Model reference control of nonlinear systems by dynamic output feedback linearization of neural network based ANARX models

A dynamic output feedback linearization technique for model reference control of nonlinear systems identified by an additive nonlinear autoregressive exogenous (ANARX) model. ANARX structure of the model can be obtained by training a neural network of the specific restricted connectivity structure. Linear discrete time reference model is given in the form of transfer function defining desired zeros and poles of the closed loop system. NN-based ANARX model can be linearized by the proposed linearization algorithm thus that the transfer function of the linear closed loop system corresponds to the given reference model. The proposed linearization algorithm can be applied to control of a wide class of nonlinear SISO and MIMO systems. The effectiveness of the proposed control technique is demonstrated on numerical example.

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

[2]  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.

[3]  E. Petlenkov,et al.  Dynamic output feedback linearization based adaptive control of nonlinear MIMO systems , 2008, 2008 American Control Conference.

[4]  E. Petlenkov,et al.  A novel taylor series based approach for control computation in NN-ANARX structure based control of nonlinear systems , 2008, 2008 27th Chinese Control Conference.

[5]  H. Spang,et al.  Second-order correlation method for bilinear system identification , 1977, 1977 IEEE Conference on Decision and Control including the 16th Symposium on Adaptive Processes and A Special Symposium on Fuzzy Set Theory and Applications.

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

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

[8]  Ülle Kotta,et al.  Neural Networks Based ANARX Structure for Identification and Model Based Control , 2006, 2006 9th International Conference on Control, Automation, Robotics and Vision.

[9]  E. Petlenkov.  NN-ANARX structure based dynamic output feedback linearization for control of nonlinear MIMO systems , 2007, 2007 Mediterranean Conference on Control & Automation.

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

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

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