由于复杂海况随机海浪对船舶航行及人命安全造成威胁，通过构建海浪波高预测模型实现高海况海浪预警对提升航行安全具有重要意义。针对海浪波高预测问题，本文提出一种MAF-GWO-LSTM预测模型。首先利用滑动平均滤波器（Moving Average Filter, MAF）对实测海浪数据进行处理得到有效波高的光滑趋势序列，作为预测模型的输入训练集；再选用长短时记忆神经网络LSTM作为预测浪模型，依据灰狼优化算法（Grey Wolf Optimization, GWO）对滑动窗口MA及神经网络训练过程中的参数进行自适应寻优，并以南海实测有效波高数据进行验证。研究结果表明，采用MAF滤波有利于提取海浪有效波高特征，再通过GWO-LSTM预测模型优化神经网络参数，最优参数下波高预报精度达到R2=0.9910。论文研究可为高海况下海浪有效波高预报预警提供一种有效手段。
As random waves in complex sea conditions pose a threat to ship navigation and human life safety, it is of great significance to build a wave height prediction model to realize high sea state wave warning for improving navigation safety. Aiming at the problem of wave height prediction, a prediction model of MAF-GWO-LSTM is proposed in this paper. Firstly, the Moving Average Filter (MAF) is used to process the measured wave data to obtain the smooth trend sequence of the significant wave height, which is used as the input training set of the prediction model. Then, LSTM was selected as the wave prediction model. Grey Wolf Optimization (GWO) was used to optimize the parameters of the sliding window MA and the neural network in the training process, and the data of significant wave height measured in the South China Sea was used to verify the results. The results show that MAF filtering is conducive to extracting significant wave height features of ocean waves, and then MAF-GWO-LSTM prediction model is used to optimize the neural network parameters. Under the optimal parameters, the prediction accuracy of wave height reaches R2=0.9910. This paper provides an effective method for wave height prediction and early warning under high sea conditions.
2024,46(21): 33-39 收稿日期：2023-12-29
DOI：10.3404/j.issn.1672-7649.2024.21.006
分类号：U666.7
基金项目：国家重点研发计划项目（2022YFC2805200）；中国博士后科学基金资助项目（2023M740466）；大连理工大学海岸和近海工程国家重点实验室开放基金资助项目（LP2204）
作者简介：陈恒轩(1999-),男,硕士,研究方向为海浪与船舶运动预报
参考文献：
[1] 赵勇, 苏丹. 基于4种长短时记忆神经网络组合模型的畸形波预报[J]. 上海交通大学学报, 2022, 56(4): 516-22.
ZHAO Yong, SU Dan. Rogue wave prediction based on four combined long short-term memory neural network model[J]. Journal of Shanghai Jiaotong University, 2022, 56(4): 516-22.
[2] 郑小罗, 李其超, 姜浩, 等. 基于多周期趋势分解和两级融合策略的浪高预测方法[J]. 海洋科学进展, 2023, 41(3): 466-476.
ZHENG Xiaoluo, LI Qichao, JIANG Hao, et al. Wave height prediction method based on multi-period trend decomposition and two-level fusion strategy[J]. Advances in Marine Science, 2023, 41(3): 466-476.
[3] 何盛琪, 李其超, 宋巍, 等. 基于近岸海面视频的浪高实时检测预测系统[J]. 计算机技术与发展, 2022, 32(7): 138-43.
[4] 李其超. 近岸浪高自动检测预测方法研究 [D]. 上海: 上海海洋大学, 2022.
[5] 卢鹏, 年圣全, 邹国良, 等. 基于变分模态分解和注意力机制的浪高预测[J]. 海洋测绘, 2021, 41(2): 34-43.
LU Peng, NIAN Shengquan, ZOU Guoliang, et al. Wave height prediction based on variational mode decomposition and attention mechanism[J]. Hydrographic Surveying and Charting, 2021, 41(2): 34-43.
[6] 薛阳, 燕宇铖, 贾巍, 等. 基于改进灰狼算法优化长短期记忆网络的光伏功率预测[J]. 太阳能学报, 2023, 44(7): 207-220.
XUE Yang, YAN Yucheng, JIA Wei, et al. Photovoltaic power prediction model based on IGWO-LSTM[J]. Acta Energiae Solaris Sinica, 2023, 44(7): 207-220.
[7] 姚汭成, 龚德文. 基于GWO-SVR的深海采矿海试区海浪高度预测[J]. 矿冶工程, 2022, 42(6): 24-32.
YAO Ruicheng, GONG Dewen. Prediction of sea wave height in testing area for deep-sea mining based on GWO-SVR[J]. Mining and Metallurgical Engineering, 2022, 42(6): 24-32.
[8] DOMALA V, KIM T-W. Application of empirical mode decomposition and hodrick prescot filter for the prediction single step and multistep significant wave height with LSTM[J]. Ocean Engineering, 2023, 285: 115229.
[9] MENG Z-F, CHEN Z, KHOO B C, et al. Long-time prediction of sea wave trains by LSTM machine learning method[J]. Ocean Engineering, 2022, 262: 112213.
[10] LOU G, LIN W, HUANG G, et al. A two-stage online remaining useful life prediction framework for supercapacitors based on the fusion of deep learning network and state estimation algorithm[J]. Engineering Applications of Artificial Intelligence, 2023, 123: 106399.
[11] ZHANG J, XIN X, SHANG Y, et al. Nonstationary significant wave height forecasting with a hybrid VMD-CNN model[J]. Ocean Engineering, 2023, 285: 115338.
[12] ZHAO L, LI Z, QU L, et al. A hybrid VMD-LSTM/GRU model to predict non-stationary and irregular waves on the east coast of China[J]. Ocean Engineering, 2023, 276: 114136.
[13] MIRJALILI S, SAREMI S, MIRJALILI S M, et al. Multi-objective grey wolf optimizer: A novel algorithm for multi-criterion optimization[J]. Expert Systems with Applications, 2016, 47: 106-119.
[14] XIE J, XUE X. A novel hybrid model based on grey wolf optimizer and group method of data handling for the prediction of monthly mean significant wave heights[J]. Ocean Engineering, 2023, 284: 115274.
[15] ZHANG X, LU B, ZHANG L, et al. An enhanced grey wolf optimizer boosted machine learning prediction model for patient-flow prediction[J]. Computers in Biology and Medicine, 2023, 163: 107166.
[16] LIANG J, DU Y, XU Y, et al. Using Adaptive chaotic grey wolf optimization for the daily streamflow prediction[J]. Expert Systems with Applications, 2024, 237: 121113.
