Deadzone compensation based on constrained RBF neural network

In this paper, a modified adaptive neural network for the compensation of deadzone is described, and simulated on a hydraulic positioning system, in which the dynamic model is separated into a series of connection of a nonlinear (deadzone) subsystem and a linear plant. The proposed approach uses two neural networks. One is the radial basis function (RBF) neural network, which is used for identifying parameters of deadzone. Based on the penalty function used in optimization theory, a multi-objective cost function with constraint is adopted to provide the best deadzone approximation. The result is used to train the other neural network for the inverse compensation of deadzone. The RBF neural network also generates the parameters of the linear plant for the design of an adaptive controller. A convergence analysis for the network training process is also presented.

[1]  瀬古 美喜.  「Urban Economics and Real Estate Markets」by Denise DiPasquale and William C.Wheaton(Prentice Hall,Englewood Cliffs,NJ,1996,378pages) , 1997 .

[2]  Okyay Kaynak,et al.  A comparative study of neural network structures in identification of nonlinear systems , 1999 .

[3]  Chng Eng Siong,et al.  Efficient computational schemes for the orthogonal least squares algorithm , 1995, IEEE Trans. Signal Process..

[4]  Gang Tao,et al.  Adaptive control of plants with unknown dead-zones , 1994 .

[5]  George Cybenko.  Neural networks in computational science and engineering , 1996 .

[6]  L.M.C. Buydens,et al.  Performance of multi-layer feedforward and radial base function neural networks in classification and modelling , 1996 .

[7]  Shengwei Zhang,et al.  Lagrange programming neural networks , 1992 .

[8]  Frank L. Lewis,et al.  Deadzone compensation in motion control systems using neural networks , 2000, IEEE Trans. Autom. Control..

[9]  B. L. Deekshatulu,et al.  Parameter identification via neural networks with fast convergence , 2000 .

[10]  L.M.C. Buydens,et al.  Robustness analysis of radial base function and multi-layered feed-forward neural network models , 1995 .

[11]  Astrom.  Computer Controlled Systems , 1990 .

[12]  E. Bai,et al.  Convergence results for an adaptive dead zone inverse , 1998 .

[13]  Heinz Unbehauen,et al.  Adaptive position control of electrohydraulic servo systems using ANN , 2000 .

[14]  Frank L. Lewis,et al.  Deadzone compensation in motion control systems using adaptive fuzzy logic control , 1999, IEEE Trans. Control. Syst. Technol..

[15]  Stephen A. Billings,et al.  On-line Supervised Adaptive Training Using Radial Basis Function Networks , 1996, Neural Networks.

[16]  Kwang Bo Cho,et al.  Radial basis function based adaptive fuzzy systems and their applications to system identification and prediction , 1996, Fuzzy Sets Syst..

[17]  Marios M. Polycarpou,et al.  Learning and convergence analysis of neural-type structured networks , 1992, IEEE Trans. Neural Networks.

[18]  Stephen A. Billings,et al.  International Journal of Control , 2004 .

[19]  Jong-Hwan Kim,et al.  Control of systems with deadzones using neural-network based learning controller , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[20]  Tommy W. S. Chow,et al.  Training multilayer neural networks using fast global learning algorithm - least-squares and penalized optimization methods , 1999, Neurocomputing.