CAJ | 학술논문

针对考虑舵机特性的船舶航向离散不确定非线性系统，提出一种自适应神经网络输出反馈控制设计方法。首先，构造等价的考虑舵机特性的船舶航向离散非线性不确定输出反馈系统；然后，仅利用系统控制输入和航向输出，对该输出反馈系统进行自适应神经网络控制器设计。该算法简单，且当系统某些状态不可测时，该算法仍是有效的，易于工程中实现。此外，闭环系统中所有信号可以被证明半全局一致最终有界，船舶航向跟踪误差趋近于零。对“育鲲”轮的仿真证明了本文所提算法的有效性。
침대고필타궤특성적선박항향리산불학정비선성계통，제출일충자괄응신경망락수출반궤공제설계방법。수선，구조등개적고필타궤특성적선박항향리산비선성불학정수출반궤계통；연후，부이용계통공제수입화항향수출，대해수출반궤계통진행자괄응신경망락공제기설계。해산법간단，차당계통모사상태불가측시，해산법잉시유효적，역우공정중실현。차외，폐배계통중소유신호가이피증명반전국일치최종유계，선박항향근종오차추근우령。대“육곤”륜적방진증명료본문소제산법적유효성。
Output feedback control was investigated for a class of ship course discrete-time uncertain nonlinear system with rudder dynamics in strict-feedback form .Firstly, the original states strict-feedback system was transformed into a cascade form.Then, the adaptive neural network controller was devel-oped for the output feedback system by only using the control input and course output .The proposed algorithm was simple , and it was feasible when some system states were unmeasur-able, and was convenient to be implemented in application . In addition , it was proved that all the signals in closed-loop system were semi-globally uniformly ultimately bounded ( SGUUB) , and the tracking error converged to a small neig-borhood of the origin .Simulation on “Yukun” illustrates the effectiveness of the proposed algorithm .