摘要
故障诊断是近年来发展起来的一门综合性的边缘学科，它涉及到的理论基础和技术手段十分广泛。随着科学技术和经济建设的发展，大型设备与控制系统的状态监测和故障诊断已成为保证系统运行稳定性、可靠性和安全性，提高产品质量和生产效率的关键技术和重要手段，并日益引起国内外学者的广泛重视。
轧机厚度自动控制系统(AGC)是现代板带轧机实现高精度轧制必不可少的关键环节。该系统是一复杂的综合控制系统，包括机械、液压、电气等方面的综合信息。因此，除了机械设备中所有可能发生的故障在该系统中都可能发生之外，厚控系统还具有液压系统特有的失效形式。故该系统的故障率较高且故障原因复杂，是维护轧机的重点和难点，也是造成故障停产和产品质量下降的主要原因。
本文就是基于此背景下所进行的研究工作，以某轧机厚控系统为对象，以故障诊断技术的实际应用为目的，主要开展了以下研究：
首先，筛选出了用于故障诊断的26种特征信号，并建立起信号的采集、处理和存储的状态监测系统；
然后，首次提出了包括从设备硬件到控制系统、直到最终产品检验三个层次的故障诊断策略；
其次，提出了基于轧机解折模型的故障诊断方案，建立了轧机厚控系统的数学模型，设计出了适合于该轧机厚控系统的故障检测观测器，实现了几类典型故障的检测与诊断；
提出了基于规则和案例的故障诊断方案，归纳出用于故障诊断具有代表性的18条规则和10个案例，并给出了具体的实现方法和步骤；
接着，基于神经网络的故障诊断思想，对该系统进行了功能上的分解，设计出了用于故障诊断的BP网络结构和参数，并就具体的应用实例进一步说明了基于神经网络诊断方法的可行性；
推导出了变刚度控制的控制模型，用仿真的方法对该模型进行了验证，并综合三个方面的效果，提出了变刚度的合理取值范围。然后，结合生产实践，在对轧机厚控系统机理分析的基础上，实现了对其控制系统几类典型故障的检测与诊断；
Condition Monitoring and Fault Diagnosis (CMFD), involved many theories and technical methods, is a comprehensive edge subject, which has been developed in recent years. Along with the development of sciences, technologies and economic, condition monitoring and fault diagnosis of large-scale equipments and their control systems have become an essential technology and important method to guarantee equipments or system to work stably, reliably and safely, to improve the product quality and the production efficiency. Now, CMFD is attached importance widely by many domestic and foreign scholars day by day.
Automatic gauge control (AGC) system is the key control system of strip rolling mills to realize high accuracy of strip exit thickness. AGC system is a complex integrated control system, including mechanical, hydraulic and electrical comprehensive information. As a result, not only faults in mechanical devices but also those in hydraulic system could happen possibly in the AGC system. Therefore, failure rate of AGC system always is high, and its fault reasons are always complex, which is the key and difficult point to maintain strip rolling mills, and is also the main reason causing strip rolling mills to break down and product quality to become poor.
Based on the study background described above, this dissertation focuses on the key technologies and methods of CMFD for the AGC system of a strip rolling mill. Taken the practical application as the goal, main work below has been studied:
First, we picked out 26 kinds of characteristic signals used in the fault diagnosis, and established a condition monitoring system of the strip rolling mill for signals gathering, processing and memory.
Then, the fault diagnosis idea including three levels, namely equipment hardware, control system and finished product, was proposed for the first time.
Next, the fault diagnosis idea based on system model was brought forward, and the mathematical model of AGC system in the strip rolling mill was established. Two suitable fault detection observers for this AGC system were designed, and several kinds of typical fault detection and diagnosis were realized.
The fault diagnosis idea based on rule and case was proposed. On the same time, 18 fault
引文
1．雷继尧，何世德．机械故障诊断基础知识[M]．西安：西安交通大学出版社，1989．
2．张雨，等．设备状态监测与故障诊断的理论与实践[M]．长沙：国防科技大学出版社，2000．
3. Frank P M, et al. New developments using AI in fault diagnosis [J]. Engineering Application of Artificial Intelligence. 1997, 10(1): 3-14.
4．钟秉林，黄仁．机械故障诊断学[M]．北京：机械工业出版社，1997．
5．黄文虎，等．设备故障诊断原理、技术及应用[M]．北京：科学出版社，1996．
6．徐章遂，等．故障信息诊断原理及应用[M]．北京：国防工业出版社，2001．
7．虞和济．故障诊断的基本原理[M]．北京：冶金工业出版社，1988．
8. Moubray J. Reliability-centered maintenance [M]. New York, New York USA: Industrial Press, 1991
9．吴今培．模糊诊断理论及其应用[M]．北京：科学出版社，1995．
10．周东华，王桂增．故障诊断技术综述[J]．化工自动化及仪表，1998，25(1)：58-62．
11. Beard R V. Failure Accommodation in Linear Systems through Self-reorganization. Dept. MIT-71-1, Man Vehicle Lab., Cambridge, MA, 1971.
12. Frank P M. Fault Diagnosis in Dynamic System Using Analytical and Knowledge Based Reduneancy-A Survey and Some New Results. Automatica, 1990, 26(3): 459-474.
13. Isermann R. Process Fault Detection Based on Modeling and Estimation Methods-A Survey. Automatica, 1984,20:387-404.
14. Massoumnia M A. A Geometric Approach to Failure Detection and Identification in Linear Systems. Ph.D.Thesis, MIT, Cambridge, MA, 1986.
15. Willskv A S. A Survey of Design Methods for Failure Detection in Dynamic System. Automation, 1976,12:601-611.
16. Ding X and Frank P M. Fault Detection via Factorization Approach. System and Control Letters, 1990,14(5): 431-436.
17. Dan T Horak. System Failure Isolation in Dynamic Systems. J. Guidance Novde, 1990: 1075-1082.
18. Dan T Horak. Failure Detection in Dynamic Systems with Modeling Errors. J.Guidance.Novdec, 1988:508-516.
19. Ding X, Guo L and Frank P M. Parajneterization of Linear Observers and Its Application??to Observer Design. IEEE Trans. on Automatic Control, 1994, 39(8): 1648-1652.
20. Ding X and Frank P M. On-line Fault Detection in Uncertain Systems Using Adaptive observers. European J. of Diagnosis andSafty in Automation, 1993, 2: 9-12.
21. Ding X and Guo L. Optimization of Observer-based Fault Detection Systems. Japan: Proc. of IFAC Sym. On SYSID97, 1997: 1201-1206.
22. Ding X and Guo L. On Observer Based Falult Detection. Proc. of IFAC Sym. on SAFEPROCESS97, 1997.
23. Aggarwal R K, Xuan Q Y and Johns A T. Fault Classification for Double-circuit Lines Using Self-organization MapPing Neural Network. Proc. 32~(nd) UPEC Sept.1997: 440-443.
24. Maruyama N, Benouarets M and DeXter A L. Fuzzy Model-Based Fault Detection and Diagnosis. Proc. of IFAC world Congress, San Francisco, USA, 1996: 121-126.
25. Frank P M. Application of Fuzzy Logic to Process SuPervision and Fault Diagnosis. Prerints of IFAC Sym. On Fault Detection. Supervision and Safly for Technical Process, 1994: 531-538.
26. Aggarwal R K, Xuan Q Y and Johns A T., et al. A Novel Approach to Fault Diagnosis in Multicircuit Transmission Lines Using Fuzzy ARTmap Neural Net~vorks. IEEE Trans. on Neural Networks, 1999: 10(5): 1214-1221.
27. Boudaoud A N, Masson M H and Dubusson B. On-line Diagnosis of A Technological System: A Fuzzy Pattern Recognition Approach. Proc.of IFAC World Congress, San Francisco, USA,1996:103-107.
28. Hibey J L and Charalambous C D. Conditional Densities for Continuous-time Nonlinear Hybrid Systems with Applications to Fault Detection. IEEE Trans.on A.C., 1998, 44(11): 2164-2169.
29. Zhou D H and Frank P M. Actuator Fanlt Diagnosis of A Class of Nonlinear Systems in Closed-loops: A Case Study. Proc. of UKACC Int. Conf., 1996:311-316.
30. Gareia A E and Frank P M. Detenninistic Noulinear Observer-based Approaches to Fault Diagnosis: A Survey. Control Engineering Practice, 1997,5(5):663-670.
31. Zhang Q, et al. Monitoring Nonlinear Dynamical Systems: A Combined Observer-based and Local Approach. Proc. IEEE CDC, 1998, 1: 1149-1154.
32．周东华，席裕庚，张钟俊．一类非线性系统参数偏差型故障的实时榆测与诊断[J]．自动化学报，1993，19(2)：184-189．33. Saludes S and Fuetlte M J. Neural-net-based Fault Detection and Acommodation in a chemical Reactor. IFAC 14th Triennial Worlrd congress, Beijing, China, 1999, 169-174.
34. Patton R J, Chen J and Siew T. Fault Diagnosis in Nonlinear Dynamic System via Neural Networks. Proc. of UKACC/IEE Int. Conf. CONTROL'1994, Coventry, UK, March 21-24, 1994, 2:1346-1351.
35. Timo S and Heikki N K. Application of Artificial Neural Networks in Process Fault Diagnosis. Automatica, 1993,29:843-849.
36. Menke T E and Maybeck P S. Sensor/Actuator Failure Detection in the Vista F-16 by Multiple Models Adaptive Estimation. IEEE trans, on Aero. and Elect. Syst., 1995, 31(4): 1218-1229.
37. Schneider H and Fran P M. Observer Based Supervision and Fault Detection for Robots. Int. Conf. on Fault Diagnosis Toulouse, 1993: 773-779.
38. Sorsa T and Koivo H N. Application of Artificial NeUral Networks in Process Fault Diagnosis. Automatica, 1993, 29(4): 843-849.
39．周鸣歧，徐军．控制系统故障诊断[J]．计算机自动测量与控制，2000，8(3)：5-8．
40．张萍，王柱增，周东华．动态系统的故障诊断方法[J]．控制理论与应用，2000，17(2)：153-158．
41．张登峰，王执铨，孙金生．控制系统故障诊断的理论与技术[J]．数据采集与处理，2002，17(3)：293-299．
42．张洪钺，闻新，周露．国内控制系统故障诊断技术的现状与展望[J]．火力与指挥控制，1997，22(161)：1-6．
43．叶昊，王桂增，方崇智．小波变换在故障检测中的应用[J]．自动化学报，1997，23(6)：736-741．
44．叶吴，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[J]．自动化学报，1998，24(3)：301-306．
45. Schneider H and Frank P M. Observer based supervision and fault detection for robots [C]. International Conference on Fault Diagnosis Toulouse, 1993: 773-779.
46. Ding S X and Jeinsch T. Application of observer based FDI schemes to the three-tank system [C]. Proc. of European Control Conference, Karlsruhe, Germang, 1999.
47. Yu D and Shields D N. A bilinear fault detection observer [J]. Automatica, 1996, 32(11): 1597-1602.
48. Yu D. Fault diagnosis for a hydraulic drive system using a parameter-estimation method??[J]. Control Engineering Practice, 1997, 5(9): 1283-1291.
49. Gertler J and Costin M. Model-based diagnosis of automotive engines-Case study on a physical vehicle [Z]. Preprints of IFAC Symposium on Fault Detection, Supervision and Safety for Technical Process, 1994, 421-430.
50. Isermann R. Fault diagnosis of machines via parameter estimation and knowledge processing-tutorial paper [J]. Automatica, 1993, 29(4): 815-835.
51．张建华，王占林．基于模糊神经网络的故障诊断方法的研究[J]．北京航空航天大学学报，1997，23(4)：502-506．
52. Maruyama N, Benouarets M and Dexter A L. Fuzzy model-based fault detection and diagnosis [C]. Proc. of IFAC World Congress, San Francisco, USA, 1996,121-126.
53．周东华，叶银忠．现代故障诊断与容错控制[M]．北京：清华大学出版社，2000．
54. Kabore P, et al. Observer-based fault diagnosis for a class of non-linear systems application to a free radical copolymerizat ion reaction [J]. Int. J. Control, 2000,73(9): 787-803.
55. TerraM H, T ino s R. Fault detection and isolation in a puma 560 manipulator via neural networks[C]. In: Proc of 14th IFAC World Congress, Beijing, 1999:175-180.
56. Statish L. Short-time Fourier and wavelet transforms for fault detection in power transformers during impulse tests [J]. IEEE Proc SciMeas Technol, 1998, 145(2): 77-84.
57. Yu D. Fault diagnosis for a hydraulic drive system using a parameter estimation method [J]. Control Eng Prac, 1997, 5(9): 1283-1291.
58. GenovesiA, Harmand J, Steyer J P. Integrated Fault Detection and Isolation: application to a winery's wastewater treatment plant [J]. Applied Intelligence, 2000, 13(1): 59-76.
59．胡昌华，许化龙．控制系统故障诊断与容错控制的分析与设计[M]．北京：国防工业出版社，2000．
60．石博强，申众华．机械故障诊断的分形方法—理论与实践[M]．北京：冶金工业出版社，2001．
61. Frank P M. Analytical and Qualitative Model-Based Fault Diagnosis--A Survey and Some New Results. EurPean Journal of Control, 1996, 2(1): 6-28.
62．周东华，王桂增．故障诊断技术综述[J]．化工自动化及仪表表，1998，25(1)：58-62．
63．陈玉东，施颂椒，翁正新．动态系统的故障诊断方法综述[J]．化工自动化及仪表表，2001，28(3)：1-14．
64．钱志勤，叶理平，周晓梅，设备故障诊断方法[J]．现代制造工程，2004(7)：105-107．65．董选明，裘丽华，王占林．机电控制系统故障诊断的回顾与展[J]．中国机械工程，1998，9(10)：63-66．
66．周东华．控制系统的故障检测与诊断技术[M]．北京：清华大学出版社，1994．
67．黄长艺，严普强．机械工程测试技术基础[J]．北京：机械工业出版社，1995．
68．叶昊，王桂增，方崇智．小波变换在故障检测中的应用[J]．自动化学报，1997，23(6)：736-741．
69. Statish L. Short-time Fourier and w avelett ransforms for fault detection in power transformers during impulse tests [J]. IEEE Proc SciMeas Technol, 1998, 145(2): 77-84.
70. Muid M, George V. Automated fault detection and identification using a fuzzy - wavelet analysis technique [C]. In: IEEE Proc of AUTOTESTCON, 1995: 169-175.
71. Zhao Z, Gu X, J iang W. Fault detection based on wavelet neural network [C]. In: Proc of 14th IFAC World Congress, Beijing, 1999: 145-150.
72. Jiang J and Jia F. A robust fault diagnosis scheme based on signal modal estimation [J]. Int. J. Control, 1995, 62(2): 461-475.
73. KumamaruK Hu J, et al. Robust Fault Detection Using Index of Kullback Discrimination Information [C]. Proc.of IFAC World Congress, San Francisco, USA, 1996: 205-210.
74．李渭华，萧德云，方崇智．一种基于自适应滑动窗格形滤波算法的故障检测器[J]．自动化学报，1996，22(2)：251-253．
75．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[J]．控制与决策，1998，13(3)：277-280．
76．姜万录，王益群．混沌工程学研究的新进展[J]．液压气动与密封，2002，92(2)：15-18．
77. D Logan and J Mathew. Determining the correlation dimension from bearing vibration acceleration data. The Research Bulletin of the Centre for Machine Condition Monitoring, 1993: 90-107.
78. Jiandong Jiang, Jin Chen. Nonlinear Analysis in gearbox faults diagnosis using correlation dimension[C]. 1998 International Conference of Vibration Engineering(ICVE' 98), Aug. 1998, Dalian.
79．陈怡然，周轶尘．发动机振动诊断中的多重分形法[J]．内燃机学报，1997，15(1)：114-119
80．姜建东，屈梁生．相关维数在大机组故障诊断中的应用[J]．西安交通大学学报，1998．32(4)：27-31．
81．丁庆海，庄志洪，祝龙石，等．混沌、分形和小波理论在被动声信号特征提取中的应??用[J]．声学学报．1999：24(2)：197-203．
82. Magni J F and Mouyon P. On Residual Generation by Observer and Parity Space Approaches. IEEE Trans. on Automatic Control, 1994: 39(2): 441-447.
83. Garcia E A and Frank P M. On the Relationship between Observer and Parameter Ideniification Based Approaches to Fault Detection. Proc. of IFAC World Conference, San Francisco, USA, 1996: 25-29.
84. Gertler J. Diagnosing Parametric Fauits from Parameter Estimation to Parity Relations. American Control Conference, Seattle,USA, 1995: 1615-1620.
85. Frank P M and Ding X. Survey of Robust Residual Generation and Evaluation Methods in Observer-based Fault Dection Systems [J], J.Process Control, 1997, 7(6): 403-424.
86. Ding S X and Jeinsch T. Application of Observer Based FDI Schemes to the Three-Tank System [C]. Proc. of EuroPean Control Conference, Karlsruhe, Germang, 1999.
87. Wang H and Daley S. Actuator fault diagnosis: an Adaptive Observer-based Technique [J]. IEEE Transactions on Automatic Control, 1996, 41(7): 1073-1075.
88. Chen J, Patton R J and Zhang H Y. Design of Unknown Input Observers and Robust Fault Detection Filters [J]. Int. J. Control, 1996, 63 (1): 85-105.
89. Kinnaert M. Design of Redundancy Relations for Failure Detection and Isolation by Constrained Optimization [J]. Int. J. Control, 1996, 63 (3): 609-622.
90. Hwang DS, Chang S K and Hsu P L. A Practical Design for a Robust Fault Detection and Isolation System [J]. Int. J. of System Science, 1997, 28 (3): 265-275.
91. Gertler J and Monajemy R. Generating Directional Residuals with Dynamic Pamty Relations [J]. Automatica, 1995, 61 (2): 395-421.
92. Gertler J and Kunwer M M. Optimal Residual DecouPling for Robust Fault Diagnosis [J]. Int. J. Control, 1995, 61(2): 395-421.
93．周东华，等．一类非线形系统参数偏差型故障的实时检测与诊断[J]．自动化学报，1993，19(2)：184-189
94. Hofling T and Isermann R. Adaptive Parity Equations and Advanced Parameter Estimation for Fault Detection and Diagnosis[C]. Proc. of IFAC World Congress, San Francisco, USA, 1996: 55-60.
95．黄席褪，熊庆宇，石为人，等．冶金连铸工业过程实时专家控制系统的设计与实现[J]．自动化学报，1998，24(3)：405-409．
96．阳春华，沈德耀，吴敏，等．焦炉配煤专家系统的定性定量综合设计方法．自动化学报，??2000，26(2)：226-232．
97. Heikki N K, Hannu K. Neural networks in Process fault diagnosis. IEEE Trans. on SMC, 1991, 21(4): 815-825.
98．刘锋，夏春先，黄振和．基于人工神经网络的故障诊断专家系统[J]．国外电子测量技，2004．4：34-36．
99．陈长征，张省，虞和济．基于神经网络的旋转机械故障诊断研究[J]．机械强度，2000，22(2)：104-107．
100．陈长征，徐玉秀．神经网络智能综合监测诊断系统研究[J]．振动与冲击，2000，19(2)：37-40
101. Ge W F. Detection of Faulty ComPonents via Robust Observation [J]. Int. J. Control, 1988; 47(2): 581-599.
102. Frark P M and KiuPel N. Residual Evaluation for Fault Diagnosis Using Adaptive Thiesholds and Fuzzy Inference[C]. Proc. of IFAC WorldC Congress, San Francisco, USA, 1996: 115-120.
103. Hwang H S. Automatic Design of Fuzzy Rule Base for Modeling and Control Using Evolutionary Programming [J]. IEEE Proc. Control Theory Appl., 1999, 146(1): 9-16.
104．王奉涛，马孝江，邹岩琨．智能故障诊断技术综述[J]．机床与液压，2003，4：6-8．
105. Juan A Carrasco. An algorithm to find minimal cuts of coherent fault-trees with event-classes [J]. IEEE Tans. on reliability, 1999,48(1): 31-41.
106．朱大奇，刘文波，于盛林．基于虚拟仪器的光电雷达电子部件性能检测和故障诊断系统[J]．航空学报，2000，21(1)：34-37．
107．张建刚．模糊树模型及其在复杂系统辨识中的应用[J]．自动化学报，2000，26(3)：378-381．
108．邓聚龙．灰色控制系统．武汉：华中理工大学出版社，1989．
109．李尔国，俞金寿．基于灰色关联度分析法的压缩机故障诊断研究[J]．上海海运学院学报，2001，22(3)：294-297．
110．王东，刘怀亮，徐国华．基于案例推理的故障诊断系统关联度计算[J]．西安电子科技大学学报(自然科学版)，2003，30(2)：264-267．
111．蒋瑜，陈循，杨雪．智能故障诊断研究与发展[J]．兵工自动化，2002，21(2)：12-15．
112. Golding A R and Rosenbloom P S. Improving Accuracy by Combining Rule-Based and Case-Based reasoning [J]. Artifical Intelligence, 1996, 87(1): 215-254.113. Feng Lin. Diagnosis ability of Discrete Event Systems and Its Applications [J]. Discrete Event Dynamic Systems, 1994, 4: 197-212.
114．杨叔子，丁洪，史铁林，等．基于知识的诊断推理[M]．北京：清华大学出版社，1994
115．陈亚勇，等．MATLAB信号处理详解[M]．北京：人民邮电出版社 2001．9．
116．郑方，徐明星．信号处理原理[M1．北京：清华大学出版社 2003．8．
117．胡广书．信号数字信号处理、算法与实现[M]．北京：清华大学出版社，1997．
118．应启珩，等．离散时间信号分析和处理[M]．北京：清华大学出版社，2001．9．
119．闻新，等．控制系统的故障诊断和容错控制[M]．北京：机械工业出版社，1998．
120．吴重光．仿真技术[M]．北京：化学工业出版社，2000．
121．孙一康．带钢热连轧计算机控制[M]．北京：机械工业出版社，1997．
122．卢长耿，李金良．液压控制系统的分析与设计[M]．北京：煤炭工业出版社，1991．
123．王春行．液压伺服控制系统[M]．北京：机械工业出版社，1981．
124．李洪人．液压控制系统[M]．北京：国防工业出版社，1981．
125．上海第二工业大学液压教研室．液压传动与控制[M]．上海：上海科学技术出版社，1990．
126．[美]Ginzburg V B．马东清等译．板带轧制工艺学[M]．北京：冶金工业出版社，1998．
127. Ginzburg V B. High-quality steel rolling: theory and practice [M]. New York: Marcel Dekkor Inc., 1993.
128．邹家祥，徐乐江等．冷连轧机系统的振动控制[M]．北京：冶金工业出版社，1998．
129．李贤燊．液压传动与控制[M]．重庆：重庆大学出版社，1993．
130. Huzyak P, Gerper T L. Design and application of hydraulic gap control systems [J]. Iron and Steel Engineer, 1984, 61(8): 13-20.
131. Ginzburg V. B. Dynamic characteristics of automatic gage control system with hydraulic actuators [J]. Iron and Steel Engineer, 1984, 61(1): 57-65.
132．薛定宇，陈阳泉著．基于MATLAB/Simulink的系统仿真技术与应用[M]．北京：清华大学出版社，2002．
133．李旭，张殿华，等 轧机液压AGC系统的动态性能仿真器[C]．2003中国钢铁年会论文集．2003：482-486．
134．谭树彬，等．冷连轧机穿带过程带钢厚度建模及仿真[J]．系统仿真学报[J]，2004，4：842-844．135. Yu D and Shield D N. A bilinear fault detection obsever [J]. Automatica, 1996, 32(11): 1597-1602.
136. Frank P M. Fault Diagnosis in Dynamic System Using Analytical and Knowledge Based Reduneancy-A Survey and Some New Results. Automatica, 1990: 26(3): 459-474.
137．孙世国，王树青，伍斌．Luenberger鲁棒故障检测器的设计[J]．浙江大学学报(工学版)，2004，38(6)：708-711
138．段广仁．线性系统理论[M]．哈尔滨：哈尔滨工业大学出版社，1998．
139．皮德常，秦小麟，王宁生．基于动态剪枝的关联规则挖掘算法[J]．小型微型计算机系统，2004，24(10)：1850-1852．
140．郜焕平，涂序彦，崔援民，等．基于模糊产生式规则的智能管理模型及其应用[J]．1999，25(5)：713-715．
141. Schank R. Dynamic Memory: A Theory of Remaiding and Learning in Computers and People [M]. Cambridge University Press, 1982.
142. Bryant S M. A Case-based Reasoning Approach to Bankruptcy Prediction Modeling [J].Intelligent Systems in Accounting, Finance and Management, 1997,(6): 195-214.
143. Shyi, Zhong Zhi, Zhou Han, et al. Applying Case-based Reasoning to Engine Oil Design [J]. Artificial Intelligence in Engineering, 1996, (11): 167-172.
144. Koloder J. An Introduction to Case-Based Reasoning [M]. California: Morgan Kanffman Publishers, 1993.
145. Lsermann R. On the applicability of model based fault detection for technical pocess [J]. Control Engineering Practice, 1999, 439-450.
146. Aamodt and Plaza. Case-based Reasoning: Foundational issues, methodological variations and system approaches [J]. AI Comunications, 1997,(7): 39-52.
147．李茹，任海涛，刘开瑛，等．基于案例的推理在农业专家系统中的应用[J]．计算机工程与应用，2004，(25)：196-198，204．
148．胡运权‘基于事例推理的智能模型构建研究[D]．哈尔滨工业大学，博士学位论文，2000．
149．罗忠良，王克运，康仁科，等．基于案例推理系统中案例检索算法的探索[J]．计算机工程与应用，2005．25：230-232．
150．张荣梅，周义等．交通事故处理智能决策支持系统(YCIDSS)[J]．计算机应用，2002，22(9)，60-61．
151．吴今培，肖健华．智能故障诊断与专家系统[M]．科：学技术出版社，1997：207-232．152．于跃海，郑瑞强等．基于案例推理的ICU应急诊断方案生成系统[J]．东南大学学报，2001，31(2)：27-30．
153. Olsson E, Funk Pr, Xiong N. Fault Diagnosis in Industry Using Sensor Readings and Case-Based Reasoning [J]. Journal of Intelligent & Fuzzy Systems, 2004, (15): 41-46.
154．张琦，孙劭文，李文鸿，等．基于案例推理的机械故障珍断方法探讨．解放军理工大学学报(自然科学版)，2004，5(5)：42-44．
155．夏虹，刘群，张志华．基于范例推理的机械故障诊断方法与系统[J]．哈尔滨工程大学学报，1999，20(5)：43-50．
156．张定会，邵惠鹤．基于神经网络的故障诊断推理方法[J]．上海交通大学学报，1999，33(5)：619-621．
157．张荣沂．基于神经网络的智能故障诊断技术[J]．自动化技术与应用，2003，22(2)：15-18．
158．虞和济，陈长征，张省，等．基于神经网络的智能诊断[M]．北京：冶金工业出版社2000．
159．焦李成．神经网络计算[M]．西安：西安电子科技大学出版社，1996．
160．楼顺天，施阳．基于MATLAB的系统分析与设计—神经网络[MJ．西安：西安电子科技大学出版社，1998．
161．汤天浩，刘以建，李杰．层次分类诊断模型的多重结构神经网络实现与应用[J]．上海海运学院学报，1998，19(4)：1-6．
162．王学武，谭得健．神经网络的应用与发展趋势[J]．计算机工程与应用，2003(3)：98-100．
163．胡良平．Windows SAS 6．12 & 8．0实用统计分析教程[M]．北京：军事医学科学出版社，2001．470-482．
164. Nielsen R H. Theory of the Back propagation neural network [J]. Proc. of IJCNN, Vol. 1, 1989: 2593-2605.
165．张颖，刘艳秋．软计算方法[M]．北京：科学出版社，2002．174-179．
166．黄胜伟，董曼玲．自适应变步长BP神经网络在水质评价中的应用[J]．水利学报，2002．10：119-123．
167．周建华．共轭梯度法在BP网络中的应用[J]．计算机工程与应用，1999(3)：17-19．
168．金丕彦，芮勇．BP算法各种改进算法的研究与应用[J]．南京航空航天大学学报，1994，26(11)：200-205．
169．张智星，孙春在，[日]水谷英二．神经—模糊和软计算[M]．西安：西安交通大学出版??社，2000．
170．赵弘，周瑞祥，林廷圻．基于Levenberg-Marquardt算法的神经网络监督控制[J]．西安交通大学学报，2002，36(5)：523-526．
171．桑应朋，范平志，郝莉．基于Levenberg-Marquardt算法的用户击键特征鉴别[J]．计算机应用，2004，24(7)：108-109，112．
172．王旭，王宏，王文辉．人工神经元网络原理与应用[M]．沈阳：东北大学出版社，2000．
173. Sartori M A, Antsaklis P J. A simple method to drive bounds on the size and to train multiplayer neural network [J]. IEEE Trans. on Neural Networks, 1993, 4(5): 740-747.
174．吴建昱，何小荣．用于过程建模的BP网络的M训练法及其改进[J]．计算机与应用化学，2001，8(5)：473-495．
175．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．
176．张进之．压力AGC分类及控制效果分析[J]．钢铁研究总院学报，1988．6：87-94．
177．王廷溥．轧钢工艺学．北京：冶金工业出版社，1981．
178．赵家骏．热轧带钢生产知识问答．北京：冶金工业出版社，1995．
179．孙一康．带钢热连轧的模型与控制[M]．北京：冶金工业出版社，2002．
180. Hiromi Hirono, Toshio Sakai. Upgrading of Hot Finishing Mill to 4-Stands and Replacement of Computer Control System [J]. Furukawa Review, 1999.18(9): 103-109.
181．张进之．动态设定型变刚度厚控方法的效果分析．重型机械[J]1998．1：30-34．
182. Adelmo F. Monaco. Hot Mill Profile/Flatness Performance and Finishing Mill Work Roll Practices [J]. Iron & Steel Technology. 2004.5: 38-45.
183．汪祥能，丁修堃．现代带钢连轧机控制[M]．沈阳：东北大学出版社，1996．
184. Bulut B and Katebi M R. Predictive Control of Hot Rolling Processes [C]. Proceedings of the American Control Conference Chicago, Illinois. 2000, 6: 2058-2062.
185．[美]V B 金兹伯格．姜明东，王国栋，等，译．高精度板带材控制理论与实践[M]．北京：冶金工业出版社，2000．
186．孙静．接近零不合格过程的有效控制——实现六西格玛质量的途径[M]．北京：清华大学出版社，2005．