Nonlinear discrete time neural network observer

State estimation for uncertain systems affected by external noises has been recognized as an important problem in control theory for either discrete and continuous plants. This paper deals with the state observation problem when the discrete-time dynamic model of a plant is partially unknown and it is affected by some sort of uncertainties and external perturbations. Recurrent Neural Networks (RNN) have shown several advantages to treat many different control and state estimation problems. In this paper, a new discrete-time Luenberger-like observer using the structure of a RNN is proposed. The class of discrete-time nonlinear system just has the input-output pairs as available information. The neural observer is training off-line using a class of least mean square method for matrix parameters. Lyapunov theory is employed to obtain the upper bounds for the weights dynamics as well for the estimation error and the learning laws to ensure the convergence of the observer. Simulation results using the van der Pol oscillator as data generator are presented to demonstrate the effectiveness of the proposed neural observer.

[1]  Alexander S. Poznyak,et al.  Matrix forgetting factor , 1999, Int. J. Syst. Sci..

[2]  K S Narendra,et al.  IDENTIFICATION AND CONTROL OF DYNAMIC SYSTEMS USING NEURAL NETWORKS , 1990 .

[3]  Huijun Gao,et al.  State estimation for discrete-time neural networks with time-varying delays , 2008, Neurocomputing.

[4]  Kay Chen Tan,et al.  Global exponential stability of discrete-time neural networks for constrained quadratic optimization , 2004, Neurocomputing.

[5]  Lorenz T. Biegler,et al.  Stability of a class of discrete-time nonlinear recursive observers , 2010 .

[6]  C. Oara,et al.  Generalized Riccati Theory and Robust Control. A Popov Function Approach , 1999 .

[7]  P. E. Wellstead,et al.  Introduction to physical system modelling , 1979 .

[8]  Pasquale Daponte,et al.  Neural network and DSP based decoder for DTMF signals , 2000 .

[9]  Ali Zemouche,et al.  Observer synthesis method for Lipschitz nonlinear discrete-time systems with time-delay: An LMI approach , 2011, Appl. Math. Comput..

[10]  Neil E. Cotter,et al.  The Stone-Weierstrass theorem and its application to neural networks , 1990, IEEE Trans. Neural Networks.

[11]  Emilia Fridman,et al.  Robust control for a class of continuous-time dynamical systems with sample-data outputs , 2009, 2009 6th International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE).

[12]  Alexander G. Loukianov,et al.  Discrete-Time High Order Neural Control - Trained with Kaiman Filtering , 2010, Studies in Computational Intelligence.

[13]  I. Chairez,et al.  Wavelet Differential Neural Network Observer , 2009, IEEE Transactions on Neural Networks.

[14]  Jacek M. Zurada,et al.  A class of discrete-time recurrent neural networks with multivalued neurons , 2009, 2009 International Joint Conference on Neural Networks.

[15]  Leiba Rodman,et al.  Algebraic Riccati equations , 1995 .

[16]  Alexander S. Poznyak,et al.  Differential Neural Networks for Robust Nonlinear Control: Identification, State Estimation and Trajectory Tracking , 2001 .

[17]  Alexander S. Poznyak,et al.  Continuous-time identification using LS-method under colored noise perturbations , 2007, 2007 46th IEEE Conference on Decision and Control.

[18]  Alexander S. Poznyak,et al.  Robust identification by dynamic neural networks using sliding mode learning , 1998 .

[19]  D. Prokhorov,et al.  Stability analysis of discrete-time recurrent multilayer neural networks , 2004, 2004 43rd IEEE Conference on Decision and Control (CDC) (IEEE Cat. No.04CH37601).

[20]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[21]  Alexander S. Poznyak,et al.  Stability analysis of dynamic neural control , 1998 .