针对传统的神经网络模型因超参数众多，在实验中比对最优参数组合效率低下导致误差较大和反应速度慢的问题。本文提出一种基于北方苍鹰优化（Northern Goshawk Optimization，NGO）算法和双向门控循环单元神经网络（Bidirectional Gated Recurrent Unit, Bi-GRU）的船舶轨迹预测模型NGO-Bi-GRU（Northern Goshawk Optimization Bidirectional Gated Recurrent Unit）。利用NGO对Bi-GRU模型的学习率、隐藏节点和正则化系数进行寻优，然后将寻优得到的网络超参数代入Bi-GRU进行船舶轨迹预测。将该模型与长短时记忆神经网络（Long Short Term Memory, LSTM）和门控循环单元神经网络模型（Gated Recurrent Unit, GRU）以及使用该算法优化的长短期神经网络模型进行实验对比，将均方误差、均方根误差、平均绝对误差作为评价标准。结果表明，NGO-Bi-GRU模型在经度和纬度预测上误差较小、精确度较高且数值波动更加稳定。
In response to the challenges posed by the numerous hyperparameters in traditional neural network models, which result in significant errors and slow response times due to the inefficiency of comparing optimal parameter combinations in experiments, this paper introduces a novel ship trajectory prediction model based on Northern Goshawk Optimization (NGO) and Bidirectional Gated Recurrent Unit neural networks (Bi-GRU), termed NGO-Bi-GRU. The NGO algorithm is employed to optimize the learning rate, hidden nodes, and regularization coefficients of the Bi-GRU model, after which the optimized network hyperparameters are applied to Bi-GRU for ship trajectory prediction. This model is experimentally compared with Long Short Term Memory (LSTM) networks, Gated Recurrent Unit (GRU) networks, and LSTM networks optimized using the same algorithm. Evaluation criteria include mean squared error, root mean squared error, and mean absolute error. The results demonstrate that the NGO-Bi-GRU model achieves lower errors and higher precision in predicting longitude and latitude, with more stable numerical fluctuations.
2025,47(4): 14-20 收稿日期：2024-5-13
DOI：10.3404/j.issn.1672-7649.2025.04.003
分类号：U661
基金项目：中国国家自然科学基金资助项目（522713602）；四川省自然科学基金资助项目（2022NSFSC0891）
作者简介：谢海波(1987-),男,硕士,副教授,研究方向为智能船舶
参考文献：
[1] 李永, 成梦雅. LSTM船舶航迹预测模型[J]. 计算机技术与发展, 2021, 31(9): 149-154.
LI Y, CHENG M Y. LSTM ship track prediction model[J]. Computer Technology and Development, 2021, 31(9): 149-154.
[2] 任宇翔, 赵建森, 刘卫, 等. 基于AIS数据和LSTM网络的船舶航行动态预测[J]. 上海海事大学学报, 2019, 40(3): 32-37.
REN Y X, ZHAO J S, LIU W, et al. Ship navigation behavior prediction based on AIS data and LSTM network,[J]. Journal of Shanghai Maritime University, 2019, 40(3): 32-37.
[3] 胡玉可, 夏维, 胡笑旋, 等. 基于循环神经网络的船舶航迹预测[J]. 系统工程与电子技术, 2020, 42(4): 871-877.
HU Y K, XIA W, HU X X, et al. Vessel trajectory prediction based on recurrent neural network,[J]. Systems Engineering and Electronics, 2020, 42(4): 871-877.
[4] 刘姗姗, 马社祥, 孟鑫, 等. 基于CNN和Bi-LSTM的船舶航迹预测[J]. 重庆理工大学学报(自然科学), 2020, 34(12): 196-205.
LIU S S, MA S X, MENG X, et al. Prediction model of ship trajectory based on CNN and Bi-LSTM,[J]. Journal of Chongqing University of Technology (Natural Science), 2020, 34(12): 196-205.
[5] 万洪亮, 潘家财, 甄荣, 等. 基于CNN-GRU的船舶轨迹预测[J]. 广州航海学院学报, 2022, 30(2): 12-18.
WAN H L, PAN J C, ZHEN R, et al. Prediction of ship trajectory based on CNN-GRU,[J]. Journal of Guangzhou Maritime University, 2022, 30(2): 12-18.
[6] 马全党, 张丁泽, 王群朋, 等. 双向门控循环单元在船舶轨迹预测中的应用[J/OL]. 安全与环境学报: 1-10[2023-10-09].
MA Q D, ZHANG D Z, WANG Q P, et al. Application of Bi-GRU for ship trajectory prediction, [J]. Journal of Safety and Environment, 1-10[2023-10-09].
[7] FISCHER T, KRAUSS C. Deep learning with long short-term memory networks for financial market predictions[J].European Journal of Operational Research, 2018, 270, 654-669.
[8] RATH P, MALLICK P K, TRIPATHY H K, et al. A tuned whale optimization-based stacked-LSTM network for digital image segmentation[J]. Arabian Journal for Science and Engineering. 2023, 48, 1735–1756.
[9] 吴春鹏, 冯姣. 结合AMS的C-LSTM船舶轨迹预测[J]. 船海工程, 2021, 50(6): 141-146+152.
WU C P, FENG J. Ship trajectory prediction based on C-LSTM combined with AMS[J]. Ship & Ocean Engineering, 2021, 50(6): 141-146+152.
[10] JIA H, YANG Y, AN J, et al. A Ship trajectory prediction model based on attention-BILSTM optimized by the whale optimization algorithm[J]. Applied Science, 2023, 13: 4907.
[11] GU W T, ZHENG S H, WANG R, et al. Forecasting realized volatility based on sentiment index and GRU model[J]. Journal of Advanced Computational Intelligence and Intelligent Informatics, 2020, 24(3): 299-306.
[12] DEHGHANI M, HUBÁLOVSKÝ Š, TROJOVSKÝ P. Northern goshawk optimization: a new swarm-based algorithm for solving optimization problems[J] IEEE Access, 2021, 9: 162059-162080.
[13] 陈凯达, 朱永生, 闫柯, 等. 基于LSTM的船舶航迹预测[J]. 船海工程, 2019, 48(6): 121-125.
CHEN K D, ZHU Y S, YAN K, et al. The ship track prediction method based on long short-term memory network[J]. Ship & Ocean Engineering, 2019, 48(6): 121-12.
