基于神经网络和L_2增益的船舶航向自动舵设计  

Neural-network and L_2-gain Based Autopilot Design of Ship Course-Keeping

作　　者：罗伟林[1] 邹早建[1,2] 李铁山[1,3] 

机构地区：[1]上海交通大学船舶海洋与建筑工程学院,上海200030 [2]上海交通大学海洋工程国家重点实验室,上海200030 [3]大连海事大学航海学院,辽宁大连116026

出　　处：《中国造船》2009年第2期40-45,共6页Shipbuilding of China

基　　金：国家自然科学基金项目(50779033);福建省教育厅科技项目(JB05032)

摘　　要：对一类带建模误差和不确定性外界干扰的船舶运动非线性系统,提出了一种基于神经网络和L2增益方法的航向自动舵设计。对模型中的建模误差采用在线神经网络予以辨识和补偿,避免了建模误差界定函数的经验选择;而对不确定外界干扰力项则采用L2增益设计,保证了闭环跟踪系统的鲁棒性。控制器设计步骤应用Lyapunov函数递推法,航向跟踪误差和神经网络权值误差被证明是一致终值有界的。合理的控制器参数选择保证了控制系统的跟踪精度。数值仿真结果验证了控制器设计的有效性。Neural-network and L2-gain theory is applied to the autopilot design of ship course-keeping with uncertain modeling errors and disturbances. The modeling errors are identified and compensated by an on-line neural network, so that the empirical selection of the bounded function of the modeling error is avoided. To guarantee the robustness, the uncertain external disturbances are suppressed by using L2-gain design. The overall controller is achieved by the method of recursive Lyapunov functions, which guarantees the uniformly ultimately boundedness of the tracking errors and the weight errors. Appropriate selection of parameters in the controller improves the tracking precision. The results of simulation have demonstrated the validity of the proposed controller.

关 键 词：船舶 舰船工程 航向自动舵 不确定性 神经网络 L2增益设计 

分 类 号：U666.153[交通运输工程—船舶及航道工程] TP18[交通运输工程—船舶与海洋工程]