上海交通大学学报 ›› 2020, Vol. 54 ›› Issue (9): 890-897.doi: 10.16183/j.cnki.jsjtu.2019.122

• 学报(中文) • 上一篇    下一篇

欠驱动水面船舶的自适应神经网络-滑模路径跟随控制

贺宏伟a, 邹早建a,b(), 曾智华a   

  1. a.上海交通大学 船舶海洋与建筑工程学院,上海200240
    b.上海交通大学 海洋工程国家重点实验室,上海200240
  • 收稿日期:2019-04-26 出版日期:2020-09-28 发布日期:2020-10-10
  • 通讯作者: 邹早建 E-mail:zjzou@sjtu.edu.cn
  • 作者简介:贺宏伟 (1997-),男,湖南省湘潭市人,硕士生,研究方向为船舶运动控制
  • 基金资助:
    国家自然科学基金资助项目(51779140)

Adaptive NN-SM Control for Path Following of Underactuated Surface Vessels

HE Hongweia, ZOU Zaojiana,b(), ZENG Zhihuaa   

  1. a.School of Naval Architecture, Ocean and Civil Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
    b.State Key Laboratory of Ocean Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
  • Received:2019-04-26 Online:2020-09-28 Published:2020-10-10
  • Contact: ZOU Zaojian E-mail:zjzou@sjtu.edu.cn

摘要:

针对欠驱动船舶的路径跟随问题,提出了一种综合神经网络和滑模控制的控制方法.采用视线(LOS)制导方法解决船舶欠驱动问题,并设计了关于漂角的自适应状态观测器,将预测的漂角引入LOS以补偿漂角引起的稳态横向偏差;使用滑模控制方法实现航向控制,并用神经网络处理控制模型的不确定性问题;应用Lyapunov理论证明了控制系统的稳定性,同时通过对比仿真试验结果,验证了本文所提出控制器的有效性.

关键词: 水面船舶, 路径跟随, 视线制导, 自适应观测器, 神经网络, 滑模控制

Abstract:

A control method combining the neural network (NN) and sliding mode (SM) is proposed for path following of underactuated surface vessels. The line-of-sight (LOS) guidance is used to solve the underactuated problem, and an adaptive state observer of drift angle is designed for counteracting the steady state cross-track error caused by the drift angle. The SM control method is applied to heading control while the NN is included to cope with the uncertainties of control model. The stability of the control system is proved by the Lyapunov theory, and the validity of the proposed controller is verified by comparing the simulation results.

Key words: surface vessel, path following, line-of-sight (LOS) guidance, adaptive observer, neural network (NN), sliding mode (SM) control

中图分类号: