针对模型参数未知和存在外界干扰的三自由度欠驱动水面船舶路径跟踪控制问题，提出一种RBF神经网络控制器.该算法利用神经网络的函数逼近特性对船舶模型未知的非线性部分在线逼近并与反步法相结合进行设计，同时实现前进速度在线可调.通过Lyapunov稳定性方法分析验证了闭环系统的稳定性.仿真计算验证了该控制策略的有效性.
For path flowing control problem of three degrees of freedom underactuated surface vessel model with unknown parameters and external disturbances, a RBF adaptive neural network controller is proposed. The controller was designed by using neural network function approximation properties combining with backstepping method to approach the unknown nonlinear part of the ship model online, and realized the forward speed adjustable. Based on Lyapunov stability analysis it is proved that the final closedloop system is stable. Simulation results show the effectiveness of the adaptive control strategy used.
［1］王勇. 欠驱动船舶航迹跟踪控制技术研究［D］. 哈尔滨：哈尔滨工程大学, 2011.
WANG Yong. Research on control algorithm of tracking for underactuated ships［D］. Harbin ：Harbin Engineering University,2011.(in Chinese)
［2］张馨文. 基于反步法的欠驱动船舶直线航迹跟踪控制［D］.大连：大连海事大学, 2011.
ZHANG Xin-wen. A robust design based on the Backstepping theory for the linearcourse trajectory control of ships［D］. Dalian : Dalian Maritime University,2011.(in Chinese)
［3］刘杨, 郭晨, 沈智鹏, 等. 欠驱动船舶路径跟踪的神经网络稳定自适应控制［J］. 控制理论与应用, 2010, 27(2): 169-174.
LIU Yang, GUO Chen, SHEN Zhi-peng, et al. Stable adaptive neural network control of path following for underactuated ships［J］. Control Theory & Applications, 2010, 27(2): 169-174. (in Chinese)
［4］段海庆, 朱齐丹. 基于反步自适应神经网络的船舶航迹控制［J］. 智能系统学报, 2012, 7(3): 259-264.
DUAN Hai-qing, ZHU Qi-dan.Trajectory tracking control of ships based on an adaptive backstepping neural network［J］. CAAI Transactions on Intelligent Systems, 2012, 7(3): 259 -264.(in Chinese)
［5］王晓飞. 基于解析模型预测控制的欠驱动船舶路径跟踪控制研究［D］. 上海：上海交通大学, 2009.
WANG Xiao-fei. Study on path following control for underactuated ships by using analytic model predictive control［D］. Shanghai: Shanghai JiaoTong University,2009.(in Chinese)
［6］FOSSEN T I. Marine control systems［M］. Trondheim,Norway:Marine Cybernetics,2002.
［7］KHALIL H K. 非线性系统 ［M］. 第3版. 北京: 电子工业出版社,2005.
