针对船舶航行中横摇运动控制问题，提出一种基于反步法与径向基函数神经网络（Radial Basis Function Neural Network, RBFNN）的船舶鳍减摇控制律，以实现船舶自适应减摇控制。首先，基于反步法设计获得PD型的控制器，并使用闭环增益成形算法确定其初始参数值；其次，引入RBFNN对PD控制器的初始参数进行优化，以经归一化处理的船舶横摇角度和横摇角速度作为网络输入，动态调节控制参数，从而实现自适应控制；最后，通过在随机波环境下的数值仿真试验，验证了所提控制器的减摇性能。仿真结果表明，该控制器能有效抑制船舶横摇运动，减摇率超过94%，并展现出优异的自适应能力。因此，本研究提出的控制策略可为船舶横摇运动控制提供一种高效且实用的解决方案。
To address the challenge of ship roll motion control during navigation, this paper proposes a ship fin anti-roll control law based on Backstepping and radial basis function neural network (RBFNN) to achieve adaptive roll reduction control. First, a PD-type controller is designed based on the Backstepping method, with its initial parameters established using a closed-loop gain shaping algorithm. Next, RBFNN is utilized to optimize the initial parameters of the PD controller, taking the normalized ship roll angle and roll angular velocity as network inputs to dynamically adjust the control parameters, thus enabling adaptive control. Finally, numerical simulation tests in random wave environments verify the roll reduction performance of the proposed controller. The simulation results show that the controller effectively suppresses ship roll motion, achieving a roll reduction rate exceeding 94%, and demonstrates superior adaptability. Therefore, the proposed control strategy provides an efficient and practical solution for ship roll motion control.
2026,48(7): 106-111 收稿日期：2025-8-2
DOI：10.3404/j.issn.1672-7649.2026.07.018
分类号：U664.72
基金项目：国家自然科学基金资助项目（52171346，52271361，52571405）；广东省南海海洋牧场智能装备重点实验室资助课题（2023B1212030003）；广东省普通高校重点领域项目（2024ZDZX3054）
作者简介：王立军(1980-),男,博士,教授,研究方向为船舶运动智能感知与不确定性控制
参考文献：
[1] 宋新宇, 张秀凤, 余英杰. 基于深度学习的船舶横摇运动预报算法研究[J]. 舰船科学技术, 2025, 47(12): 6-13 SONG X Y, ZHANG X F, YU Y J. Research on ship roll prediction algorithm based on deep learning[J]. Ship Science and Technology, 2025, 47(12): 6-13
[2] 张婷, 王志明, 王培良. 基于改进小波神经网络的集装箱船纵摇角度预测[J]. 广东海洋大学学报, 2022, 42(3): 117-121 ZHANG T, WANG Z M, WANG P L. Pitch angle prediction of container ship based on improved wavelet neural network[J]. Journal of Guangdong Ocean University, 2022, 42(3): 117-121
[3] XU W, JIAO J, XU G, et al. Intelligent control of flap-type fin stabilizer for ship roll motion reduction[J]. Ocean Engineering, 2025, 323: 120630
[4] 张显库, 曹添. 基于反正切函数非线性反馈的船舶减纵摇控制[J]. 广东海洋大学学报, 2022, 42(6): 30-37 ZHANG X K, CAO T. Ship pitch reduction control based on arctangent function nonlinear feedback[J]. Journal of Guangdong Ocean University, 2022, 42(6): 30-37
[5] 李冲, 章文俊, 薛宗耀, 等. 具有外源输入的船舶横摇运动 NARX 神经网络预测[J]. 舰船科学技术, 2022, 44(11): 63-67 LI C, ZHANG W J, XUE Z Y, et al. Improved prediction method for ship rolling motion via NARX neural network[J]. Ship Science and Technology, 2022, 44(11): 63-67
[6] SUN M, LUAN T, LIANG L. RBF neural network compensation-based adaptive control for lift-feedback system of ship fin stabilizers to improve anti-rolling effect[J]. Ocean Engineering, 2018, 163: 307-321
[7] LUO W, HU B, LI T. Neural network based fin control for ship roll stabilization with guaranteed robustness[J]. Neurocomputing, 2017, 230: 210-218
[8] HUANG L, HAN Y, DUAN W, et al. Ship pitch-roll stabilization by active fins using a controller based on onboard hydrodynamic prediction[J]. Ocean Engineering, 2018, 164: 212-227
[9] DENG Y, ZHANG X, ZHANG Q, et al. Event-triggered composite adaptive fuzzy control of sailboat with heeling constraint[J]. Ocean Engineering, 2020, 211: 107627
[10] ZHANG X K, ZHANG G Q, CHEN X J. A kind of linear reduction of backstepping algorithm based on nonlinear feedback[J]. Control and Decision, 2015, 30(9): 1641-1645
[11] ZHANG X K, ZHANG Q, REN H X, et al. Linear reduction of backstepping algorithm based on nonlinear decoration for ship course-keeping control system[J]. Ocean Engineering, 2018, 147: 1-8
[12] JIN Z, ZHANG W, LIU S, et al. Command-filtered backstepping integral sliding mode control with prescribed performance for ship roll stabilization[J]. Applied Sciences, 2019, 9(20): 4288
[13] ZHANG X, HAN X, GUAN W, et al. Improvement of integrator backstepping control for ships with concise robust control and nonlinear decoration[J]. Ocean Engineering, 2019, 189: 106349
[14] LI R, LI T, BAI W, et al. An adaptive neural network approach for ship roll stabilization via fin control[J]. Neurocomputing, 2016, 173: 953-957
[15] 田宇, 刘志全, 高妍南. 基于神经网络滑模的欠驱动船舶路径跟踪与避障协同控制[J]. 广东海洋大学学报, 2024, 44(5): 144-152 TIAN Y, LIU Z Q, GAO Y N. Collaborative control of path following and obstacle avoidance for underactuated ships based on neural network sliding mode[J]. Journal of Guangdong Ocean University, 2024, 44(5): 144-152
[16] DU J, YANG Y, WANG D, et al. A robust adaptive neural networks controller for maritime dynamic positioning system[J]. Neurocomputing, 2013, 110: 128-136
[17] 李荣辉, 陈志娟, 李宗宣, 等. 基于欧拉迭代模型预测的欠驱动水面船舶路径跟踪控制[J]. 广东海洋大学学报, 2020, 40(1): 104-110 LI R H, CHEN Z J, LI Z X, et al. Path following control of under-actuated surface ships based on euler iterative model prediction[J]. Journal of Guangdong Ocean University, 2020, 40(1): 104-110
[18] ZHANG Y T, SHI W R, QIU M B. Sliding backstepping control for fin stabilizer with nonlinear disturbance observer[J]. Control and Decision, 2010, 25(8): 1255-1260
[19] ZHANG G, DENG Y, ZHANG W, et al. Novel DVS guidance and path-following control for underactuated ships in presence of multiple static and moving obstacles[J]. Ocean Engineering, 2018, 170: 100-110
[20] WANG L, LIAO S, WANG S, et al. Real-time prediction of metacentric height of ro-ro passenger ships in Qiongzhou strait based on improved RBF neural network[J]. Ocean Engineering, 2024, 312: 119067
[21] 章沪淦, 张显库. 船舶航向保持控制研究综述[J]. 广东海洋大学学报, 2022, 42(6): 38-46 ZHANG H G, ZHANG X K. Review of ship course keeping control[J]. Journal of Guangdong Ocean University, 2022, 42(6): 38-46
[22] WANG L, LIAO S, WANG S, et al. Real-time prediction of port water levels based on EMD-PSO-RBFNN[J]. Frontiers in Marine Science, 2025, 12: 1537696
[23] 王新屏, 张显库. 基于反馈线性化与闭环增益成形的减摇鳍控制[J]. 中国航海, 2007(4): 5-8 WANG X P, ZHANG X K. Control of fin stabilizer based on feedback linearization and closed-loop gain shaping[J]. Navigation of China, 2007(4): 5-8
[24] 王新屏, 张显库. 基于 Backstepping 与闭环增益成形的减摇鳍控制[J]. 大连海事大学学报, 2008, 34(3): 89-92 WANG X P, ZHANG X K. Fin stabilizer control based on backstepping and closed-loop gain shaping algorithms[J]. Journal of Dalian Maritime University, 2008, 34(3): 89-92
