Rudder Roll Damping Autopilot Using Dual Extended Kalman Filter-Trained Neural Networks for Ships in Waves

Abstract

The roll motions of ships advancing in heavy seas have severe impacts on the safety of crews, vessels, and cargoes; thus, it must be damped. This study presents the design of a rudder roll damping autopilot by utilizing the dual extended Kalman filter (DEKF)–trained radial basis function neural networks (RBFNN) for the surface vessels. The autopilot system constitutes the roll reduction controller and the yaw motion controller implemented in parallel. After analyzing the advantages of the DEKF-trained RBFNN control method theoretically, the ship’s nonlinear model with environmental disturbances was employed to verify the performance of the proposed stabilization system. Different sailing scenarios were conducted to investigate the motion responses of the ship in waves. The results demonstrate that the DEKF RBFNN–based control system is efficient and practical in reducing roll motions and following the path for the ship sailing in waves only through rudder actions.