Neural Networks Based ANARX Structure for Identification and Model Based Control

This article is devoted to the training and application of neural networks based additive nonlinear autoregressive exogenous (NN-based ANARX) model. Training of NN-based ANARX model with MATLAB is discussed in detail and illustrated by examples. Dynamic state feedback linearization control algorithm is then applied for control of unknown nonlinear system

[1]  S. Billings,et al.  The Practical Identification of Systems with Nonlinearities , 1985 .

[2]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[3]  R. De Keyser,et al.  Comparative study of neural predictors in model based predictive control , 1996, Proceedings of International Workshop on Neural Networks for Identification, Control, Robotics and Signal/Image Processing.

[4]  Hector Budman,et al.  Robust control design of non-linear processes using empirical state affine models , 2000 .

[5]  Ülle Kotta,et al.  Output Feedback Linearization of Nonlinear Discrete Time Systems , 2000 .

[6]  Ülle Kotta,et al.  On a New Type of Neural-Network-Based Input-Output Model: The ANARMA Structure , 2001 .

[7]  D. C. Foley,et al.  Modelling of nonlinear systems from input-output data for state space realization , 2001, Proceedings of the 40th IEEE Conference on Decision and Control (Cat. No.01CH37228).

[8]  Ülle Kotta,et al.  Two Approaches for State Space Realization of NARMA Models: Bridging the Gap , 2002 .

[9]  R. Pearson,et al.  Nonlinear discrete-time models: state-space vs. I/O representations , 2004 .

[10]  Miguel Pinzolas,et al.  Improvement of the neighborhood based Levenberg-Marquardt algorithm by local adaptation of the learning coefficient , 2005, IEEE Transactions on Neural Networks.

[11]  Ülle Kotta,et al.  On realizability of neural networks-based input-output models in the classical state-space form , 2006, Autom..