对船舶姿态的准确预测有利于保障船舶航行安全、提高船载仪器的数据质量。针对船舶运动姿态预测与分析问题，将特征选择（Feature Selection，FS）方法与长短期记忆神经网络（Long Short Term Memory，LSTM）相结合，以提高LSTM网络对船舶运动姿态的预测精度，为船舶运动姿态的补偿奠定基础。以船舶运动姿态预测为目标，基于无人艇采集到的包含船舶运动状态信息的数据集，构建并训练了适应性较强的FS-LSTM神经网络预测模型。最终结果表明，本文所提出的方法具有较高的预测精度。
The accurate prediction of ship attitude is conducive to ensuring ship navigation safety and improving the data quality of shipborne instruments. Aiming at the problem of ship motion attitude prediction and analysis, this paper combines the Feature Selection (FS) method with the Long Short Term Memory (LSTM) neural network to improve the accuracy of ship motion attitude prediction by LSTM network. It lays the foundation for the compensation of ship motion attitude. Based on the data set of ship motion state information collected by unmanned boat, this paper constructs and trains the FS-LSTM neural network prediction model with strong adaptability. The final results show that the proposed method has high prediction accuracy.
2024,46(19): 25-30 收稿日期：2023-11-16
DOI：10.3404/j.issn.1672-7649.2024.19.005
分类号：U674.98
基金项目：国家重点研发计划资助项目（2022YFC3006000）
作者简介：吕东坡(1996-),男,硕士,助理工程师,研究方向为船载稳定平台设计、制造及应用技术
参考文献：
[1] 蒋银, 朱仁传, 缪国平, 等. 三维船体横摇运动数值模拟及舭龙骨阻尼特性研究[J]. 船舶力学, 2020, 24(6): 706-719.
JIANG Yin, ZHU Renchuan, MIAO Guoping, et al. Numerical simulation of three-dimensional hull roll motion and study on bilge keel damping characteristics[J]. Journal of Ship Mechanics, 2020, 24(6): 706-719.
[2] 阮光维. 船舶减摇鳍系统的控制方法研究[D]. 大连: 大连海事大学, 2020.
[3] 张文杰. 基于深度学习的无人艇运动姿态预报[D]. 上海: 上海大学, 2020.
[4] 谷达京, 施哲源, 陈根良, 等. 基于神经网络的船体运动位姿预测方法[J]. 舰船科学技术, 2022, 44(15): 55-59.
GU Dajing, SHI Zheyuan, CHEN Genliang, et al. A method of hull motion posture prediction based on neural network[J]. Ship Science and Technology, 2022, 44(15): 55-59.
[5] 周佳宇, 韩俊庆, 李伟, 等. 基于扩张状态卡尔曼原理的海浪滤波算法[J]. 舰船科学技术, 2023, 45(7): 62-65.
ZHOU Jiayu, HAN Junqing, LI Wei, et al. Wave filtering algorithm based on extended state Kalman principle[J]. Ship Science and Technology, 2023, 45(7): 62-65.
[6] 李娜, 郑少智. 平滑转移自回归模型及其应用[J]. 统计与决策, 2018, 34(10): 24-28.
LI Na, ZHENG Shaozhi. Smooth transfer autoregressive model and its application[J]. Statistics and Decision, 2018, 34(10): 24-28.
[7] SHEN C, ZHANG Y, GUO X, et al. Seamless GPS/inertial navigation system based on self-learning square-root cubature Kalman filter [J]. Transactions on Indastrial Electronics, 2020, 68(1): 499–508.
[8] GE Yang, QIN Mingjie, NIU Qingtao. Prediction of ship motion attitude based on BP network [C]//2017 29th Chinese Control And Decision Conference (CCDC), 2017: 1596-1600.
[9] 王国栋. 基于LSTM的舰船运动姿态短期预测及仿真研究[D]. 镇江: 江苏科技大学, 2017.
[10] 徐国庆, 马建文, 吴晨辉, 等. 基于Attenton-LSTM神经网络的船舶航行预测[J]. 舰船科学技术, 2019, 41(23): 177-180.
XU Guoqing, MA Jianwen, WU Chenhui, et al. Ship navigation prediction based on attenton-LSTM neural network[J]. Ship Science and Technology, 2019, 41(23): 177-180.
[11] 王研婷. 基于CNN和LSTM的船舶航迹预测[D]. 大连: 大连海事大学, 2020.
[12] 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 Shanshan, MA Shexiang, MENG Xin, et al. Ship track prediction based on CNN and Bi-LSTM[J]. Journal of Chongqing University of Technology (Natural Sciences), 2020, 34(12): 196-205.
[13] 王文标, 董贵平, 汪思源, 等. 基于CEEMD-PSO-MNN的船舶航迹预测[J]. 电子器件, 2021, 44(1): 119-124.
WANG Wenbiao, DONG Guiping, WANG Siyuan, et al. Ship track prediction based on CEEMD-PSO-MNN[J]. Electronic Device, 2021, 44(1): 119-124.
[14] 王余宽, 谢新连, 马昊, 等. 基于滑动窗口LSTM网络的船舶航迹预测[J]. 上海海事大学学报, 2022, 43(1): 14-22.
WANG Yukuan, XIE Xinlian, MA Hao, et al. Ship track prediction based on sliding window LSTM network[J]. Journal of Shanghai Maritime University, 2022, 43(1): 14-22.
[15] 石宇芃, 马宏军, 陈豹. 基于四元数的四旋翼无人机扩展卡尔曼滤波算法[J]. 控制工程, 2021, 28(11): 2131-2135.
SHI Yufan, MA Hongjun, CHEN Bao. Extended Kalman filtering algorithm for four-rotor UAV based on quaternion[J]. Control Engineering, 2021, 28(11): 2131-2135.
[16] 周增光, 唐娉. 基于质量权重的Savitzky-Golay时间序列滤波方法[J]. 遥感技术与应用, 2013, 28(2): 232-239.
ZHOU Zengguang, TANG Pin. Savitzky-Golay time series filtering method based on mass weights[J]. Remote Sensing Technology and Application, 2013, 28(2): 232-239.
[17] OH Sejong. Predictive case-based feature importance and interaction[J]. Information Sciences, 2022, 593.
