大连海事大学学报
大連海事大學學報
대련해사대학학보
JOURNAL OF DALIAN MARITIME UNIVERSITY
2014年
3期
28-32
,共5页
船舶%航向控制%输入饱和%Backstepping%神经网络%最少学习参数
船舶%航嚮控製%輸入飽和%Backstepping%神經網絡%最少學習參數
선박%항향공제%수입포화%Backstepping%신경망락%최소학습삼수
ship%course control%input saturation%Backstep-ping%neural network%minimum learning parame-ters
基于Lyapunov 稳定性定理和Backstepping 方法，针对非线性船舶航向运动数学模型提出一种考虑输入饱和的直接自适应神经网络控制方法。采用Backstepping 方法对系统进行递归式设计并借助一种饱和内补偿辅助系统处理系统中的输入饱和限制问题，同时运用最少学习参数（ MLP）技术，以减少控制器的计算负担，便于工程实现和应用。本文设计的控制器保证了闭环系统信号一致最终有界，而且使系统输出能收敛到零的一个较小领域。数值仿真验证了该算法的有效性。
基于Lyapunov 穩定性定理和Backstepping 方法，針對非線性船舶航嚮運動數學模型提齣一種攷慮輸入飽和的直接自適應神經網絡控製方法。採用Backstepping 方法對繫統進行遞歸式設計併藉助一種飽和內補償輔助繫統處理繫統中的輸入飽和限製問題，同時運用最少學習參數（ MLP）技術，以減少控製器的計算負擔，便于工程實現和應用。本文設計的控製器保證瞭閉環繫統信號一緻最終有界，而且使繫統輸齣能收斂到零的一箇較小領域。數值倣真驗證瞭該算法的有效性。
기우Lyapunov 은정성정리화Backstepping 방법，침대비선성선박항향운동수학모형제출일충고필수입포화적직접자괄응신경망락공제방법。채용Backstepping 방법대계통진행체귀식설계병차조일충포화내보상보조계통처리계통중적수입포화한제문제，동시운용최소학습삼수（ MLP）기술，이감소공제기적계산부담，편우공정실현화응용。본문설계적공제기보증료폐배계통신호일치최종유계，이차사계통수출능수렴도령적일개교소영역。수치방진험증료해산법적유효성。
Based on the Lyapunov stability theory and the backstepping technique , a direct adaptive neural network con-troller was proposed for ship course-keeping control in the presence of input saturation .The scheme proposed was con-structed by combining backstepping technique and “minimum learning parameter” technique , so the computational burden of the algorithm could be reduced drastically and the algorithm is convenient to be implemented in applications .A stability a-nalysis which is subject to the effect of input saturation con-strains is conducted with the help of an auxiliary design sys-tem.The proposed NN based controller guarantees that all the close-loop signals are uniform ultimate bounded ( UUB) and the output of system converges to a small neighborhood of the desired trajectory .Numerical simulations illustrate the effec-tiveness of the proposed algorithm .
