Selection of optimal learning rates in CMAC based control schemes

CMAC based control schemes have been studied by many researchers. It is well recognized that properly designed CMAC controllers provide useful and practical tools for precision control of nonlinear systems. For complex trajectories, however, the convergence speed of CMAC can be slow because the CMAC module takes much time in learning the inverse dynamics of the plant. Therefore, one practical difficulty of CMAC based controller design is the selection of appropriate learning rate. In this paper, we present a method for selection of optimal CMAC learning rate. Furthermore, we demonstrate that the proposed GA-based approach to parameter selection can provide a global optimal solution. Computer simulation results confirm the effectiveness of the proposed method.

[1]  Xaro Benavent,et al.  Two suggestions for efficient implementation of CMAC's , 2000, Proceedings of the 2000 IEEE International Symposium on Intelligent Control. Held jointly with the 8th IEEE Mediterranean Conference on Control and Automation (Cat. No.00CH37147).

[2]  Zhang Youwei,et al.  Parametric optimization in nonlinear system based on genetic algorithms , 2000, WCC 2000 - ICSP 2000. 2000 5th International Conference on Signal Processing Proceedings. 16th World Computer Congress 2000.

[3]  F J Gonzalez Serrano,et al.  FOURIER ANALYSIS OF THE GENERALIZED CMAC NERAL NETWORK , 1998 .

[4]  Fu-Chuang Chen,et al.  Practical stability issues in CMAC neural network control systems , 1996, IEEE Trans. Control. Syst. Technol..

[5]  Filson H. Glanz,et al.  Application of a General Learning Algorithm to the Control of Robotic Manipulators , 1987 .

[6]  Antonio Artés-Rodríguez,et al.  Fourier analysis of the generalized CMAC neural network , 1998, Neural Networks.

[7]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[8]  Chien-Chung Lin,et al.  Improved CMAC neural network control scheme , 1999 .

[9]  James S. Albus,et al.  New Approach to Manipulator Control: The Cerebellar Model Articulation Controller (CMAC)1 , 1975 .

[10]  W. Thomas Miller,et al.  Real-time dynamic control of an industrial manipulator using a neural network-based learning controller , 1990, IEEE Trans. Robotics Autom..

[11]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[12]  Jing Wang,et al.  The optimization of PI controller parameters using genetic algorithm in the DC speed control system , 2000, Proceedings of the 3rd World Congress on Intelligent Control and Automation (Cat. No.00EX393).