用户名: 密码: 验证码:
神经网络PID控制器的研究及仿真
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
PID控制技术是一种应用很普遍的控制技术,目前在很多方面都有广泛的应用。论文深入研究了神经网络PID控制器。首先简要介绍了神经网络的理论基础和神经网络的学习算法,传统的常规PID控制器,针对常规PID控制器对于复杂的、动态的和不确定的系统控制还存在着许多不足之处进行了分析,为了达到改善常规PID控制器在复杂的、动态的和不确定的系统控制还存在着许多不足之处的目的,文中系统的提出了五种改进方式(模糊PID控制器、专家PID控制器、灰色PID控制器、遗传算法PID控制器和神经网络PID控制器)。
     本文主要研究了神经网络PID控制器。利用神经网络具有强的非线性映射能力、自学习能力、联想记忆能力、并行信息处理方式及优良的容错性能,应用神经网络对PID控制器进行改进后,对于工业控制中的复杂系统控制有着更好的控制效果,有效的改善了由于系统结构和参数变化导致的控制效果不稳定。文中深入研究了基于神经网络的神经元PID控制器、BP算法神经网络PID控制器,并针对BP算法在应用时易陷入局部极小点,而且学习时间长甚至达不到学习的目的提出了应用模糊算法、遗传算法对BP网络进行改进的组合优化神经网络PID控制器。最后,对常规PID控制器和神经网络PID控制器进行了仿真比较,仿真结果表明,应用神经网络对常规PID控制器进行改进后提高了系统的鲁棒性和动态特性,有效的改善了系统的控制结果,达到了预期的目的。
The techologic of PID control is very general, there is extensive application in many fields at present. The paper further investigates the neural network PID controller. Have introduced the theoretical foundation of the neural network and studying algorithm of the neural network, traditional routine PID controller briefly at first, is it analyse to traditional PID controller to complicated, dynamic and uncertain system control for a lot of weak points to it to go on, in order to achieve the goal of improving traditional PID controller, five kinds of improvement ways of systematic proposition in the article (fuzzy PID controller, expert PID controller, grey PID controller, hereditary algorithm PID controller and neural network PID controller).
    The text has discussed the neural network PID controller mainly. Because the neural network has strong nonlinearity to shine upon ability, study adaptive capacity, associative memory ability, the information processing way run side by side by oneself and fine fault-tolerant performance, there are better control result to the complicated system in industrial control, improveing the structure of system effective and change of the parameter result in controlling the unstability of the result. The paper further investigate the neuron PID controller based on neural network, neural network PID controller of BP algorithm, and algorithm while using easy to put some snack very much into to BP, but also has learnt the chronic purpose to even reach study and proposed using the fuzzy algorithm, the hereditary algorithm carries on the improved association and optimizes the neural network PID controller to BP network. Finally, carried on simulation to traditional PID controller and neural network PID controller, simulatio
    n result indicate, use neural network go on after improving raising stupid getting wonderful and dynamic characteristicking of system to routine PID controller, the effective systematic control result of improvement, has achieved the anticipated goal.
引文
[1] 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,1998,74-84
    [2] 易继锴,侯嫒彬.智能控制技术.北京:北京工业大学出版社,1999,130-132
    [3] 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,1999,225-234
    [4] 马宪民.人工智能的原理与方法.西安:西北工业大学出版社,2002,133-136
    [5] 诸静,模糊控制原理与应用.北京:机械工业出版社,1998,194-197,338-362
    [6] 陆伟民.人工智能技术及应用.上海:同济大学出版社,1998,100-103
    [7] 徐丽娜.神经网络控制.哈尔滨,哈尔滨工业大学出版社,1999,1-55
    [8] 李士勇.模糊控制和智能控制理论与应用.哈尔滨,哈尔滨工业大学出版社,1990,100-150
    [9] W.S. Mclulloch, W. Pitts, A Logical Calculus of the Ideas Immanent in Nervors Activity. Bulletin of Mathematical Biophysics, 1943, 5: 115-133
    [10] 焦李成著.神经网络系统理论.西安:西安电子科技大学出版社,1990,1-124
    [11] Bumjin Song. Nural Network Model Based Control of Nonlinear Flexible Link Systems. U.S.A:Bell & Information and Learning Company, 1999, (4):38-60
    [12] F.J. Pineda. Generalization of Back-Propagation to Recurrent Neural Networks. Phy. Rev. let, 1985,59(19):2229-2232
    [13] F.J. Pineda. Recurrent Backpropagation and Dynamical Approach to Adaptive Neural Computation. Neural Computation, 1989,1:161-172
    [14] S. Chen et al. Orthogonal Least Squares Learning Algorithm for Radial Basis Function Networks. IEEE Trans. Neural Networks, 1991, 2(2): 302-309
    [15] S. Chen et al. Orthogonal Least Squares Algorithm for Training Multi Output Radial Basis Function Networks. IEEE Proc.-F, 1992, 139(6): 378-384
    [16] 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):59-62
    
    
    [17] 汪小帆等.径向基函数神经网络的新型混合递推学习算法.控制理论与应用,1998,15(2):272-275
    [18] J.S. Albus, Data Storage in the Cerebellar Model Articulation Control(CMAC). Trans. of ASME Joural of Dynamic Systems. Measurements and Control, 1975, (9): 228-233
    [19] 段培永,邵惠鹤.一种CMAC超闭球结构及其学习算法.自动化学报.1999,25(6),816—819
    [20] H.L. Stegher et al. Theory and Development of Higher-Order CMAC Neural Networks. IEEE Control Systems, April 1992
    [21] 罗忠等.CMAC学习过程收敛性的研究.自动化学报,1997,23(4):455—461
    [22] Martin T. Hagan, Howard B. Demuch, Mark H. Beale. Neural Network Design. 北京:机械工业出版社,2002,197-226
    [23] 戴葵等译.神经网络设计.北京:机械工业出版社,2002,99-181
    [24] 孙亮,杨鹏.自动控制原理.北京:北京工业大学出版社,1999,53-55
    [25] 胡寿松.自动控制原理.北京:国防工业大学出版社,1998,71-103
    [26] 陶永华.新型PID控制及其应用.北京:机械工业出版社,2002,1-196
    [27] 张建民,王涛,王忠礼.智能控制原理及应用.北京:冶金工业出版社,2003,60-61
    [28] 蔡自兴.智能控制——基础与应用.北京:国防工业大学出版社,1998,128—132
    [29] 陶永华.新型PID控制及其应用.工业仪表与自动化装置,1998,1:57-62
    [30] 陶永华.新型PID控制及其应用.工业仪表与自动化装置,1997,4:60-64
    [31] P. Cominos and N. Munro. PID controllers: recent tuning methods and design to specification. IEE Proc-Control Theory. 2002,14(1):46-53
    [32] 陶永华.新型PID控制及其应用.工业仪表与自动化装置,1997,5:57—61
    [33] 王小平,曹立明.遗传算法——理论.应用与软件实现.西安:西安交通大学出版社,1-4
    [34] 顾毅,刘新国.基于遗传算法的PID控制器的研究.信息技术,2000,8:24-25
    [35] 侯宏霞,王涛.杨国清等.影响遗传算法PID参数优化性能的主要因素.西北水利发电,2002,18(4):5-8
    [36] 邓聚龙.灰色系统基本方法.武汉:华中理工大学出版社,1992,1-16
    
    
    [37] 邓聚龙.灰色控制系统.武汉:华中理工大学出版社,1992,187-194
    [38] F.C. Chen and C.C. Liu. Adaptive controlling nonlinear continuous-time systems using multilayer neural networks. IEEE Trans. Automat. Contr, 1994,39(6): 1306-1310
    [39] F.L. Lewis, A. Yessldirek and K. Liu, Multilayer neural-net robot controller with guaranteed tracking performance. IEEE Trans. Neural Networks, 1996,7(1): 1-12
    [40] 武志云,段志信,马瑞平.基于神经网络的PID控制器研究.内蒙古工业大学学报,2000,19(3):234-237
    [41] 曾军,方厚辉.神经网络PID控制及其MATLAB仿真.现代电子技术,2004,27(2):51-52
    [42] 宋滨,谷丽娜.基于神经网络的PID控制.青岛大学学报,2001,16(3):90-91
    [43] 舒迪前,李春涛,尹怡欣.单神经元自适应PID控制器及其在电加热炉上的应用.电气传动,1995,25(1):29-32
    [44] A.J. Calise, N. Hovakimyan, and M. Idan. Adaptive output feedback control of nonlinear systems using neural networks. Autmatic, 2001, 37(8): 1201-1211
    [45] Naira Hovakimyan, Flavio Nardi, Anthony Calise and Nakwan iim. Adaptive Output Feedbak Control of Uncertain Nonlinear Systems Using Single-Hidden-Layer Neural Networks. Neural Networks, 2002, 13(6): 1420-1431
    [46] 田明,戴汝为.基于动态BP神经网络德系统辨识方法.自动化学报,1994,19(4):451-453
    [47] 龙晓林,徐金方.基于优化BP神经网络的PID控制器研究.计算机测量与控制,2003,11(2):106-108
    [48] 高雪鹏,丛爽.BP网络改进算法的性能对比的研究.控制与决策,2001,16(2):167-171
    [49] 李英顺,伦淑娴,皮红梅.基于模糊神经网络的PID温度控制系统.鞍山钢铁学院学报,2002,25(6):408-414
    [50] 唐斌,凌旭峰,杨杰.基于模糊神经网络的决策树生成.红外与激光工程,2000,29(5):52-55
    [51] 程卫国,冯峰,姚东等.MATLAB5.3应用指南.北京:人民邮电出版社,1999,
    
    1-255
    [52] 欧阳黎明.MATLAB控制系统设计.北京:国防工业出版社,2001,1-45
    [53] 薛定宇,陈阳泉.基于MATLAB/Simulink的系统仿真技术与应用.北京:清华大学出版社,2002,50-93

© 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