摘要
我国是一个幅员辽阔、山区铁路众多的发展中国家，摆式列车技术的应用具有巨大的潜力。倾摆控制系统是摆式列车的核心部分，其可靠性对列车的安全运行至关重要，故障诊断技术为提高系统的可靠性开辟了一条新的途径。论文结合铁道部科技开发项目：“摆式列车倾摆控制系统的研制”，对摆式列车倾摆控制系统的故障诊断进行了探索性研究。
摆式列车倾摆控制系统是一个复杂的、具有诸多不确定性因素的动态系统，采用常规的故障诊断方法很难达到有效的诊断。神经网络作为一种新的方法和手段，已被广泛地应用于诸多领域的故障诊断中，但其在机车车辆故障诊断中的应用少有报道。论文在国内首次系统地将神经网络引入摆式列车倾摆控制系统的故障诊断中，从工程应用的角度深入研究了基于神经网络的故障诊断理论，探讨了其在摆式列车倾摆控制系统设计中的应用问题。
论文的主要创新成果有：
(1)在摆式列车实际运行中，检测子系统的加速度传感器存在严重零偏，使用硬件冗余法进行故障诊断的设计初衷面临着巨大的困难。论文采用RBF神经网络构成传感器输出预测器，通过检测预测值与实际值之差来在线检测故障。对每个加速度传感器构造输出预测器，然后通过一复合故障决策策略来实现多传感器故障的同时诊断，该方法不仅消除了零偏对故障诊断的影响，而且提高了故障检测率及可靠性。
(2)根据检测子系统采用双冗余陀螺仪的实际情况，利用自适应噪声消除器的基本原理构造了双余度传感器的故障诊断模型，给出了双余度传感器的故障诊断原理和递推算法，实现了双冗余陀螺仪的故障诊断。
(3)作动子系统是一个复杂的非线性系统，其故障存在模糊性和相关性。论文将模糊逻辑和神经网络结合在一起，给出了模糊BP神经网络的结构、隶属度函数确定方法，并提出了基于阈值原则的故障判别方法，用模糊神经网络对作动子系统的常见故障进行了诊断。
(4)针对小波基的选择缺乏完善理论指导的实际情况，通过对常用的正交、半正交、双正交小波基提取信号特性的比较，确定出了适合摆式列车倾摆控制系统故障诊断的小波基——半正交小波基，并提出了一种新的确定故障检测阈值的方法，可以快速地检测出故障发生时刻。
(5)将小波分析技术与神经网络技术相结合，形成广义上的小波神经网
西南交通大学博士研究生学位论文 第！I页
络，提出了一种基于小波包预处理的神经网络故障诊断方法。利用小波包分
析，将摆式车体试验台上采集到的振动加速度信号分解在相互独立的频带之
p
内，各频带内的能量值形成一个向量，将其作为神经网络的输入特征向量，＼。
然后用神经网络对摆式列车倾摆控制系统的常见故障进行了识别和诊断。
实验和研究结果表明，论文提出的基于神经网络的摆式列车倾摆控制
系统故障诊断方法在理论上是可行的，在工程上也是可实现的。采用神经网
络理论诊断摆式列车倾摆控制系统故障，为我国的机车车辆尤其是高速列车
的故障检测和诊断指出了新的研究方向，论文的研究结果对摆式列车倾摆控
制系统的设计具有理论指导意义。
The tilting train is a way of high-speed railways suiting for the situation of
our railways and country, which has great economic potential. The tilting colltrol
system is the key technique of tilting train, whose safety is very important for
tilting train to transport normally. Fault diagnosis technology has provided a new
means to enhance the reliability of system. Fault diagnosis of tilting control
system in tilting train is discussed in this thesis, which is the main substance of
developing the tilting control system supported by the R&D Program of Ministry
of Railways of China.
Considering the fact that the tilting control system of tilting train is working
in quite an uncertain environment, a conventional fault diagnosis method is hard
to perfOrm effectively. Neural network has been widely used in fault diagnosis in
many fields as a novel method or measure. However, there are very few
published studies dealing in neural network used in fault diagnosis of the
locomotive and rolling stock. Neural network has been systematically introduced
into fault diagnosis of tilting contro1 system in tilting train for the first time in
our country by this thesis. Fault diagnosis theory based on neural network is
studied in detail. Some practical issues of the tilting control system design are
addressed by applying neural network.
The main contributions are as follows.
(1) In view of practice that the data obtained from accelerometer has serious
zero deviation, it is very difficult to diagnosis fault by hardware redundant. A
fault diagnosis scheme for multi-accelerometers employing predictor based on
radial basis function (RBF) neural network is proposed. The strategy eliminates
the disturbance with zero deviation and improves the reliability of fault
diagnosis.
(2) In the light of reality adopting double redundant gyroscope, the fault
diagnosis model for double redundant sensors taking the basic principle of
adaptive noise cleaner is established. The diagnosis method, recurrence algorithm
and implement are given.
(3) On the basis of the fuzzy property and correlation characteristics existing
in the fault of tilting driving subsystem, several typical faults in tilting driving
system are analyzed and identified with the fiizzy neural network (FNN). The structure of FNN and the membership function are given. Meanwhile a fault discriminate method for threshold vector is addressed.
(4) Since there is no perfect theoretical guide, the characteristics of orthogonal wavelet, semi-orthogonal wavelet and biorthogonal wavelet in signal decomposition and reconstruction are compared, and the conclusion of the study demonstrates that semi-orthogonal wavelet is a good wavelet for fault diagnosis in tilting control system of tilting train. A new approach is presented for deciding the fault threshold.
(5) A generalized wavelet neural network is put forward by integrating wavelet analysis with neural network. A fault diagnosis method using wavelet packet as its pretreatment is proposed. The method using wavelet packet analysis is proposed to extract fault information from vibration signal obtained from testing jig of tilting train. The vector comprised of the energy of signal in all spectrum bands is input to a feed forward neural network. The trained neural network can explore the typical faults of tilting control system.
Trial and research show that the fault diagnosis method based on neural network is practicable in terms of theory. A direction to set up the fault diagnosis of the locomotive and rolling stock, especially, high-speed train by means of neural network is pointed out. The research results in this thesis lay the theoretical foundation of fault diagnosis in tilting control system of the first tilting train of our country.
引文
[1]严隽耄．摆式列车的发展和应用．国内外摆式列车文集．成都：西南交通大学出版社，1998
[2]李芾．国外摆式列车发展和运用概况．西南交通大学学报．2000，35(6)：569～575
[3]Thomas Nilsson. High speed tilting trains for the future. 铁道部摆式列车技术研讨会会议资料(Adtranz 摆式列车), 1998
[4]Bo Marklund. How to achieve high speed with low investments in infrastructure and reducing capital cost in rolling stock. 铁道部摆式列车技术研讨会会议资料(Adtranz 摆式列车), 1998
[5]Evert Anderson. Introduction to tilting train technology. 铁道部摆式列车技术研讨会会议资料(Adtranz 摆式列车), 1998
[6]Casini C著，李亚斌译，意大利摆式列车的开发．国外铁道车辆．1997，34(5)：38～45
[7]Anderson E, Bahr H V and Nilstam N G. Allowing higher speeds on existing tracks-design consideration of the X2000 train for Swedish State Railways. Proceedings of the Institution of Mechanical Engineers (Part F, Journal of Rail and Rapid Transit), 1995, 209(F2): 93～104
[8]傅小日，徐小平．瑞典X2000高速旅客列车．国外铁道车辆．1993，30(5)：1～6
[9]Roger Goodall. Active railway suspension: implementation status and technological trends. Vehicle System Dynamics. 1997, 28(1): 87～117
[10]杨名利．摆式列车控制系统的试验模拟及其鲁棒控制的研究．博士学位论文．成都：西南交通大学，1998
[11]戴小文．小波分析和DSP技术在摆式列车倾摆监视系统中的应用研究．博士学位论文．成都：西南交通大学，2000
[12]陆廷孝，郑鹏洲．可靠性设计与分析．北京：国防工业出版社，1995
[13]周东华，孙优贤．控制系统的故障检测与诊断技术．北京：清华大学出版社，1994
[14]严云升．现代高速列车的诊断系统，机车电传动，1995，(2)：1～6
[15]吴浩中，孙明昌，王开文．一种新的摆式列车倾摆控制系统的故障检测
方法．铁道车辆．2001，39(2)：12～15
[16]戴小文，钟桂英，吴浩中．小波变换在摆式列车倾摆系统故障诊断中的应用．西南交通大学学报．2000，35(6)：651～655
[17]周东华，Ding X.容错控制理论及其应用．自动化学报．2000，26(6)：788～797
[18]Isermann R and Balle P. Trends in the application of model based fault detection and diagnosis of technical processes. Proceedings of IFAC World Congress. San Francisco, USA, 1996, 1～12
[19]Frank P M. Fault diagnosis in dynamic systems using analytical and knowledge-based redundancy—a survey and some new results. Automatica. 1990, 26(3): 459～474
[20]张萍，王桂增，周东华．动态系统的故障诊断方法．控制理论与应用．2000，17(2)：153～158
[21]闻新，张洪钺，周露．控制系统的故障诊断和容错控制．北京：机械工业出版社，1998
[22]Ge W and Fang C Z. Detection of faulty components via robust observation. International Journal of Control. 1988, 47(2): 581～599
[23]Frank P M and Ding X. Survey of robust residual generation and evaluation methods in observer-based fault detection systems. Journal of Process Control. 1997, 7(6): 403～424
[24]Medvedev A. State estimation and fault detection by a bank of continuous finite-memory filters. International Journal of Control. 1998, 69(4): 499～517
[25]Wang H and Daley S. Actuator fault diagnosis: an adaptive observer-based technique. IEEE Transactions on Automatic Control. 1996, 41(7): 1073～1078
[26]Wang H, Huang Z J and Daley S. On the used of adaptive updating rules for actuator and sensor fault diagnosis. Automatica. 1997, 33(2): 217～225
[27]Chen J, Patton R J and Zhang H Y. Design of unknown input observers and robust fault detection filters. International Journal of Control, 1996, 63(1): 85～105
[28]吴浩中，戴小文，黄运华．基于UIO的摆式列车倾摆控制系统执行机构
的故障检测．西南交通大学学报．2000，35(6)：656～660
[29]陈金水，孙优贤．一种基于UIO观测器的故障检测方法．控制理论与应用．1997，14(1)：112～116
[30]Maria E V. State observers for discrete-time linear systems with unknown inputs. IEEE Transactions on Automatic Control. 1999, 44(2): 397～401
[31]Park S H, Kim D S, Kwon O -K, et al. Estimation and detection of unknown inputs using optimal FIR filter. Automatica. 2000, 36(10):1481～1488
[32]Vemuri A T and Polycarpou M M. Robust nonlinear fault diagnosis in input-output systems. International Journal of Control. 1997, 68(2): 343～360
[33]Kinnaert M. Robust fault detection based on observers for bilinear systems. Automatica. 1999, 35(11): 1829～1842
[34]Edwards C, Spurgeon S K and Patton R J. Slide mode observers for fault detection and isolation. Automatica. 2000, 36(2): 541～553
[35]Hwang D S, Chang S K and Hsu P L. A practical design for a robust fault detection and isolation system. International Journal of System Science. 1997, 28(3): 265～275
[36]Gertler J and Monajamy R. Generating directional residuals with dynamic parity relations. Automatica. 1995, 31(4): 627～635
[37]Kinneart M. Design of redundancy relations for failure detection and isolation by constrained optimization. International Journal of Control. 1996, 63(6): 609～622
[38]周东华．一种非线性系统的传感器故障检测与诊断新方法．自动化学报．1995，21(3)：362～365
[39]Yu D. Fault diagnosis for a hydraulic drive system using a parameterestimation method. Control Engineering Practice. 1997, 5(9): 1283～1291
[40]Isermann R. Fault diagnosis of machines via parameter estimation and knowledge processing—tutorial paper. Automatica. 1993, 29(4): 815 835
[41]Keller J Y and Darouach. Two-stage Kalman estimator with unknown exogenous inputs. Automatica. 1999, 35(2): 329～342
[42]周东华，叶银忠．现代故障诊断与容错控制．北京：清华大学出版社，2000
[43]Kumamaru K, Hu J, Inoue K and Soderstrom T. Robust fault detection using index of Kullback discrimination information. Proceedings of IFAC World Congress. San Francisco, USA, 1996, 205～210
[44]萧德云，李渭华，方崇智．一种适用于故障检测的归一化滑动窗协方差格形滤波器．控制理论与应用．1995，12(2)：230～235
[45]萧德云，李渭华．双通道自适应Lattice滤波器及其在故障检测中的应用．控制与决策．1998，13(3)：277～280
[46]Jiang F and Jia F. A robust fault diagnosis scheme based signal modal estimation. International Journal of Control. 1995, 62(2): 461～475
[47]Staszewski W J, Torlinson G R. Application of the wavelet transform to fault detection in a spur gear. Mechanical System and Signal Processing. 1994, 8(3): 289～307
[48]Wang W J, McFadden P D. Application of orthogonal wavelets to early gear damage detection. Mechanical System and Signal Processing. 1995, 9(5): 497～507
[49]Wang W J. Application of wavelets to gearbox vibration signals for fault detection. Journal of Sound and Vibration. 1996, 192(5): 927～939
[50]Satish L. Short-time fourier and wavelet transforms for fault detection in power transformers during impulse tests. IEE Proceedings of Science Measurement Technology. 1998, 145(2): 77-84
[51]Yen G G, Lim K C. Wavelet packet feature extraction for vibration monitoring. IEEE Transactions on Industrial Electronics. 2000, 47(3):650～667
[52]任震，黄群古，黄雯莹．两种小波变换方法及其在发电机故障信号分析中的应用．中国电机工程学报．2000，20(10)：59～63
[53]林京，屈梁生．基于连续小波变换的奇异性检测与故障诊断．振动工程学报．2000，13(4)：523～530
[54]荆双喜，孟国营，方佳雨．基于图形显示算法的小波变换在机械故障诊断中的应用研究．中国机械工程．2000，11(12)：1367～1369
[55]李宏亮，黄润华，朝国明等．谐波小波的时频特性分析及其在故障诊断中的应用．机械强度．2000，22(2)：81～85
[56]叶昊，王桂增，方崇智．小波变换在故障检测中的应用．自动化学报．1997，23(6)：736～741
[57]叶昊，王桂增，方崇智等．一种基于小波变换的导弹运输车辆故障诊断方法．自动化学报．1998，24(3)：301～306
[58]Mallat S and Hwang W L. Singularity detection and processing with wavelet. IEEE Transactions on Information Theory. 1992, 38(2): 617～643
[59]杨叔子，丁洪等．基于知识的诊断推理．北京：清华大学出版社，1993
[60]吴今培，肖健华．故障诊断专家系统的一种新设计方案．振动、测试与诊断．1996，16(4)：520～524
[61]王向周，王渝，白志大．电液伺服阀故障诊断专家系统的研究．北京理工大学学报．1997，17(3)：315～320
[62]Batanov D N and Cheng Z. An object-oriented expert system for fault diagnosis in the ethylene distillation process. Computers in Industry. 1995, 27(3): 237～249
[63]Maruyama N, Benouarets M and Dexter A L. Fuzzy model-based fault detection and diagnosis. Proceedings of IFAC World Congress.San Francisco, USA, 1996, 121～126
[64]Boudaoud A N, Masson M H and Dubuisson B. On-line diagnosis of a technological system: a fuzzy pattern recognition approach. Proceedings of IFAC World Congress. San Francisco, USA, 1996, 103～107
[65]Good P V and Chow M. Using a neural/fuzzy system to extract heuristic knowledge of incipient faults in induction motors. IEEE Transactions on Industrial Electronics. 1995, 42:131～145
[66]Chen S M. A fuzzy reasoning approach for rule-based systems based on fuzzy logic. IEEE Transactions on System, Man and Cybernetics—Part B. 1996, 26(5): 769～778
[67]廉小亲，王信义，朱小燕．故障诊断系统中的模糊推理算法的研究．北京理工大学学报．1996，16(1)：97～101
[68]虞和济，陈长征，张省等．基于神经网络的智能诊断．北京：冶金工业出版社，2000
[69]Venkat Venkatasubramanian, King Chan. A neural network methodology for process fault diagnosis. Journal of AIChE. 1989, 35(12): 1993～2002
[70]Kajior Watanable, et al. Incipient fault diagnosis of chemical process via artificial neural networks. Journal of AIChE. 1989, 35(11): 1803～1812
[71]Hoskins J C, Kaliyur K M and David M H. Fault diagnosis in complex
chemical plants using artificial neural networks. Journal of AIChE. 1991,37(1): 137～141
[72]陈岳东，屈梁生．神经网络在大型回转机械故障诊断中的应用．西安交通大学学报．1992，26(4)：53～56
[73]颜廷虎，钟秉林，黄仁．神经网络技术及其在旋转机械故障诊断中的应用．振动工程学报．1993，6(3)：205～211
[74]张小栋，朱均，丘大谋等．BP网络在200MW汽轮发电机组故障模糊诊断中的应用研究．振动、测试与诊断．1994，14(4)：23～30
[75]黄晓光，王永泓，翁史烈．基于BP算法的电站燃气机故障诊断．中国电机工程学报．2000，20(12)：72～74
[76]张义忠，冯振声．基于神经网络的复杂电子装备故障诊断系统．计算机工程与应用．2000，36(3)：159～161
[77]芮勇，金丕彦．基于人工神经网络的FMS物料搬运机器人的故障诊断．控制理论与应用．1994，11(4)：460～463
[78]Vemuri A T, Polycarpou M M. Neural-network-based robust fault diagnosis in robotic systems. IEEE Transactions on Neural Network. 1997, 8(6): 1410～1420
[79]胡寿松，汪晨曦．基于神经网络预测模型的歼击机结构故障检测方法．航空学报．2000，21(4)：355～357
[80]Naidu S R, Zafiriou E, et al. Use of neural networks for sensor failure detection in control system. IEEE Control System Magazine. 1990, 49(2): 225～231
[81]张炜，张优云，战仁军等．旋转机械故障诊断中的神经网络改进算法研究．振动工程学报．1996，9(1)：31～37
[82]陈长征，白秉三，虞和济．三层感知器算法的改进及其故障诊断中的应用．振动、测试与诊断．2000，20(1)：19～23
[83]Ergezinger S and Thomsen E. An accelerated learning algorithm for multilayer perceptron: optimization layer by layer. IEEE Transactions on Neural Network. 1995, 6(1): 31～42
[84]宋宜斌．多层感知器的一种快速网络训练法及其应用．控制与决策．2000，15(1)：125～127
[85]虞和济．机械设备故障诊断的人工神经网络识别法．机械强度．1995，17(2)：48～50
[86]胡凯成，孔凡让，李川奇．神经网络诊断模型的隐层压缩算法．振动工程学报．1997，10(3)：356～361
[87]杨建刚，戴德成，高wei等．改进BP网络在旋转机械故障诊断中的应用．振动工程学报．1995，8(4)：342～349
[88]Leonard J A and Kramer M A. Radial basis function networks for classifying process faults. IEEE Control Systems. 1991, 4(1): 31～38
[89]李捷辉．RBF神经网络用于发动机控制系统的故障诊断．江苏理工大学学报．1999，20(5)：36～39
[90]Wilson D J H, Irwin G W and Lightbody G. RBF principal manifolds for process monitoring. IEEE Transactions on Neural Network. 1999, 10(6): 1424～1434
[91]谭民，疏松桂．神经元网络在故障诊断中的双向联想记忆方法．自动化学报．1991，17(1)：95～99
[92]程鹏，钟芳源．BAM神经网络在热力参数故障诊断中的应用和模式编码方法的改进．电站系统工程．1995，11(3)：56～59
[93]钟敏，唐锡宽，张正松．自组织特征映射人工神经网络用于旋转机械故障诊断．振动、测试与诊断．1993，13(3)：52～57
[94]汪健，蒋东翔，倪维斗．模糊自组织神经网络在汽轮机转子故障诊断中的应用．热能动力工程．1998，13(1)：43～45
[95]Srinivasan A and Batur C. Hopfield/ART-1 neural network-based fault detection and isolation. IEEE Transactions on Neural Network. 1994, 5(6): 890～899
[96]张小栋，朱均，丘大谋．旋转机械故障诊断中的主从混合神经网络模型研究．振动工程学报．1996，9(3)：220～229
[97]姜惠兰，孙雅明．反馈式Hopfield神经网络在输电线路故障诊断中的应用．电力系统及其自动化学报．1999，11(1)：6～12
[98]张建华，王占林．基于模糊神经网络的故障诊断方法的研究．北京航空航天大学学报．1997，23(4)：502～506
[99]Zhang J, Morris A J and Martin E B. Robust process fault detection and diagnosis using neuro-fuzzy networks. Proceedings of IFAC World Congress. San Francisco, USA, 1996, 169～174
[100]Gomm J B. On-line learning for fault classification using an adaptive neuro-fuzzy network. Proceedings of IFAC World Congress. San
Francisco, USA, 1996, 175～180
[101]Patton R J, Chen J and Benkhedda. A study on neuro-fuzzy systems for fault diagnosis. International Journal of System Science. 2000, 31(11):1441～1448
[102]刘宜平，沈毅，刘志言．一种基于模糊神经网络的故障分类器及其在多传感器故障诊断中的应用．传感技术学报．2000，13(1)：38～43
[103]张苗苗，文敏，谢剑英．轴承故障的智能诊断方法．控制与决策．2000，15(4)：489～492
[104]陈耀武，汪乐宇．转子机械故障诊断仪器系统．中国电机工程学报．2000，20(12)：47～51
[105]沈国重，陈章位，方志宏等．基于小波变换预处理的一种神经网络故障诊断方法的研究．中国机械工程．1999，10(11)：1253～1255
[106]荆双喜，方佳雨，孟惠荣．小波包—神经网络在斜轴泵故障诊断中的应用研究．振动、测试与诊断．2000，20(2)：97～101
[107]吕柏权，李天铎．一种基于小波网络的故障诊断方法．控制理论与应用．1998，15(5)：802～805
[108]吕柏权，李天铎，吕崇德．一种非线性系统故障检测新方法．中国电机工程学报．1998，18(1)：19～21
[109]Bissessur Y, Martin E B, Morris A J and Kitson P. Fault detection in hot steel rolling using neural networks and multivariate statistics. IEE Proceedings—Control Theory and Applications. 2000, 147(6): 633～640
[110]胡守仁，余少波，戴葵．神经网络导论．长沙：国防科技大学出版社，1993
[111]沈清，胡德文，时春．神经网络应用技术．长沙：国防科技大学出版社，1993
[112]靳蕃，范俊波，谭永东．神经网络与神经计算机原理·应用．成都：西南交通大学出版社，1991
[113]阎平凡，张长水．人工神经网络与模拟进化计算．北京：清华大学出版社，2000
[114]Nielson R H. Theory of the back propagation neural network. Proceedings of IJCNN. 1989, 1:2593～2605
[115]Reed R. Pruning algorithm—a survey. IEEE Transactions on Neural Network. 1993, 4(): 740～747
[116] Setiono R. A penalty function approach for pruning feedforward NN. Neural Computation. 1997, 9 (): 185--204
[117] Castellano G, et al. An iterative pruning algorithm for feedforward NN. IEEE Transactions on Neural Network. 1997, 8(3) : 519--531
[118] Marchand M, et al. A convergence theorem for sequential learning in two layered perceptron. Europhysics Letters. 1990, 11: 487--492
[119] Frean M. The upstart algorithm. Neural Computation. 1990, 2: 198--209
[120] Mezard M, et al. Learning in feedforward layered network, the tiling algorithm. Journal of Physics A. 1989, 22: 2191--2204
[121] Littmann E, et al. Learning and generalization in cascade network architectures. Neural Computation. 1996, 8: 1521--1539
[122] Huang J, et al. The cascade-correlation learning, a projection pursuit learning perspective. IEEE Transactions on Neural Network. 1996, 7 (2) : 278-289
[123] Platt J. A resource-allocating network for function interpolation. Neural Computation. 1991, 3: 213--225
[124] Moody JO, et al. The dependence identification NN construction algorithm. IEEE Transactions on Neural Network. 1996, 7 (1) : 3--15
[125] 应行仁.三层神经网络隐单元与样本记忆的关系.模式识别与人工智能 . 1993, 3(1) : 29-30
[126] Sarkav D. Methods to speed up error BP learning algorithm. ACM Computing Survey. 1995, 27: 519--592
[127] Jacobs R A. Increased rates of convergence through learning rate adaptation. Neural Networks. 1998, 1 (4) : 295--307
[128] Battit R. First and second order methods for learning: between steepest descent and Newton' s method. Neural Computation. 1992, 4: 141--166
[129] Moller M F. A scaled conjugate gradient algorithm for fast supervised learning. Neural Computation. 1993, 6: 525--533
[130] Yao X. Evolving artificial neural networks. Proceedings of IEEE. 1999, 87(5) : 1423-1447
[131] Yao X, et al. A new evolving system for evolving artificial neural networks. IEEE Transactions on Neural Network. 1997, 8(2) : 697--713
[132]高小榕，杨福生．采用同伦BP算法进行多层前向神经网络的训练．计算机学报．1996，19(9)：687～694
[133]边肇祺等．模式识别(第二版)．北京：清华大学出版社，2000
[134]Musaoi M T, et al. On the training of RBF classifiers. Neural Networks. 1992, 5: 595～603
[135]Chen S, et al. Orthogonal least square learning algorithm for RBF networks. IEEE Transactions on Neural Network. 1991, 2():302～309
[136]Orr M J. Regularization in the selection of RBF centers. Neural Computation. 1995, 7:606～623
[137]Freenan J A and David S. On line learning in RBF network. Neural Computation. 1997, 9(7): 1601～1622
[138]Lu Y, et al. A sequential learning scheme for function approximation using minimal RBF NN. Neural Computation. 1997, 9(2): 461～478
[139]Gomm J B and Ding L Y. Selecting radial basis function networks centers with recursive orthogonal least square training. IEEE Transactions on Neural Network. 2000, 11(2): 306～314
[140]Park J, et al. Approximation and RBF networks. Neural Computation.1993, 50: 305～316
[141]Pal S K and Mitra S. Multilayer perceptron, fuzzy sets and classification. IEEE Transactions on Neural Network. 1992, 3(5). 683～697
[142]Kuo Y H, Kao C I and Chen J J. A fuzzy neural networks model and its hardware implementation. IEEE Transactions on Fuzzy Systems. 1993,1(3): 171～183
[143]Ronald R Y. Modeling and formulating fuzzy knowledge bases using neural networks. Neural Networks. 1994, 7(8): 1273～1283
[144]Mitra S, De R K and Pal S K. Knowledge-based fuzzy MLP for classification and rule generation. IEEE Transactions on Neural Network. 1997, 8(6): 1338～1349
[145]罗发龙，李衍达．神经网络信号处理．北京：电子工业出版社，1993
[146]Kawamura A, Watanable N, Okada H, et al. A prototype of neuro-fuzzy cooperation system. IEEE Fuzzy' 92:1275～1282
[147]钮永胜，赵新民，孙金玮．采用基于神经网络的时间序列预测器的
传感器故障诊断新方法．仪器仪表学报．1998，19(4)：383～387
[148]孟晓风，王行仁．双余度传感器的故障检测与识别．自动化学报．1996，22(4)：393～400
[149]吴浩中，戴小文，王开文．摆式列车用传感器的故障检测与识别．测控技术．2001，20(6)：19～21
[150]Marcello R N, Charles N, Van C, et al. Neural-network-based scheme for sensor failure detection, identification and accommodation. Journal of Guidance, Control and Dynamics. 1995, 18(6): 1280～1286
[151]Zhao X, Ye X and Zhang C. Artificial neural network for sensor failure detection in hovercraft engine. IEEE International Measurement and Test Conference. 1994, 1:167～170
[152]丁晖，刘君华，申忠如．基于径向基函数神经网络预测器的多传感器故障在线检测和信号恢复的研究．模式识别与人工智能．2000，13(4)：429～433
[153]Goodwin G and Sin K S. Adaptive filtering prediction and control. New Jersey: Prentice-Hall, 1994
[154]方崇智，萧德云，过程辨识．北京：清华大学出版社，1988
[155][美]崔锦泰著，程正兴译．小波分析导论．西安：西安交通大学出版社，1995
[156]荆双喜，方佳雨，孟惠荣．机械故障诊断中的小波基及算法研究．振动工程学报．2000，13(2)：290～294
[157]胡子谷，石来德．故障振动信号的小波包分解与诊断．振动与冲击．1998，17(2)：54～59