改进LSTM神经网络在极短期波浪时序预报中的应用

doi:10.16183/j.cnki.jsjtu.2021.438

上海交通大学学报 ›› 2023, Vol. 57 ›› Issue (6): 659-665.doi: 10.16183/j.cnki.jsjtu.2021.438

所属专题：《上海交通大学学报》2023年“船舶海洋与建筑工程”专题

改进LSTM神经网络在极短期波浪时序预报中的应用

尚凡成¹, 李传庆¹^,², 詹可¹, 朱仁传¹()

1.上海交通大学海洋工程国家重点实验室; 船舶海洋与建筑工程学院,上海 200240
2.上海船舶运输科学研究所航运技术与安全国家重点实验室,上海 200135

收稿日期:2021-11-02 接受日期:2022-08-10 出版日期:2023-06-28 发布日期:2023-07-05
通讯作者: 朱仁传 E-mail:renchuan@sjtu.edu.cn.
作者简介:尚凡成(1998-),硕士生,从事船海工程水动力学研究.

Application of Improved LSTM Neural Network in Time-Series Prediction of Extreme Short-Term Wave

SHANG Fancheng¹, LI Chuanqing¹^,², ZHAN Ke¹, ZHU Renchuan¹()

1. State Key Laboratory of Ocean Engineering; School of Naval Architecture, Ocean and Civil Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
2. State Key Laboratory of Navigation and Safety Technology, Shanghai Ship and Shipping Research Institute, Shanghai 200135, China

Received:2021-11-02 Accepted:2022-08-10 Online:2023-06-28 Published:2023-07-05
Contact: ZHU Renchuan E-mail:renchuan@sjtu.edu.cn.

摘要/Abstract

摘要：

高效准确的极短期预报对实海况下船海结构物的施工作业安全意义重大.由于海浪的随机性,短期预报往往使用时间序列分析进行,近年来神经网络特别是长短期记忆(LSTM)神经网络在时间序列分析上预报能力强.基于此,提出一种结合生成式对抗思想的LSTM改进形式,在神经网络中嵌入频域特性等的先验知识,实现时频域信息耦合预报.经实验测试可知,该方法预报精度优于传统时序分析方法和LSTM神经网络结果,适用于极短期时序预报,有助于实现更好的船舶操纵控制.

关键词: 极短期预报, 时序分析, 长短期记忆神经网络, 生成式对抗

Abstract:

Efficient and accurate extreme short-term prediction is of great significance for the safety of ship and marine structures in actual sea waves. Due to the stochastic of actual sea waves, short-term prediction always uses time series analysis. The neural networks, particularly long short-term memory (LSTM) neural networks, have received increasing attention for their powerful forecasting capability in time series analysis. Based on this, an improved form of LSTM combining generative adversarial ideas is proposed, in which the frequency domain characteristics are embedded in the neural network to achieve coupled time-frequency domain information forecasting. The experimental test shows that the forecasting accuracy of this method is better than the results of traditional time series analysis methods and the LSTM neural network, and it is suitable for extreme short-term time series prediction for better ship maneuvering.

Key words: extreme short-term prediction, time-series analysis, long short-term memory (LSTM) neural network, generative adversarial

中图分类号:

U664.82

尚凡成, 李传庆, 詹可, 朱仁传. 改进LSTM神经网络在极短期波浪时序预报中的应用[J]. 上海交通大学学报, 2023, 57(6): 659-665.

SHANG Fancheng, LI Chuanqing, ZHAN Ke, ZHU Renchuan. Application of Improved LSTM Neural Network in Time-Series Prediction of Extreme Short-Term Wave[J]. Journal of Shanghai Jiao Tong University, 2023, 57(6): 659-665.

图/表 8

图1

图2

图3

图4

图5

表1

图6

图7

参考文献 15

[1]	朱仁传, 缪国平. 船舶在波浪上的运动理论[M]. 上海: 上海交通大学出版社, 2019: 179-186.
	ZHU Renchuan, MIAO Guoping. The theory of ship motion in waves[M]. Shanghai: Shanghai Jiao Tong University Press, 2019: 179-186.
[2]	刘煜城. 基于深度学习的船舶运动极短期预报方法研究[D]. 哈尔滨: 哈尔滨工程大学, 2019.
	LIU Yucheng. Research on short-term forecasting method of ship motion based on deep learning[D]. Harbin:Harbin Engineering University, 2019.
[3]	YUMORI I. Real time prediction of ship response to ocean waves using time series analysis[C]// Oceans. Boston,USA: IEEE, 2010: 1082-1089.
[4]	GREFF K, SRIVASTAVA R K, KOUTNIK J, et al. LSTM: A search space odyssey[J]. IEEE Transactions on Neural Networks and Learning Systems, 2017, 28(10): 2222-2232. doi: 10.1109/TNNLS.2016.2582924 pmid: 27411231
[5]	DUAN W Y, HAN Y, HUANG L M, et al. A hybrid EMD-SVR model for the short-term prediction of significant wave height[J]. Ocean Engineering, 2016, 124: 54-73. doi: 10.1016/j.oceaneng.2016.05.049 URL
[6]	LI G Y, KAWAN B, WANG H, et al. Neural-network-based modelling and analysis for time series prediction of ship motion[J]. Ship Technology Research, 2017, 64(1): 30-39. doi: 10.1080/09377255.2017.1309786 URL
[7]	张彪, 彭秀艳, 高杰. 基于ELM-EMD-LSTM组合模型的船舶运动姿态预测[J]. 船舶力学, 2020, 24(11): 1413-1421.
	ZHANG Biao, PENG Xiuyan, GAO Jie. Ship motion attitude prediction based on ELM-EMD-LSTM integrated model[J]. Journal of Ship Mechanics, 2020, 24(11): 1413-1421.
[8]	张钹, 朱军, 苏航. 迈向第三代人工智能[J]. 中国科学: 信息科学, 2020, 50(9): 1281-1302.
	ZHANG Bo, ZHU Jun, SU Hang. Toward the third generation of artificial intelligence[J]. Scientia Sinica (Informationis), 2020, 50(9): 1281-1302.
[9]	邱锡鹏. 神经网络与深度学习[M]. 北京: 机械工业出版社, 2020: 129-145, 180-186.
	QIU Xipeng. Neural networks and deep learning[M]. Beijing: China Machine Press, 2020: 129-145, 180-186.
[10]	王坤峰, 苟超, 段艳杰, 等. 生成式对抗网络GAN的研究进展与展望[J]. 自动化学报, 2017, 43(3): 321-332.
	WANG Kunfeng, GOU Chao, DUAN Yanjie, et al. Generative adversarial networks: The state of the art and beyond[J]. Acta Automatica Sinica, 2017, 43(3): 321-332.
[11]	CRESWELL A, WHITE T, DUMOULIN V, et al. Generative adversarial networks: An overview[J]. IEEE Signal Processing Magazine, 2018, 35(1): 53-65. doi: 10.1109/MSP.2017.2765202 URL
[12]	TZENG E, HOFFMAN J, SAENKO K, et al. Adversarial discriminative domain adaptation[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE, 2017: 2962-2971.
[13]	何新林, 戚宗锋, 李建勋. 基于隐变量后验生成对抗网络的不平衡学习[J]. 上海交通大学学报, 2021, 55(5): 557-565.
	HE Xinlin, QI Zongfeng, LI Jianxun. Unbalanced learning of generative adversarial network based on latent posterior[J]. Journal of Shanghai Jiao Tong University, 2021, 55(5): 557-565.
[14]	TUKEY C J W. An algorithm for the machine calculation of complex Fourier series[J]. Mathematics of Computation, 1965, 19(90): 297-301. doi: 10.1090/mcom/1965-19-090 URL
[15]	于宁莉, 易东云, 涂先勤. 时间序列中自相关与偏相关函数分析[J]. 数学理论与应用, 2007, 27(1): 54-57.
	YU Ningli, YI Dongyun, TU Xianqin. Analyze auto-correlations and partial-correlations function in time series[J]. Mathematical Theory and Applications, 2007, 27(1): 54-57.

方法	MSE/MAE
方法	AR模型	LSTM模型	改进LSTM模型
提前5步	1.736/0.932	1.539/0.943	1.273/0.848
提前10步	2.499/1.207	2.311/1.175	2.294/1.179
提前15步	2.514/1.222	2.248/1.149	2.178/1.134
提前20步	3.839/1.501	3.256/1.395	3.236/1.385

改进LSTM神经网络在极短期波浪时序预报中的应用

Application of Improved LSTM Neural Network in Time-Series Prediction of Extreme Short-Term Wave

RichHTML

PDF (PC)

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 15

相关文章 6

编辑推荐

Metrics

本文评价

[1]	. 基于生成式对抗网络的红外单像素成像[J]. J Shanghai Jiaotong Univ Sci, 2025, 30(6): 1114-1124.
[2]	刘俊城, 谭勇, 张生杰. 地铁车站深基坑开挖变形智能多步预测方法[J]. 上海交通大学学报, 2024, 58(7): 1108-1117.
[3]	卫慧, 陈鹏, 张芮菡, 程正顺. 基于长短期记忆网络的大型漂浮式风力发电机平台运动极短期预报方法[J]. 上海交通大学学报, 2023, 57(S1): 37-45.
[4]	曹现刚1, 2，雷卓1，李彦川1，张梦园1，段欣宇1. 基于Self-Attention-LSTM神经网络的设备剩余寿命预测方法[J]. J Shanghai Jiaotong Univ Sci, 2023, 28(5): 652-664.
[5]	张松林, 马栋梁, 王德禹. 基于长短期记忆神经网络的板裂纹损伤检测方法[J]. 上海交通大学学报, 2021, 55(5): 527-535.
[6]	谭嘉, 李知艺, 杨欢, 赵荣祥, 鞠平. 基于分布式优化思想的配电网用电负荷多层协同预测方法[J]. 上海交通大学学报, 2021, 55(12): 1544-1553.