为了提高船舶在随机海况下运动的预测精度，本文提出一种基于鲸鱼优化算法（Whale Optimization Algorithm, WOA）优化的BP神经网络（WOA-BP）模型，用于船舶横摇运动的极短期预报。该模型在传统BP神经网络的基础上，融合了WOA的高效全局搜索能力，以优化网络参数，从而提升预测的准确性和收敛速度。通过对一艘17000 DWT油船运动的极短期预测，验证了WOA-BP模型在船舶横摇角、横摇角速度及横摇角加速度预测方面的高精度和泛化能力。通过与AQWA软件计算结果的对比分析，表明WOA-BP模型的预测频率响应与AQWA结果具有高度一致性，且预测性能显著优于传统BP神经网络，进一步验证了所提方法在船舶横摇预测方面的准确性和可靠性。本研究可望为船舶运动预测和控制提供一定的理论基础。
To enhance the prediction accuracy of ship motion under random sea conditions, this paper introduces an ultra-short-term forecasting model for ship rolling motion, known as the WOA-BP model. This model integrates the Whale Optimization Algorithm (WOA) with the Back Propagation (BP) neural network, utilizing WOA's efficient global search capabilities to optimize network parameters, thereby improving the accuracy of predictions and the speed of convergence. The effectiveness of the WOA-BP model was validated through an ultra-short-term prediction case study of a 17000 DWT tanker, demonstrating high precision and generalization capabilities in forecasting ship roll angle, roll angular velocity, and roll angular acceleration. A comparative analysis with AQWA software calculations revealed a high degree of consistency between the WOA-BP model's predictive frequency responses and AQWA results, with the WOA-BP model significantly outperforming the traditional BP neural network in predictive accuracy. This study not only confirms the accuracy and reliability of the proposed method in ship roll prediction but also provides a theoretical foundation for ship motion prediction and control.
2025,47(16): 83-90 收稿日期：2024-10-27
DOI：10.3404/j.issn.1672-7649.2025.16.013
分类号：U661.33
基金项目：国家自然科学基金资助项目（52371325，W2421063）；山东省自然科学基金资助项目（ZR2020ME263）
作者简介：牟新宇(1999-),女,硕士,研究方向为船舶运动预测与控制
参考文献：
[1] YIN J C, PERAKIS A N, WANG N. A real-time ship roll motion prediction using wavelet transform and variable RBF network[J]. Ocean Engineering, 2018, 160: 10-19.
[2] 于艳博. 船舶横摇运动建模与控制仿真研究[D]. 大连: 大连海事大学, 2015.
[3] 朱杰, 刘在良, 林艳, 等. 随机海浪下船舶横摇运动响应极值预报研究[J]. 中国舰船研究, 2020, 20(2): 196-202.
ZHU J, LIU Z L, LIN Y, et al. Extreme value prediction of ship roll motion response under random waves[J]. Chinese Journal of Ship Research, 2024, 19(3): 1-10.
[4] WANG Y, WANG H, ZHOU B, et al. Multi-dimensional prediction method based on Bi-LSTMC for ship roll[J]. Ocean Engineering, 2021, 242: 110106.
[5] DING S, SU C, YU J. An optimizing BP neural network algorithm based on genetic algorithm[J]. Artificial Intelligence Review, 2011, 36: 153-162.
[6] 李冲. 基于改进NARX神经网络的船舶横摇运动预测[D]. 大连: 大连海事大学, 2023.
[7] 张琴, 林欣如, 向阳, 等. 基于最优变分模态分解与相空间重构的LSTM船舶横摇运动预测[J]. 船舶工程, 2023, 45(12): 68-74.
ZHANG Q, LIN X R, XIANG Y, et al. Ship roll motion prediction using LSTM based on optimal variational mode decomposition and phase space reconstruction[J]. Journal of Ship Engineering, 2023, 45(12): 68-74.
[8] MIRJALILI S, LEWIS A. The Whale Optimization Algorithm[J]. Advances in Engineering Software, 2016, 95: 51-67.
[9] SOLEIMANIAN GHARECHOPOGH F, GHOLIZADEH H. A comprehensive survey: Whale Optimization Algorithm and its applications[J]. Swarm and Evolutionary Computation, 2019, 48: 1-24.
[10] 刘磊, 白克强, 但志宏, 等. 一种全局搜索策略的鲸鱼优化算法[J]. 小型微型计算机系统, 2020, 41(9): 1820-1825.
LIU L, BAI K Q, DAN Z H, et al. A whale optimization algorithm with global search strategy[J]. Journal of Chinese Computer Systems, 2020, 41(9): 1820-1825.
[11] 国际海事组织. MSC. 267(85). 2008国际完整稳性规则及修正案[S]. 北京: 人民交通出版社, 2016.
[12] 柴威. 随机海浪下的船舶非线性横摇与倾覆研究[D]. 上海: 上海交通大学, 2013.
[13] 胡丽芬, 张明, 巩庆涛, 等. 基于MPC的船舶横摇运动控制方法研究[J]. 水动力学研究与进展A辑, 2023, 38(4): 551-557.
HU L F, ZHANG M, GONG Q T, et al. Model predictive control-based ship roll motion control method[J]. Journal of Hydrodynamics, Ser. A, 2023, 38(4): 551-557.
[14] FRIZZELL J, FURTH M. Prediction of Vessel RAOs: Applications of Deep Learning to Assist in Design[C]// Proceedings of the 27th Offshore Symposium. Houston: SNAME, 2022.
