基于神经网络的一类MIMO非线性系统的自适应控制
|
摘要
本文沿着理论研究与工程实际相结合、创新与实用相结合的思路,根据自适应神经网络控制理论的现状、存在的问题以及工程实际应用的基本要求,对未知非线性多输入多输出系统的控制理论进行了深入的研究,建立了系统化的整体设计框架,为解决某些传统方法难以解决的工程实际问题提供了新思路。
本论文主要研究了一类未知多输入多输出非线性系统的自适应控制问题,提出了两种在线自适应控制器。第一种是基于GP-RBF算法的自适应RBF神经网络控制器(A-RBFNNC)。采用所提出的神经元灵敏度概念,并结合超球体聚类的方法,建立了一种新颖的增加和删除规则,在线确定RBF神经网络的结构和参数。当误差满足一定要求时,该控制器转入按照基于Lyapunov稳定性理论的自适应律进行网络权值的进一步调整,保证了控制器的全局稳定性和收敛性。
第二种是基于一种混合遗传算法,针对非线性系统设计了一种自适应RBF神经网络控制器。文中将改进的标准遗传算法与梯度算法相结合,设计了一种混合遗传算法。所设计的控制器首先利用混合遗传算法在线确定RBF神经网络的结构和初始参数,然后按照基于Lyapunov稳定性理论的自适应律进行神经网络权值的进一步调整,保证了闭环系统的全局稳定性和收敛性。
所设计的两种控制器都不需要先验知识就可以在线确定神经网络的初始结构,不仅无需辨识被控对象的模型就可进行神经网络控制器的在线设计,而且神经网络控制器的学习过程和系统的控制过程同时进行,不需要特定的教师信号,避免了离线训练通常存在训练数据不足的问题;基于Lyapunov稳定性理论设计的自适应律,保证了控制器的全局稳定性和收敛性。
两关节机械手的仿真实验和锅炉内胆与夹套水温的控制实验证明了所给方法的有效性,不仅实现了神经网络的结构和参数的在线自适应,还保证了闭环系统的全局稳定,鲁棒性好。
Considering the principles of combining theoretical study with engineering application and innovation with practicality, based on the state of the research of adaptive neural control theory, the existing main problems and the practical requirements of engineering applications, this dissertation deeply investigates the control theory for unknown nonlinear multi-input and multi-output systems, succeeds in constructing a systematic design structure, and provides new effective approaches.
In this thesis, the problem of adaptive control for unknown affine MIMO nonlinear system is studied and proposes two adaptive controllers. The first one is adaptive RBF neural network controller based on Growing and Pruning algorithm for RBF (GP-RBF). The structure and parameters of RBF neural network are determined online with the algorithm of growing and pruning which is obtained through combining a proposed neural sensitivity concept with hyper-sphere clustering. When the error condition is satisfied, the weights of controller are further adjusted and obtained by the adaptive law based on Lyapunov theory, which guarantees the global stability and convergence of controller. Simulation results show that the fast tracking ability, perfect stability and convergence of the controller.
The second controller is adaptive RBF neural network controller based on hybrid genetic algorithm (HGA-RBFNNC). The structure and parameters of RBF neural network are determined online by hybrid genetic algorithm which is the combination of the improved genetic algorithm with and the steepest decent algorithm. Then the weights of controller are further adjusted and obtained by the adaptive law based on Lyapunov theory, which guarantees the global stability and convergence of the system. Simulation results show that the fast tracking ability, perfect stability and convergence of the controller.
The two controllers needn’t experiences to define the structure and parameters of neural network. Not only online design the neural network don’t need recognize the model of the plant but also the study of controller and the control of the system are simultaneous and the teacher signal is not needed, which avoids the shortage of the training data in the offline study. They all use the adaptive law based on Lyapunov theory, which guarantees the global stability and convergence of the system.
The simulations of two-link robot manipulator and the experiment on the boiler temperature show that the proposed methods are effective, which realizes the adaptive tuning of the structure and parameters of RBF neural network and ensures the global stability and convergence of the system.
本论文主要研究了一类未知多输入多输出非线性系统的自适应控制问题,提出了两种在线自适应控制器。第一种是基于GP-RBF算法的自适应RBF神经网络控制器(A-RBFNNC)。采用所提出的神经元灵敏度概念,并结合超球体聚类的方法,建立了一种新颖的增加和删除规则,在线确定RBF神经网络的结构和参数。当误差满足一定要求时,该控制器转入按照基于Lyapunov稳定性理论的自适应律进行网络权值的进一步调整,保证了控制器的全局稳定性和收敛性。
第二种是基于一种混合遗传算法,针对非线性系统设计了一种自适应RBF神经网络控制器。文中将改进的标准遗传算法与梯度算法相结合,设计了一种混合遗传算法。所设计的控制器首先利用混合遗传算法在线确定RBF神经网络的结构和初始参数,然后按照基于Lyapunov稳定性理论的自适应律进行神经网络权值的进一步调整,保证了闭环系统的全局稳定性和收敛性。
所设计的两种控制器都不需要先验知识就可以在线确定神经网络的初始结构,不仅无需辨识被控对象的模型就可进行神经网络控制器的在线设计,而且神经网络控制器的学习过程和系统的控制过程同时进行,不需要特定的教师信号,避免了离线训练通常存在训练数据不足的问题;基于Lyapunov稳定性理论设计的自适应律,保证了控制器的全局稳定性和收敛性。
两关节机械手的仿真实验和锅炉内胆与夹套水温的控制实验证明了所给方法的有效性,不仅实现了神经网络的结构和参数的在线自适应,还保证了闭环系统的全局稳定,鲁棒性好。
Considering the principles of combining theoretical study with engineering application and innovation with practicality, based on the state of the research of adaptive neural control theory, the existing main problems and the practical requirements of engineering applications, this dissertation deeply investigates the control theory for unknown nonlinear multi-input and multi-output systems, succeeds in constructing a systematic design structure, and provides new effective approaches.
In this thesis, the problem of adaptive control for unknown affine MIMO nonlinear system is studied and proposes two adaptive controllers. The first one is adaptive RBF neural network controller based on Growing and Pruning algorithm for RBF (GP-RBF). The structure and parameters of RBF neural network are determined online with the algorithm of growing and pruning which is obtained through combining a proposed neural sensitivity concept with hyper-sphere clustering. When the error condition is satisfied, the weights of controller are further adjusted and obtained by the adaptive law based on Lyapunov theory, which guarantees the global stability and convergence of controller. Simulation results show that the fast tracking ability, perfect stability and convergence of the controller.
The second controller is adaptive RBF neural network controller based on hybrid genetic algorithm (HGA-RBFNNC). The structure and parameters of RBF neural network are determined online by hybrid genetic algorithm which is the combination of the improved genetic algorithm with and the steepest decent algorithm. Then the weights of controller are further adjusted and obtained by the adaptive law based on Lyapunov theory, which guarantees the global stability and convergence of the system. Simulation results show that the fast tracking ability, perfect stability and convergence of the controller.
The two controllers needn’t experiences to define the structure and parameters of neural network. Not only online design the neural network don’t need recognize the model of the plant but also the study of controller and the control of the system are simultaneous and the teacher signal is not needed, which avoids the shortage of the training data in the offline study. They all use the adaptive law based on Lyapunov theory, which guarantees the global stability and convergence of the system.
The simulations of two-link robot manipulator and the experiment on the boiler temperature show that the proposed methods are effective, which realizes the adaptive tuning of the structure and parameters of RBF neural network and ensures the global stability and convergence of the system.
引文
[1] 王耀南.智能控制系统——模糊逻辑·专家系统·神经网络控制[M].长沙:湖南大学出版社,1996.
[2] 胡守仁,沈清,胡德文,时春.神经网络应用技术[M].长沙:国防科学技术出版社,1995.
[3] 王秀峰.系统建模与辨识[M].北京:电子工业出版社,2004.
[4] 韩曾晋.自适应控制[M].北京:清华大学出版社,2002.
[5] 王永城,涂建.神经元网络控制[M].北京:机械工业出版社,1998.
[6] 费树氓.非线性控制系统与设计[M].北京:电子工业出版社,1998.
[7] A.M. Karshenas, M .w. Dunnigan and Williams. Adaptive inverse control algorithm for shock testing[J].IEE proc.-Control Theory App1.,2000,147(3):267-276.
[8] 易之光.自适应逆控制方法及其应用研究[D].燕山大学硕士学位论文,2005.
[9] Widrow B, Eugene Walach.自适应逆控制[M].西安: 西安交通大学出版社,2000.
[10] C.L.M Hamold,K.Y.Lee. Free-model Based Adaptive Inverse Neurocontroller for Dynamic systems[C].The37th IEEE Conference on Decision and Contro1,Tampa, Florida,1998:507-512.
[11] C.L.M.Harnold,K.Y.Lee Application of the Free-mode1Based Neura1 Networks in Model Reference Adaptive Inverse Control[C]. American Control Conference,Chicago,Illinois,2000:1664-1668.
[12] G.L.Plett,H.Botrich.DDEK-F Learning for Fast Nonlinear Adaptive Inverse Control[C]. International Joint Conference on Neural Networks, 2002:2092-2097.
[13] 张兴华.戴先中基于逆系统方法感应电机调速控制系统[J].控制与决策, 2000 , 15 (6):708-711.
[14] 刘士荣,俞金寿.神经逆模型 PID复合控制在 CSTR中的应用[J].控制理论与应用,2001, 18 (5):769-773.
[15] 党映农,韩崇昭.基于 Volterra 基函数网络的自适应逆控制方法[J].西安交通大学学报,2000,34(9):8-12.
[16] 秦 孝 艳 .一 类 非 线 性 系 统 的 鲁 棒 自 适 应 跟 踪 控 制 [J].安 徽 工 业 大 学 学 报 ,2006, 23(3):360-364.
[17] 丘 东 强 , 涂 亚 庆 . 神 经 网 络 控 制 的 现 状 与 展 望 [J]. 自 动 化 与 仪 器 仪 表 ,2001, 97(5):1-7.
[18] Sanner R M, Slotine J J. Gaussian networks for direct adaptive control[J].IEEE Transaction on Neural Networks, 1992, 3 (6): 837-863.
[19] T.Zhang, S. S. Ge, and C .C .Hang. Stable Adaptive Control for a Class of Nonlinear Systems Using a Modified Lyapunov Function [J], IEEE Trans. On Automatic Control,2000,45:129-135.
[20] Zhuo Wang,Ping Li,Shuo Guo. Adaptive inverse control for nonlinear systems based on RBF neural network [J]. Intelligent Control and Automation, 2004,Volume 1:485-487.
[21] 唐超颖,王彪.基于在线神经网络的自适应控制器的设计与应用[J].华南理工大学学报(自然科学版)2006,34(6):34-38.
[22] Sunan N . huang, K .K.Tan and T .H.Lee. Further Results on Adaptive Control for a Class of Nonlinear Systems Using Neural Networks[J]. IEEE Transaction On Neural Networks, 2003, 14 (3):719-722.
[23] Tomahisa Hauakawa, Wassim M. Haddad,Naira Hovakimyan and Vijay Sekhar Chellaboina. Neural Network Adaptive Control for Nonlinear Nonnegative Dynamical Systems [J]. IEEE Transactions on Neural Networks, 2005,16 (2):399-413.
[24] 杜红彬,邵惠鹤.一类非线性系统的自适应神经网络控制[J].控制与决策,2005, 20(4):455-459.
[25] H.E.Psillakis and A.T.Alexandridis. Adaptive Neural Motion Control of n-link Robot Manipulators Subject to Unknown Disturbances and Stochastic Perturbations [J].IEEE Proc.-Control Theory Appl.,2006, 153(2):127-138.
[26] Y. Li, S. Qiang, X. Zhung, and O. Kaynak. Robust and adaptive backstepping control for nonlinear systems using RBF neural networks[J].IEEE Trans. Neural Network, 2004,15(3): 693–701.
[27] S. S. Ge and J. Zhang.Neural-network control of nonaffine nonlinear system with zero dynamics by state and output feedback[J].IEEE Trans. Neural Network,2003,14(4): 900–918.
[28] Shuzhi Sam Ge and Cong Wang .Adaptive Neural Control of Uncertain MIMO Nonlinear Systems[J].IEEE TRANSACTIONS ON NEURAL NETWORKS, 2004, 15(3):674-692.
[29] Youshen S. Xia, Gang Feng, and Jun Wang. A Primal-Dual Neural Network for Online Resolving Constrained Kinematic Redundancy in Robot Motion Control[J].IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS—PART B:CYBERNETICS, 2005, 35(1):54-64.
[30] 童桦,刘一江,易理刚.神经网络在线学习补偿自适应控制及其应用[J].控制理论与应用,2004,21(4):579-583.
[31] Yang Gao and M.J.Er. Online adaptive fuzzy neural identification and control of a class of MIMO nonlinear system [J]. IEEE Trans. Fuzzy Syst., 2003,vol.11(4):462-477.
[32] 冯川,孙增圻,孙富春. 机械手动态T-S神经模糊H∞控制器设计[J]. 清华大学学报(自然科学版),2005,45(1):73-76.
[33] 张友旺,桂卫华 ,赵泉明.基于动态递归模糊神经网络的自适应电液位置跟踪系统[J].控制理论与应用,2005,22(4):551-556.
[34] 刘 军,刘 丁,韩 霞,白华煜. 模糊神经网络控制器的优化设[J].系统工程理论与实践,2004(5):100-105.
[35] Qinghui Wu and Cheng Shao. Novel Hybrid Sliding-mode Controller for DirectTorque Control Induction Motor Drives[J]. Proceedings of the 2006 American Control Conference Minneapolis, Minnesota, USA, June 14-16, 2006, IEEE: 2754-3758.
[36] Weitian Chen and Mehrdad Saif. Novel Sliding Mode Observers for a Class of Uncertain Systems[J]. Proceedings of the 2006 American Control Conference Minneapolis, Minnesota, USA, June 14-16, 2006, IEEE:2622-2627.
[37] Yildiz Y ,Sabanovic A.Neuro sliding mode control of timing belt servo—system [J].Proceedings of the 8th IEEE International Workshop on Advanced Motion Control [C].Piscataway,NJ,USA:IEEE,2004:159 -163.
[38] 陈谋,姜长生.基于神经网络的一类非线性系统自适应滑模控制[J].应用科学学报,2004,22(1):76-80.
[39] Huang S J,Huang K S,Chiou K C.Development and application of a novel radial basis function sliding mode controller [J].Mechatronics,2003,13(4):313-329.
[40] Tong S C,Wang T,Li H X. Fuzzy tracking control design for nonlinear dynamic systems[J]. International Journal of Approximate Reasoning,2002,30(2): 73-90.
[41] 孙炜伟,武玉强. 机器人操作器的自适应模糊滑模控制器设计[J].控制理论与应用, 2006,23(3):397-402.
[42] Chen C T,Peng S T.A nonlinear control scheme for imprecisely known processes using the sliding mode and neural fuzzy technique[J] . Process Control, 2004,14(5):501-515.
[43] Faa-Jeng Lin, Kuo-Kai Shyu, and Rong-Jong Wai.Recurrent -Fuzzy- Neural- Network Sliding-Mode Controlled Motor-Toggle Servomechanism[J].IEEE/ASME TRANSACTIONS ON MECHATRONICS, 2001,6(4):453-466.
[44] Lin F J,Lin C H,Huang P K.Recurrent fuzzy neural network controller designusing sliding — mode control for linear synchronous motor drive[J] . IEE Proceedings: Control Theory and Applications,2004,151(4):407-416.
[45] 吴志远,邵惠鹤一种新的自适应遗传算法及其在多峰值函数优化中的应用[J].控制理论与应用 1999,16(1):127-129.
[46] 曹先彬,郑振.融合神经网络的一种改进遗传算法[J].模式识别与人工智能,1999, 12(4):486-492.
[47] 孙艳丰,戴春荣.几种随机搜索算法的比较研究[J].系统工程与电子技术,1998(2): 43-47.
[48] 戴 晓 晖 ,李 敏 强 ,寇 纪 淞 .遗 传 算 法 理 论 综 述 研 究 [J].控 制 与 决 策 ,2000,15(3): 264-268.
[49] 沈细群.一类未知非线性系统的模糊神经网络自适应鲁棒控制[D].湘潭大学硕士学位论文,2005.
[50] 高隽.人工神经网络原理及仿真实例[M].北京:机械工业出版社,2003.
[51] 赵亮.基于遗传算法的模糊控制和神经网络控制策略研究[D].辽宁工程技术大学硕士论文,2005.
[52] 郑玉胜.基于神经网络的灌溉用水量预测研究[D].武汉大学硕士学位论文,2004.
[53] 楼顺天,施阳.基于 MATLAB 的系统分析与设计[M].西安:西安电子科技大学出版社,1998.
[54] 闻新.MATLAB 神经网络应用设计[M].北京:科学出版社,2000.
[55] 杨 国 军 ,崔 平 远 ,李 琳 琳 .遗 传 算 法 在 神 经 网 络 控 制 中 的 应 用 [J].系 统 仿 真 学报,2001,13(5):567-570.
[56] 赵立波,李丹妮.新型遗传算法的神经网络控制器[J].青岛大学学报,2001,15(1): 40-45.
[57] 刘莉.混合遗传算法全局收敛性分析[D].华中科技大学硕士学位论文,2004.
[58] 闵惜琳,刘国华.人工神经网络结合遗传算法在建模和优化中的应用[J].计算机应用研究,2002,6(1):79-82.
[59] 周志坚,毛宗源.一种基于遗传算法的模糊神经网络最优控制[J]. 控制理论与应用,2000,17(5):784-788.
[60] H.K.Lam,S.H.Ling,F.H.F.Leung,P.K.S.Tam. Tunning of structure and parameters of neural network using an improved genetic algorithm[J]. IEEE 2001.0 -7803-7108-9/01.
[61] 张栋.模糊与神经网络建模的新方法研究[D].北京航空航天大学博士学位论文.2004.
[62] 李仁俊.基于神经网络的自适应逆控制研究[D].昆明理工大学硕士学位论文.2003.
[63] 丛延奇,谢君,张云.基于神经网络的多变量非线性自适应解耦控制研究[J].微计算机信息,2004,20(3):22-23.
[64] 王桂娟等.基于 MATLAB 仿真的神经网络控制器的设计与实现[J].系统仿真学报,2005, 17(3):742-745.
[65] 李琳琳,张广莹,赵长安.未知非线性系统的神经网络跟踪与仿真研究[J]. 系统仿真学报,2001,13(6)732-735.
[66] 陈启 明 ,陈 刚 ,王 勇 浩 .一 种 模 糊 神 经 网 络 控 制 系 统 研 究 [J].系 统 工 程 与 电 子 技术,2005,27(3):501-504.
[67] 安凯.一类适用于非线性动态系统控制的模糊神经网络及其算法[D].西安交通大学博士论文,1999
[68] Guang-Bin Huang,Saratchandran and Narasimhan Sundararajan . A Generalized Growing and Pruning RBF (GGAP-RBF) Neural Network for Function Approximation [J]. IEEE Transactions on Neural Networks,2005,16(1):57-67.
[69] 陈国良,王煦法等.遗传算法及其应用[M].北京:人民邮电出版社,2001.
[70] 关志华,寇纪松,李敏强.一种改进的遗传算法 Scatter GA[J].控制与决策,2002, 17(5):479-582.
[71] 蒋伟进,罗定提等.新型混合遗传算法研究及其在问题优化中的应用[C].第五届全球智能控制与自动化大会,2004.
[72] 都 伟 ,韩 正 之 .一 种 自 适 应 杂 交 算 子 的 浮 点 遗 传 算 法 [J].系 统 仿 真 学 报 ,2006, 18(6):1711-1713.
[73] Rudolph G..Convergence analysis of canonical genetic algorithms[J]. IEEE Transaction on Neural Networks, 1994,5(1):96-10.
[74] 北京昆仑通态自动化软件科技有限公司. MCGS 用户指南[D].北京:北京昆仑通态自动化软件科技有限公司.
[2] 胡守仁,沈清,胡德文,时春.神经网络应用技术[M].长沙:国防科学技术出版社,1995.
[3] 王秀峰.系统建模与辨识[M].北京:电子工业出版社,2004.
[4] 韩曾晋.自适应控制[M].北京:清华大学出版社,2002.
[5] 王永城,涂建.神经元网络控制[M].北京:机械工业出版社,1998.
[6] 费树氓.非线性控制系统与设计[M].北京:电子工业出版社,1998.
[7] A.M. Karshenas, M .w. Dunnigan and Williams. Adaptive inverse control algorithm for shock testing[J].IEE proc.-Control Theory App1.,2000,147(3):267-276.
[8] 易之光.自适应逆控制方法及其应用研究[D].燕山大学硕士学位论文,2005.
[9] Widrow B, Eugene Walach.自适应逆控制[M].西安: 西安交通大学出版社,2000.
[10] C.L.M Hamold,K.Y.Lee. Free-model Based Adaptive Inverse Neurocontroller for Dynamic systems[C].The37th IEEE Conference on Decision and Contro1,Tampa, Florida,1998:507-512.
[11] C.L.M.Harnold,K.Y.Lee Application of the Free-mode1Based Neura1 Networks in Model Reference Adaptive Inverse Control[C]. American Control Conference,Chicago,Illinois,2000:1664-1668.
[12] G.L.Plett,H.Botrich.DDEK-F Learning for Fast Nonlinear Adaptive Inverse Control[C]. International Joint Conference on Neural Networks, 2002:2092-2097.
[13] 张兴华.戴先中基于逆系统方法感应电机调速控制系统[J].控制与决策, 2000 , 15 (6):708-711.
[14] 刘士荣,俞金寿.神经逆模型 PID复合控制在 CSTR中的应用[J].控制理论与应用,2001, 18 (5):769-773.
[15] 党映农,韩崇昭.基于 Volterra 基函数网络的自适应逆控制方法[J].西安交通大学学报,2000,34(9):8-12.
[16] 秦 孝 艳 .一 类 非 线 性 系 统 的 鲁 棒 自 适 应 跟 踪 控 制 [J].安 徽 工 业 大 学 学 报 ,2006, 23(3):360-364.
[17] 丘 东 强 , 涂 亚 庆 . 神 经 网 络 控 制 的 现 状 与 展 望 [J]. 自 动 化 与 仪 器 仪 表 ,2001, 97(5):1-7.
[18] Sanner R M, Slotine J J. Gaussian networks for direct adaptive control[J].IEEE Transaction on Neural Networks, 1992, 3 (6): 837-863.
[19] T.Zhang, S. S. Ge, and C .C .Hang. Stable Adaptive Control for a Class of Nonlinear Systems Using a Modified Lyapunov Function [J], IEEE Trans. On Automatic Control,2000,45:129-135.
[20] Zhuo Wang,Ping Li,Shuo Guo. Adaptive inverse control for nonlinear systems based on RBF neural network [J]. Intelligent Control and Automation, 2004,Volume 1:485-487.
[21] 唐超颖,王彪.基于在线神经网络的自适应控制器的设计与应用[J].华南理工大学学报(自然科学版)2006,34(6):34-38.
[22] Sunan N . huang, K .K.Tan and T .H.Lee. Further Results on Adaptive Control for a Class of Nonlinear Systems Using Neural Networks[J]. IEEE Transaction On Neural Networks, 2003, 14 (3):719-722.
[23] Tomahisa Hauakawa, Wassim M. Haddad,Naira Hovakimyan and Vijay Sekhar Chellaboina. Neural Network Adaptive Control for Nonlinear Nonnegative Dynamical Systems [J]. IEEE Transactions on Neural Networks, 2005,16 (2):399-413.
[24] 杜红彬,邵惠鹤.一类非线性系统的自适应神经网络控制[J].控制与决策,2005, 20(4):455-459.
[25] H.E.Psillakis and A.T.Alexandridis. Adaptive Neural Motion Control of n-link Robot Manipulators Subject to Unknown Disturbances and Stochastic Perturbations [J].IEEE Proc.-Control Theory Appl.,2006, 153(2):127-138.
[26] Y. Li, S. Qiang, X. Zhung, and O. Kaynak. Robust and adaptive backstepping control for nonlinear systems using RBF neural networks[J].IEEE Trans. Neural Network, 2004,15(3): 693–701.
[27] S. S. Ge and J. Zhang.Neural-network control of nonaffine nonlinear system with zero dynamics by state and output feedback[J].IEEE Trans. Neural Network,2003,14(4): 900–918.
[28] Shuzhi Sam Ge and Cong Wang .Adaptive Neural Control of Uncertain MIMO Nonlinear Systems[J].IEEE TRANSACTIONS ON NEURAL NETWORKS, 2004, 15(3):674-692.
[29] Youshen S. Xia, Gang Feng, and Jun Wang. A Primal-Dual Neural Network for Online Resolving Constrained Kinematic Redundancy in Robot Motion Control[J].IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS—PART B:CYBERNETICS, 2005, 35(1):54-64.
[30] 童桦,刘一江,易理刚.神经网络在线学习补偿自适应控制及其应用[J].控制理论与应用,2004,21(4):579-583.
[31] Yang Gao and M.J.Er. Online adaptive fuzzy neural identification and control of a class of MIMO nonlinear system [J]. IEEE Trans. Fuzzy Syst., 2003,vol.11(4):462-477.
[32] 冯川,孙增圻,孙富春. 机械手动态T-S神经模糊H∞控制器设计[J]. 清华大学学报(自然科学版),2005,45(1):73-76.
[33] 张友旺,桂卫华 ,赵泉明.基于动态递归模糊神经网络的自适应电液位置跟踪系统[J].控制理论与应用,2005,22(4):551-556.
[34] 刘 军,刘 丁,韩 霞,白华煜. 模糊神经网络控制器的优化设[J].系统工程理论与实践,2004(5):100-105.
[35] Qinghui Wu and Cheng Shao. Novel Hybrid Sliding-mode Controller for DirectTorque Control Induction Motor Drives[J]. Proceedings of the 2006 American Control Conference Minneapolis, Minnesota, USA, June 14-16, 2006, IEEE: 2754-3758.
[36] Weitian Chen and Mehrdad Saif. Novel Sliding Mode Observers for a Class of Uncertain Systems[J]. Proceedings of the 2006 American Control Conference Minneapolis, Minnesota, USA, June 14-16, 2006, IEEE:2622-2627.
[37] Yildiz Y ,Sabanovic A.Neuro sliding mode control of timing belt servo—system [J].Proceedings of the 8th IEEE International Workshop on Advanced Motion Control [C].Piscataway,NJ,USA:IEEE,2004:159 -163.
[38] 陈谋,姜长生.基于神经网络的一类非线性系统自适应滑模控制[J].应用科学学报,2004,22(1):76-80.
[39] Huang S J,Huang K S,Chiou K C.Development and application of a novel radial basis function sliding mode controller [J].Mechatronics,2003,13(4):313-329.
[40] Tong S C,Wang T,Li H X. Fuzzy tracking control design for nonlinear dynamic systems[J]. International Journal of Approximate Reasoning,2002,30(2): 73-90.
[41] 孙炜伟,武玉强. 机器人操作器的自适应模糊滑模控制器设计[J].控制理论与应用, 2006,23(3):397-402.
[42] Chen C T,Peng S T.A nonlinear control scheme for imprecisely known processes using the sliding mode and neural fuzzy technique[J] . Process Control, 2004,14(5):501-515.
[43] Faa-Jeng Lin, Kuo-Kai Shyu, and Rong-Jong Wai.Recurrent -Fuzzy- Neural- Network Sliding-Mode Controlled Motor-Toggle Servomechanism[J].IEEE/ASME TRANSACTIONS ON MECHATRONICS, 2001,6(4):453-466.
[44] Lin F J,Lin C H,Huang P K.Recurrent fuzzy neural network controller designusing sliding — mode control for linear synchronous motor drive[J] . IEE Proceedings: Control Theory and Applications,2004,151(4):407-416.
[45] 吴志远,邵惠鹤一种新的自适应遗传算法及其在多峰值函数优化中的应用[J].控制理论与应用 1999,16(1):127-129.
[46] 曹先彬,郑振.融合神经网络的一种改进遗传算法[J].模式识别与人工智能,1999, 12(4):486-492.
[47] 孙艳丰,戴春荣.几种随机搜索算法的比较研究[J].系统工程与电子技术,1998(2): 43-47.
[48] 戴 晓 晖 ,李 敏 强 ,寇 纪 淞 .遗 传 算 法 理 论 综 述 研 究 [J].控 制 与 决 策 ,2000,15(3): 264-268.
[49] 沈细群.一类未知非线性系统的模糊神经网络自适应鲁棒控制[D].湘潭大学硕士学位论文,2005.
[50] 高隽.人工神经网络原理及仿真实例[M].北京:机械工业出版社,2003.
[51] 赵亮.基于遗传算法的模糊控制和神经网络控制策略研究[D].辽宁工程技术大学硕士论文,2005.
[52] 郑玉胜.基于神经网络的灌溉用水量预测研究[D].武汉大学硕士学位论文,2004.
[53] 楼顺天,施阳.基于 MATLAB 的系统分析与设计[M].西安:西安电子科技大学出版社,1998.
[54] 闻新.MATLAB 神经网络应用设计[M].北京:科学出版社,2000.
[55] 杨 国 军 ,崔 平 远 ,李 琳 琳 .遗 传 算 法 在 神 经 网 络 控 制 中 的 应 用 [J].系 统 仿 真 学报,2001,13(5):567-570.
[56] 赵立波,李丹妮.新型遗传算法的神经网络控制器[J].青岛大学学报,2001,15(1): 40-45.
[57] 刘莉.混合遗传算法全局收敛性分析[D].华中科技大学硕士学位论文,2004.
[58] 闵惜琳,刘国华.人工神经网络结合遗传算法在建模和优化中的应用[J].计算机应用研究,2002,6(1):79-82.
[59] 周志坚,毛宗源.一种基于遗传算法的模糊神经网络最优控制[J]. 控制理论与应用,2000,17(5):784-788.
[60] H.K.Lam,S.H.Ling,F.H.F.Leung,P.K.S.Tam. Tunning of structure and parameters of neural network using an improved genetic algorithm[J]. IEEE 2001.0 -7803-7108-9/01.
[61] 张栋.模糊与神经网络建模的新方法研究[D].北京航空航天大学博士学位论文.2004.
[62] 李仁俊.基于神经网络的自适应逆控制研究[D].昆明理工大学硕士学位论文.2003.
[63] 丛延奇,谢君,张云.基于神经网络的多变量非线性自适应解耦控制研究[J].微计算机信息,2004,20(3):22-23.
[64] 王桂娟等.基于 MATLAB 仿真的神经网络控制器的设计与实现[J].系统仿真学报,2005, 17(3):742-745.
[65] 李琳琳,张广莹,赵长安.未知非线性系统的神经网络跟踪与仿真研究[J]. 系统仿真学报,2001,13(6)732-735.
[66] 陈启 明 ,陈 刚 ,王 勇 浩 .一 种 模 糊 神 经 网 络 控 制 系 统 研 究 [J].系 统 工 程 与 电 子 技术,2005,27(3):501-504.
[67] 安凯.一类适用于非线性动态系统控制的模糊神经网络及其算法[D].西安交通大学博士论文,1999
[68] Guang-Bin Huang,Saratchandran and Narasimhan Sundararajan . A Generalized Growing and Pruning RBF (GGAP-RBF) Neural Network for Function Approximation [J]. IEEE Transactions on Neural Networks,2005,16(1):57-67.
[69] 陈国良,王煦法等.遗传算法及其应用[M].北京:人民邮电出版社,2001.
[70] 关志华,寇纪松,李敏强.一种改进的遗传算法 Scatter GA[J].控制与决策,2002, 17(5):479-582.
[71] 蒋伟进,罗定提等.新型混合遗传算法研究及其在问题优化中的应用[C].第五届全球智能控制与自动化大会,2004.
[72] 都 伟 ,韩 正 之 .一 种 自 适 应 杂 交 算 子 的 浮 点 遗 传 算 法 [J].系 统 仿 真 学 报 ,2006, 18(6):1711-1713.
[73] Rudolph G..Convergence analysis of canonical genetic algorithms[J]. IEEE Transaction on Neural Networks, 1994,5(1):96-10.
[74] 北京昆仑通态自动化软件科技有限公司. MCGS 用户指南[D].北京:北京昆仑通态自动化软件科技有限公司.