带钢冷轧轧辊热行为及其补偿策略研究
|
摘要
轧辊的热行为，特别是工作辊的热膨胀、热凸度及其变化过程是轧制过程中的主要干扰因素之一。在市场竞争中，高质量、高成材率、低成本成为现代钢铁企业竞争的核心。对于带钢产品，厚度偏差和平直度是冷轧带钢最重要的尺寸精度指标。如何进一步提高冷轧带钢的板厚、板形精度是摆在所有相关领域研究者面前的难题。在现代冷轧过程中，冷轧机组速度高、功率大，部分能量将在轧制过程中转化为轧件变形热和轧制区摩擦热。动态热交换过程会使轧辊产生一定的膨胀和变形，导致工作辊平均直径和初始辊型的改变，影响板形板厚质量。对轧辊的热行为进行必要的研究，进而应用到板形板厚控制当中进行动态补偿是提高冷轧水平的新的突破口。因此，论文以300轧机为主要对象，对轧辊温度场的建模方法、热行为的预报方式以及模型的维护方法进行了深入的研究。
首先，在原有轧辊温度场及热行为数值建模的基础上提出了基于扫描法的准三维温度场模型。针对轧辊的高速旋转的工作特点，用局部二维温度场过程拓展出全局三维温度场。虽然研究对象是一个两维的轴半剖面，但是考虑的热传导是轴向、径向、以及周向三个方向的热传导，经过一段时间累积和延拓可以得到轧辊的三维全局温度场，这种方法可以准确全面刻画出轧辊温度场的分布。同时，合理的简化方案大大减少了计算工作量。
其次，在对冷轧过程的板厚、板形控制原理和过程进行适当分析的基础上，找出了轧辊热膨胀和热凸度与纵向厚差、横向厚差、轧机刚度、压下缸位移、轧制力、弯辊力等过程变量的相关关系，结合650轧机的过程数据，提出了一套基于轧制过程数据库进行数据挖掘和误差溯源，将隐藏在海量过程数据背后的有价值的知识和规律特别是轧辊热行为规律进行发掘的技术方案。
然后在300可逆冷轧实验轧机上，进行了实际的轧制实验，通过专门的过程数据库对各过程数据进行归档和保存。实验后可根据过程数据溯源出该过程的热凸度曲线和热膨胀曲线。同时在轧制实验过程中采用红外热像仪对轧辊表面温度场进行拍摄，获得轧辊表面瞬时温度分布，同溯源得到的热行为曲线一起，构成了对轧辊热行为过程全面、立体的证据体系，为数值模型和预报模型的校验和优化提供充分的证据。在完成轧制实验的基础上，融合获得的现场数据，运用遗传算法对数值模型的若干不确定参数进行了参数优化。优化的结果使得数值模型预报精度、可靠性和适应性得到了进一步的提高，具有了实际应用价值。
最后在300可逆冷轧实验轧机的板形板厚控制系统中设计了热凸度补偿和热膨胀补偿模块，为了提高模型的适应性和准确性，设计了预报模型的自适应方法，实现了热行为的在线预报和补偿，根据热行为变化过程的预报，控制系统对压下缸位置设定值和弯辊力设定值进行了动态的补偿，并进行了与其它控制策略的对比轧制实验。补偿结果表明，这种热行为的预报模型基本准确，补偿后纵向厚差显著降低，横向厚差更加稳定，板形良好。
The thermal behavior of rollers is one of the main interferences in rolling process, especially for the thermal expansion, the thermal camber and their change process. In the market competition, the quality of production is the key to win for all steel enterprises. For the cold rolling strip, the thickness precision and the shape of strip is the most important dimension precision target, and a severity challenge must face to is how to improve this dimension precision. During modern cold rolling process, the rolling speed and the power is rather high, and a part of power is transferred to heat conducting to the rollers, the strip, and environment. The dynamical heat exchange results in the thermal expansion and camber, and influence the thickness precision and the shape of strip. The new sally port to improve rolling quality is that study on the thermal behavior of rollers, and compensate it according the prediction in the AGC and AFC. This dissertation takes the temperature field and thermal behavior of working rollers and as the research objects, focuses on the solutions to key technologies, and put the research result to compensate thermal behavior in 300 strip cold rolling control system. The main work is as follows:
Firstly, basing on the conventional model of temperature field and thermal behavior, a new building model method called "scanning method" is advocated, which derivates the quasi three dimensional temperature field from a sequence two-dimensional temperature field. Although the research object is a longitudinal section actually, the continuation of this section can form the whole roller temperature. During the analysis, all the three dimensional conducting is take in calculation. This new method can descript the feature of temperature field on detail, and reduce the computing work at the most. This is very rational for thermal behavior of roll.
Secondly, basing on the reasonable analysis of the theory of AGC andAFC, the relation of the thermal behavior, the thickness of strip, the stiffness of roll mills, and other variables in process is find out. According the data mining theory and the error tracing technology, and basing on the data of 650 reversible cold strip roll mill, a new method is putting forward to discover the valuable rule hiding behind mass process datum, including the thermal behavior of working rollers.
Thirdly, the rolling experiment is proceeds on 300 reversible cold strip roll mill. During experiment, all the process data are saved in a process database, according to which the thermal behavior of rollers in the rolling process is tracing out. It provides the directly evidence to testify and optimize the digital model and predication model. And the thermal image of rollers is collect and record on period, as a reliable evidence for digital model. Basing on the experiment and fusing all the field data, some model parameter is optimized with a genetic algorithm program. The optimized model is more accurate and more reliable.
Finally, According the predication of the thermal expansion, the thermal camber, the control system adjusts the set value of press down displacement and the bending roller force to compensate influence of thermal behavior of rollers. The rolling results show that this model is accuracy, and the longitudinal thickness error is lowed significantly, the cross difference of thickness error is more stable, and the shape of strip is rather good.
首先，在原有轧辊温度场及热行为数值建模的基础上提出了基于扫描法的准三维温度场模型。针对轧辊的高速旋转的工作特点，用局部二维温度场过程拓展出全局三维温度场。虽然研究对象是一个两维的轴半剖面，但是考虑的热传导是轴向、径向、以及周向三个方向的热传导，经过一段时间累积和延拓可以得到轧辊的三维全局温度场，这种方法可以准确全面刻画出轧辊温度场的分布。同时，合理的简化方案大大减少了计算工作量。
其次，在对冷轧过程的板厚、板形控制原理和过程进行适当分析的基础上，找出了轧辊热膨胀和热凸度与纵向厚差、横向厚差、轧机刚度、压下缸位移、轧制力、弯辊力等过程变量的相关关系，结合650轧机的过程数据，提出了一套基于轧制过程数据库进行数据挖掘和误差溯源，将隐藏在海量过程数据背后的有价值的知识和规律特别是轧辊热行为规律进行发掘的技术方案。
然后在300可逆冷轧实验轧机上，进行了实际的轧制实验，通过专门的过程数据库对各过程数据进行归档和保存。实验后可根据过程数据溯源出该过程的热凸度曲线和热膨胀曲线。同时在轧制实验过程中采用红外热像仪对轧辊表面温度场进行拍摄，获得轧辊表面瞬时温度分布，同溯源得到的热行为曲线一起，构成了对轧辊热行为过程全面、立体的证据体系，为数值模型和预报模型的校验和优化提供充分的证据。在完成轧制实验的基础上，融合获得的现场数据，运用遗传算法对数值模型的若干不确定参数进行了参数优化。优化的结果使得数值模型预报精度、可靠性和适应性得到了进一步的提高，具有了实际应用价值。
最后在300可逆冷轧实验轧机的板形板厚控制系统中设计了热凸度补偿和热膨胀补偿模块，为了提高模型的适应性和准确性，设计了预报模型的自适应方法，实现了热行为的在线预报和补偿，根据热行为变化过程的预报，控制系统对压下缸位置设定值和弯辊力设定值进行了动态的补偿，并进行了与其它控制策略的对比轧制实验。补偿结果表明，这种热行为的预报模型基本准确，补偿后纵向厚差显著降低，横向厚差更加稳定，板形良好。
The thermal behavior of rollers is one of the main interferences in rolling process, especially for the thermal expansion, the thermal camber and their change process. In the market competition, the quality of production is the key to win for all steel enterprises. For the cold rolling strip, the thickness precision and the shape of strip is the most important dimension precision target, and a severity challenge must face to is how to improve this dimension precision. During modern cold rolling process, the rolling speed and the power is rather high, and a part of power is transferred to heat conducting to the rollers, the strip, and environment. The dynamical heat exchange results in the thermal expansion and camber, and influence the thickness precision and the shape of strip. The new sally port to improve rolling quality is that study on the thermal behavior of rollers, and compensate it according the prediction in the AGC and AFC. This dissertation takes the temperature field and thermal behavior of working rollers and as the research objects, focuses on the solutions to key technologies, and put the research result to compensate thermal behavior in 300 strip cold rolling control system. The main work is as follows:
Firstly, basing on the conventional model of temperature field and thermal behavior, a new building model method called "scanning method" is advocated, which derivates the quasi three dimensional temperature field from a sequence two-dimensional temperature field. Although the research object is a longitudinal section actually, the continuation of this section can form the whole roller temperature. During the analysis, all the three dimensional conducting is take in calculation. This new method can descript the feature of temperature field on detail, and reduce the computing work at the most. This is very rational for thermal behavior of roll.
Secondly, basing on the reasonable analysis of the theory of AGC andAFC, the relation of the thermal behavior, the thickness of strip, the stiffness of roll mills, and other variables in process is find out. According the data mining theory and the error tracing technology, and basing on the data of 650 reversible cold strip roll mill, a new method is putting forward to discover the valuable rule hiding behind mass process datum, including the thermal behavior of working rollers.
Thirdly, the rolling experiment is proceeds on 300 reversible cold strip roll mill. During experiment, all the process data are saved in a process database, according to which the thermal behavior of rollers in the rolling process is tracing out. It provides the directly evidence to testify and optimize the digital model and predication model. And the thermal image of rollers is collect and record on period, as a reliable evidence for digital model. Basing on the experiment and fusing all the field data, some model parameter is optimized with a genetic algorithm program. The optimized model is more accurate and more reliable.
Finally, According the predication of the thermal expansion, the thermal camber, the control system adjusts the set value of press down displacement and the bending roller force to compensate influence of thermal behavior of rollers. The rolling results show that this model is accuracy, and the longitudinal thickness error is lowed significantly, the cross difference of thickness error is more stable, and the shape of strip is rather good.
引文
1 Lawrence W. Dunn, Buffalo, N. Y. Cold Mill Automation. Iron and Steel Engineer, 1975, (2) : 42-46
2 杨景明．IGC650HCW冷带轧机控制系统关键技术研究．[燕山大学工学博士学位论文]．2000：10-17
3 木村弘，杉江明士，星野郁弥．薄板压延技术術现状动向．塑性加工，1991，32(4)：427-433
4 K. Gollmer, C. Posten. Fieldbus Application in the Hierarchical Automation Structure of a Biotechnological Pilot Plant. Journal of Biotechnology, 1995, 40(2) : 99-109
5 孙一康．带钢冷连轧计算机控制．北京：冶金工业出版社，2002：12-18
6 张小平，张少琴，张进之，等．板形理论与板形控制技术的发展．塑性工程学报，2005，12(7)：12-21
7 Chen Lu, A. Keit Tieu, ZhengYi Jiang. A Design of a Third-order CVC Roll Profile. Journal of Material Process Technology, 2002, 125: 645-648
8 M. P. F. Sutcliffe, P. J. Rayner. Experimental Measurements of Load and Strip Profile in Thin Strip Rolling. International Journal of Mechanical Sciences, 1998, 40(9) : 887-899
9 JIA Chun-yu, LIU Hong-min. Fuzzy Shape Control Based on Elman Dynamic Recursion Network Prediction Model. International Journal of Iron and Steel Research, 2006, 13(1) 31-35
10 Dr. A. S. Deshpande, K. Srinivasa Murthy. Computer Analysis for the Prediction of a Strip Profile in Cold Rolling. International Journal of Mechanical Sciences. 1997, 63: 712-717
11 张秀玲，刘宏民．神经网络模型参考自适应控制及其在带材板形控制系统中的应用．机械工程学报，2001，37(9)：83-87
12 罗永军．热连轧宽带钢板形板厚综合控制与仿真的研究．[北京科技大学工学博士学位论文]．2003：43-56
13 张利，王国栋，刘相华．中厚板四辊轧机机架优化设计的遗传算法．冶金设备，2000，119(2)：8-10
14 吕程，朱洪涛，王国栋．利用遗传算法优化板坯立轧短行程控制曲线．钢铁研究学报，1998，10(5)：19-22
15 王秀梅，吕程，王国栋，等．轧制力预报中的神经网络和数学模型．华东北大学学报(自然科学版)，1999，20(3)：28-32
16 A. F. M. Arif, Ovaisullah Khan, A. K. Sheikh. Roll Deformation and Stress Distribution under Thermo-mechanical Loading in Cold Rolling. Journal of Materials Processing Technology, 2004, 147: 255-267
17 张步坤．轧制工艺模型的自适应自学习理论研究及工程实践．[燕山大学工学硕士学位论文]．2005：28-34
18 彭力，涂序彦．热轧带钢卷取温度控制中的自适应律．北京科技大学报，2001，(5)：26-30
19 岳晓丽，连家创，李俊洪．热带钢连轧机轧辊热凸度在线计算模型的研究．冶金设备，2002，(6)：1-43
20 李俊洪，连家创，岳晓丽．热带钢连轧机工作辊温度场和热凸度预报．模型钢铁研究学报，2003，15(6)：25-28
21 A. Perez, R. L. Corral, R. Fuentes, R. Colas. Computer Simulation of the Thermal Behavior of a Work Roll During Hot Rolling of Steel Strip. Journal of Materials Processing Technology. 2004, 153: 894-899
22 杨利坡，刘宏民，彭艳，等．热连轧轧辊瞬态温度场研究．钢铁，2005，40(10)：38-40
23 胡秋．轧辊三维瞬态温度场的一种二维简化计算模型——400×1850铝板带冷轧机工作辊温度场与热变形数值模拟．[中南大学工学硕士学位论文]．2003：18-25
24 米山猛著，蔡千华译．冷轧时轧辊表面温度的变化和热流量，铝加工技术，1997，(4)：34-40
25 尹凤福．铝带箔轧机分段冷却技术及智能化控制模型的研究．[北京科技大学工学博士学位论文]．2003：25-39
26 Cemi S. The Temperature and Thermal Stresses in the Rolling of Metal Strip. Doctoral Dissertation, Dept. of Mech. Englng, Camegie Mellon University, 1963: 13-18
27 Cemi S, Weistein A. S, Zorowski C. F. Temperatures and Thermal Stresses in Rolling of Metal Strip, Iron and Steel Engineer Year Book, 1963: 717-723
28 Hogshead, T. H. Temperature Distributions in the Rolling of Metal Strip, Doctoral Dissertation, Dept. of Mech. Eng Camegie Mellon University, 1967: 43-47
29 Haubitzer W. Steady-state Temperature Distribution in Rolls. Archufer das Eisenhutenwesen. 1974, 46(10), 635-638
30 Tseng A. A. Thermal Behavior of Aluminum Rolling. ASME Journal of Heat Transfer. 1990, 112: 301-307
31 Tseng A. A, S. Tong, F. H. Lin. Thermal Stresses of Rotating Rolls in Rolling Process. J of Thermal Stresses, 12, 1989, 427-450
32 王国栋．板形控制和板形理论．北京：冶金工业出版社，1986：386-408
33 李晓燕．冷轧平整板形问题的研究．[北京科技大学工学博士学位论文]．2004：57-65
34 陈宝官，陈先霖，用有限元法预测板带轧机工作辊热变形．钢铁，1991，(8)：30-37
35 Z. Y. Jiang, A. K. Tieu, X. M. Zhang, C. Lua, W. H. Suna. Finite Element Simulation of Cold Rolling of Thin Strip. Journal of Materials Processing Technology 2003, 140: 542-547
36 孔祥伟，李壬龙，王秉新，等．轧辊温度场及轴向热凸度有限元计算，钢铁研究学报，2000，12(9)：20-52
37 日本钢铁协会．板带轧制理论与实践．北京：中国铁道出版社，1990：56-60
38 廖三三．宽带钢热连轧机轧辊温度场及热凸度的研究．[北京科技大学硕士学位论文]．2000：37-39
39 王文明，熊勇刚，胡仕成．铸轧辊温度场及热变形测定．轻合金加工技术，2002，30(4)：17-20
40 P. A. Attack. Control of Thermal Camber by Spray Cooling When Hot Rolling Aluminum. Ironmaking and Steelmaking, 1996, 23 (1) : 69-73
41 尹凤福．铝带箔轧机分段冷却技术及智能化控制模型的研究．[北京科技大学工学博士学位论文]．2003：25-39
42 Fayyad U M, Piatetsky Shapiro G, Smyth P, et, al Advances in Knowledge Discovery and Data Mining, AAAI/MIT Press, 1996: 83-115
43 徐毅，金德琨，敬忠良．数据融合研究的回顾与展望．信息与控制．2002，(3)：250-254
44 许桢英．动态系统误差溯源与精度损失诊断的理论与方法研究．[合肥工业大学工学博士论文]．2003：25-37
45 罗志增，蒋静坪．机器人感觉与多信息融合．北京：机械工业出版社，2002：95-100
46 Briceno, J. F, E. Mounayri, H. Mukhopadhyay. Selecting an Artificial Neural Network for Efficient Modeling and Accurate Simulation of the Milling Process. International Journal of Machine Tools and Manufacture, 2002, 42 (6) : 663-674
47 C. T. A. Pires, H. C. Ferreira, R. M. Sales, M. A. Silva. Set-up Optimization for Tandem Cold Mills: A Case Study. Journal of Materials Processing Technology. 2006, 173: 368-375
48 J. Larkiola, P. Myllykoski, J. Nylander, A. S. Korhonen. Prediction of Rolling Force in Cold Rolling by Using Physical Models and Neural Computing. Journal of Materials Processing Technology. 1996, 60: 381-386
49 张凤琴，刘娟，徐建忠．粗轧过程轧制BP神经网络预报．上海金属，2004，26(4)：38-42
50 K. Aistleitner, L, G. Mattersdorfer, W. Haas, A. Kugi. Neural Network for Identification of Roll Eccentricity in Rolling Mills. Journal of Materials Processing Technology. 1996, 60: 387-392
51 J. S. Gunasekera a, Zhengjie Jia b, J. C. Malasc, L. Rabelod. Development of a Neural Network Model for a Cold Rolling Process. Engineering Applications of Articial Intelligence. 1998, 11: 597-603
52 Auzinger D, Pfaffermayr M, Pichler R et al. Advanced Process Models for Today's Hot StripMills. MPT International, 1995, 53(6) : 58-64
53 Wang D D, Kiet Tieu, et al, Evolution Optimization Schedule for the Setup of a Tandem Cold Rolling Mill In: Proc. 7th int Conf On STEEL ROLLING: Chiba, Japan: Nov 9-11, 1998: 173-177
54 D. D. Wanga, A. K. Tieua, F. G. de Boera, B. Maa, W. Y. D. Yuen. Toward a Heuristic Optimum Design of Rolling Schedules Fortandem Cold Rrolling Mills. Engineering Applications of Articial Intelligence. 2000, 13: 397-406
55 何安瑞．宽带钢热轧精轧机组辊形的研究．[北京科技大学工学博士论文]．2000：3-14
56 张大志，程秉祥，李谋渭．基于遗传神经网络的冷连轧机轧制压力模型．北京科技大学学报，2000．22(4)：384-388
57 杨世铭，陶文铨．传热学．北京：高等教育出版社，1998：20-28
58 黄光杰，汪凌云．冷轧变形热及温升研究．金届成形工艺，1999，17(1)：45-46
59 胡秋，肖刚．冷轧薄板摩擦热及温升模型研究．金属成形工艺，2002，20(1)：16-18
60 边宇虹，刘宏民．应用预位移原理求解冷轧板带接触表面层摩擦力．钢铁研究学报，1994，(1)：34-37
61 王伟，连家创．用新的摩擦模型研究板带轧机工作辊最大许用直径．重型机械，1999，(4)：17-20
62 王伟，连家创．采用混合摩擦模型预报冷轧薄板轧制力．钢铁研究学报，2000，(1)：10-13
63 黄传清，连家创．关于板带轧制变形粘着区长度的计算．重型机械，1994，(4)：37-41
64 下土桥渡，冈村俊一．压延口一解析．塑性加工，1988，29(3)：327-332
65 V．B．金兹伯格．姜明东，王国栋译．高精度板带材轧制理论与实践．北京：冶金工业出版社，2000：205-231，316-327
66 日本钢铁协会．板带轧制理论与实践．北京：中国铁道出版社，1990：56-60
67 郭剑波．热带钢连轧机板凸度和板形控制技术的研究．[燕山大学工学博士学位论文]．1998：29-33
68 Fayyad U M, Piatetsky Shapiro G, Smyth P, et, al Advances in Knowledge Discovery and Data Mining, AAAI/MIT Press, 1996: 83-115
69 Usama Fayyad, Paul Stolorz. Data Mining and KDD Promise and Challenges. Future Generation Computer Systems. 1997, 13: 99-115
70 Wu Xin-dong, Yu P S, Piatetsky-Shapiro G.. Data Mining: How Research Meets Practical Development. Knowledge and Information Systems, 2003, 5 (2) : 248-261
71 SchAolkopf B, Smols A J. Learning with Kernel. MIT Press, Cambridge MA, 2002: 105-126
72 贾琳，李明．基于数据挖掘的电信客户流失模型的建立与实现．计算机工程与应用，2004，(4)185-188
73 李秋丹．数据挖掘相关算法的研究与平台实现．[大连理工大学工学博士论文]．2004：51-83
74 吴婕．浅析数据挖掘软件的发展．情报理论与实践，2004，21(2)：212-215
75 Chen Lei-da. Data Mining Methods, Applications, Tools. Information Systems Management, 2000, 17(1) : 65-70
76 A. Feeldersa, H. Danielsa, b, M. Holsheimer. Methodological and Practical Aspects of Data Mining. Information & Management, 2000, 37: 271-281
77 Zhen Jian-guo, Liu Fang, Jiao Li-cheng. A Novel Induction Algorithm for DM. Journal of Systems Engineering and Electronics, 2001, 12(4) : 91-96
78 John F. Krosa, Mike Linb, Marvin L. Brownc. Effects of the Neural Network s-Sigrnoid Function on KDD in The Presence of Imprecise Data. Computers & Operations Research, 2006, 33: 3136-3149
79 Fernando Crespoa, Richard Weber. A Methodology for Dynamic Data Mining Basedon Fuzzy Clustering. Fuzzy Sets and Systems, 2005, 150: 267-284
80 Zhengxin Chen, Qiuming Zhu. Query Construction for User-guided Knowledge Discovery in Databases. Information Sciences, 1998, 109: 49-64
81 Ching-Yao Wang, Shian-Shyong Tseng, Tzung-Pei Hong. Flexible Online Association Rule Mining Based on Multidimensional Pattern Relations. Information Sciences, 2006, 176: 1752-1780
82 费业泰，于连栋：论全糸统动态测试精度理论研究．合肥工业大学学报，2000，23(1)：6-9
83 杨福生．小波变换的工程分析与应用．北京：科学出版社，1999：23-46
84 连家创，刘宏民．板厚板形控制．北京：兵器工业出版社，1996：11-20
85 姜万录，王益群，张建成．小波分析及其在伺服阀性能测试中的应用．液压气动与密 封，2001(5)：39-42
86 Yong-Tae Park. An Empirical Investigation of the Effects of Data Warehousing on Decision Performance. Information & Management.2006,43: 51-61
87 Arun Sen. Metadata management: Past, Present and Future. Decision Support Systems.2004,37: 151-173
88 Ching-Ming Chao. Incremental Maintenance of Object-oriented Data Warehouses. Information Sciences .2004,160:91-110
89 Z.Y. Jiang, H.T. Zhu, A.K. Tieu, W.H. Sun. Modelling of Work Roll Edge Contact in thin Strip Rolling. Journal of Materials Processing Technology .2004,155:1280-1285
90 Z.Y. Jiang, H.T. Zhu, A.K. Tieu..Mechanics of Roll Edge Contact in Cold Rolling of Thin strip. International Journal of Mechanical Sciences.2006,48:697-706
91 Dr Tim J. Phillips.High Performance Thermal Imaging Technology. The Advanced Semiconductor Magazine, 2002, 15(7):32-35
92 杨红，何建宏，喻娅君．红外热像仪及其在建筑节能检测中的应用．新型建筑材．2003．50(4)：50-51
93 J. Varith, G.M. Hyde, A.L. Baritelle, J.K. Fellman, T. Sattabongkot. Non-contact Bruise Detection in Apples by Thermal Imaging. Innovative Food Science and Emerging Technologies. 2003,4: 211-218
94 Igor V. Maslov, Izidor Gertner. Multi-sensor Fusion: an Evolutionary Algorithm Approach. Information Fusion.2006,7:304-330
95 Shengli Wu, Sally McClean. Performance Prediction of Data Fusion for Information retrieval. Information Processing and Management.2006,42:899-915
96 王小平，曹立明．遗传算法．西安：西安交通大学出版社，2002：68-102
97 L. Shia, S. OA lafssonb, Q. Chen. A New Hybrid Optimization Algorithm. Computers & Industrial Engineering. 1999,36:409-426
98 Noureddine Bouhmala. A Multilevel Genetic Algorithm for the Traveling Salesman Problem. Electronic Notes in Discrete Mathematics. 2003,15(5): 1-10
99 Greg C. Smith, Shan S. F. Smith. An Enhanced Genetic Algorithm for Automated Assembly Planning. Robotics and Computer Integrated Manufacturing.2002,18:355-364
100 Shun-Fa Hwang, Rong-Song He. A Hybrid Real-parameter Genetic Algorithm for Function Optimization. Advanced Engineering Informatics. 2006,20:7-21
101 Lothar, M. Sehmitt. Theory of Genetic Algorithms. Theoretical Computer Science. 2001, 259:1-61
102 李敏强，寇纪淞．林丹等．遗传算法的基本理论与应用．北京：科学出版社，2002：17-66
103 何克忠，李伟．计算机控制系统．北京：清华大学出版社，2003：155-180
104 方一鸣，陈刚，王益群，等．高精度可逆冷带轧机全数字厚度自动控制系统．冶金自动化，2005，(6)：28-45
105 李伟明，穆志纯．基于实测值的自适应算法在中厚板轧制中的应用，北京科技大学学报，2003，01：25-30
106 师黎．基于自适应模糊神经网络的多模型在线故障诊断，自动化仪表，2004，(7)：16-20
107 孙登月，杜凤山，朱泉封．五机架冷连轧机轧制力人工神经网络预报，钢铁，2002，37(2)：28-32
108 Vladimir, B. Ginzburg. Selection of Optimum Strip Profile and Flatness Technology for Rolling Mills. I&S Engineer, 1997,(7):30-37
2 杨景明．IGC650HCW冷带轧机控制系统关键技术研究．[燕山大学工学博士学位论文]．2000：10-17
3 木村弘，杉江明士，星野郁弥．薄板压延技术術现状动向．塑性加工，1991，32(4)：427-433
4 K. Gollmer, C. Posten. Fieldbus Application in the Hierarchical Automation Structure of a Biotechnological Pilot Plant. Journal of Biotechnology, 1995, 40(2) : 99-109
5 孙一康．带钢冷连轧计算机控制．北京：冶金工业出版社，2002：12-18
6 张小平，张少琴，张进之，等．板形理论与板形控制技术的发展．塑性工程学报，2005，12(7)：12-21
7 Chen Lu, A. Keit Tieu, ZhengYi Jiang. A Design of a Third-order CVC Roll Profile. Journal of Material Process Technology, 2002, 125: 645-648
8 M. P. F. Sutcliffe, P. J. Rayner. Experimental Measurements of Load and Strip Profile in Thin Strip Rolling. International Journal of Mechanical Sciences, 1998, 40(9) : 887-899
9 JIA Chun-yu, LIU Hong-min. Fuzzy Shape Control Based on Elman Dynamic Recursion Network Prediction Model. International Journal of Iron and Steel Research, 2006, 13(1) 31-35
10 Dr. A. S. Deshpande, K. Srinivasa Murthy. Computer Analysis for the Prediction of a Strip Profile in Cold Rolling. International Journal of Mechanical Sciences. 1997, 63: 712-717
11 张秀玲，刘宏民．神经网络模型参考自适应控制及其在带材板形控制系统中的应用．机械工程学报，2001，37(9)：83-87
12 罗永军．热连轧宽带钢板形板厚综合控制与仿真的研究．[北京科技大学工学博士学位论文]．2003：43-56
13 张利，王国栋，刘相华．中厚板四辊轧机机架优化设计的遗传算法．冶金设备，2000，119(2)：8-10
14 吕程，朱洪涛，王国栋．利用遗传算法优化板坯立轧短行程控制曲线．钢铁研究学报，1998，10(5)：19-22
15 王秀梅，吕程，王国栋，等．轧制力预报中的神经网络和数学模型．华东北大学学报(自然科学版)，1999，20(3)：28-32
16 A. F. M. Arif, Ovaisullah Khan, A. K. Sheikh. Roll Deformation and Stress Distribution under Thermo-mechanical Loading in Cold Rolling. Journal of Materials Processing Technology, 2004, 147: 255-267
17 张步坤．轧制工艺模型的自适应自学习理论研究及工程实践．[燕山大学工学硕士学位论文]．2005：28-34
18 彭力，涂序彦．热轧带钢卷取温度控制中的自适应律．北京科技大学报，2001，(5)：26-30
19 岳晓丽，连家创，李俊洪．热带钢连轧机轧辊热凸度在线计算模型的研究．冶金设备，2002，(6)：1-43
20 李俊洪，连家创，岳晓丽．热带钢连轧机工作辊温度场和热凸度预报．模型钢铁研究学报，2003，15(6)：25-28
21 A. Perez, R. L. Corral, R. Fuentes, R. Colas. Computer Simulation of the Thermal Behavior of a Work Roll During Hot Rolling of Steel Strip. Journal of Materials Processing Technology. 2004, 153: 894-899
22 杨利坡，刘宏民，彭艳，等．热连轧轧辊瞬态温度场研究．钢铁，2005，40(10)：38-40
23 胡秋．轧辊三维瞬态温度场的一种二维简化计算模型——400×1850铝板带冷轧机工作辊温度场与热变形数值模拟．[中南大学工学硕士学位论文]．2003：18-25
24 米山猛著，蔡千华译．冷轧时轧辊表面温度的变化和热流量，铝加工技术，1997，(4)：34-40
25 尹凤福．铝带箔轧机分段冷却技术及智能化控制模型的研究．[北京科技大学工学博士学位论文]．2003：25-39
26 Cemi S. The Temperature and Thermal Stresses in the Rolling of Metal Strip. Doctoral Dissertation, Dept. of Mech. Englng, Camegie Mellon University, 1963: 13-18
27 Cemi S, Weistein A. S, Zorowski C. F. Temperatures and Thermal Stresses in Rolling of Metal Strip, Iron and Steel Engineer Year Book, 1963: 717-723
28 Hogshead, T. H. Temperature Distributions in the Rolling of Metal Strip, Doctoral Dissertation, Dept. of Mech. Eng Camegie Mellon University, 1967: 43-47
29 Haubitzer W. Steady-state Temperature Distribution in Rolls. Archufer das Eisenhutenwesen. 1974, 46(10), 635-638
30 Tseng A. A. Thermal Behavior of Aluminum Rolling. ASME Journal of Heat Transfer. 1990, 112: 301-307
31 Tseng A. A, S. Tong, F. H. Lin. Thermal Stresses of Rotating Rolls in Rolling Process. J of Thermal Stresses, 12, 1989, 427-450
32 王国栋．板形控制和板形理论．北京：冶金工业出版社，1986：386-408
33 李晓燕．冷轧平整板形问题的研究．[北京科技大学工学博士学位论文]．2004：57-65
34 陈宝官，陈先霖，用有限元法预测板带轧机工作辊热变形．钢铁，1991，(8)：30-37
35 Z. Y. Jiang, A. K. Tieu, X. M. Zhang, C. Lua, W. H. Suna. Finite Element Simulation of Cold Rolling of Thin Strip. Journal of Materials Processing Technology 2003, 140: 542-547
36 孔祥伟，李壬龙，王秉新，等．轧辊温度场及轴向热凸度有限元计算，钢铁研究学报，2000，12(9)：20-52
37 日本钢铁协会．板带轧制理论与实践．北京：中国铁道出版社，1990：56-60
38 廖三三．宽带钢热连轧机轧辊温度场及热凸度的研究．[北京科技大学硕士学位论文]．2000：37-39
39 王文明，熊勇刚，胡仕成．铸轧辊温度场及热变形测定．轻合金加工技术，2002，30(4)：17-20
40 P. A. Attack. Control of Thermal Camber by Spray Cooling When Hot Rolling Aluminum. Ironmaking and Steelmaking, 1996, 23 (1) : 69-73
41 尹凤福．铝带箔轧机分段冷却技术及智能化控制模型的研究．[北京科技大学工学博士学位论文]．2003：25-39
42 Fayyad U M, Piatetsky Shapiro G, Smyth P, et, al Advances in Knowledge Discovery and Data Mining, AAAI/MIT Press, 1996: 83-115
43 徐毅，金德琨，敬忠良．数据融合研究的回顾与展望．信息与控制．2002，(3)：250-254
44 许桢英．动态系统误差溯源与精度损失诊断的理论与方法研究．[合肥工业大学工学博士论文]．2003：25-37
45 罗志增，蒋静坪．机器人感觉与多信息融合．北京：机械工业出版社，2002：95-100
46 Briceno, J. F, E. Mounayri, H. Mukhopadhyay. Selecting an Artificial Neural Network for Efficient Modeling and Accurate Simulation of the Milling Process. International Journal of Machine Tools and Manufacture, 2002, 42 (6) : 663-674
47 C. T. A. Pires, H. C. Ferreira, R. M. Sales, M. A. Silva. Set-up Optimization for Tandem Cold Mills: A Case Study. Journal of Materials Processing Technology. 2006, 173: 368-375
48 J. Larkiola, P. Myllykoski, J. Nylander, A. S. Korhonen. Prediction of Rolling Force in Cold Rolling by Using Physical Models and Neural Computing. Journal of Materials Processing Technology. 1996, 60: 381-386
49 张凤琴，刘娟，徐建忠．粗轧过程轧制BP神经网络预报．上海金属，2004，26(4)：38-42
50 K. Aistleitner, L, G. Mattersdorfer, W. Haas, A. Kugi. Neural Network for Identification of Roll Eccentricity in Rolling Mills. Journal of Materials Processing Technology. 1996, 60: 387-392
51 J. S. Gunasekera a, Zhengjie Jia b, J. C. Malasc, L. Rabelod. Development of a Neural Network Model for a Cold Rolling Process. Engineering Applications of Articial Intelligence. 1998, 11: 597-603
52 Auzinger D, Pfaffermayr M, Pichler R et al. Advanced Process Models for Today's Hot StripMills. MPT International, 1995, 53(6) : 58-64
53 Wang D D, Kiet Tieu, et al, Evolution Optimization Schedule for the Setup of a Tandem Cold Rolling Mill In: Proc. 7th int Conf On STEEL ROLLING: Chiba, Japan: Nov 9-11, 1998: 173-177
54 D. D. Wanga, A. K. Tieua, F. G. de Boera, B. Maa, W. Y. D. Yuen. Toward a Heuristic Optimum Design of Rolling Schedules Fortandem Cold Rrolling Mills. Engineering Applications of Articial Intelligence. 2000, 13: 397-406
55 何安瑞．宽带钢热轧精轧机组辊形的研究．[北京科技大学工学博士论文]．2000：3-14
56 张大志，程秉祥，李谋渭．基于遗传神经网络的冷连轧机轧制压力模型．北京科技大学学报，2000．22(4)：384-388
57 杨世铭，陶文铨．传热学．北京：高等教育出版社，1998：20-28
58 黄光杰，汪凌云．冷轧变形热及温升研究．金届成形工艺，1999，17(1)：45-46
59 胡秋，肖刚．冷轧薄板摩擦热及温升模型研究．金属成形工艺，2002，20(1)：16-18
60 边宇虹，刘宏民．应用预位移原理求解冷轧板带接触表面层摩擦力．钢铁研究学报，1994，(1)：34-37
61 王伟，连家创．用新的摩擦模型研究板带轧机工作辊最大许用直径．重型机械，1999，(4)：17-20
62 王伟，连家创．采用混合摩擦模型预报冷轧薄板轧制力．钢铁研究学报，2000，(1)：10-13
63 黄传清，连家创．关于板带轧制变形粘着区长度的计算．重型机械，1994，(4)：37-41
64 下土桥渡，冈村俊一．压延口一解析．塑性加工，1988，29(3)：327-332
65 V．B．金兹伯格．姜明东，王国栋译．高精度板带材轧制理论与实践．北京：冶金工业出版社，2000：205-231，316-327
66 日本钢铁协会．板带轧制理论与实践．北京：中国铁道出版社，1990：56-60
67 郭剑波．热带钢连轧机板凸度和板形控制技术的研究．[燕山大学工学博士学位论文]．1998：29-33
68 Fayyad U M, Piatetsky Shapiro G, Smyth P, et, al Advances in Knowledge Discovery and Data Mining, AAAI/MIT Press, 1996: 83-115
69 Usama Fayyad, Paul Stolorz. Data Mining and KDD Promise and Challenges. Future Generation Computer Systems. 1997, 13: 99-115
70 Wu Xin-dong, Yu P S, Piatetsky-Shapiro G.. Data Mining: How Research Meets Practical Development. Knowledge and Information Systems, 2003, 5 (2) : 248-261
71 SchAolkopf B, Smols A J. Learning with Kernel. MIT Press, Cambridge MA, 2002: 105-126
72 贾琳，李明．基于数据挖掘的电信客户流失模型的建立与实现．计算机工程与应用，2004，(4)185-188
73 李秋丹．数据挖掘相关算法的研究与平台实现．[大连理工大学工学博士论文]．2004：51-83
74 吴婕．浅析数据挖掘软件的发展．情报理论与实践，2004，21(2)：212-215
75 Chen Lei-da. Data Mining Methods, Applications, Tools. Information Systems Management, 2000, 17(1) : 65-70
76 A. Feeldersa, H. Danielsa, b, M. Holsheimer. Methodological and Practical Aspects of Data Mining. Information & Management, 2000, 37: 271-281
77 Zhen Jian-guo, Liu Fang, Jiao Li-cheng. A Novel Induction Algorithm for DM. Journal of Systems Engineering and Electronics, 2001, 12(4) : 91-96
78 John F. Krosa, Mike Linb, Marvin L. Brownc. Effects of the Neural Network s-Sigrnoid Function on KDD in The Presence of Imprecise Data. Computers & Operations Research, 2006, 33: 3136-3149
79 Fernando Crespoa, Richard Weber. A Methodology for Dynamic Data Mining Basedon Fuzzy Clustering. Fuzzy Sets and Systems, 2005, 150: 267-284
80 Zhengxin Chen, Qiuming Zhu. Query Construction for User-guided Knowledge Discovery in Databases. Information Sciences, 1998, 109: 49-64
81 Ching-Yao Wang, Shian-Shyong Tseng, Tzung-Pei Hong. Flexible Online Association Rule Mining Based on Multidimensional Pattern Relations. Information Sciences, 2006, 176: 1752-1780
82 费业泰，于连栋：论全糸统动态测试精度理论研究．合肥工业大学学报，2000，23(1)：6-9
83 杨福生．小波变换的工程分析与应用．北京：科学出版社，1999：23-46
84 连家创，刘宏民．板厚板形控制．北京：兵器工业出版社，1996：11-20
85 姜万录，王益群，张建成．小波分析及其在伺服阀性能测试中的应用．液压气动与密 封，2001(5)：39-42
86 Yong-Tae Park. An Empirical Investigation of the Effects of Data Warehousing on Decision Performance. Information & Management.2006,43: 51-61
87 Arun Sen. Metadata management: Past, Present and Future. Decision Support Systems.2004,37: 151-173
88 Ching-Ming Chao. Incremental Maintenance of Object-oriented Data Warehouses. Information Sciences .2004,160:91-110
89 Z.Y. Jiang, H.T. Zhu, A.K. Tieu, W.H. Sun. Modelling of Work Roll Edge Contact in thin Strip Rolling. Journal of Materials Processing Technology .2004,155:1280-1285
90 Z.Y. Jiang, H.T. Zhu, A.K. Tieu..Mechanics of Roll Edge Contact in Cold Rolling of Thin strip. International Journal of Mechanical Sciences.2006,48:697-706
91 Dr Tim J. Phillips.High Performance Thermal Imaging Technology. The Advanced Semiconductor Magazine, 2002, 15(7):32-35
92 杨红，何建宏，喻娅君．红外热像仪及其在建筑节能检测中的应用．新型建筑材．2003．50(4)：50-51
93 J. Varith, G.M. Hyde, A.L. Baritelle, J.K. Fellman, T. Sattabongkot. Non-contact Bruise Detection in Apples by Thermal Imaging. Innovative Food Science and Emerging Technologies. 2003,4: 211-218
94 Igor V. Maslov, Izidor Gertner. Multi-sensor Fusion: an Evolutionary Algorithm Approach. Information Fusion.2006,7:304-330
95 Shengli Wu, Sally McClean. Performance Prediction of Data Fusion for Information retrieval. Information Processing and Management.2006,42:899-915
96 王小平，曹立明．遗传算法．西安：西安交通大学出版社，2002：68-102
97 L. Shia, S. OA lafssonb, Q. Chen. A New Hybrid Optimization Algorithm. Computers & Industrial Engineering. 1999,36:409-426
98 Noureddine Bouhmala. A Multilevel Genetic Algorithm for the Traveling Salesman Problem. Electronic Notes in Discrete Mathematics. 2003,15(5): 1-10
99 Greg C. Smith, Shan S. F. Smith. An Enhanced Genetic Algorithm for Automated Assembly Planning. Robotics and Computer Integrated Manufacturing.2002,18:355-364
100 Shun-Fa Hwang, Rong-Song He. A Hybrid Real-parameter Genetic Algorithm for Function Optimization. Advanced Engineering Informatics. 2006,20:7-21
101 Lothar, M. Sehmitt. Theory of Genetic Algorithms. Theoretical Computer Science. 2001, 259:1-61
102 李敏强，寇纪淞．林丹等．遗传算法的基本理论与应用．北京：科学出版社，2002：17-66
103 何克忠，李伟．计算机控制系统．北京：清华大学出版社，2003：155-180
104 方一鸣，陈刚，王益群，等．高精度可逆冷带轧机全数字厚度自动控制系统．冶金自动化，2005，(6)：28-45
105 李伟明，穆志纯．基于实测值的自适应算法在中厚板轧制中的应用，北京科技大学学报，2003，01：25-30
106 师黎．基于自适应模糊神经网络的多模型在线故障诊断，自动化仪表，2004，(7)：16-20
107 孙登月，杜凤山，朱泉封．五机架冷连轧机轧制力人工神经网络预报，钢铁，2002，37(2)：28-32
108 Vladimir, B. Ginzburg. Selection of Optimum Strip Profile and Flatness Technology for Rolling Mills. I&S Engineer, 1997,(7):30-37
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |