Anti-windup neural network-sliding mode control for dynamic positioning vessels

In this paper, a control strategy based on sliding mode control and radial basis function neural network is proposed for dynamic positioning vessels with nonlinearity, model uncertainty, time-varying disturbances, and input saturation. Sliding mode control is employed in the design of a novel nonlinear controller for dynamic positioning vessels to enhance the robustness. Radial basis function neural network is introduced to approximate model uncertainty and time-varying disturbances, which can mitigate the chattering problem of sliding mode control. Moreover, an auxiliary design system is applied to mitigate the effectiveness of input saturation, which is widely existed in the marine control actuators. The closedloop signals are proved to be stable by Lyapunov theory. In conclusion, the multiple simulations illustrate the feasibility and advantages of the presented anti-windup neural network-sliding mode controller.