Neural Sliding Mode Control of Systems with Unknown Dynamics and Its Application to Chaotic Systems Control

In this paper, a neural sliding mode controller (NSMC) is proposed as an asymptotically stable robust controller for a class of nonlinear systemswith unknown dynamics as well as unknowndisturbances which the disturbances are not available for measurement. Comparing with the previous works,the proposed method converts the dynamical system identification problem to two simple static function approximation problems which can be easily solved bymulti-layer Perceptron (MLP). Due to high degree of robustness as well as design and implementation simplicity, the proposed controller can be widely usedin real world applications. To demonstrate this efficiency, a robust control system is successfully designed for a chaotic Duffing forced oscillator systemin the presence of unknown dynamics as well as the unknown oscillation disturbance which is not availablefor measurement.

Keywords:

Neural Sliding Mode Control , Nonlinear Control , Unknown Dynamics , Chaotic Systems , Duffing Forced Oscillator