Home Journals Articles Updates About
CN
image
收藏切换
An improved LSTM method for extremely short-term forecasting of ship movement
收藏切换
PDF
Zhi-chao HONG1, 5, Yi-jie DING1, Lei LIU2, Hao WANG3, 4, Wei-wei ZHANG3, 4, Li-xin XU1, 5
Journal of Ship Mechanics | 2025, 29(9) : 1383 - 1396
Less
收藏切换
Journal of Ship Mechanics | 2025, 29(9): 1383-1396
• Hydrodynamics •
An improved LSTM method for extremely short-term forecasting of ship movement
Full
Zhi-chao HONG1, 5, Yi-jie DING1, Lei LIU2, Hao WANG3, 4, Wei-wei ZHANG3, 4, Li-xin XU1, 5
Affiliations
  • 1.Jiangsu University of Science and Technology, Zhenjiang 212100, China
  • 2.China Shipbuilding Engineering Society, Beijing 100861, China
  • 3.Nantong Pengrui Offshore Engineering Co., Ltd., Nantong 226000, China
  • 4.Nantong Jihai Marine Equipment Co., Ltd., Nantong 226100, China
  • 5.Jiangsu Provincial Technology Innovation Center for Shipbuilding and Offshore Engineering Equipment, Nantong 226100, China
Published: 2025-09-20 doi: 10.3969/j.issn.1007-7294.2025.09.005
Outline
收藏切换

The motion of ships and marine structures is a nonlinear motion with time series characteristics. The Long Short-Term Memory (LSTM) artificial neural network has the characteristics of memorizing time interval information and processing nonlinear data, which is very suitable for processing such nonlinear motion with time series characteristics. Therefore, LSTM has significant advantages in predicting the very short-term motion response of ships. In this paper, an improved LSTM method for the prediction of very short-term motion response of ships is proposed. This method converts the prediction of ship motion into the prediction of peak and valley values by means of extracting envelopes, which can reduce the data demand of the traditional LSTM model and simplify the complexity of the prediction curve, thereby significantly improving the forecast duration. In this paper, the improved LSTM was used to predict the regular wave curve, irregular wave curve and real ship motion curve. The results show that the improved LSTM prediction method can enlarge the maximum forecast duration of the traditional LSTM model from 6~8 s to about 20 s, and has ideal prediction results for special signals such as abrupt signals, which has high practical value.

LSTM  /  ship movement  /  very short-term forecast  /  envelope line analysis
Zhi-chao HONG, Yi-jie DING, Lei LIU, Hao WANG, Wei-wei ZHANG, Li-xin XU. An improved LSTM method for extremely short-term forecasting of ship movement[J]. Journal of Ship Mechanics, 2025 , 29 (9) : 1383 -1396 . DOI: 10.3969/j.issn.1007-7294.2025.09.005
Appendix
Less
Year 2025 volume 29 Issue 9
PDF
81
35
Cite this Article
BibTeX
Article Info
doi: 10.3969/j.issn.1007-7294.2025.09.005
  • Receive Date：2025-03-15
  • Online Date：2026-03-26
  • Published：2025-09-20
Article Data
Affiliations
History
  • Received：2025-03-15
Funding
Affiliations
    1.Jiangsu University of Science and Technology, Zhenjiang 212100, China
    2.China Shipbuilding Engineering Society, Beijing 100861, China
    3.Nantong Pengrui Offshore Engineering Co., Ltd., Nantong 226000, China
    4.Nantong Jihai Marine Equipment Co., Ltd., Nantong 226100, China
    5.Jiangsu Provincial Technology Innovation Center for Shipbuilding and Offshore Engineering Equipment, Nantong 226100, China
References
Share
https://castjournals.cast.org.cn/joweb/cblx/EN/10.3969/j.issn.1007-7294.2025.09.005
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family		 属数
Number of
genus		 种数
Number of
species		 占总种数比例
Percentage of
total species (%)		 属
Genus		 种数
Number of
species		 占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT
Links
Articles
Latest Articles
Most Read
Collections
Updates
Events
News
Multimedia
About
About Us
Contact
No. 86 Xueyuan South Road, Haidian District, Beijing
100081
010-62199257
qkjq@cast.org.cn

Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House