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 th...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.展开更多
使用深度学习技术进行语音分离已经取得了优异的成果。当前主流的语音分离模型主要基于注意力模块或卷积神经网络,它们通过许多中间状态传递信息,难以对较长的语音序列建模导致分离性能不佳。首先提出了一种端到端的双路径语音分离网络(...使用深度学习技术进行语音分离已经取得了优异的成果。当前主流的语音分离模型主要基于注意力模块或卷积神经网络,它们通过许多中间状态传递信息,难以对较长的语音序列建模导致分离性能不佳。首先提出了一种端到端的双路径语音分离网络(DPCFNet),该网络通过引入改进的密集连接块,使编码器能提取到丰富的语音特征。然后使用卷积增强Transformer(Conformer)作为分离层的主要组成部分,使语音序列中的元素可以直接交互,不再通过中间状态传递信息。最后将Conformer与双路径结构相结合使得该模型能够有效地进行长语音序列建模。实验结果表明,相比于当前主流的Conv-Tasnet算法及DPTNet算法,所提出的模型在信噪失真比(Signal to noise Distortion Ratio,SDR)和尺度不变信噪失真比(Scale-Invariant Signal to noise Distortion Ratio,SI-SDR)上有明显提高,分离性能更好。展开更多
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
文摘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.
文摘使用深度学习技术进行语音分离已经取得了优异的成果。当前主流的语音分离模型主要基于注意力模块或卷积神经网络,它们通过许多中间状态传递信息,难以对较长的语音序列建模导致分离性能不佳。首先提出了一种端到端的双路径语音分离网络(DPCFNet),该网络通过引入改进的密集连接块,使编码器能提取到丰富的语音特征。然后使用卷积增强Transformer(Conformer)作为分离层的主要组成部分,使语音序列中的元素可以直接交互,不再通过中间状态传递信息。最后将Conformer与双路径结构相结合使得该模型能够有效地进行长语音序列建模。实验结果表明,相比于当前主流的Conv-Tasnet算法及DPTNet算法,所提出的模型在信噪失真比(Signal to noise Distortion Ratio,SDR)和尺度不变信噪失真比(Scale-Invariant Signal to noise Distortion Ratio,SI-SDR)上有明显提高,分离性能更好。
