基于神经网络自适应控制的热轧卷取机步进控制系统的研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
现代热轧卷取机的发展主要着眼于提高产品的产量和质量。电液伺服系统在现代的热轧卷取机中的应用主要是实现带头的自动步进回避,这样就有效地消除冲击,同时也使卷取过程中各种事故大为减少,大大提高了轧制过程的自动化水平,产品产量和质量。
     本文以热轧卷取机步进控制系统为研究对象,针对实际现场卷取机卷取工艺,在实验室建造了热轧卷取机系统物理实验模型,在国内首次研制了针对卷取机步进控制的电液伺服控制系统,建立了电液伺服系统的数学模型。
     本论文详细研究了神经网络自适应控制结构。人工神经网络是一门发展十分迅速的交叉学科,它具有信息的分布存储,并行处理以及自学习能力等优点,遗传算法是一种借鉴生物界自然选择和自然遗传机制的随机化搜索算法,其主要特点是群体搜索策略和群体中个体之间的信息交换,搜索不依赖于梯度信息,人工神经网络和遗传算法在智能控制领域中有着广泛的应用。本文利用人工神经网络和遗传算法自身的特点结合自适应控制来实现对液压伺服系统的实时控制。
     本文建立了液压伺服步进控制系统数学模型,利用遗传算法优化神经网络自适应控制模型,以Windows98为操作平台,利用Visual C++编程语言开发了可视化控制软件。该软件人机交互性能好,操作简单,实用性强。
     实验证明,该控制系统能实现带头的自动步进回避,提高材料利用率,为研制高水平热轧卷取机奠定基础。
The development of modern coiler system is mainly aiming at improving the yield and quality of product. Hydraulic servo system used in coiler is mainly to realize the step-by-step control. By using the servo system, vibration and striking are largely decreased, the accidents are reduced, and the level of automation is largely improved, as well as the quality of production.
    This paper is focused on step-by-step control system for coiler of hot rolling mill, and based on the real work process of coiler at worksite, a mechanical model for coiler control system is built at laboratory used for research work. This is the first time in China to develop an electro-hydraulic servo system for this step-by-step control system.
    In the thesis, neural network adaptive control method in the coiler control system is studied in detail. Artificial neural network (ANN), which is a rapidly developing crossing subjects, has many advantages such as parallel storing, parallel processing of information, teaching itself etc. Genetic algorithm (GA), a probability search algorithm, simulates the mechanism of natural choose and natural genetic and its main features are group research strategy and individual information exchange which do not depend on gradient information. ANN and GA have a broad application in intellectual control. This thesis realizes the real-time control of hydraulic servo system by using neural network adaptive control method, which is used the features and virtues of ANN and GA.
    This thesis establishes a GA-NNI model for identification of hydraulic system. Utilizing Windows98 as its O.S., the control software is developed by using Visual C++ language. The results show that the software has strong application value and its interface is interactive and easy to operate.
    Experiments show that in the system, step-by-step control is realized, the utilization rate of materials is gained. This model lays the basis for developing the better coiler.
引文
1 李人厚.智能控制理论和方法.西安:西安电子科技大学出版社,1999:24-56
    2 陈国良,王熙法,庄镇泉,王东生.遗传算法及其应用.北京:人民邮电出版社,1996:1-3
    3 连家创,刘宏民.板厚板形控制.北京:兵器工业出版社,1996:137-140
    4 邹家祥.轧钢机械.北京:冶金工业出版社,1989:403-405
    5 李运华等.近代液压伺服系统控制策略的现状与发展.液压与气动,1995:2-74
    6 王占林.近代液压控制.北京:机械工业出版社,1997:1-17
    7 Saridis G N. Toward the Realization of Intelligence Controls. IEEE Proc, 1979:67-68
    8 袁曾任.智能控制研究的新进展.信息与控制,1994,23(5):45-48
    9 李士勇.模糊控制神经控制和智能控制论.哈尔滨:哈尔滨工业大学出版社,1996:72-74
    10 J.H. Holland. Adaptation in Natural and Artificial Systems. The Universtiy of Michigan Press, 1975:45-52
    11 De Jong K A. An Snalysis of Behaviour of a Class of Genetic Adaptive Systenms. [Ph.D. Dissertation]. University of Michigan, No.76-9381,1975
    12 Lu Jin. A Hidden Node Value Regulation Algorithm for Neural Network Training. Control Theory and Application. 1998,15(1):53-59
    13 贾财潮等.一种用人工神经网络重建自由曲面的方法.中国机械工 程.1998,9(9):42-45
    14 王旭东,邵惠鹤.RBF神经元网络在非线性系统建模中的应用.控制理论与应用.1997,14(1):59-66
    15 何述东等.多层前向神经网络结构的研究进展.控制理论与应用.1998,15(3):313-318
    16 刘卫国等.基于单纯形优化学习算法的前向神经网络电机模型辨识.信息与控制.1998,27(5):382-385
    
    
    17 李歧强等.神经网络的具有自适应动量和步长的伪牛顿算法.信息与控制.1998,27(2):146-150
    18 T.Warren Liao, L.J.Chen. Manufacturing Process Modeling and Optimization Based on Multi-layer Perceptron Network. Journal of Manufacturing Science and Engineering. 1998,120:109-119
    19 B.R. Pramod, S.C. Bose. System Identification Using ARMA Modelling and Neural Networks. Journal of Engineering for Industry. 1993,115:487-491
    20 宋耕田,周宁生,周汉武.热轧地下卷取机助卷辊控制系统改造.冶金设备,2001,8(4):27-29
    21 顾瑞龙.工程控制理论.北京:北京科学技术出版社,1990:24-66
    22 李福义.液压技术与液压伺服系统.哈尔滨:哈尔滨工程大学出版社,1992:131-138
    23 高英杰.轧机AGC液压系统故障诊断技术的研究.[燕山大学博士论文].2001:22-23
    24 刘勇.非数值并行算法(2)—遗传算法[M].北京:科学出版社,1977:1-200
    25 L.Plonecki, W. Trampeczynski, J.Cendrowicz. A Concept of Digital Control System to Assist the Operator of Hydraulic Excavators, Automation in contruction. 1998,7:401-411
    26 韩曾晋.自适应控制,北京:清华大学出版社,2000:5-15
    27 史维祥等.近代机电控制工程.北京:机械工业出版社,1998:1-200
    28 陈平,裘丽华.液压伺服系统的直接自适应神经网络控制.机床与液压,2001,2:40-41
    29 T. Knohl, H.Unbehauen. Adaptive Position Control of Electrohydraulic Servo Systems Using ANN. Mechatronics. 2000,10:127-143
    30 N.SEPEHRI, A.A.KHAYYAT, B.HEINRICHS. Development of A Nonlinear PI Controller for Accurate Postioning of An Industrial Hydraulic Manipulator. Mechatronics. 1997,7:683-700
    31 G.P. Liu, S.Daley. Optimal-tuning Nonlinear PID Control of Hydraulic Systems. Control Engineering Practice. 2000,8:1045-1053
    32 刘建昌.基于神经网络的自适应厚度控制.钢铁,1999,11:26-29
    33 Benno Stein, Elmar Vier. Structural Analysis in Control Systems Design of Hydraulic Drives. Engineering Application of Artificial Interlligence, 2000,13:741-750
    
    
    34 胡建华等.神经网络和PID控制器在过程控制中的应用.上海大学学报,1997,8:54-56
    35 I.A.Basheer, M.Hajmeer. Artificial Neural Networks: Fundamentals, Computing, Design, and Application. Journal of Microbiological Methods, 2000,43:3-41
    36 王顺晃,舒迪前.智能控制系统及其应用.北京:机械工业出版社,1998:251-257
    37 刘镇清.人工神经网络BP算法的改进及其在无损检测中的应用.测控技术,2001,20:56-58
    38 潘昊,钟咯,陈杰.BP神经网络训练的函数变步长搜索调整法.湖北工学院学报,1997,6:12-14
    39 Irie B, Miyake S. Capabilities of Three-layered Perceptrons. Proceedings of the IEEE Inter Conf on Neural Network, 1998(Ⅰ):641-648
    40 Health-Nielsem R. The Theory of Backpropagation Neural Network. In Review, 1998
    41 R.C.Eberhart, R.W. Dobbbins. Neural Network. Pc tools. Acdemic Press, 1990
    42 张立明.人工神经网络的模型及其应用.南京:复旦大学出版社,1994:22-50
    43 王雷等.利用GA-BP算法对模糊神经网络进行优化.燕山大学学报,1999,9
    44 Jahangir Morshed & Jagath, J.Kaluarachchi. Application of Artificial Neural Network and Genetic Algorithm in Flow and Transport Simulations. Advances in Water Resource, 1998,22:145-158
    45 Weixiang Zhao, Dezhao Chen, Shangxu Hu. Optimizing Operating Conditions Based on ANN and Modified Gas. Computers & Chemical Engineering, 2000,24:61-65
    46 David J.Kruglinski, Scot Wingo, George Shepherd. Programming Visual C++6.0 技术内幕(5).北京:北京希望电子出版社.1999,5:1-650
    47 谢建英.微型计算机控制技术.北京:国防工业出版社,1991:2-4
    
    
    48 张豫文,曹建文译.Windows汇编语言及系统程序设计.北京:北京大学出版社,1995:1-124
    49 钟向群,龙旭东等译.(美)James. W. Melord著.用 Borland C++开发Windows应用程序.北京:清华大学出版社,1993:1-220
    50 杨亮,万玉丹,魏晋鹏.Windows深入剖析—内核篇.北京:清华大学出版社,1997:1-260
    51 汪成为,郑小军,彭木昌.面向对象分析、设计及应用.北京:国防工业出版社,1992:1-80
    52 郭立新等.遗传算法在机械优化设计中的应用.机械设计与制造,1999,1:15-18
    53 De Jong K A. An Analysis of the Behavior of a Class of Genetic Adaptive System. [Ph. D Dissertation] Michigan: University of Michigan, 1975
    54 吴超仲等.一种多层遗传算法的提出及实现.武汉交通科技大学学报,2000,4:11-13
    55 Goldberg D E. Genetic Algorithms in Search, Optimization and Machine Learning. MA: Addison-Wesley, 1989:1-83
    56 朱朝艳,郭鹏飞,张旭.谈遗传算法的改进策略.辽宁工学院学报,2001,10(5):7-9
    57 候格贤,王义和.模拟退火与遗传算法的结合.计算机学报,1997,20(4):381-384
    58 XU Zhong ben, GAO Yong. Traits Analysis and Prevention of Premature Convergence in Genetic Algorithms. Journal of China Science. 1996,26(4):364-375
    59 LI Shu quan, ZHAO Liang ying, SHI Zhi-xing etc. An Effective Method on Preventing Prematurity of Genetic Algorithm. Journal of Theory and Practice of System Engineering. 1999,19(5):72-77
    60 宗敬群.一类混合自适应遗传算法及性能分析.系统工程理论与实践,2001,4(4):6-9
    61 肖永韧,解刁农,刘晓峰.VC与MATLAB混合编程之DLL实现方法.计算机工程与应用,2001,3:34-36
    62 徐昕,李涛,伯晓晨等.Matlab工具箱应用指南—控制工程篇.北京:电子工业出版社,2000:169-229
    
    
    63 龚剑,朱亮.MATLAB入门与提高.北京:清华大学出版社,2000:1-200
    64 王威,方蕾,陈景亮.用 VC++6.0 开发数据库应用程序.计算机应用,2001,5:38-41

© 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