Data based predictive control using neural networks and stochastic approximation

A novel data based predictive control method is proposed by introducing the notion of neural network based predictive control to a model-free control method based on Simultaneous Perturbation Stochastic Approximation (SPSA). The controller is constructed through use of a Function Ap-proximator (FA), which is fixed as a neural network here. In the novel approach, the ability of the controller has been greatly improved. At last, the proposed novel control method is applied to solve nonlinear tracking problems. Simulation comparison tests were done on two typical non-linear plants, through which, the effectiveness of the novel data based predictive control method is fully illustrated.

[1]  K S Narendra,et al.  Control of nonlinear dynamical systems using neural networks. II. Observability, identification, and control , 1996, IEEE Trans. Neural Networks.

[2]  J. Spall.  Multivariate stochastic approximation using a simultaneous perturbation gradient approximation , 1992 .

[3]  Zengqiang Chen,et al.  Simple Recurrent Neural Network‐Based Adaptive Predictive Control for Nonlinear Systems , 2002 .

[4]  Derong Liu,et al.  Finite horizon discrete-time approximate dynamic programming , 2006, 2006 IEEE Conference on Computer Aided Control System Design, 2006 IEEE International Conference on Control Applications, 2006 IEEE International Symposium on Intelligent Control.

[5]  Na Dong,et al.  A modified neural network based predictive control for non-linear systems , 2009, Int. J. Model. Identif. Control..

[6]  Kumpati S. Narendra,et al.  Neural networks in control systems , 1992, [1992] Proceedings of the 31st IEEE Conference on Decision and Control.

[7]  J. Spall,et al.  Model-free control of general discrete-time systems , 1993, Proceedings of 32nd IEEE Conference on Decision and Control.

[8]  Derong Liu,et al.  Discrete-Time /spl epsilon/-Adaptive Dynamic Programming Algorithm Using Neural Networks , 2008, 2008 IEEE International Symposium on Intelligent Control.

[9]  Şahin Yildirim.  A proposed hybrid neural network for position control of a walking robot , 2008 .

[10]  W. Rudin.  Principles of mathematical analysis , 1964 .

[11]  Huaguang Zhang,et al.  Adaptive Dynamic Programming: An Introduction , 2009, IEEE Computational Intelligence Magazine.

[12]  Hong Wang,et al.  A direct adaptive neural-network control for unknown nonlinear systems and its application , 1998, IEEE Trans. Neural Networks.