Nonlinear hysteresis system control based on sliding mode neural network and observer

In this paper, a sliding mode neural network controller with observer is presented and employed in a nonlinear hysteresis system to eliminate the system's unknown hysteresis and uncertainties. First, a sliding mode controller is proposed for trajectory tracking, which simplifies the computational complexity and ensures robustness. Second, radial basis function neural network is applied for approximating unknown nonlinear function in the control system. Then, an observer is utilized to estimate and observe the hysteresis nonlinearity and cancel the effect of the hysteresis phenomenon. Based on the proposed control scheme, the influence of hysteresis is suppressed, and the system has robust stability and achieves high output tracking performance. Finally, theoretical analysis and numerical simulations confirm the effectiveness of the designed control law.