Optimal Neuro-adaptive Funnel Heading Control for Marine Vessels Subject to Dead-zone Actuator

Neuro-adaptive funnel controller for heading control of marine vessels (MVs) preceded by unknown dead-zone in rudder angle is addressed in this article. To remove the effect of unknown nonlinearities, radial basis function neural networks (RBFNNs) are deployed. Modeling errors and exogenous disturbances such as wave, wind, and ocean currents are handled by introducing an adaptive continuous robust term. The proposed controller not only can ensure steady-state performance but also it can satisfy a predetermined transient condition. The semi-global uniform ultimate boundedness of all closed-loop signals in the presented controller is proved using Lyapunov stability analysis. Furthermore, it is ensured that the heading tracking error is always constrained by the funnel. To tune the parameters of the proposed controller, a suitable optimization problem is defined and solved using grey wolf optimization (GWO) algorithm. To authenticate the efficacy and applicability of the presented controller, simulation results on a case study are provided.