Mooring-line Tension Prediction Based on Re-decomposition and Deep Learning

FAN Shijie; ZHANG Weiye; MIAO Weipao; WEN Qi; LI Chun; YUE Minnan

doi:10.19805/j.cnki.jcspe.2025.240449

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Mooring-line Tension Prediction Based on Re-decomposition and Deep Learning

更新时间：2026-10-10

- Mooring-line Tension Prediction Based on Re-decomposition and Deep Learning
- Chinese Journal of Power Engineering Vol. 45, Issue 9, Pages: 1422-1432(2025)
- 作者机构：
  
  1. 上海理工大学能源与动力工程学院,上海,200093
  2. 上海非碳基能源转换与利用研究院,上海,200240
- 作者简介：
- 基金信息：
- DOI：10.19805/j.cnki.jcspe.2025.240449
  CLC：
- Online First：16 September 2025，
  
  Published：2025
- 稿件说明：
移动端阅览
范士杰,张伟业,缪维跑,闻麒,李春,岳敏楠. 基于重分解和深度学习的系泊张力预测方法研究动力工程学报, 2025, 45(9): 1422-1432 https://doi.

org/10.19805/j.cnki.jcspe.2025.240449
范士杰,张伟业,缪维跑,闻麒,李春,岳敏楠. 基于重分解和深度学习的系泊张力预测方法研究动力工程学报, 2025, 45(9): 1422-1432 https://doi. DOI： 10.19805/j.cnki.jcspe.2025.240449.

org/10.19805/j.cnki.jcspe.2025.240449 DOI：

摘要

海上漂浮式风力机平台依靠系泊系统的回复力减小平台运动并进行定位

而系泊的结构完整性可通过其力学特性反映

故准确预测系泊系统的张力有助于建立高效、健康的监测系统。基于深度学习方法对系泊张力进行健康监测

为解决数据驱动方法在预测时间序列时丢失物理信息的问题

利用自适应白噪声平均总体经验模态分解(CEEMDAN)与样本熵进行一次模态分解重构

并利用变分模态分解(VMD)与盒维数进行二次分解重构

构建出有效的特征样本集。通过引入注意力机制

并将其与卷积神经网络(CNN)和双向长短期记忆网络(BiLSTM)相结合

构建深度学习预测模型AM-CNN-BiLSTM。结果表明:该模型应用于有效特征样本集时

重分解重构方法能有效提取特征

提升模型预测精度;在各种海况和系泊系统设计方案下

所提模型均能实现精确预测

且预测结果的决定系数

均不小于0.879

充分证明该方法具有良好的泛化能力。

Abstract

Offshore floating wind turbine platforms rely on the restoring forces provided by the mooring system to reduce the platform motion and maintain position. As the structural integrity of the mooring can be reflected by its mechanical properties

accurate prediction of the mooring system tension is essential for an efficient and reliable health monitoring system. A data-driven approach based on deep learning was developed to predict mooring-line tension. To preserve physical information that was often lost in pure time-series forecasting

complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) combined with sample entropy was applied for primary mode decomposition and reconstruc

tion. Variational mode decomposition (VMD) together with box dimension was employed for secondary decomposition and reconstruction

yielding a high-quality feature set. Attention mechanism was then integrated with a convolutional neural network and a bidirectional long short-term memory network (AM-CNN-BiLSTM) to construct the deep-learning tension-prediction model. Results show that the decomposition-reconstruction strategy effectively extracts informative features and improves prediction accuracy when applied to the feature set. Across diverse sea states and mooring-system configurations

the proposed model achieves precise tension predictions

with the coefficient-of-determination (

) values exceeding 0.879

confirming its strong generalization capability.

关键词

Keywords

references

Global Wind Energy Council. Global offshore wind report 2023[R]. Brussels, Belgium: Global Wind Energy Council, 2023.

韩志伟, 丁勤卫, 李春, 等. 风波耦合作用下悬链线系泊参数对不同漂浮式风力机平台动态响应的影响[J]. 动力工程学报, 2020, 40(8): 660-670. HAN Zhiwei, DING Qinwei, LI Chun, et al. Influence of parameters of catenary mooring systems on dynamic response of different floating wind turbine platforms under the coupling effect of wind and wave[J]. Journal of Chinese Society of Power Engineering, 2020, 40(8): 660-670.

KVITRUD A. Lessons learned from Norwegian mooring line failures 2010—2013[C]//International Conference on Offshore Mechanics and Arctic Engineering. San Francisco, USA: ASME, 2014.

MA K T, SHU Hongbo, SMEDLEY P, et al. A historical review on integrity issues of permanent mooring systems[C]//Offshore Technology Conference. Houston,USA: Offshore Technology Conference, 2013.

单桂敏. 新型深水系泊系统疲劳破坏分析[D]. 天津: 天津大学, 2010.

MAO Yixuan, WANG Tianqi, DUAN Menglan. A DNN-based approach to predict dynamic mooring tensions for semi-submersible platform under a mooring line failure condition[J]. Ocean Engineering, 2022, 266: 112767.

YANG Yu, PENG Tao, LIAO Shijun. Predicting future mooring line tension of floating structure by machine learning[J].Ocean Engineering, 2023, 269: 113470.

YU Yang, CHENG Siyuan, CUI Yupeng, et al. Mooring line failure diagnosis and motion control of semi-submersible platform based on the predictive model[J]. Ocean Engineering, 2023, 280: 114907.

LEE K, CHUNG M, KIM S, et al. Damage detection of catenary mooring line based on recurrent neural networks[J]. Ocean Engineering, 2021, 227: 108898.

MAO Yixuan, ZHENG Miaozi, WANG Tianqi, et al. A new mooring failure detection approach based on hybrid LSTM-SVM model for semi-submersible platform[J]. Ocean Engineering, 2023, 275: 114161.

孙康, 金江涛, 李春, 等. 漂浮式风力机平台局部系泊蠕变模式下动态响应分析[J]. 动力工程学报, 2022, 42(10): 933-943. SUN Kang, JIN Jiangtao, LI Chun, et al. Dynamic response analysis of floating wind turbine platform in local mooring creep mode[J]. Journal of Chinese Society of Power Engineering, 2022, 42(10): 933-943.

JONKMAN J M. Dynamics modeling and loads analysis of an offshore floating wind turbine[R]. United States: University of Colorado at Boulder, 2007.

LACKNER M A, ROTEA M A. Structural control of floating wind turbines[J]. Mechatronics, 2011, 21(4): 704-719.

YE Kan, JI Jinchen. Current, wave, wind and interaction induced dynamic response of a 5 MW spar-type offshore direct-drive wind turbine[J]. Engineering Structures, 2019, 178: 395-409.

HU Yaokun, TODA T. The effect of multi-directional on remote heart rate measurement using PA-LI joint ICEEMDAN method with mm-wave FMCW radar[J]. IEICE Transactions on Communications, 2022, E105.B(2): 159-167.

YIN Chen, WANG Yulin, MA Guocai, et al. Weak fault feature extraction of rolling bearings based on improved ensemble noise-reconstructed EMD and adaptive threshold denoising[J]. Mechanical Systems and Signal Processing, 2022, 171: 108834.

XU Zifei, LI Chun, YANG Yang. Fault diagnosis of rolling bearings using an improved multi-scale convolutional neural network with feature attention mechanism[J]. ISA Transactions, 2021, 110: 379-393.

YANG Dongchuan, GUO Ju'e, LI Yanzhao, et al. Short-term load forecasting with an improved dynamic decomposition-reconstruction-ensemble approach[J]. Energy, 2023, 263: 125609.

GU Haoyu, LIU Xianxue, ZHAO Baolin, et al. A compensation method for long-term zero bias drift of MEMS gyroscope based on improved CEEMD and ELM[C]//2018 IEEE 8th International Nanoelectronics Conferences (INEC). Kuala Lumpur, Malaysia: IEEE, 2018: 13-14.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Boiler Reheater Wall Temperature Prediction Model Based on CNN-BiLSTM-SSA

Day-ahead Irradiance Forecasting Framework Based on CEEMDAN-KDBSCAN-Informer

Study on Fault Early Warning of Induced Draft Fan Based on TCN-SDAE Model and Adaptive Dynamic Threshold

Prediction of SO2 Emission Concentration for CFB Units Under Quick Load Change Conditions Based on MLO-HIKAN

Spatio-temporal Graph Attention Network-based Fault Warning of Coal Mill

Related Author

ZHOU Huaichun

LIU Yang

QU Shuyang

WANG Junlue

FAN Jingwei

SHANG Zhongbao

PENG Xianyong

HE Zhiqian

Related Institution

Jiangsu Smart Energy Technology and Equipment Engineering Research Center

Huaneng Yingkou Thermal Power Co., Ltd.

School of Low Carbon Energy and Power Engineering, China University of Mining and Technology

School of Automation, Central South University

School of Electrical & Information Engineering, Changsha University of Science & Technology

AI问答

⁰