臺灣博碩士論文加值系統

在本文中，使用適應控制及小腦模型(Cerebellar Model Articulation Controller)理論來學習補償油壓伺服系統的非線性死區(deadzone) 現象，把受控動態系統模型分解成非線性的死區系統及線性系統。使用兩個小腦模型，一個小腦模型用來鑑別死區參數。鑑別出來的死區參數用來訓練另一個反死區補償的小腦模型，反死區補償可用來消除非線性死區現象。線性系統的參數使用遞迴鑑定理論來作系統鑑別，鑑別得到的參數使用參考模型及極點配置法來設計控制器，模擬可以得到良好結果。

In this paper, the utilization of adaptive control and Cerebellar Model Articulation Controller is the compensation of the phenomenon of Non-Linear Deadzone which is in Servo-Hydraulic System. In addition, the controlled-dynamical model is separated into Non-Linear Deadzone System and Linear Time-Invariant System. In the systems, there are two Cerebellar Model Articulation Controller; One is for identifying the parameters of Deadzone, then the result is used to train the other one which is used for the inverse compensation of Deadzone that is employed to eliminate the phenomenon of Non-Linear Deadzone. The parameters of Liner System in the theory of Recursive identification are utilized to identify the systems, and the parameters from the end of the testament are used model reference adaptive pole placement to design the controller. According to these simulations, it can be obtained good results.

中 文 摘 要i
ABSTRACTii
誌謝iii
目 錄iv
圖 目 錄vi
表 目 錄vii
第一章 緒論1
1.1 前言1
1.2 文獻回顧2
1.2.1 類神經網路之文獻回顧2
1.2.2 CMAC 之文獻回顧2
1.2.3 DCMAC 之文獻回顧3
1.2.4 死區之文獻回顧4
1.3 研究動機5
1.4 論文架構6
第二章 小腦模型理論7
2.1 簡介7
2.2 傳統 CMAC 理論7
2.3 傳統 CMAC 的基本架構8
2.3.1 CMAC 之使用程序11
2.4 可微分小腦模型（DCMAC）理論12
2.4.1 DCMAC 之使用程序16
第三章 系統控制器設計17
3.1 控制系統架構17
第四章 控制器及反死區補償器設計21
4.1設定死區估測小腦模型22
第五章 模擬結果28
第六章 結論31
參考文獻32

[1] M. Gori, A. Tesi, “On The Problem Of Local Minima In Back-propagation,” IEEE Transactions. Pattern Anal. Mach. Intell (1992).
[2] K.S. Narendra, L.G. Kraft, L. Ungar, S.T. Venkataraman, “Neural Networks for Identification and Control, 33 IEEE Constabilizer Applications Using Participation Factors,” IEEE Proc. 134 ference on Decision and Control, Workshop no. 6, pp. 12-13, December (1994).
[3] D.E. Rumelhart, G.E. Hinton, and R.J. Williams, “Learning Internal Representation by Error Propagation,” Parallel Distributed Processing, Vol. 1 (1986).
[4] R. Grino, G. Cembrano, and C. Torras, “Nonlinear System Identification Using Additive Dynamic Neural Networks-two On-line Approaches,” IEEE Transactions on Circuits and Systems, Part I: Fundamental Theory and Applications, Vol. 47, No. 2, pp. 150-165, February (2000).
[5] J.C. Patra, R.N. Pal, B.N. Chatterji, and G. Panda, “Identification of Nonlinear Dynamic Systems Using Functional Link Artificial Neural Networks,” IEEE Transactions on Systems, Man and Cybernetics, Part B, Vol. 29, No. 2, April (1999).
[6] J.S.Albus, A New Approach ManipulatorControl: The Cerebellar Model Articulation Controller(CMAC), Journal of Dynamic Systems, Measurement and Control, Transaction of ASME, 220-227 (97) (1975).
[7] J.S. Albus, Data Storage in the Cerebellar Model Articulation Controller(CMAC),Journal of Dynamic Systems,Measurement and Control ,Transaction of ASME ,228-233, (97) (1975).
[8] W.Thomas Miller,Filson H.Glanz and L.Gordon Kraf,"CMAC :An Associative Neural Network Alternative to Backpropagation,"Proceeding of the IEEE,Vol.78,No.10,pp.1561-1567 (1990).
[9] Miller,T.W.,Glanz,F.H.,and Kraft,L.G, "Application of a General Learning Algorithm to the Control of Robotics Manipulators,"The International Journal of Robotics Research,Vol.,6,No.2,pp.84-98 (1987).
[10] Chun-Shin Lin and Hyongsuk Kim, " CMAC-Based Adaptive CriticSelf-Learning Control, "IEEE Transactions on Neural Network,Vol.2,No.5,pp.530-535 (1996).
[11] Chun-Shin Lin and Hyongsuk Kim, "Selection of Learning Parameters for CMAC-Based Adaptive Critic Learning, "IEEE Transactions on Neural Network,Vol.6,No.3,pp.642-647 (1996).
[12] Karr,C.L., "Applying Genetic to fuzzy logic ,"AI Expert ,pp.38-43,March (1991).
[13] Neil E.Cotter and Thierry J.Guillerm, "The CMAC and a Theorem of Kolmogorov, "Neural Network ,Vol.5 , pp.221-228 (1991).
[14] P.C.Parks and J.Militizer, "A Comparison of Five Algorithm for the Training of CMAC Memories for Learning Control Systems, "Vol.28,No.5,pp.1027-1035 (1992).
[15] Yiu-fai Wong and Athanasions Sideris, "Learning Convergence in the Model Articulation Controller, "IEEE Transactions on Neural Network,Vol.3,No.1,pp.115-121 (1992).
[16] Neil E. Cotter and Omar N. Main, "A Pulsed Neural Network Capable of Universal Approximation, "IEEE Transactions on Neural Network,Vol,3,No.2,pp.308-314 (1992).
[17] Ching-Tsan Chiang and Chun-Shin Lin, "CMAC with General Basis Functions, "Neural Networks,Vol.9,No.7, pp.1199-1211 (1996).
[18] S.H.Lane, D.A.Handelman, J.J.Gelfand, "Theory and Development of Higher-Order CMAC Neural Network, " IEEE Contr.Syst.,Vol,12,pp.23-30 (1992).
[19] C.T.Chiang and C.S.Lin, "Integration of CMAC and Radial Basis Function Techniques, "IEEE International Conference on Intelligent Systems for the 21st , Vol4 , pp3263-3268 (1995).
[20] Tao, G. and Kokotović, P.V. "Adaptive control of plants with unknow dead-zones", IEEE Transactions on Automatic Control, Vol. 39, No. 1, pp. 59-68 (1994).
[21] Wang, X.-S., Su, C.-Y., and Hong, H. "Robust adaptive control of a class of nonlinear systems with unknow dead-zone", Automatica, Vol. 40, No. 3, pp. 407-413 (2004).
[22] Zhou, J., Wen, C., and Zhang, Y. "Adaptive output control of nonlinear systems with uncertain dead-zone nonlinearity", IEEE Transactions on Automatic Control, Vol. 51, No. 3, pp. 504-511 (2006).
[23] Ibrir, S., Xie, W.F., and Su, C.-Y. "Adaptive tracking of nonlinear systems with nonsymmetric dead-zone input", Automatica, Vol. 43, No. 3, pp. 522-530 (2007).
[24] Tsai, C.-H. and Chuang, H.-T. "Deadzone compensation based on constrained RBF neural network", Journal of The Franklin Institute, Vol.341, No.4, pp. 361-374 (2004).
[25] Zhang, T.-P. and Ge, S.S., "Adaptive neural control of MIMO nonlinear state timevarying delay systems with unknown dead-zones and gain signs", Automatica, Vol. 43, No. 6, pp. 1021-1033 (2007).
[26] Corradini, M.L. and Orlando, G, "Robust stabilization of nonlinear uncertain plants with backlash or dead zone in the actuator", IEEE Transactions on Control Systems Technology, Vol. 10, No. 1, pp. 158-166 (2002).
[27] Shyu, K.-K., Liu, W.-J., and Hsu, K.-C., "Design of large-scale time-delayed systems with dead-zone input via variable structure control", Automatica, Vol. 41, No. 7, pp. 1239-1246 (2005).
[28] Kim, J.-H., Park, J.-H., Lee, S.-W., and Chong, E.K.P., "A two-layered fuzzy logic controller for systems with deadzones", IEEE Transactions on Industrial Electronics, Vol. 41, No. 2, pp. 155-162 (1994).
[29] Oh, S.-Y. and Park, D.-J., "Design of new adaptive fuzzy logic controller for nonlinear plants with unknown or time-varying dead zones", IEEE Transactions on Fuzzy Systems, Vol. 6, No. 4, pp. 482-491 (1998).
[30] Šelmić, R.R. and Lewis, F.L., "Deadzone compensation in motion control systems using neural networks",IEEE Transactions on Automatic Control, Vol. 45, No. 4, pp. 602-613 (2000).
[31] Zhou, J., Wen, C., and Zhang, Y., "Adaptive output control of nonlinear systems with uncertain dead-zone nonlinearity", IEEE Transactions on Automatic Control, Vol. 51, No. 3, pp. 504-511 (2006).
[32] Lewis, F.L., Tim, W.K., Wang, L.-Z., and Li, Z.X., "Deadzone compensation in motion control systems using adaptive fuzzy logic control", IEEE Transactions on Control Systems Technology, Vol. 7, No. 6, pp. 731-742 (1999).
[33] H. Cho, E.W. Bai, Convergence results for an adaptive deadzone inverse, Int. J.A daptive .Control Signal Processing. 451–466 (1998).
[34] G. Tao, P.V. Kokotivic, Adaptive control of plants with unknown deadzones, IEEE T rans . Autom . Control 39 (1) 59–68 (1994).
[35] F.L. Lewis, W.K. Tim, L.Z. Wang, Z.X.Li, Deadzone compensation in motion control systems using adaptive fuzzy logic control, IEEE Control Syst.Technol. 7 (6) 731–742 (1999).
[36] R.R. Selmic, F.L. Lewis, Deadzone compensation in motion control systems using neural networks, IEEE Trans.Autom. Control 45 (4) 602–613 (2000).
[37] T. Knohl, H. Unbehauen, Adaptive position control of electrohydraulic servo systems using ANN, Mechatronics 10,127–173 (2000).
[38] C.H. Tsai, H.T. Chuang, Deadzone compensation based on constrained RBF neural network, Journal of the Franklin Institute 341,361-374 (2004).
[39] 韓曾晉，適應控制系統，台北：科技圖書股份有限公司(2002)。
[40] 張力祥，“可微分小腦模型用於函數逼近及馬達控制”，中原大學電機工程學系碩士論文 (2003)。