本研究旨在開發出一套以自調式類神經網路演算法為基礎之PD控制器，用來模擬無動力船隻受拖船牽曳下在波浪中之航行路線。經由拖船拖曳角度之自動化操控，被拖曳船隻之航跡及航向角呈現相當不錯之結果。在模擬過程中，不同波向角之波浪、風及洋流力則分別用來探討、比較對拖船系統的影響。模擬結果顯示出，以類神經網路演算法為基礎所發展的最佳化PD控制器，相較傳統試誤法對於拖船系統有相當不錯的應用，而且將有助於未來在不規則波中之實際應用。

The present study aims to develop a mathematical model, including PD controller based on the selftuning neural network algorithm, to simulate the trajectory of an un-powered ship towed by tugboats in waves. Through the automatic control on the towing angles of the tugboats, the tracking trajectory and course keeping of the towed ship could be achieved well. The effects of the waves with different wave headings, the wind and the drift forces on the system are taken into account in the present simulation. An un-powered containership is adopted here to be as the calculation model towed by the towing system consisting of three tugboats. The simulation results reveal that the optimized PD control based on the neural network indeed works on the towing system and is superior to the conventional trial-and-error method and may be practically applied to the realistic towing system in random waves.