Indirect adaptive self-organizing RBF neural controller design with a dynamical training approach

This study proposes an indirect adaptive self-organizing RBF neural control (IASRNC) system which is composed of a feedback controller, a neural identifier and a smooth compensator. The neural identifier which contains a self-organizing RBF (SORBF) network with structure and parameter learning is designed to online estimate a system dynamics using the gradient descent method. The SORBF network can add new hidden neurons and prune insignificant hidden neurons online. The smooth compensator is designed to dispel the effect of minimum approximation error introduced by the neural identifier in the Lyapunov stability theorem. In general, how to determine the learning rate of parameter adaptation laws usually requires some trial-and-error tuning procedures. This paper proposes a dynamical learning rate approach based on a discrete-type Lyapunov function to speed up the convergence of tracking error. Finally, the proposed IASRNC system is applied to control two chaotic systems. Simulation results verify that the proposed IASRNC scheme can achieve a favorable tracking performance.

[1]  Vadlamani Ravi,et al.  Differential evolution trained wavelet neural networks: Application to bankruptcy prediction in banks , 2009, Expert Syst. Appl..

[2]  Maria Bortman,et al.  A Growing and Pruning Method for Radial Basis Function Networks , 2009, IEEE Transactions on Neural Networks.

[3]  Weiping Li,et al.  Applied Nonlinear Control , 1991 .

[4]  Huai-Ning Wu,et al.  Active fault-tolerant fuzzy control design of nonlinear model tracking with application to chaotic systems , 2009 .

[5]  Chih-Min Lin,et al.  Intelligent adaptive control for MIMO uncertain nonlinear systems , 2008, Expert Syst. Appl..

[6]  Chih-Min Lin,et al.  Adaptive CMAC-based supervisory control for uncertain nonlinear systems , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[7]  Chun-Fei Hsu,et al.  Recurrent fuzzy-neural approach for nonlinear control using dynamic structure learning scheme , 2008, Neurocomputing.

[8]  Chun-Fei Hsu,et al.  Identification-based chaos control via backstepping design using self-organizing fuzzy neural networks , 2009 .

[9]  Ya-Fu Peng.  Adaptive intelligent backstepping longitudinal control of vehicleplatoons using output recurrent cerebellar model articulation controller , 2010, Expert Syst. Appl..

[10]  Chih-Min Lin,et al.  Supervisory recurrent fuzzy neural network control of wing rock for slender delta wings , 2004, IEEE Trans. Fuzzy Syst..

[11]  Tsu-Tian Lee,et al.  Neuroadaptive Combined Lateral and Longitudinal Control of Highway Vehicles Using RBF Networks , 2006, IEEE Transactions on Intelligent Transportation Systems.

[12]  Guanrong Chen,et al.  On feedback control of chaotic continuous-time systems , 1993 .

[13]  Chun-Fei Hsu,et al.  Adaptive fuzzy wavelet neural controller design for chaos synchronization , 2011, Expert Syst. Appl..

[14]  Ming-Feng Yeh,et al.  A self-organizing CMAC network with gray credit assignment , 2006, IEEE Trans. Syst. Man Cybern. Part B.

[15]  Chih-Min Lin,et al.  Adaptive CMAC neural control of chaotic systems with a PI-type learning algorithm , 2009, Expert Syst. Appl..

[16]  Narasimhan Sundararajan,et al.  A generalized growing and pruning RBF (GGAP-RBF) neural network for function approximation , 2005, IEEE Transactions on Neural Networks.

[17]  Oguz Ustun,et al.  A neuro-fuzzy controller for speed control of a permanent magnet synchronous motor drive , 2008, Expert Syst. Appl..

[18]  Chaio-Shiung Chen,et al.  Dynamic structure adaptive neural fuzzy control for MIMO uncertain nonlinear systems , 2009, Inf. Sci..

[19]  Rong-Jong Wai,et al.  Design of backstepping particle-swarmoptimisation control for maglev transportation system , 2010 .

[20]  Tong Zhao,et al.  RBFN-based decentralized adaptive control of a class of large-scale non-affine nonlinear systems , 2008, Neural Computing and Applications.

[21]  Davut Hanbay,et al.  An expert system based on wavelet decomposition and neural network for modeling Chua's circuit , 2008, Expert Syst. Appl..

[22]  Chih-Min Lin,et al.  Wavelet Adaptive Backstepping Control for a Class of Nonlinear Systems , 2006, IEEE Transactions on Neural Networks.

[23]  Ming-Feng Yeh,et al.  Standalone CMAC Control System With Online Learning Ability , 2010, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[24]  Chih-Min Lin,et al.  SYNCHRONIZATION OF CHAOTIC GYRO SYSTEMS USING RECURRENT WAVELET CMAC , 2010, Cybern. Syst..

[25]  Faa-Jeng Lin,et al.  Recurrent-Fuzzy-Neural-Network-Controlled Linear Induction Motor Servo Drive Using Genetic Algorithms , 2007, IEEE Transactions on Industrial Electronics.

[26]  Y.-C. Chang.  Robust H/sup /spl infin// control for a class of uncertain nonlinear time-varying systems and its application , 2004 .

[27]  C. S. George Lee,et al.  Neural fuzzy systems: a neuro-fuzzy synergism to intelligent systems , 1996 .

[28]  Chun-Fei Hsu,et al.  Self-Organizing Adaptive Fuzzy Neural Control for a Class of Nonlinear Systems , 2007, IEEE Transactions on Neural Networks.

[29]  Chun-Fei Hsu.  Adaptive growing-and-pruning neural network control for a linear piezoelectric ceramic motor , 2008, Eng. Appl. Artif. Intell..

[30]  Andrew Chi-Sing Leung,et al.  Combined learning and pruning for recurrent radial basis function networks based on recursive least square algorithms , 2005, Neural Computing & Applications.