Nonlinear system control using neural networks based on trajectory linearization

A nonlinear control technique using neural networks based on trajectory linearization control (TLC) is proposed. Trajectory linearization control is a novel control design method that combines a dynamic inversion and linear time-varying feedback stabilization along a nominal trajectory. In this paper, the TLC design procedure using neural networks model is developed, and the stability and robustness are analyzed. Simulation results are presented to show the feasibility of the proposed method.

[1]  Kevin M. Passino,et al.  Stable adaptive control using fuzzy systems and neural networks , 1996, IEEE Trans. Fuzzy Syst..

[2]  J.J. Zhu.  PD-spectral theory for multivariable linear time-varying systems , 1997, Proceedings of the 36th IEEE Conference on Decision and Control.

[3]  R. Sanner,et al.  Gaussian Networks for Direct Adaptive Control , 1991 .

[4]  Frank L. Lewis,et al.  Design and implementation of industrial neural network controller using backstepping , 2003, IEEE Trans. Ind. Electron..

[5]  Frank L. Lewis,et al.  Robust backstepping control of induction motors using neural networks , 2000, IEEE Trans. Neural Networks Learn. Syst..

[6]  M. C. Mickle,et al.  Bank-to-turn roll-yaw-pitch autopilot design using dynamic nonlinear inversion and PD-eigenvalue assignment , 2000, Proceedings of the 2000 American Control Conference. ACC (IEEE Cat. No.00CH36334).

[7]  A. Isidori,et al.  Adaptive control of linearizable systems , 1989 .

[8]  Frank L. Lewis,et al.  Feedback linearization using neural networks , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[9]  M. C. Mickle,et al.  Nonlinear time-varying observer design using trajectory linearization , 2003, Proceedings of the 2003 American Control Conference, 2003..

[10]  Kevin M. Passino,et al.  Adaptive control of a class of decentralized nonlinear systems , 1996 .

[11]  Robin J. Evans,et al.  Trajectory-approximation-based adaptive control for nonlinear systems under matching conditions , 1998, Autom..

[12]  Jean-Jacques E. Slotine,et al.  Space-frequency localized basis function networks for nonlinear system estimation and control , 1995, Neurocomputing.

[13]  Robin J. Evans,et al.  Controlling nonlinear time-varying systems via euler approximations , 1992, Autom..

[14]  J. Jim Zhu,et al.  X-33 Ascent Flight Controller Design by Trajectory Linearization: A Singular Perturbational Approach , 2000 .

[15]  Visakan Kadirkamanathan,et al.  Dynamic structure neural networks for stable adaptive control of nonlinear systems , 1996, IEEE Trans. Neural Networks.

[16]  J. Jim Zhu,et al.  Design and real time testing of a trajectory linearization flight controller for the "Quanser UFO" , 2003, Proceedings of the 2003 American Control Conference, 2003..