采用經雙擴展卡爾曼濾波訓練的神經網絡模型的船舶波浪中減橫搖舵自動駕駛儀

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.

發文機構：National Center for Maritime Engineering and Hydrodynamics

關鍵詞：RUDDERROLLdampingAUTOPILOTRadialbasisfunctionNeuralnetworksDualextendedKALMANfiltertrainingIntelligentcontrolPathfollowingAdvancinginwavesRudder roll dampingAutopilotRadial basis functionNeural networksDual extended Kalman filter trainingIntelligent controlPath followingAdvancing in waves

分類號： TP1[自動化與計算機技術—控制科學與工程][自動化與計算機技術—控制理論與控制工程]