內模式控制架構之類神經船舶自航器設計

An Internal Model Control-Based Neural Network Ship Steering Autopilot Design

曾慶耀(C. Y. Tzeng) ； 盧嘉弘(J. H. Lu)

《中國造船暨輪機工程學刊》 22卷1期 (2003/02) Pp. 13-22

https://doi.org/10.29982/JTSNAME.200302.0002

摘要

船舶於海上航行時，其運動行爲受著流體流場變化而改變，很難以正確無誤的數學模式，來描述出船舶所受流體的作用力與力矩。在設計控制系統時，爲簡化設計程序，通常以線性化之模式爲依據。但爲使控制器具有較佳強建性，必須考量真實受控體(plant)與受控體模式(model)之間模式誤差的變化。若能即時、有效地掌控系統操作點受環境變化的影響，來告知控制器，使其能適時地調變控制器參數，使之作出正確的反應，如此控制效果將能有所提升。本文結合平行內模式控制(internal model control,IMC)來作爲控制迴路系統基本架構，並運用類神經網路（兩層前鐀網路及三層前鐀網路）來設計扮演受控體模式與控制器的角色，以建構自航器控制器系統。經由模擬結果顯示，本研究所提出之結合內模式控制架構與類神經網路之自航器設計方法，均能順利追蹤給予參考訊號，完成追蹤任務。

關鍵字

內模式架構 ； Norrbin非線性平擺方程式 ； 兩層前鐀網路 ； 三層前鐀網路 ； 倒傳遞演算法

並列摘要

It is well known that the ship steering dynamics is characterized by a highly complicated nonlinear behavior. For simplicity, a linearized model is often adopted in the autopilot design. However, to make the autopilot of practical use, the modeling error between the model and the plant under control has to be monitored and the controller parameters should be adjusted accordingly.
In this work, the internal model control (IMC) configuration is adopted and the neural network (NN) is employed in describing the model and the controller, which is essentially the model inverse under the IMC structure. Both two-layer and three-layer feedforward networks are considered in the design of a heading control autopilot and a yaw rate control autopilot. Numerical simulations indicate that very good tracking performance is achieved for the sine wave reference inputs.

並列關鍵字

Internal Model Control ； Norrbin Nonlinear Yaw Model ； Two-Layer Feedforward Network ； Three-Layer Feedforward Network ； Back Propagation Algorithm