NN-ANARX structure based dynamic output feedback linearization for control of nonlinear MIMO systems

An application of Neural Networks based Additive Nonlinear Autoregressive Exogenous (NN-ANARX) structure for modeling and control of nonlinear MIMO systems is presented in the paper. A subclass of NN-ANARX structure is proposed to simplify the calculation of controls by ANARX-based control technique. The problem of the inverse function calculation in the control algorithm is solved. After that the ANARX-based dynamic output feedback linearization control algorithm is applied for control of nonlinear MIMO systems. The effectiveness of the approach proposed in the paper is demonstrated on examples.

[1]  E. Petlenkov,et al.  Adaptive Output Feedback Linearization for a Class of NN-based ANARX Models , 2007, 2007 IEEE International Conference on Control and Automation.

[2]  Karl Johan Åström,et al.  Adaptive Control , 1989, Embedded Digital Control with Microcontrollers.

[3]  Heinz Unbehauen,et al.  Recursive identification of a turbo-generator plant using structurally adaptive neural networks , 2000, Proceedings of IEEE International Conference on Industrial Technology 2000 (IEEE Cat. No.00TH8482).

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

[5]  Shaocheng Tong,et al.  Adaptive fuzzy output feedback control for nonlinear MIMO systems , 2004, 2004 IEEE International Conference on Fuzzy Systems (IEEE Cat. No.04CH37542).

[6]  Ping Li,et al.  MIMO Decoupling Control Based on Support Vector Machines αth-order Inversion , 2006, 2006 6th World Congress on Intelligent Control and Automation.

[7]  Kevin M. Passino,et al.  Stable multi-input multi-output adaptive fuzzy/neural control , 1999, IEEE Trans. Fuzzy Syst..

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

[9]  Tao Wang.  Indirect adaptive fuzzy output feedback control for nonlinear MIMO system , 2004, Fifth World Congress on Intelligent Control and Automation (IEEE Cat. No.04EX788).

[10]  Xinli Li,et al.  Neural Network Online Decoupling for a Class of Nonlinear System , 2006, 2006 6th World Congress on Intelligent Control and Automation.

[11]  Gu Shusheng,et al.  Fuzzy adaptive output feedback control for nonlinear MIMO systems based on observer , 2004, Fifth World Congress on Intelligent Control and Automation (IEEE Cat. No.04EX788).

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

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

[14]  Fahmida N. Chowdhury.  Input-output modeling of nonlinear systems with time-varying linear models , 2000, IEEE Trans. Autom. Control..

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

[16]  B. Pasik-Duncan,et al.  Adaptive Control , 1996, IEEE Control Systems.

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

[18]  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.

[19]  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.