针对非线性船舶航向运动数学模型存在模型误差的情况，提出一种神经网络控制方法.基于Lyapunov稳定性分析理论，采用动态面（DSC）控制技术，以消除传统Backstepping方法中存在的“计算爆炸”问题，并采用最少学习参数（MLP）技术，以减少控制器的计算负担，便于工程实现和应用.设计的神经网络控制器可以保证闭环系统中所有信号一致最终有界，使跟踪误差任意小.仿真验证了算法的有效性.
Abstract
A neural network （NN） based control method is proposed for ship coursekeeping control in the presence of modeling errors. The controller is constructed by combining both the dynamic surface control(DSC) technique and minimum learning parameter(MLP) technique based on Lyapunov stability theory, and the problem of explosion of complexity is avoided, so that the computational burden of the algorithm can be reduced drastically ,which is convenient for practice and applications. The proposed NN based controller guarantees that all the closeloop signals are uniform ultimate bounded (UUB) and that the tracking errors converge to a small neighborhood of the desired trajectory. Simulations illustrate the effectiveness of the proposed algorithm.
关键词
船舶 /
航向控制 /
动态面(DSC) /
神经网络(NN) /
最少学习参数(MLP)
Key words
ship /
course control /
dynamic surface control(DSC) /
neural network(NN) /
minimum learning parameter(MLP)
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
［1］DU J L, GUO C. Nonlinear adaptive design for coursetracking control of ship without a priori knowledge of control gain ［J］. Journal of Control Theory & Applications, 2005, 22(2):315-320.
［2］罗伟林, 邹早建, 李铁山. 船舶航向非线性系统鲁棒跟踪控制［J］. 控制理论与应用, 2009, 26(8):893-895.
LUO Wei-lin, ZOU Zao-jian, LI Tie-shan. Robust tracking control of nonlinear ship steering ［J］. Journal of Control Theory and Applications, 2009 26(8):893895.(in Chinese)
［3］卜仁祥, 刘正江, 李铁山. 迭代滑膜增量反馈及在船舶航向控制中的应用［J］. 哈尔滨工程大学学报, 2007, 28(3):268-272.
BU Ren-xiang, LIU Zheng-jiang, LI Tie-shan. Iterative sliding mode based increment feedback control and its application to ship autopilot ［J］. Journal of Harbin Engineering University, 2007, 28(3):268-272.(in Chinese)
［4]王林, 陈楠, 高嵬. 基于Backstepping的船舶航向自适应滑模控制［J］.船电技术, 2012,32(4):16-18.
WANG Lin, CHEN Nan, GAO Wei. Adaptive sliding mode control based on backstepping for marine autopilot systems ［J］. 2012, 32(4):16-18.(in Chinese)
［5]LI Jun-fang, LI Tie-shan. Design of ship’s course autopilot with input saturation ［J］. ICIC Express Letters, 2011, 5(10):3779-3784.
［6］ LI Jun-fang, LI Tie-shan, Fan Zhongzhou et al. Direct adaptive NN control of ship course autopilot with input saturation ［C］// Proceedings of the 4th International Workshop on Advanced Computational Intelligence. Wuhan : IEEE Press, 2011:663-669.
［7］ LUO Wei-lin, ZOU Zao-jian. Neural network based robust controller for trajectory tracking of underwater vehicles ［J］. China Ocean Engineering, 2007, 21(2):281-292.
［8］LI Ya-hui, QIANG Sheng, ZHUANG Xian-yi ，et al. Robust and adaptive backstepping control for nonlinear systems using RBF neural networks ［J］. IEEE Transactions on Neural Networks, 2004, 15(3):693-701.
［9］ WANG Dan, HUANG Jie. Neural networkbased adaptive dynamic surface control for a class of uncertain nonlinear systems in strictfeedback form［J］. IEEE Transactions on Neural Networks, 2005, 16(1):195-202.
［10］SWAROOP D, HEDRICK J K, YIP P P，et al. Dynamic surface control for a class of nonlinear systems ［J］. IEEE Trans Autom Control, 2000, 45(10):1893-1899.
［11］ LI Tie-shan, WANG Dan, FENG Gang,et al. A DSC approach to robust adaptive NN tracking control for strictfeedback nonlinear systems ［J］. IEEE Transactions on Systems, Man, and Cybernetics Part B: Cybernetics, 2010, 40(3):915-927.
［12］ LI Tie-shan, LI Rong-hui,LI Jun-fang, et al. Decentralized adaptive neural control of nonlinear systems with unknown time delays ［J］. Nonlinear Dynamics, 2012, 67(3):2017-2026.
［13］ LIN W, QIAN C. Adaptive control of nonlinearly parameterized systems: The smooth feedback case ［J］. IEEE Trans Autom Control, 2002, 47(8):1249-1266.
基金
国家自然科学基金资助项目（51079031 ; 51179019 ; 60874056）；辽宁省自然科学资助项目（20102012）；福建省自然科学基金资助项目（2010J01004）；辽宁省高等学校优秀人才支持计划A类（LR2012016）.
PDF(438 KB)
