半潜式浮式风机基础水动力特性及系泊系统张力特性预测

doi:10.11978/2024177

Abstract

Abstract:

Climate change has caused frequent extreme sea conditions in China's coastal regions. This has resulted in significant dynamic movements of the semi-submersible floating wind turbine foundation at sea, leading to the slack-tension phenomenon of the mooring cables. This phenomenon greatly reduces the service life of the mooring system and poses a safety risk to the overall operation of the wind turbine platform. In order to achieve an efficient, accurate and low-cost safety warning for mooring systems, this paper proposes a method which uses a fully connected neural network to predict the load, dynamic response and tension characteristics of the mooring system based on wave conditions. Using numerical simulation, a database of wave heights and the load and motion response of the foundation of a semi-submersible floating wind turbine under extreme sea conditions was constructed, and then based on which a fully connected neural network method was used to learn and make predictions. The results showed that the prediction accuracy of the tension in the mooring cables, the motion response and the load of the wind turbine foundation reached 99.57%, 98.91% and 99.79%, respectively, which proved the feasibility and reliability of the method for predicting the safety of mooring systems and provided reference for the practical application of advanced safety warning for offshore wind turbines.

Key words: semi-submersible floating platform, mooring system, fully connected neural network, deep learning, dynamic response

CLC Number:

LI Tiankuo, QU Ke, LI Xiaohan, WANG Aoyu, WANG Chao. The hydrodynamic characteristics and the prediction of mooring system tensions for a semi-submersible floating wind turbine foundation[J].Journal of Tropical Oceanography, 2025, 44(3): 36-47.

Figures/Tables 22

Tab. 1

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Fig. 6

Tab. 2

Tab. 3

Tab. 4

Tab. 5

Fig. 7

Fig. 8

Fig. 9

Fig. 10

Fig. 11

Fig. 12

Fig. 13

Fig. 14

Fig. 15

Tab. 7

References 23

[1]	杜君峰, 王顺坤, 张德庆, 等, 2022. 基于神经网络模型的波候变化影响下深海系泊缆疲劳损伤评估[J]. 船舶力学, 26(8): 1189-1198.
	DU JUNFENG, WANG SHUNKUN, ZHANG DEQING, et al, 2022. Fatigue damage assessment of deep-sea mooring lines under the influence of wave climate change based on neural network model[J]. Journal of Ship Mechanics, 26(8): 1189-1198 (in Chinese with English abstract).
[2]	高言乐, 2020. 风浪联合作用下Braceless半潜式风机动力特性分析[D]. 大连: 大连理工大学.
	GAO YANLE, 2020. Dynamic characteristics analysis of braceless semi-submersible offshore wind turbine under the combined wind and wave conditions[D]. Dalian: Dalian University of Technology (in Chinese with English abstract).
[3]	刘超, 2007. 海洋工程锚泊系统计算与分析[D]. 武汉: 武汉理工大学: 1-55.
	LIU CHAO, 2007. The calculation and analysis of mooring system[D]. Wuhan: Wuhan University of Technology: 1-55 (in Chinese with English abstract).
[4]	马刚, 何栗兴, 张旭, 等, 2022. 向变极端相干阵风下浮式风机系泊线断裂风险因素分析[J]. 风机技术, 64(3): 57-62.
	MA GANG, HE LIXING, ZHANG XU, et al, 2022. Hazardous factor analysis of mooring fracture in floating offshore wind turbine under extreme coherent gust with direction change[J]. Chinese Journal of Turbomachinery, 64(3): 57-62 (in Chinese with English abstract).
[5]	唐友刚, 张若瑜, 程楠, 等, 2009. 集中质量法计算深海系泊冲击张力[J]. 天津大学学报, 42(8): 695-701.
	TANG YOUGANG, ZHANG RUOYU, CHENG NAN, et al, 2009. Analysis of snap tension of deep water mooring with lumped mass method[J]. Journal of Tianjin University, 42(8): 695-701 (in Chinese with English abstract).
[6]	王春, 陆义超, 邢占清, 等, 2015. 基于神经网络算法的海上风机结构状态监测研究[J]. 中国水利水电科学研究院学报, 13(5): 344-351.
	WANG CHUN, LU YICHAO, XING ZHANQING, et al, 2015. Research of offshore wind turbine status monitoring based on neural network algorithm[J]. Journal of China Institute of Water Resources and Hydropower Research, 13(5): 344-351 (in Chinese with English abstract).
[7]	王瑞华, 张素侠, 刘习军, 2020. 浸没式浮筒对系泊缆松弛-张紧特性的影响研究[J]. 应用力学学报, 37(2): 543-549, 926.
	WANG RUIHUA, ZHANG SUXIA, LIU XIJUN, 2020. Study on the effect of submersed buoy on the taut-slack characteristics of the mooring line[J]. Chinese Journal of Applied Mechanics, 37(2): 543-549, 926 (in Chinese with English abstract).
[8]	易振宇, 蒋昌波, 屈科, 等, 2021. 聚焦波浪在浅堤上传播变形高精度数值模拟研究[J]. 海洋工程, 39(1): 32-42.
	YI ZHENYU, JIANG CHANGBO, QU KE, et al, 2021. High-resolution numerical simulation of focused wave propagation and deformation on submerged breakwater[J]. The Ocean Engineering, 39(1): 32-42 (in Chinese with English abstract).
[9]	张德庆, 王超, 杜君峰, 2021. 基于人工神经网络算法的深海浮式系统动力响应预报方法[J]. 中国造船, 62(1): 123-132.
	ZHANG DEQING, WANG CHAO, DU JUNFENG, 2021. A novel method for predicting dynamic response of deep-sea floating system based on artificial neural network[J]. Shipbuilding of China, 62(1): 123-132 (in Chinese with English abstract).
[10]	张素侠, 唐友刚, 林维学, 等, 2008. 水下缆绳松弛-张紧过程的冲击张力实验研究[J] 中国造船, 49(增刊2): 385-390.
	ZHANG SU XIA, TANG YOU GANG, LIN WEI XUE, et al, 2008. Experimental investigation of marine cable snap tension in taut-slack condition[J]. Shipbuilding of China, 49(Special 2): 385-390 (in Chinese with English abstract).
[11]	仲凡, 连宇顺, 郑金海, 等, 2024. 不同材质共享缆绳对浮式风电场系泊响应的影响[J]. 中国舰船研究, 19(4): 59-70.
	ZHONG FAN, LIAN YUSHUN, ZHENG JINHAI, et al, 2024. Effects of shared lines with different materials on mooring response of the floating wind farm[J]. Chinese Journal of Ship Research, 19(4): 59-70 (in Chinese with English abstract).
[12]	BERTHELSEN P A, FALTINSEN O M, 2008. A local directional ghost cell approach for incompressible viscous flow problems with irregular boundaries[J]. Journal of Computational Physics, 227(9): 4354-4397.
[13]	BIHS H, CHELLA M A, KAMATH A, et al, 2017. Numerical investigation of focused waves and their interaction with a vertical cylinder using REEF3D[J]. Journal of Offshore Mechanics and Arctic Engineering, 139(4): 041101.
[14]	KINGMA D P, BA J, 2017. Adam: A Method for Stochastic Optimization[J/OL]. arXiv:1412.6980v9 (2017-01-30)[2024-09-13]. https://arxiv.org/abs/1412.6980.
[15]	LECUN Y, BENGIO Y, HINTON G, 2015. Deep learning[J]. Nature, 521(7553): 436-444.
[16]	LU WEI, GE FEI, WANG LEI, et al, 2011. On the slack phenomena and snap force in tethers of submerged floating tunnels under wave conditions[J]. Marine Structures, 24(4): 358-376.
[17]	NING D Z, ZANG J, LIU S X, et al, 2009. Free-surface evolution and wave kinematics for nonlinear uni-directional focused wave groups[J]. Ocean Engineering, 36(15/16): 1226-1243.
[18]	QIAO DONGSHENG, LI PENG, MA GANG, et al, 2021. Realtime prediction of dynamic mooring lines responses with LSTM neural network model[J]. Ocean Engineering, 219: 108368.
[19]	SHI WEI, HU LEHAN, LIN ZAIBIN, et al, 2023. Short-term motion prediction of floating offshore wind turbine based on Muti-input LSTM neural network[J]. Ocean Engineering, 280: 114558.
[20]	VASSALOS D, HUANG SHAN, KOUROUKLIS A, 2004. Experimental investigation of snap loading of marine cables[C/OL]. Toulon:The International Society of Offshore and Polar Engineers, [2024-09-13]. https://publications.isope.org/proceedings/ISOPE/ISOPE%202004/volume2/2004-jsc-122.pdf
[21]	NAIR V, HINTON G E, NAIR V, et al, 2010. Rectified linear units improve restricted Boltzmann machines[C]// Proceedings of the 27th International Conference on International Conference on Machine Learning. Haifa: ACM: 807-814.
[22]	WANG ZIMING, QIAO DONGSHENG, YAN JUN, et al, 2022. A new approach to predict dynamic mooring tension using LSTM neural network based on responses of floating structure[J]. Ocean Engineering, 249: 110905.
[23]	WU MINGHAO, STRATIGAKI V, TROCH P, et al, 2019. Experimental study of a moored floating oscillating water column wave-energy converter and of a moored cubic box[J]. Energies, 12(10): 1834.

工况	参数
工况	H_F/m	T/s	x_F/m	t_F/s
N1	0.0626	1.20	7.5	10.0
N2	0.1750	1.25	7.2	10.0

参数	设计参数
中心柱直径/m	6.5
侧柱直径/m	6.5
浮筒高度/m	6
浮筒宽度/m	9
侧柱圆心到中心柱圆心长度/m	41
浮筒长度/m	45.5
侧柱高度/m	34
中心柱高度/m	44
作业吃水/m	30
排水体积/m³	10555
浮体总重量/kg	9738000

参数	设计参数值
相邻系泊缆的夹角	120°
系泊点距离自由水面的距离/m	200
导缆孔距离自由水面的距离/m	18
系泊缆的原始长度/m	835.5
系泊缆的直径/m	0.0766
系泊缆的等效线密度/(kg·m^-1)	45.5

位置	x/m	y/m	z/m
导缆孔a	144.25	100.0	182.0
导缆孔b	77.875	138.322	182.0
导缆孔c	77.875	61.778	182.0
锚固点A	937.6	100.0	0.0
锚固点B	-318.8	825.4	0.0
锚固点C	-318.8	-625.4	0.0

模型	参数类型	参数配置
全连接神经网络	激活函数	Relu
	优化器	Adam
	损失函数	MSE
	丢弃层数量	2
	隐藏层数量	6
	隐藏层神经元数量	64
	迭代次数	10000
	批次大小	512

The hydrodynamic characteristics and the prediction of mooring system tensions for a semi-submersible floating wind turbine foundation

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 22

References 23

Related Articles 4

Metrics

Comments

Recommended 0

工况编号	有效波高H_S/m	谱峰周期T_P/s	工况编号	有效波高H_S/m	谱峰周期T_P/s
1	1	10	26	13.5	10
2	1.5	10	27	14	10
3	2	10	28	14.5	10
4	2.5	10	29	3	12
5	3	10	30	5	12
6	3.5	10	31	5.5	12
7	4	10	32	6	12
8	4.5	10	33	7	12
9	5	10	34	7.5	12
10	5.5	10	35	8	12
11	6	10	36	8.5	12
12	6.5	10	37	9	12
13	7	10	38	9.5	12
14	7.5	10	39	10	12
15	8	10	40	10.5	12
16	8.5	10	41	11	12
17	9	10	42	11.5	12
18	9.5	10	43	3	14
19	10	10	44	5	14
20	10.5	10	45	7	14
21	11	10	46	7.5	14
22	11.5	10	47	8	14
23	12	10	48	3	8
24	12.5	10	49	5	8
25	13	10	50	7.5	8

预测案例	RMSE	MAE	R²
图13a	5.7207384	4.4730477	0.99571687
图13b	6.565532	4.3595	0.9739415
图14a	0.29001784	0.22374631	0.9727198
图14b	0.0922789	0.068423904	0.98917085
图15a	2.670674	2.109916	0.9979997
图15b	2.9917114	2.5716374	0.9897062

[1]	GAO Rongze, QU Ke, REN Xingyue, WANG Xu. Application of convolutional neural network methods in the evolution of hydrodynamic characteristics of tsunamis like-wave over fringing reef [J]. Journal of Tropical Oceanography, 2024, 43(4): 68-75.
[2]	ZHAO Jie, LIN Yanjiang, LIU Ran, DU Rong. Prediction of mesoscale eddies in the South China Sea based on the PredRNN++ model [J]. Journal of Tropical Oceanography, 2024, 43(1): 16-27.
[3]	YAN Jing, WEI Xing. Geomorphological changes and dynamic responses of the Huangmaohai Estuary in the Pearl River Delta [J]. Journal of Tropical Oceanography, 2023, 42(2): 9-20.
[4]	LIU Shuang, JING Zhiyou, ZHAN Haigang. Predicting the mesoscale eddy in the tropical and subtropical ocean based on generative adversarial network model [J]. Journal of Tropical Oceanography, 2022, 41(5): 1-16.