Skip to Main Content
In this paper, a neural network based adaptive control scheme for systems with unknown hysteresis is proposed. In the control scheme, a neural network model is developed to describe the characteristic of hysteresis. The architecture of the proposed model is motivated by Preisach model. The advantage of the proposed model is that it can be easily updated on-line for controller design. Then, the adaptive controller based on the proposed neural model is presented for a class of single-input nonlinear systems preceded by unknown hysteresis non-linearity. In order to handle the case where the output of hysteresis is unmeasurable, the neural network model is utilized to estimate the influence of hysteresis. Based on the model-based estimation, the controller can compensate for hysteresis' effect on the performance of the system. The weights of the neural adaptive controller are adjusted based on Lyapunov stability criterion in order to guarantee the ultimate boundedness of the closed-loop system. A numerical example is illustrated to evaluate the performance of the proposed control scheme.