输入饱和约束下神经网络自适应非线性调节船舶航向控制

doi:10.19423/j.cnki.31-1561/u.2025.063

船舶 ›› 2026, Vol. 37 ›› Issue (01): 66-73.DOI: 10.19423/j.cnki.31-1561/u.2025.063

输入饱和约束下神经网络自适应非线性调节船舶航向控制

赵子俊, 胡宴才^*, 张强, 丁胜达

山东交通学院航运学院威海 264200

收稿日期:2025-03-27 修回日期:2025-06-23 出版日期:2026-02-25 发布日期:2026-03-04
通讯作者: 胡宴才（1987—），男，博士，副教授。研究方向：船舶避碰、船舶运动控制。张强（1982—），男，博士，教授。研究方向：船舶运动与控制。丁胜达（1999—），男，硕士研究生。研究方向：非线性控制、船舶航向控制。
作者简介:赵子俊（2002—），男，硕士研究生。研究方向：非线性控制、船舶航向控制。
基金资助:
山东省高等学校“青创团队计划”（2022KJ210）; 山东省重点研发计划（重大科技创新项目2024CXGC010804）

Adaptive Nonlinear Ship Heading Control Using Neural Networks Under Input Saturation Constraints

ZHAO Zijun, HU Yancai^*, ZHANG Qiang, DING Shengda

School of Navigation and Shipping, Shandong Jiaotong University, Weihai 264200, China

Received:2025-03-27 Revised:2025-06-23 Online:2026-02-25 Published:2026-03-04

摘要/Abstract

摘要： 针对船舶航向控制中，输入饱和约束下存在外部干扰和未知非线性函数的不确定系统控制问题，该文设计了一种融合自适应神经网络与动态面技术的非线性调节控制算法。该算法通过径向基函数（radial basis function，RBF）神经网络逼近外界扰动和未知函数，并结合动态面控制（dynamic surface control，DSC）技术以有效降低计算复杂度;然后，在控制律设计中引入一个具有误差增益反相关特征的非线性函数，提出一种自适应非线性控制方法，以消除奇异值问题，同时构造辅助系统对输入饱和约束进行补偿;最后，基于Lyapunov稳定性理论，证明闭环系统所有信号的一致有界性。该研究以输入饱和约束下的船舶航向跟踪控制为例，通过MATLAB仿真对比实验，验证所提算法的优越性能。研究成果可为相关领域提供理论依据和实践参考，具有重要工程应用价值。

关键词: RBF神经网络, 输入饱和, DSC技术, 非线性调节控制, 船舶控制

Abstract: This paper addresses the control problem of uncertain systems subject to external disturbances, unknown nonlinearities, and input saturation constraints in ship heading control. A nonlinear regulation control algorithm is designed that integrates adaptive neural networks with dynamic surface control (DSC) technology. The algorithm employs a radial basis function (RBF) neural network to approximate external disturbances and unknown nonlinear functions, while the integration of DSC technology effectively reduces computational complexity. A nonlinear function featuring error-dependent gain characteristics is incorporated into the control law design. This adaptive nonlinear control approach effectively eliminates potential singularity issues, while an auxiliary system is designed to compensate for the effects of input saturation constraints. Using Lyapunov stability theory, the uniform ultimate boundedness of all closed-loop signals is rigorously proven. The proposed algorithm is validated through MATLAB simulations of ship heading tracking control under input saturation constraints. Comparative experimental results demonstrate the superior performance and advantages of the proposed method. The findings provide both theoretical foundations and practical references for related fields, demonstrating significant application value in ship engineering practice.

Key words: radial basis function neural network, input saturation, dynamic surface control(DSC) technology, nonlinear regulation control, ship control

中图分类号:

U664.82

赵子俊, 胡宴才, 张强, 丁胜达. 输入饱和约束下神经网络自适应非线性调节船舶航向控制[J]. 船舶, 2026, 37(01): 66-73.

ZHAO Zijun, HU Yancai, ZHANG Qiang, DING Shengda. Adaptive Nonlinear Ship Heading Control Using Neural Networks Under Input Saturation Constraints[J]. Ship & Boat, 2026, 37(01): 66-73.

参考文献

[1] 唐丽,贾继阳. 具有输入饱和的严格反馈系统的约束控制[J]. 建模与仿真,2019,8(3):102-116.
[2] WANG C S,WANG D, HAN Y Z.Neural network based adaptive dynamic surface control for omnidirectional mobile robots tracking control with full-state constraints and input saturation[J]. International Journal of Control,Automation,and Systems,2021,19,4067-4077.
[3] 张强,李昊洋,孟祥飞,等. 基于Lyapunov理论考虑不确定扰动的船舶自适应跟踪控制[J]. 上海海事大学学报,2023,44(1):8-16.
[4] CUI D,ZOU W C, GUO J,et al,Neural network-based adaptive finite-time tracking control of switched nonlinear systems with time-varying delay[J]. Applied Mathematics and Computation,2022,428:127216.
[5] WANG C H, CUI L M,LIANG M,et al.Adaptive neural network control for a class of fractional-order nonstrict-feedback nonlinear systems with full-state constraints and input saturation[J]. IEEE Transactions on Neural Networks and Learning Systems,2022,33(11):6677-6689.
[6] HU Y,DU Z,WANG Y.et al.Adaptive event-triggered fuzzy control for unreliable networked control systems with time-varying delay[J]. International Journal of Fuzzy Systems,2024,26:1448-1465.
[7] TESSLER C,MANKOWITZ D J,MANNOR S.Reward constrained policy optimization[J]. arXiv preprint,2018:1805.11074.
[8] HU X, GONG Q T,LI K Q.Event-triggered adaptive disturbance rejection for marine surface vehicles with unknown dynamics and disturbances[J]. Ocean Engineering,2023,268,113379.
[9] FAN Y,ZOU X,WANG G,et al . Robust adaptive path following control strategy for underactuated unmanned surface vehicles with model deviation and actuator saturation[J]. Applied Sciences,2022,12(5):2696.
[10] LI T S,WANG D,FENG G,et al.A DSC approach to robust adaptive NN tracking control for strict-feedback nonlinear systems[J]. IEEE Transactions on Systems,Man,and Cybernetics,Part b (Cybernetics),2009,40(3):915-927.
[11] 刘训文,褚善东,骆海洋,等. 基于自适应神经网络的船舶航向保持预定义性能PI控制[J]. 上海海事大学学报,2022,45(1):10-15.
[12] REN C E.Adaptive fuzzy disturbance observer-based control for nonlinear uncertain systems with general exogenous disturbances[J]. Fuzzy Information and Engineering,2021,3(1):1-14.
[13] SUN W,DIAO S F,SU S F,et al.Fixed-time adaptive neural network control for nonlinear systems with input saturation[J]. IEEE Transactions on Neural Networks and Learning Systems,2021,32(10):4480-4492.
[14] SONG J,YAN M, YANG P.Neural adaptive dynamic surface asymptotic tracking control for a class of uncertain nonlinear system[J]. Circuits,Systems,and Signal Processing,2021,40,1673-1698.
[15] WANG Q L,SUN C Y, CHEN Y Y.Adaptive neural network control for course-keeping of ships with input constraints[J]. Transactions of the Institute of Measurement and Control,2019,41(4):1010-1018.
[16] LIU H Q,ZHANG T P,XIA X N.Adaptive neural dynamic surface control of MIMO pure-feedback nonlinear systems with output constraints[J]. Neurocomputing,2019,333:101-109.
[17] 苏文学,孟祥飞,张强. 输入饱和约束下自适应RBF神经网络非线性反馈船舶航向控制[J]. 上海海事大学学报,2024,45(2):14-19.
[18] PATIL O S,GRIFFIS E,DIXON W E.Deep recurrent neural network-based observer for uncertain nonlinear systems[J]. Neurocomputing,2023,557,126890.
[19] ZHANG Y H,LI J,SHEN Q.Adaptive neural output feedback tracking control of underactuated ships against uncertainties in kinematics and system matrices[J]. IEEE Journal of Oceanic Engineering,2022,46(3):720-735.
[20] GLOROT X,BORDES A,BENGIO Y.Deep sparse rectifier neural networks[C]// Proceedings of the 14th International Conference on Artificial Intelligence and Statistics. Fort Lauderdale,FL,USA:PMLR,2011:315-323.
[21] 贾欣乐,杨盐生. 船舶运动数学模型[M]. 大连:大连海事大学出版社,1997.

编辑推荐

Metrics

联系电话：（021）63161688-105006
传真：（021）63151255
E-mail：chuanbo@maric.com.cn

输入饱和约束下神经网络自适应非线性调节船舶航向控制

Adaptive Nonlinear Ship Heading Control Using Neural Networks Under Input Saturation Constraints

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics