The design of neural network controller of a class of nonlinear systems with unknown actuator hard-nonlinear

The problem of actuator hard-nonlinear appears in many practical control systems especially the plant with serious nonlinearity and need run in large rang situations. If the controller is designed only with conventional linearly techniques, the presence of hard-nonlinear can debase the performance even lead the closed-loop system to an unstable behavior. In this paper, neural net-based actuator hard-nonlinear compensation scheme with on-line weights tuning law for the nonlinear systems in Brunovsky form is presented to decrease the influence of hard-nonlinear for improving output tracking. Simulation example is given to illustrate the effectiveness of this method.

[1]  Frank L. Lewis,et al.  Deadzone compensation in discrete time using adaptive fuzzy logic , 1998, Proceedings of the 37th IEEE Conference on Decision and Control (Cat. No.98CH36171).

[2]  R. Marino,et al.  Adaptive input-output linearizing control of induction motors , 1993, IEEE Trans. Autom. Control..

[3]  Guomin Li,et al.  Robust nonlinear nominal-model following control to overcome deadzone nonlinearities , 2001, IEEE Trans. Ind. Electron..

[4]  Gang Tao,et al.  An adaptive dead-zone inverse controller for systems with sandwiched dead-zones , 2001, Proceedings of the 2001 American Control Conference. (Cat. No.01CH37148).

[5]  G. Franklin,et al.  Adaptive proximate time-optimal servomechanisms: Discrete-time case , 1987, 26th IEEE Conference on Decision and Control.

[6]  Rastko R. Selmic,et al.  Neural network control of a class of nonlinear systems with actuator saturation , 2004 .

[7]  Tong Heng Lee,et al.  Composite nonlinear feedback control for linear systems with input saturation: theory and an application , 2003, IEEE Trans. Autom. Control..