采用经双扩展卡尔曼滤波训练的神经网络模型的船舶波浪中减横摇舵自动驾驶仪

作者：Yuanyuan Wang,Hung Duc Nguyen

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.

发文机构：National Center for Maritime Engineering and Hydrodynamics

关键词：RUDDERROLLdampingAUTOPILOTRadialbasisfunctionNeuralnetworksDualextendedKALMANfiltertrainingIntelligentcontrolPathfollowingAdvancinginwavesRudder roll dampingAutopilotRadial basis functionNeural networksDual extended Kalman filter trainingIntelligent controlPath followingAdvancing in waves

分类号： TP1[自动化与计算机技术—控制科学与工程][自动化与计算机技术—控制理论与控制工程]