基于神经网络的自适应逆控制及其在飞机自动着陆中的应用
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
本文在深入分析了神经网络和自适应逆方法的原理与特点的基础上,将神经网络与自适应逆方法相结合,着重研究了将这种方法应用于非线性系统的控制问题,最后,用飞机自动着陆的过程,验证了神经网络自适应逆方法的效果。
     本文的主要工作如下:
     1.演化神经网络。介绍了典型多层前向网络——BP网络的模型、算法以及存在的问题,充分考虑了遗传算法大范围寻优的特点,引入了遗传算法作为神经网络的学习方法,自动设计和训练,提高学习效率,快速达到最优解。
     2.自适应逆控制。介绍了自适应逆控制的基本原理,以及适用于自适应逆控制的Wiener滤波器结构和自适应LMS算法,并将自适应逆方法应用于线性和非线性控制系统中。结合神经网络,给出了对于非线性系统进行控制的实现途径,并通过实例,进行仿真。
     3.自适应逆控制方法在飞机自动着陆系统中的应用。着陆是飞行任务中的一个事故多发阶段,因此飞机自动着陆是发展现代飞机的关键技术。本文以某国产飞机为对象,采用自适应逆控制的方法,设计飞机纵向自动着陆控制系统并仿真,还对所设计的系统进行了鲁棒性验证仿真。结果表明,自适应逆控制完全能够满足任务要求。最后将自适应逆方法与反馈线性化后的模糊控制方法比较,自适应逆方法的抗干扰能力明显优于模糊控制方法,但是抗参数摄动能力稍差。
     通过对一般非线性系统和飞机运动的控制仿真,说明了自适应逆控制的有效性和可行性,以及所具有的应用价值。
This thesis combines artificial neural networks(NN) with adaptive inverse control(NNAI) on the basis of analyzing their principle and characteristics, and applies them in the control of nonlinear system. An application in the design of automatic landing is shown.
    The main works are:
    1. Evolutionary neural networks. Present the models, algorithms and the existing problems of the Back Propagation(BP) network, a typical multilayer neural network. Introduce the genetic algorithm to train neural networks in order to improve the learning efficiency.
    2. Adaptive inverse control. First give the elementary knowledge of adaptive inverse, then give the construction of filter which is proper to adaptive inverse, and LMS adaptive algorithm. The policy is used in the system control, and an achieving way in the design of nonlinear plant is proposed. Last, provide the related simulation results.
    3. Automatic landing system of airplane using adaptive inverse control. Traffic accidents occur during landing frequently. Adaptive inverse control is applied in the design of automatic landing system and robustness is verified. Good simulation results are obtained. At last, NNAI is contrasted with the system adopting fuzzy control after linearization.
    The study shows that NNAI is effective and practicable.
引文
1.李绍棠等.自适应逆控制.西安:西安交通大学出版社,1999
    2.张立明.人工神经网络的模型及其应用.上海:复旦大学出版社,1993
    3.T.凯拉斯著,李清泉等译.线性系统.北京:科学出版社,1985
    4.章卫国等.先进控制理论与方法导论.西安:西北工业大学出版社,1999
    5.李士勇.模糊控制,神经网络和智能控制论.哈尔滨:哈尔滨工业大学出版社,1997
    6.潘正君等.演化计算.北京:清华大学出版社,1998
    7.邢文洲等.现代优化计算方法.北京:清华大学出版社,1999
    8.施阳等.Matlab语言精要及动态仿真工具Simulink.西安:西北工业大学出版社,1999
    9.薛定宇.控制系统计算机辅助设计—Matlab语言及应用.西安:清华大学出版社,1996
    10.鲁道夫著,金长江译.飞行控制.北京:国防工业出版社,1999
    11.楼顺天.基于Matlab的系统分析与设计—神经网络.西安:西安电子科技大学出版社,1999
    12.于洋.神经网络在控制中的应用.西安:西北工业大学硕士论文,2001
    13.章卫国,刘长林,王新民.舰载飞机自动着舰系统研究报告.西安:西北工业大学九零六教研室,1994
    14.文传源,现代飞行控制系统.北京:北京航空航天大学出版社,1992
    15.韩璞等,神经网路自适应逆控制的仿真研究,华北电力大学学报,Vol28,No3,2001:26-30
    16.唐永哲.直升机控制系统设计.北京:国防工业出版社,2000
    17.王立新.自适应模糊系统与控制.北京:国防工业出版社,1995
    18.何植岱,高浩.高等飞行动力学.西安:西北工业大学出版社,1990
    19.何克忠,李伟.计算机控制系统.北京:清华大学出版社,1998
    20.卢强等,电力系统非线性.科学出版社,1993
    21.肖业伦,飞行器运动方程.航空工业出版社,1988
    22.胡际芳,飞机自动着陆纵向控制系统非线性设计方法研究.西北工业大学硕士学位论文
    23.欧阳晋,微波自动着陆控制系统设计.西北工业大学硕士学位论文,2000
    24.徐士良,C常用算法程序集.清华大学出版社,1993
    25.陈小红.逆系统方法的径向基函数网络实现.控制与决策.1998,Vol13,No 2:147-150
    26.刘淑祥.基于动态逆的神经网络超机动飞行控制.航空学报,1997,Vol18,No1:26-30
    27.杨熔等.用神经网络建立非线性系统模型研究.控制理论与应用,1995,Vol 12,No1:81-86
    28.李人厚,王魁生.用于神经网络直接逆控制的连续空间遗传算法.西安石油学院学报,2000,Vol15,No4:67-72
    29.孙富春,孙增沂.采样非线性系统的动态神经网络稳定自适应控制.自动化学报,2002,Vol 26,No6:721-727
    
    
    30. 岳恒,柴天佑,邵诚.一类非最小相位非线性统的神经网络自适应控制策略.信息与控制, 1998, Vol27, No6: 451-455
    31. Aircraft Control & Simulation, USA, 1992
    32. Eric R. Weeks, John M. Burgess, Evolving Artificial Neural Network to Control Chaotic System, Physical Review, Vol56, No2, 1997
    33. J. Hernandez, R. Parra, J. Alvarez, J. Alarcon, J. Ibarra. A Nneural Nnetwork Structure and Learning Algorithm For Control of Dynamic Systems. Journal of the Mexican Society of Instrumentation Revista de la Sociedad Mexicana de Instrumentacion, A. C. :62-68
    34. K. J. Hunt, et al., "Neural Networks for Control Systems-A Survey" , Automatica, 28, 768-775, 1992.
    35. Ku, Chao-Chee y Lee, Kwang, "Diagonal Recurrent Neural Networks for Dynamics Systems ontrol" , IEEE Transactions on Neural Networks, 6, January, 144-155, (1995)
    36. Parra H., R., "Sistema de Control Supervisorio y Control de Velocidad para una Turbina de Gas basados en Redes Neuronales Artificiales" , Tesis de Maestri a; Cuernavaca: Centro Nacional de Investigacion y Desarrollo Tecnolbgico, 91H1, (1996)
    37. Passino, Kevin M, "Intelligent Control for Autonomous Systems" , IEEE Spectrum, 55-62, (1995)
    38. Jen Wang, Chich-Cheng Chen, "A Fast Multilayer Neural-Network Training Algorithm Based on the Layer by Layer Optimizing Procedures" , IEEE Transactions on Neural Networks, 7, 1083-1112, (1996)
    39. Silvia Ferrari, Robert F. Stenge . Classical/Neural Synthesis of Nonlinear Control Systems. AIAA-2000-4552
    40. Narendra, K. S., Parthasaranthy, K. Identification and Control of Dynamical Systems Using Neural Networks . IEEE Trans. Neural Networks, V 1, 1995: 4-27
    41. Narendra, K. S. Neural Networks for Control:Theory and Practice. Proc. of The IEEE, V 84, no. 10, 1996:1385-1406
    42. Iwasa, T., Morizumi, N. , Omatu, S. Temperature Control in a Batch Process by Neural Networks. IEEE International Conference, IEEE-0-7803-41223-8/97, V 6, no.1, 1997:2430-2433
    43. Ergezinger, S. y, Thomson, E. , "An Accelerated Learning Algorithm for Multilayer erceptrons:Optimization Layer by Layer" , IEEE Transactions on Neural Networks. 6, 31-41, (1995)
    44. Georgia, Neural Network-Based Adaptive Algorithms for Nonlinear Control , Ph. D Theses, Institute of Technology, 2000. 11
NGLC 2004-2010.National Geological Library of China All Rights Reserved.
Add:29 Xueyuan Rd,Haidian District,Beijing,PRC. Mail Add: 8324 mailbox 100083
For exchange or info please contact us via email.