56]Arias-Cuevas O., Z. Li, R. Lewis. Investigating the lubricity and electrical insulation caused by sanding in dry wheel-rail contacts[J]. Tribology Letters,2010.37(3):623-635.
[57]Millar A. H., A. Lindsay. Developments in track circuit condition monitoring[C].4th IET International Conference on Railway Condition Monitoring(ICRCM).2008, Derby, United kingdom: Institution of Engineering and Technology,2008:1-6.
[58]Weston P. F., J. Chen, E. Stewart, C. Roberts. Condition monitoring of audio frequency track circuits[C].IET International Conference on Railway Engineering(ICRE),2008. Hong Kong, China:Institution of Engineering and Technology,2008:129-134.
[59]Patra A. P., U. Kumar, P. O. L. Kraik. Availability target of the railway infrastructure:an analysis[C]. The Proceeding of Reliability and Maintainability Symposium (RAMS),2010 San Jose. 2010:1-6.
[60]Patra A. P., U. Kumar. Availability analysis of railway track circuits[C]. Proceedings of the Institution of Mechanical Engineers, Part F:Journal of Rail and Rapid Transit.2010. London. Professional Engineering Publishing Ltd.2010.224(F3):169-177.
[61]高金吉.机器故障诊治与自愈化[M].北京：高等教育出版社.2012：1-60.
[62]高金吉.锋芒初露的设备诊断工程[J].中国科学技术前沿(中国工程院版)第六卷.北京：高等教育出版社.2003.263-299.
[63]张炜,张玉祥.导弹动力系统故障机理分析与诊断技术[M].西北工业大学出版社.2006：5-19.
[64]黄采伦,樊晓平,陈特放.列车故障在线诊断技术及应用[M].北京：国防工业出版社.2006：1-22.
[65]Venkatasubramanian Venkat, Raghunathan Rengaswamy, Kewen Yin, Surya N. Kavuri. A review of process fault detection and diagnosis:Part Ⅰ:Quantitative model-based methods[J]. Computers & Chemical Engineering,2003.27(3):293-311.
[66]Venkatasubramanian Venkat, Raghunathan Rengaswamy, Surya N. Kavuri, Kewen Yin. A review of process fault detection and diagnosis:Part Ⅲ:Process history based methods[J]. Computers & Chemical Engineering,2003.27(3):327-346.
[67]Venkatasubramanian Venkat, Raghunathan Rengaswamy, Surya N. Kavuri. A review of process fault detection and diagnosis:Part Ⅱ:Qualitative models and search strategies[J]. Computers & Chemical Engineering,2003.27(3):313-326.
[68]Yang Qingsong. Model-based and data driven fault diagnosis methods with applications to process monitoring[D], Ohio, Case Western Reserve University.2004:1-17.
[69]Jardine Andrew K. S., Darning Lin, Dragan Banjevic. A review on machinery diagnostics and prognostics implementing condition-based maintenance[J]. Mechanical Systems and Signal Processing,2006.20(7):1483-1510.
[70]Ribeiro L., J. Barata. Re-thinking diagnosis for future automation systems:An analysis of current diagnostic practices and their applicability in emerging IT based production paradigms[J]. Computers in Industry,2011.62(7):639-659.
[71]Barlow Richard, Larry Hunter. Optimum preventive maintenance policies[J]. Operations Research,1960.8(1):90-100.
[72]Thurston M Lebold M. Open standards for condition-based maintenance and prognostic systems[C].5th Annual Maintenance and Reliability Conference(MARCON). Gatlinburg.2001.
[73]Lebold Mitchell S., Karl M. Reichard, Daniel Ferullo, David Boylan. Open system architecture for condition-based maintenance overview and training material[R]. The Pennsylvania State University.2003.
[74]Zhang S. N., R. Kang, X. F. He, M. G. Pecht. China's efforts in prognostics and health management[C]. IEEE Transactions on Components and Packaging Technologies,2008.31(2): 509-518.
[75]Thatoi D. N., H. C. Das, D. R. Parhi. Review of techniques for fault diagnosis in damaged structure and engineering system[J]. Advances in Mechanical Engineering,2012:1-11.
[76]李晗,萧德云.基于数据驱动的故障诊断方法综述[J].控制与决策.2011.26(1)：1-9.
[77]Djuric Natasa, Vojislav Novakovic. Review of possibilities and necessities for building lifetime commissioning[J]. Renewable and Sustainable Energy Reviews,2009.13(2):486-492.
[78]周东华,李钢,李元著.数据驱动的工业过程故障诊断技术—基于主元分析与偏最小二乘的方法[M].北京：科学出版社2011:1-11.
[79]Jurgen Schmidhuber. Deep Learning in Neural Networks:An Overview[R].University of Lugano & SUPSI. Switzerland.2014:1-70.
[80]Henley Ernest J, Hiromitsu Kumamoto. Reliability engineering and risk assessmen[J]. Prentice-Hall Englewood Cliffs (NJ).1981:45-198.
[81]Pumfrey David John. The principled design of computer system safety analyses[D]. York,University of York,1999:1-23.
[82]Iri Masao, Katsuaki Aoki, Eiji O'shima, H Matsuyama. An algorithm for diagnosis of system failures in the chemical process[J]. Computers & Chemical Engineering,1979.3(1):489-493.
[83]Maurya Mano Ram, Praveen K. Paritosh, Raghunathan Rengaswamy, Venkat Venkatasubramanian. A framework for on-line trend extraction and fault diagnosis[J]. Engineering Applications of Artificial Intelligence,2010.23(6):950-960.
[84]Maurya M. R., R. Rengaswamy, V. Venkatasubramanian. A signed directed graph and qualitative trend analysis-based framework for incipient fault diagnosis[J]. Chemical Engineering Research & Design,2007.85(A10):1407-1422.
[85]Maurya M., R. Rengaswamy, V. Venkatasubramanian. Fault diagnosis using dynamic trend analysis:A review and recent developments[J]. Engineering Applications of Artificial Intelligence, 2007.20(2):133-146.
[86]Maurya Mano Ram, Raghunathan Rengaswamy, Venkat Venkatasubramanian. A Systematic Framework for the Development and Analysis of Signed Digraphs for Chemical Processes.2. Control Loops and Flowsheet Analysis[J]. Industrial & Engineering Chemistry Research,2003.42(20):4811-4827.
[87]张贝克,张海洋,马听.定性趋势分析在过程故障诊断中的应用研究[J].系统仿真学报.2008.28(10)：2750-2754.
[88]张海洋,张贝克,吴重光.用于监测复杂系统的计算机辅助定性趋势分析[J].计算机工程与应用.2007.43(17)：41-45.
[89]Dash Sourabh, Raghunathan Rengaswamy, Venkat Venkatasubramanian. Fuzzy-logic based trend classification for fault diagnosis of chemical processes[J]. Computers & Chemical Engineering,2003.27(3):347-362.
[90]Dash S., M. R. Maurya, V. Venkatasubramanian, R. Rengaswamy. A novel interval-halving framework for automated identification of process trends[J]. Aiche Journal,2004.50(1):149-162.
[91]Dash S., M. R. Maurya, V. Venkatasubramanian, R. Rengaswamy. A Novel Interval-Halving Framework For Automated Identification of Process Trends Extended Version[R]. 2003:1-83.
[92]Smola Alex, S.V.N. Vishwanathan. Introduction to Machine Learning[M]. Cambridge: Cambridge University Press 2010:1-36.
[93]Cortes Corinna, Vladimir Vapnik. Support-vector networks. Machine learning[J],1995. 20(3):273-297.
[94]Boser Bernhard E, Isabelle M Guyon, Vladimir N Vapnik. A training algorithm for optimal margin classifiers[C].Proceedings of the fifth annual workshop on Computational learning theory. 1992:144-152.
[95]Shawe-Taylor J., S. L. Sun. A review of optimization methodologies in support vector machines[J]. Neurocomputing,2011.74(17):3609-3618.
[96]Luts Jan, Fabian Ojeda, Raf Van De Plas, Bart De Moor, Sabine Van Huffel, Johan A. K. Suykens. A tutorial on support vector machine-based methods for classification problems in chemometrics[J]. Analytica Chimica Acta,2010.665(2):129-145.
[97]Zinzen R. P., C. Girardot, J. Gagneur, M. Braun, E. E. M. Furlong. Combinatorial binding predicts spatio-temporal cis-regulatory activity[J]. Nature,2009.462(7269):65-72.
[98]Marquez F. P. G., I. P. Garcia-Pardo. Principal Component Analysis applied to filtered signals for maintenance management[J]. Quality and Reliability Engineering International,2010. 26(6):523-527.
[99]Efron Bradley. Bayes'Theorem in the twenty-first century[J]. Science.2013.340(6137): 1177-1178.
[100]Salem Ab, L Bouillaut, P Aknin, P Weber. Dynamic Bayesian Networks for classification of rail defects[J].2004:353-370.
[101]Bouillaut Laurent, Weber P, Salem A.B, Aknin P. Use of causal probabilistic networks for the improvement of the maintenance of railway infrastructure[C]. IEEE International Conference on Systems, Man and Cybernetics(ICSMC),2004. The Hague, Netherlands:Institute of Electrical and Electronics Engineers Inc.2004:6243-6249.
[102]褚福磊.机械故障诊断中的现代信号处理方法[M].科学出版社.2009：1-13.
[103]Shin K, Jk Hammond, Pr White. Iterative SVD method for noise reduction of low-dimensional chaotic time series. Mechanical Systems and Signal Processing. [J] 1999.13(1): 115-124.
[104]Wang Wj, Zt Wu, J Chen. Fault identification in rotating machinery using the correlation dimension and bispectra[J]. Nonlinear Dynamics,2001.25(4):383-393.
[105]Feng Zhipeng, Ming Liang, Fulei Chu. Recent advances in time-frequency analysis methods for machinery fault diagnosis:A review with application examples. Mechanical Systems and Signal Processing[J].2013.38(1):165-205.
[106]Jin Yu, Xifeng Zheng, Tiefu Ding. A high-accuracy parameter estimation algorithm for jointless Frequency-shift track circuit[C]. Guangzhou.2008, International Colloquium on Computing, Communication, Control, and Management(ICCCM).2008.(1):750-753.
[107]Zhao Linhai, Zhankui Li, Weining Liu. The compensation capacitors fault detection method of jointless track circuit based on DBWT and WR[C]. IEEE International Conference on Intelligent Computing and Intelligent Systems(ICIS).2009. Shanghai, China:IEEE Computer Society.2009:875-879.
[108]Oukhellou L., P. Aknin, E. Delechelle. Railway infrastructure system diagnosis using empirical mode decomposition and Hilbert transform[C]. IEEE International Conference on Acoustics, Speech and Signal Processing.2006. Toulouse.2006.1-13:3615-3618.
[109]张腾飞,王锡淮,叶银忠,肖健梅.粗糙集理论在故障诊断中的应用综述[J].上海海事大学学报.2005,26(4)：20-28.
[110]李华莹,刘建敏,乔新勇,李晓磊.基于AGA-RS的故障特征参数提取方法研究.计算机工程与应用[J].2014.50(5)：257-260.
[111]Buchla D.M.,弗洛伊德著,施惠琼,夏琳译.电路分析基础[M].北京：清华大学出版社.2006：223-276.
[112]胡永生.轨道电路分路不良整治方案研究[J].铁道通信信号.2008.44(5)：24-26.
[113]徐木根,陈辛怡.对轨道电路分路不良安全风险控制的体会与建议[J].铁道通信信号.2013.49(6)：13-15.
[114]Holm R., E. Holm. Electric contacts:theory and application[M]. Vol.9:Springer-Verlag New York.1967:23-67.
[115]Persson B. N. J. Contact mechanics for layered materials with randomly rough surfaces[J]. Journal of Physics-Condensed Matter,2012.24(9):33-42.
[116]瓦伦丁L.波波夫著,李强译.接触力学与摩擦学的原理及其应用[M].北京：清华大学出版社.2011：1-73.
[117]Greenwood J A. Constriction resistance and the real area of contact[J]. British Journal of Applied Physics,1966.17(12):1621-1632.
[518]Godet Maurice. The third-body approach:A mechanical view of wear[J]. Wear,1984. 100(1-3):437-452.
[119]Berthier Y., S. Descartes, M. Busquet, E. Niccolini, C. Desrayaud, L. Baillet, M. C. Baietto-Dubourg. The role and effects of the third body in the wheel-rail interaction[J]. Fatigue & Fracture of Engineering Materials & Structures,2004.27(5):423-436.
[120]Sawada Shigeru, Kaori Shimizu, Shigeki Shimada, Yasuhiro Hattori. Prediction of Electrical Contact Resistance of Tin-Plated and Silver-Plated Terminals [J]. SEI Technical Review, 2010. (71):37-43.
[121]Bucher F., A. I. Dmitriev, M. Ertz, K. Knothe, V. L. Popov, S. G. Psakhie, E. V. Shilko. Multiscale simulation of dry friction in wheel/rail contact[J]. Wear,2006.261(7-8):874-884.
[122]肖乾,林凤涛,王成国.变摩擦系数条件下的轮轨滚动接触特性分析[J].铁道学报.2012.34(6)：24-28.
[123]温诗铸,黄平.摩擦学原理(下)[M].第二版.北京：清华大学出版社.2002：286-300.
[124]Railways. International Union Of. UIC5 10-5 Technical Approval of Solid Wheels[S]. Paris:International Union of Railways,2003.
[125]神圣,张军,孙传喜.磨耗状态下机车车轮与曲线钢轨的接触分析[J].铁道学报.2012.34(6)：15-19.
[126]金学松,沈志云.轮轨濡滑理论及其试验研究[D].成都：西南交通大学出版社.2006：9-69.
[127]Braunovic Milenko, Valery V. Konchits, Nikolai K. Myshkin. Electrical Contacts: Fundamentals、Applications and technology[M]. Newyork:CRC Press.2006:1-33.
[128]Cristianini Nello, John Shawe-Taylor. An Introduction to Support Vector Machines and Other Kernel-based Learning Methods[M]. Cambridge:Cambridge University Press.2003:73-105.
[129]Sanchez A V. David. Advanced support vector machines and kernel methods[J]. Neurocomputing,2003.55(1-2):5-20.
[130]Weston Jason, Chris Watkins. Multi-class support vector machines[R]. Citeseer, 1998:1-10
[131]Dietterich Thomas G., Ghulum Bakiri. Solving multiclass learning problems via error-correcting output codes[J]. Journal of Artificial Intelligence Research,1995.(2):263-286.
[132]Zadrozny Bianca, Charles Elkan, Transforming classifier scores into accurate multiclass probability estimates[C]. in Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining. ACM:Edmonton, Alberta, Canada.2002:694-699.
[133]Hsu Chih-Wei, Chih-Jen Lin. A comparison of methods for multiclass support vector machines[J]. IEEE Transactions on Neural Networks.2002.13(2):415-425.
[134]Rifkin Ryan, Aldebaro Klautau. In defense of One-Vs-All classification[J]. J. Mach. Learn. Res.,2004.5:101-141.
[135]Platt John. Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods[J]. Advances in large margin classifiers.1999.10(3):61-74.
[136]Wahba Grace. Support vector machines, reproducing kernel Hilbert spaces and the randomized GACV[J]. Advances in Kernel Methods-Support Vector Learning,1999.6:69-87.
[137]杜京义,候媛彬.基于最小风险的SVM及其在故障诊断中的应用[J].振动、测试与诊断.2006.26(2)：108-111.
[138]Bradley Ralph Allan, Milton E Terry. Rank analysis of incomplete block designs:I. The method of paired comparisons[J]. Biometrika,1952.42(3-4):324-345.
[139]Caron Francois, Doucet Arnaud, Efficient bayesian inference for generalized Bradley-Terry models[J]. Journal of Computational and Graphical Statistics.2012.21(1):174-196.
[140]Long Xi, W. Louis Cleveland, Y. Lawrence Yao. Multiclass cell detection in bright field images of cell mixtures with ECOC probability estimation. Image and Vision Computing[J].2008. 26(4):578-591.
[141]金向阳.基于振动样本民航发动机故障诊断方法及应用研究[D].哈尔滨：哈尔滨工业大学2012：68-85.
[142]Widodo A., B. S. Yang. Support vector machine in machine condition monitoring and fault diagnosis[J]. Mechanical Systems and Signal Processing,2007,21(6):2560-2574.
[143]Yang Bo-Suk, Tian Han, Won-Woo Hwang. Fault diagnosis of rotating machinery based on multi-class support vector machines[J]. Journal of Mechanical Science and Technology,2005. 19(3):846-859.
[144]Huang Ne, Z Shen, Sr Long, Me Wu, Hh Shih, Q Zheng, Nc Yen, Cc Tung, Hh Liu. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings:Mathematical, Physical and Engineering Sciences,1998.454(1971): 903-995.
[145]Wu Zhaohua, Norden E Huang. Ensemble empirical mode decomposition:a noise-assisted data analysis method[J]. Advances in Adaptive Data Analysis,2009. 1(01):1-41.
[146]Takens F. Detecting strange attractors in turbulence[J]. Dynamical systems and turbulence, Warwick 1980,1981:366-381.
[147]Packard N. H., J. P. Crutchfield, J. D. Farmer, R. S. Shaw. Geometry from a Time Series[J]. Physical Review Letters,1980.45(9):712-716.
[148]Jiang Ai-Hua, Xiu-Chang Huang, Zhen-Hua Zhang, Jun Li, Zhi-Yi Zhang, Hong-Xin Hua. Mutual information algorithms[J]. Mechanical Systems and Signal Processing,2010.24(8): 2947-2960.
[149]Andrew R. Sloboda. Parametric variation identification techniques in nonlinear dynamical systems[D]. Michigan:University of Michigan.2013:37-96.
[150]Zhongyuan Su, Yaoming Zhang, Minping Jia, Feiyun Xu, Jianzhong Hu. Gear fault identification and classification of singular value decomposition based on Hilbert-Huang transform[J]. Journal of Mechanical Science and Technology.25(2):267-272.
[151]Lin-Hai Zhao, Wu Jian-Ping, Ran Yi-Kui. Fault diagnosis for track circuit using AOK-TFRs and AGA[J]. Control Engineering Practice,2012.20(12):1270-1280.
[2]新华网. 中国高铁总里程达11028公里占世界一半[0L].http://news.xinhuanet.com/fortune/2014-03/05/c 119626642.htm.2014.
[3]人民网.中国高铁总里程将翻番,铁路革命令中国前行[0L].http://scitech.people.com.cn/n/2014/2306/c1007-24543679.html,2014.
[4]宁滨,唐涛,李开成,董海荣.高速列车运行控制系统[M].北京：科学出版社.2012：5-32.
[5]《当代中国铁路信号(2006-2010)》编辑委员会.当代中国铁路信号(2006-2010)[M].北京：中国铁道出版社.2013：1-58,454-508.
[6]傅世善.傅世善铁路信号论文选集[M].北京：中国铁道出版社.2012：293-300.
[7]中华人民共和国铁道部.CTCS-3级列控系统系统标准规范系列-CTCS-3级列控系统功能需求规范[S].北京：中国铁道出版社.2009：1-12.
[8]汪希时.智能铁路运输系统ITS-R[M].北京：中国铁道出版社.2004：1-40.
[9]赵自信.ZPW--2000A无绝缘移频自动闭塞系统的技术综述.铁路通信信号工程技术[J]2003,A01：12-19.
[10]铁道部铁运函(2003)196号.关于规范ZPW-2000自动闭塞上道管理工作的通知[S].2003.
[11]铁道部运输局运基信号(2003)240号.关于加强ZPW-2000自动闭塞上道管理的实施意见[S].2003.
[12]黄赞武,魏学业,李绍斌.轨道电路故障预测与健康管理体系结构设计[M].计算机工程.2012,38(20)：232-235.
[13]袁成华,皇甫开春,陈延国,董龙.铁路信号设备故障分析与处理[M].北京：中国铁道出版社.2011：245-280.
[14]罗海涛.国外无绝缘轨道电路及列车自动控制系统[R],专题情报资料88-8.铁道部科学技术情报研究所.1988(9).
[15]阿.米.布列也夫尤.阿.克拉夫错夫,阿.付.希师良柯夫合著,孙铭甫译.轨道电路的分析与综合[M].北京：中国铁道出版社.1981：67-83.
[16]朱淇昌,胡同光,司徒镇国.轨道电路及其研究(上)[J].铁道研究通讯.1953(1)：33-38.
[17]《当代中国铁路信号(1986-1990)》编辑委员会.当代中国铁路信号(1986-1990)[M].北京：中国铁道出版社.1993：1-37.
[18]《当代中国铁路信号(1991-1995)》编辑委员会.当代中国铁路信号(1991-1995)[M].北京：中国铁道出版社.1997：1-35.
[19]《当代中国铁路信号(1996-2000)》编辑委员会当代中国铁路信号(1996-2000)[M].北京：中国铁道出版社.2002：1-45.
[20]李德垂,杨奎芳.轨道电路参数模拟装置的研制[J].铁道通信信号,1997.33(5)：12-15.
[21]费锡康.无绝缘轨道电路原理及分析[M].北京：中国铁道出版社.1993：17-60.
[22]赵会兵.轨道电路系统数字仿真的研究[D].北京.北京交通大学.1998：1-18.
[23]毛广智,解学书.S型电气绝缘节的建模与分析[J].清华大学学报(自然科学版).2004.44(10)：1364-1367.
[24]仝百祥UM71 (ZPW-2000A)型无绝缘移频轨道电路绝缘节窜码原因分析[J].铁道通信信号.2009.45(9)：5-8.
[25]刘朝英,莫志松.京津城际高速铁路信号系统集成[M].北京：中国铁道出版社.2010：325-332.
[26]大秦重载铁路电务技术与应用编辑委员会.大秦重载铁路电务技术与应用[M].北京：中国铁道出版社.2009：473-481.
[27]徐啸明.列控地面系统设备[M].北京：中国铁道出版社.2007：106-133.
[28]李文海.ZPW-2000A移频自动闭塞系统原理、维护和故障处理[M].北京：中国铁道出版社.2010：57-66.
[29]中华人民共和国铁道部.中华人民共和国铁道部信号维护规则技术标准[M].北京：中国铁道出版社.2008：7-23.
[30]赵林海,穆建成.基于AOK-TFR的轨道电路故障诊断方法[J].西南交通大学学报.2011.46(1)：84-91.
[31]邱宽明等编著,袁湘鄂,刘大为审.JT1-CZ2000型机车信号车载系统[M].北京：中国铁道出版社.2007.
[32]孟景辉,谢保锋,高利民.基于线性拟合的区间轨道电路传输特性[J].中国铁道科学.2011.32(1)：112-117.
[33]Li Liang, Wei Dong, Yindong Ji, Zengke Zhang. An improved parameter identification approach for piecewise affine model[J]. Control Engineering Practice,2013.21(1):54-64.
[34]杨世武,魏学业,范博,蒋大明.基于数据的轨道电路故障诊断的混合算法[J].北京交通大学学报.2012.36(2)：40-46.
[35]谢保锋,林涛,鲁恩斌.基于数据融合的轨道电路工作状态综合分析系统[J].中国铁路.2011(6)：54-58.
[36]袁孝均.轨道电路分路不良问题研究[J].铁路通信信号.2007.43(4)：11-14.
[37]北京全路通信信号研究设计院有限公司.解决区间ZPW-2000A轨道电路分路不良海南东环、郑西线阶段试验报告[R].2011.12：2-40.
[38]#12
[39]H.Q.科拉列克著武正贵,杨易民,罗海涛译.轨道电路[M].人民铁道出版社.1966.
[40] Hill R. J., S. Brillante, P. J. Leonard. Electromagnetic field modelling for transmission line distributed parameters of railway track[J]. Electric Power Applications, IEE Proceedings,1999. 146(1):53-59.
[41] Hill R. J., S. Brillante, C. R. De Souza, P. J. Leonard. Electrical material data for railway track transmission line parameter studies[J]. IEE Proceedings:Electric Power Applications,1999. 146(1):60-68.
[42] Hill R. J., M. L. Berova. Computer modelling and simulation of jointless audio-frequency track circuit[C]. Proceedings of the 4th International Conference on Computer Aided Design, Manufacture and Operation in the Railway and Other Mass Transit Systems. Part 1 (of 2),1994. Madrid, Spain:515-522.
[43] Fessant F, P Aknin, F Vilette, M Antoni. Modelisation electrique du circuit de voie, element du systeme de transmission voie-machine des TGV[J]. Revue 3,2001.27:46-52.
[44]Mariscotti A., M. Ruscelli, M. Vanti. Modeling of audiofrequency track circuits for validation, tuning, and conducted interference prediction. [J] Intelligent Transportation Systems, IEEE Transactions on,2010.11(1):52-60.
[45]Kim Min-Seok, Jong-Woo Lee. A study on the distance between the track circuits using identical frequency in railway track circuit system[J]. Transactions of the Korean Institute of Electrical Engineers,2009.58(11):2168-2174.
[46]Chen J., C. Roberts, P. Weston. Fault detection and diagnosis for railway track circuits using neuro-fuzzy systems[J]. Control Engineering Practice,2008.16(5):585-596.
[47]Chen J., C. Roberts. Effective condition monitoring of line side assets[C]. IET International Conference on Railway Condition Monitoring,2006. Birmingham, United kingdom: Institution of Engineering and Technology,78-83.
[48]Oukhellou L., A. Debiolles, T. Denoeux, P. Aknin. Fault diagnosis in railway track circuits using Dempster-Shafer classifier fusion[C]. Engineering Applications of Artificial Intelligence,2010. 23(1):117-128.
[49]Come E, L Oukhellou, T Denoeux, P Aknin. Independent Factor Analysis with mixing constraints in a semi-supervised framework:Application to railway device fault diagnosis[C]. International Conference on Artificial Neural Networks(ICICANN).2009:416-425.
[50]Come E., L. Oukhellou, T. Denoeux, P. Aknin. Learning from partially supervised data using mixture models and belief functions[J]. Pattern Recognition,2009.42(3):334-348.
[51]Nagase K., T. Nomura, J. Hirama. Influence of contact condition between rails and wheels upon track circuit shunting (1st report quantitative evaluation of factors that cause inadequate track circuit shunting) [J]. Transactions of the Japan Society of Mechanical Engineers, Part C,1997. 63(616):4187-4194.
[52]Yusuke Wakabayashi, Nakagawa Daisuke, Hirama Junji. Influence of contact condition between rails and wheels upon track circuit shunting (2nd Report, measuring methods and results of track circuit shunting resistance of running train's wheelset) [J]. Transactions of the Japan Society of Mechanical Engineers. PartC,2002.68(672):2402-2409.
[53]Wakabayashi Yusuke, Daisuke Nakagawa, Tomoya Kitagawa, Junji Hirama, Kazuhiko Nagase. Influence of contact condition between rails and wheels upon track circuit shunting (3rd report, electric resonance phenomena by track circuit shunting of running train's wheelset) [J]. Transactions of the Japan Society of Mechanical Engineers, Part C,2002.68(674):3023-3028.
[54]Hirama Junji, Yusuke Wakabayashi, Tomoya Kitagawa, Kazuhiko Nagase. Influence of contact condition between rails and wheels upon track circuit shunting (4th report, result of continuously measured shunting resistance of the running wheelsets) [J]. Transactions of the Japan Society of Mechanical Engineers, Part C,2005.71(4):1263-1268.
[55]Lewis R., J. Masing. Static wheel/rail contact isolation due to track contamination[J]. Proceedings of the Institution of Mechanical Engineers Part F-Journal of Rail and Rapid Transit, 2006.220(1):43-53.
[56]Arias-Cuevas O., Z. Li, R. Lewis. Investigating the lubricity and electrical insulation caused by sanding in dry wheel-rail contacts[J]. Tribology Letters,2010.37(3):623-635.
[57]Millar A. H., A. Lindsay. Developments in track circuit condition monitoring[C].4th IET International Conference on Railway Condition Monitoring(ICRCM).2008, Derby, United kingdom: Institution of Engineering and Technology,2008:1-6.
[58]Weston P. F., J. Chen, E. Stewart, C. Roberts. Condition monitoring of audio frequency track circuits[C].IET International Conference on Railway Engineering(ICRE),2008. Hong Kong, China:Institution of Engineering and Technology,2008:129-134.
[59]Patra A. P., U. Kumar, P. O. L. Kraik. Availability target of the railway infrastructure:an analysis[C]. The Proceeding of Reliability and Maintainability Symposium (RAMS),2010 San Jose. 2010:1-6.
[60]Patra A. P., U. Kumar. Availability analysis of railway track circuits[C]. Proceedings of the Institution of Mechanical Engineers, Part F:Journal of Rail and Rapid Transit.2010. London. Professional Engineering Publishing Ltd.2010.224(F3):169-177.
[61]高金吉.机器故障诊治与自愈化[M].北京：高等教育出版社.2012：1-60.
[62]高金吉.锋芒初露的设备诊断工程[J].中国科学技术前沿(中国工程院版)第六卷.北京：高等教育出版社.2003.263-299.
[63]张炜,张玉祥.导弹动力系统故障机理分析与诊断技术[M].西北工业大学出版社.2006：5-19.
[64]黄采伦,樊晓平,陈特放.列车故障在线诊断技术及应用[M].北京：国防工业出版社.2006：1-22.
[65]Venkatasubramanian Venkat, Raghunathan Rengaswamy, Kewen Yin, Surya N. Kavuri. A review of process fault detection and diagnosis:Part Ⅰ:Quantitative model-based methods[J]. Computers & Chemical Engineering,2003.27(3):293-311.
[66]Venkatasubramanian Venkat, Raghunathan Rengaswamy, Surya N. Kavuri, Kewen Yin. A review of process fault detection and diagnosis:Part Ⅲ:Process history based methods[J]. Computers & Chemical Engineering,2003.27(3):327-346.
[67]Venkatasubramanian Venkat, Raghunathan Rengaswamy, Surya N. Kavuri. A review of process fault detection and diagnosis:Part Ⅱ:Qualitative models and search strategies[J]. Computers & Chemical Engineering,2003.27(3):313-326.
[68]Yang Qingsong. Model-based and data driven fault diagnosis methods with applications to process monitoring[D], Ohio, Case Western Reserve University.2004:1-17.
[69]Jardine Andrew K. S., Darning Lin, Dragan Banjevic. A review on machinery diagnostics and prognostics implementing condition-based maintenance[J]. Mechanical Systems and Signal Processing,2006.20(7):1483-1510.
[70]Ribeiro L., J. Barata. Re-thinking diagnosis for future automation systems:An analysis of current diagnostic practices and their applicability in emerging IT based production paradigms[J]. Computers in Industry,2011.62(7):639-659.
[71]Barlow Richard, Larry Hunter. Optimum preventive maintenance policies[J]. Operations Research,1960.8(1):90-100.
[72]Thurston M Lebold M. Open standards for condition-based maintenance and prognostic systems[C].5th Annual Maintenance and Reliability Conference(MARCON). Gatlinburg.2001.
[73]Lebold Mitchell S., Karl M. Reichard, Daniel Ferullo, David Boylan. Open system architecture for condition-based maintenance overview and training material[R]. The Pennsylvania State University.2003.
[74]Zhang S. N., R. Kang, X. F. He, M. G. Pecht. China's efforts in prognostics and health management[C]. IEEE Transactions on Components and Packaging Technologies,2008.31(2): 509-518.
[75]Thatoi D. N., H. C. Das, D. R. Parhi. Review of techniques for fault diagnosis in damaged structure and engineering system[J]. Advances in Mechanical Engineering,2012:1-11.
[76]李晗,萧德云.基于数据驱动的故障诊断方法综述[J].控制与决策.2011.26(1)：1-9.
[77]Djuric Natasa, Vojislav Novakovic. Review of possibilities and necessities for building lifetime commissioning[J]. Renewable and Sustainable Energy Reviews,2009.13(2):486-492.
[78]周东华,李钢,李元著.数据驱动的工业过程故障诊断技术—基于主元分析与偏最小二乘的方法[M].北京：科学出版社2011:1-11.
[79]Jurgen Schmidhuber. Deep Learning in Neural Networks:An Overview[R].University of Lugano & SUPSI. Switzerland.2014:1-70.
[80]Henley Ernest J, Hiromitsu Kumamoto. Reliability engineering and risk assessmen[J]. Prentice-Hall Englewood Cliffs (NJ).1981:45-198.
[81]Pumfrey David John. The principled design of computer system safety analyses[D]. York,University of York,1999:1-23.
[82]Iri Masao, Katsuaki Aoki, Eiji O'shima, H Matsuyama. An algorithm for diagnosis of system failures in the chemical process[J]. Computers & Chemical Engineering,1979.3(1):489-493.
[83]Maurya Mano Ram, Praveen K. Paritosh, Raghunathan Rengaswamy, Venkat Venkatasubramanian. A framework for on-line trend extraction and fault diagnosis[J]. Engineering Applications of Artificial Intelligence,2010.23(6):950-960.
[84]Maurya M. R., R. Rengaswamy, V. Venkatasubramanian. A signed directed graph and qualitative trend analysis-based framework for incipient fault diagnosis[J]. Chemical Engineering Research & Design,2007.85(A10):1407-1422.
[85]Maurya M., R. Rengaswamy, V. Venkatasubramanian. Fault diagnosis using dynamic trend analysis:A review and recent developments[J]. Engineering Applications of Artificial Intelligence, 2007.20(2):133-146.
[86]Maurya Mano Ram, Raghunathan Rengaswamy, Venkat Venkatasubramanian. A Systematic Framework for the Development and Analysis of Signed Digraphs for Chemical Processes.2. Control Loops and Flowsheet Analysis[J]. Industrial & Engineering Chemistry Research,2003.42(20):4811-4827.
[87]张贝克,张海洋,马听.定性趋势分析在过程故障诊断中的应用研究[J].系统仿真学报.2008.28(10)：2750-2754.
[88]张海洋,张贝克,吴重光.用于监测复杂系统的计算机辅助定性趋势分析[J].计算机工程与应用.2007.43(17)：41-45.
[89]Dash Sourabh, Raghunathan Rengaswamy, Venkat Venkatasubramanian. Fuzzy-logic based trend classification for fault diagnosis of chemical processes[J]. Computers & Chemical Engineering,2003.27(3):347-362.
[90]Dash S., M. R. Maurya, V. Venkatasubramanian, R. Rengaswamy. A novel interval-halving framework for automated identification of process trends[J]. Aiche Journal,2004.50(1):149-162.
[91]Dash S., M. R. Maurya, V. Venkatasubramanian, R. Rengaswamy. A Novel Interval-Halving Framework For Automated Identification of Process Trends Extended Version[R]. 2003:1-83.
[92]Smola Alex, S.V.N. Vishwanathan. Introduction to Machine Learning[M]. Cambridge: Cambridge University Press 2010:1-36.
[93]Cortes Corinna, Vladimir Vapnik. Support-vector networks. Machine learning[J],1995. 20(3):273-297.
[94]Boser Bernhard E, Isabelle M Guyon, Vladimir N Vapnik. A training algorithm for optimal margin classifiers[C].Proceedings of the fifth annual workshop on Computational learning theory. 1992:144-152.
[95]Shawe-Taylor J., S. L. Sun. A review of optimization methodologies in support vector machines[J]. Neurocomputing,2011.74(17):3609-3618.
[96]Luts Jan, Fabian Ojeda, Raf Van De Plas, Bart De Moor, Sabine Van Huffel, Johan A. K. Suykens. A tutorial on support vector machine-based methods for classification problems in chemometrics[J]. Analytica Chimica Acta,2010.665(2):129-145.
[97]Zinzen R. P., C. Girardot, J. Gagneur, M. Braun, E. E. M. Furlong. Combinatorial binding predicts spatio-temporal cis-regulatory activity[J]. Nature,2009.462(7269):65-72.
[98]Marquez F. P. G., I. P. Garcia-Pardo. Principal Component Analysis applied to filtered signals for maintenance management[J]. Quality and Reliability Engineering International,2010. 26(6):523-527.
[99]Efron Bradley. Bayes'Theorem in the twenty-first century[J]. Science.2013.340(6137): 1177-1178.
[100]Salem Ab, L Bouillaut, P Aknin, P Weber. Dynamic Bayesian Networks for classification of rail defects[J].2004:353-370.
[101]Bouillaut Laurent, Weber P, Salem A.B, Aknin P. Use of causal probabilistic networks for the improvement of the maintenance of railway infrastructure[C]. IEEE International Conference on Systems, Man and Cybernetics(ICSMC),2004. The Hague, Netherlands:Institute of Electrical and Electronics Engineers Inc.2004:6243-6249.
[102]褚福磊.机械故障诊断中的现代信号处理方法[M].科学出版社.2009：1-13.
[103]Shin K, Jk Hammond, Pr White. Iterative SVD method for noise reduction of low-dimensional chaotic time series. Mechanical Systems and Signal Processing. [J] 1999.13(1): 115-124.
[104]Wang Wj, Zt Wu, J Chen. Fault identification in rotating machinery using the correlation dimension and bispectra[J]. Nonlinear Dynamics,2001.25(4):383-393.
[105]Feng Zhipeng, Ming Liang, Fulei Chu. Recent advances in time-frequency analysis methods for machinery fault diagnosis:A review with application examples. Mechanical Systems and Signal Processing[J].2013.38(1):165-205.
[106]Jin Yu, Xifeng Zheng, Tiefu Ding. A high-accuracy parameter estimation algorithm for jointless Frequency-shift track circuit[C]. Guangzhou.2008, International Colloquium on Computing, Communication, Control, and Management(ICCCM).2008.(1):750-753.
[107]Zhao Linhai, Zhankui Li, Weining Liu. The compensation capacitors fault detection method of jointless track circuit based on DBWT and WR[C]. IEEE International Conference on Intelligent Computing and Intelligent Systems(ICIS).2009. Shanghai, China:IEEE Computer Society.2009:875-879.
[108]Oukhellou L., P. Aknin, E. Delechelle. Railway infrastructure system diagnosis using empirical mode decomposition and Hilbert transform[C]. IEEE International Conference on Acoustics, Speech and Signal Processing.2006. Toulouse.2006.1-13:3615-3618.
[109]张腾飞,王锡淮,叶银忠,肖健梅.粗糙集理论在故障诊断中的应用综述[J].上海海事大学学报.2005,26(4)：20-28.
[110]李华莹,刘建敏,乔新勇,李晓磊.基于AGA-RS的故障特征参数提取方法研究.计算机工程与应用[J].2014.50(5)：257-260.
[111]Buchla D.M.,弗洛伊德著,施惠琼,夏琳译.电路分析基础[M].北京：清华大学出版社.2006：223-276.
[112]胡永生.轨道电路分路不良整治方案研究[J].铁道通信信号.2008.44(5)：24-26.
[113]徐木根,陈辛怡.对轨道电路分路不良安全风险控制的体会与建议[J].铁道通信信号.2013.49(6)：13-15.
[114]Holm R., E. Holm. Electric contacts:theory and application[M]. Vol.9:Springer-Verlag New York.1967:23-67.
[115]Persson B. N. J. Contact mechanics for layered materials with randomly rough surfaces[J]. Journal of Physics-Condensed Matter,2012.24(9):33-42.
[116]瓦伦丁L.波波夫著,李强译.接触力学与摩擦学的原理及其应用[M].北京：清华大学出版社.2011：1-73.
[117]Greenwood J A. Constriction resistance and the real area of contact[J]. British Journal of Applied Physics,1966.17(12):1621-1632.
[518]Godet Maurice. The third-body approach:A mechanical view of wear[J]. Wear,1984. 100(1-3):437-452.
[119]Berthier Y., S. Descartes, M. Busquet, E. Niccolini, C. Desrayaud, L. Baillet, M. C. Baietto-Dubourg. The role and effects of the third body in the wheel-rail interaction[J]. Fatigue & Fracture of Engineering Materials & Structures,2004.27(5):423-436.
[120]Sawada Shigeru, Kaori Shimizu, Shigeki Shimada, Yasuhiro Hattori. Prediction of Electrical Contact Resistance of Tin-Plated and Silver-Plated Terminals [J]. SEI Technical Review, 2010. (71):37-43.
[121]Bucher F., A. I. Dmitriev, M. Ertz, K. Knothe, V. L. Popov, S. G. Psakhie, E. V. Shilko. Multiscale simulation of dry friction in wheel/rail contact[J]. Wear,2006.261(7-8):874-884.
[122]肖乾,林凤涛,王成国.变摩擦系数条件下的轮轨滚动接触特性分析[J].铁道学报.2012.34(6)：24-28.
[123]温诗铸,黄平.摩擦学原理(下)[M].第二版.北京：清华大学出版社.2002：286-300.
[124]Railways. International Union Of. UIC5 10-5 Technical Approval of Solid Wheels[S]. Paris:International Union of Railways,2003.
[125]神圣,张军,孙传喜.磨耗状态下机车车轮与曲线钢轨的接触分析[J].铁道学报.2012.34(6)：15-19.
[126]金学松,沈志云.轮轨濡滑理论及其试验研究[D].成都：西南交通大学出版社.2006：9-69.
[127]Braunovic Milenko, Valery V. Konchits, Nikolai K. Myshkin. Electrical Contacts: Fundamentals、Applications and technology[M]. Newyork:CRC Press.2006:1-33.
[128]Cristianini Nello, John Shawe-Taylor. An Introduction to Support Vector Machines and Other Kernel-based Learning Methods[M]. Cambridge:Cambridge University Press.2003:73-105.
[129]Sanchez A V. David. Advanced support vector machines and kernel methods[J]. Neurocomputing,2003.55(1-2):5-20.
[130]Weston Jason, Chris Watkins. Multi-class support vector machines[R]. Citeseer, 1998:1-10
[131]Dietterich Thomas G., Ghulum Bakiri. Solving multiclass learning problems via error-correcting output codes[J]. Journal of Artificial Intelligence Research,1995.(2):263-286.
[132]Zadrozny Bianca, Charles Elkan, Transforming classifier scores into accurate multiclass probability estimates[C]. in Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining. ACM:Edmonton, Alberta, Canada.2002:694-699.
[133]Hsu Chih-Wei, Chih-Jen Lin. A comparison of methods for multiclass support vector machines[J]. IEEE Transactions on Neural Networks.2002.13(2):415-425.
[134]Rifkin Ryan, Aldebaro Klautau. In defense of One-Vs-All classification[J]. J. Mach. Learn. Res.,2004.5:101-141.
[135]Platt John. Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods[J]. Advances in large margin classifiers.1999.10(3):61-74.
[136]Wahba Grace. Support vector machines, reproducing kernel Hilbert spaces and the randomized GACV[J]. Advances in Kernel Methods-Support Vector Learning,1999.6:69-87.
[137]杜京义,候媛彬.基于最小风险的SVM及其在故障诊断中的应用[J].振动、测试与诊断.2006.26(2)：108-111.
[138]Bradley Ralph Allan, Milton E Terry. Rank analysis of incomplete block designs:I. The method of paired comparisons[J]. Biometrika,1952.42(3-4):324-345.
[139]Caron Francois, Doucet Arnaud, Efficient bayesian inference for generalized Bradley-Terry models[J]. Journal of Computational and Graphical Statistics.2012.21(1):174-196.
[140]Long Xi, W. Louis Cleveland, Y. Lawrence Yao. Multiclass cell detection in bright field images of cell mixtures with ECOC probability estimation. Image and Vision Computing[J].2008. 26(4):578-591.
[141]金向阳.基于振动样本民航发动机故障诊断方法及应用研究[D].哈尔滨：哈尔滨工业大学2012：68-85.
[142]Widodo A., B. S. Yang. Support vector machine in machine condition monitoring and fault diagnosis[J]. Mechanical Systems and Signal Processing,2007,21(6):2560-2574.
[143]Yang Bo-Suk, Tian Han, Won-Woo Hwang. Fault diagnosis of rotating machinery based on multi-class support vector machines[J]. Journal of Mechanical Science and Technology,2005. 19(3):846-859.
[144]Huang Ne, Z Shen, Sr Long, Me Wu, Hh Shih, Q Zheng, Nc Yen, Cc Tung, Hh Liu. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings:Mathematical, Physical and Engineering Sciences,1998.454(1971): 903-995.
[145]Wu Zhaohua, Norden E Huang. Ensemble empirical mode decomposition:a noise-assisted data analysis method[J]. Advances in Adaptive Data Analysis,2009. 1(01):1-41.
[146]Takens F. Detecting strange attractors in turbulence[J]. Dynamical systems and turbulence, Warwick 1980,1981:366-381.
[147]Packard N. H., J. P. Crutchfield, J. D. Farmer, R. S. Shaw. Geometry from a Time Series[J]. Physical Review Letters,1980.45(9):712-716.
[148]Jiang Ai-Hua, Xiu-Chang Huang, Zhen-Hua Zhang, Jun Li, Zhi-Yi Zhang, Hong-Xin Hua. Mutual information algorithms[J]. Mechanical Systems and Signal Processing,2010.24(8): 2947-2960.
[149]Andrew R. Sloboda. Parametric variation identification techniques in nonlinear dynamical systems[D]. Michigan:University of Michigan.2013:37-96.
[150]Zhongyuan Su, Yaoming Zhang, Minping Jia, Feiyun Xu, Jianzhong Hu. Gear fault identification and classification of singular value decomposition based on Hilbert-Huang transform[J]. Journal of Mechanical Science and Technology.25(2):267-272.
[151]Lin-Hai Zhao, Wu Jian-Ping, Ran Yi-Kui. Fault diagnosis for track circuit using AOK-TFRs and AGA[J]. Control Engineering Practice,2012.20(12):1270-1280.