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

护卫舰横摇稳定舵的H∞/H2控制器的设计和比较（英文）

作　　者：Yuanyuan Wang Hung Duc Nguyen 

机构地区：[1]National Center for Maritime Engineering and Hydrodynamics,Australian Maritime College, University of Tasmania

出　　处：《Journal of Marine Science and Application》2019年第4期510-521,共12页船舶与海洋工程学报（英文版）

基　　金：a part of the project titled ’Intelligent Control for Surface Vessels Based on Kalman Filter Variants Trained Radial Basis Function Neural Networks’ partially funded by the Institutional Grants Scheme(TGRS 060515)of Tasmania,Australia

摘　　要：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.

关 键 词：Rudder roll damping AUTOPILOT Radial basis function Neural networks Dual extended Kalman filter training Intelligent control Path following Advancing in waves 

分 类 号：U664.82[交通运输工程—船舶及航道工程] U674.774[交通运输工程—船舶与海洋工程]