LIN XuMei 1,2, MEI Tao1, LUO MinZhou1, SONG YanFeng1
1.Center of Biomimetic Sensing and Control Research, Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei 230031 2.Department of Precision Machinery and Precision Instrumentation, School of Engineering Science, University of Science and Technology of China, Hefei 230026
Abstract Generalization is very important in Cerebellar Model Articulation Controller (CMAC). If CMAC has good generalization, it will have high precision. In this paper, the principle, structure and learning algorithm of CMAC are described. The relationship between the quantification precision and sampling precision that influences the generalization is discussed theoretically. Simulation results show the correctness of relationship between the quantification and sampling precision, and the conclusion that the quantification precision should be higher than the sampling precision is gotten. Moreover, a new kind of optimization based on pareto genetic algorithm (PGA) about generalization parameter and quantification precision is proposed. Experimental results show the correctness of the new method.
[1] Albus J S. A New Approach to Manipulator Control: The Cerebellar Model Articulation Controller (CMAC). Journal of Dynamic Systems Measurement and Control, 1975, 97(3): 220-227 [2] Albus J S. Data Storage in the Cerebellar Model Articulation Controller. Journal of Dynamic Systems Measurement and Control, 1975, 97(3): 228-233 [3] Kim C M, Choi K H, Cho Y B. Hardware Design of CMAC Neural Network for Control Applications. In: Proc of the International Joint Conference on Neural Networks. Portland, USA, 2003, Ⅱ: 953-958 [4] Lin C M, Peng Y F. Adaptive CMAC-Based Supervisory Control for Uncertain Nonlinear Systems. IEEE Trans on Systems, Man, and Cybernetics-Part B: Cybernetics, 2004, 34(2): 1248-1260 [5] Cetinkunt S, Donmez M A. CMAC Learning Controller for Servo Control of High Precision Machine Tools. In: Proc of American Control Conference. San Francisco, USA, 1993, 1976-1980 [6] He C, Xu L X, Zhang Y H. Convergence and Generalization Ability of CMAC. Control and Decision, 2001,16(5): 523-529 (in Chinese) (何 超,徐立新,张宇河.CMAC 算法收敛性分析及泛化能力研究.控制与决策, 2001, 16(5): 523-529) [7] Ouyang K, Chen H, Zhou P, et al. Generalization of Neural Network Model (CMAC) for Coordinate Transformation in Neural Computation. Acta Automatica Sinica, 1997, 23(4): 475-481 (in Chinese) (欧阳楷,陈 卉,周 萍,等.神经计算中坐标变换的网络模型(CMAC) 的泛化特性.自动化学报, 1997, 23(4): 475-481) [8] Oppenheim A V,Schafer R W. Discrete-Time Signal Processing.Englewood Cliffs, USA: Prentice-Hall,1989 [9] LI M Q. Basic Theory and Application of GA. Beijing, China: Science Press, 2002 (in Chinese) (李敏强,著.遗传算法的基本理论与应用.北京:科学出版社, 2002) [10] Ma L, Zhang Y D. Multiobjective Genetic Algorithms and Its Application to the Design of Automatic Control System. Systems Engineering and Electronics, 1997, 19(9): 71-76 (in Chinese) (马 岚,张燕东.多目标遗传算法及其在自动控制系统设计中的应用.系统工程与电子技术, 1997, 19(9): 71-76)
2006, Vol. 19 
