基于深度学习的深海天然气水合物开采立管非线性振动预测模型

PDF(4136 KB)

振动与冲击 ›› 2025, Vol. 44 ›› Issue (11) : 80-91.

振动理论与交叉研究

基于深度学习的深海天然气水合物开采立管非线性振动预测模型

郭晓强1，李莹伟2，李琦2，吕俊霖1，杨恪伦1，李欣业*1

作者信息 +

Nonlinear vibration prediction model for deep-sea natural gas hydrate mining riser based on deep learning

GUO Xiaoqiang1, LI Yingwei2, LI Qi2, L Junlin1, YANG Kelun1, LI Xinye*1

Author information +

文章历史 +

摘要

针对复杂环境下深海水合物开采立管传统振动力学模型预测结果精度低的问题，利用基于深度学习的长短期记忆（Long Short-Term Memory, LSTM）网络，建立了深海水合物开采立管的三维振动预测模型，该模型可以借助现场获得的开采立管振动数据进行训练，实现对开采立管后期振动响应的提前预测。采用相似原理，研发了内外流激励下开采立管振动模拟实验系统，构建了实验数据集。采用所提出的深度学习模型，对多因素影响的立管顺流向及横流向振动位移进行预测，将预测结果和实验测试数据对比，决定系数（R2）达到99%，验证了预测模型的正确性。此外，为了进一步验证该模型可以实现深海开采立管的振动预测，采用能量法和哈密顿原理，建立了深海水合物开采立管气-液-固三相流致振动理论模型，将后期预测结果与理论模型计算结果进行比较，决定系数（R2）达到94.59%，进一步验证了深海水合物开采立管振动深度学习预测模型的有效性。研究成果为智能油田的建设提供了模型基础。

Abstract

Abstract: In response to the problem of low prediction accuracy of traditional vibration mechanics models for deep-sea hydrate mining risers in complex environments, the vibration prediction model for deep-sea gas hydrate mining riser is established using a Long Short-Term Memory (LSTM) network based on deep-learning, which can be trained with the help of the vibration data of the mining riser obtained in the field, and realize the advance prediction of the vibration response of the mining riser in the later period. In order to effectively verify the correctness of the model, a similar principle is used to develop an experimental rig for simulating the vibration of the mining riser under the excitation of internal and external flow. The experimental test results are compared with the model prediction results, and the decision coefficient (R2) reaches 99%, which verifies the correctness of the prediction model. Moreover, to further verify that the model can achieve vibration prediction of deep-see mining riser, the energy method and Hamilton's principle are used to establish a theoretical model of gas-liquid-solid three-phase flow-induced vibration of the deep-sea hydrate mining riser. The results of the predictions in the later period are compared with the results of the theoretical model calculations. It is found that the coefficient of determination (R2) reaches 94.59%, which further verifies the effectiveness of the deep-learning prediction model. The research results provide a model foundation for the construction of intelligent oil fields.

导出引用

郭晓强1, 李莹伟2, 李琦2, 吕俊霖1, 杨恪伦1, 李欣业1. 基于深度学习的深海天然气水合物开采立管非线性振动预测模型[J]. 振动与冲击, 2025, 44(11): 80-91

GUO Xiaoqiang1, LI Yingwei2, LI Qi2, L Junlin1, YANG Kelun1, LI Xinye1. Nonlinear vibration prediction model for deep-sea natural gas hydrate mining riser based on deep learning[J]. Journal of Vibration and Shock, 2025, 44(11): 80-91

参考文献

[1] 周守为, 陈伟, 李清平, 等. 深水浅层非成岩天然气水合物固态流化试采技术研究及进展[J]. 中国海上油气, 2017, 29(4):1-8.
ZHOU Shouwei, CHEN Wei, LI Qingping, et al. Research on the solid fluidization well testing and production for shallow non-diagenetic natural gas hydrate in deep water area[J]. China Offshore Oil and Gas, 2017, 29(4):1-8.
[2] 韩泽龙, 宋刚, 牛庆磊, 等. 深海井口吸力锚安装分析与实践[J]. 钻探工程, 2023, 50(5):109-115.
HAN Zelong, SONG Gang, NIU Qinglei, et al. Analysis and practice of wellhead suction anchor installation in deep sea[J]. Drilling Engineering, 2023, 50(5):109-115.
[3] Yang J., Li L.. Research on stability of deepwater drilling riser system in freestanding mode[J]. Ocean Engineering, 2023, 279: 114439.
[4] 徐万海, 曾晓辉, 吴应湘. 海洋平台张力腿非线性动力响应[J]. 海洋工程, 2008(2):11-16.
XU Wanhai, ZENG Xiaohui, WU Yingxiang. Nonlinear dynamic response of the tendon[J]. The Ocean Engineering, 2008(2):11-16.
[5] 马孟达, 尤云祥, 张新曙. 海洋内孤立波作用下张力腿平台动力响应特性[J]. 水动力学研究与进展, 2016, 31(2):135-144.
MA Mengda, YOU Yunxiang, ZHANG Xinshu. Dynamic response characteristics of a tension leg platform under internal solitary waves[J]. Chinese Journal of Hydrodynamics, 2016, 31(2):135-144.
[6] 韩晓双, 周波, TAN S K. 考虑平台—群桩—水流—土体相互作用的导管架式海洋平台振动特性研究[J]. 船舶力学, 2018, 22(3):365-373.
HAN Xiaoshuang, ZHOU Bo, TAN S K. Study on vibration characteristic of jacket platform considering the structure-pile-fluid-soil interaction[J]. Journal of Ship Mechanics, 2018, 22(3):365-373.
[7] 李伟, 唐友刚, 曲晓奇, 等. Spar平台垂荡-横摇-纵摇非线性动力响应模型试验[J]. 哈尔滨工程大学学报, 2019, 40(3):534-539.
LI Wei, TANG Yougang, QU Xiaoqi, et al. Experimental study on nonlinear ,motion of spar platform for heave-roll-pitch[J]. Journal of Habrin Engineering University, 2019, 40(3):534-539.
[8] 朱仁庆, 王志东, 杨松林. 完全非线性波的数值模拟[J].船舶力学, 2002, 2002(5):14-18.
ZHU Renqing, WANG Zhidong, YANG Songlin. Fully nonlinear wave simulations[J]. Journal of Ship Mechanics, 2002, 2002(5):14-18.
[9] 张婷, 贺捷, 黄锦林. 海洋平台波浪荷载数值模拟研究[J]. 船海工程, 2013, 42(5):150-154.
ZHANG Ting, HE Jie, HUANG Jinlin. Numerical simulations of wave forces on the offshore platform[J]. Ship ＆ Ocean Engineering, 2013, 42(5):150-154.
[10] Zhang G., Chen X., Wan D.C.. MPS-FEM coupled method for study of wave-structure interaction[J]. Journal of Marine Science and Application, 2019, 18:387-399.
[11] 张慎颜, 刘秀全, 畅元江, 等. 深水钻井平台-隔水管系统波激疲劳分析[J]. 船舶力学, 2019, 23(7):843-850.
ZHANG Shenyan, LIU Xiuquan, CHANG Yuanjiang, et al. Wave-loading fatigue analysis on deep water drilling platform riser system[J]. Journal of Ship Mechanics, 2019, 23(7):843-850.
[12] 张智奇, 任浩杰, 付世晓, 等. 均匀流作用下双柔性异管径立管响应特性试验研究[J]. 船舶力学, 2021, 25(1):16-28.
ZHANG Zhiqi, REN Haojie, FU Shixiao, et al. Experimental study on response characteristics of double flexible pipe with different diameters under uniform flow[J]. Journal of Ship Mechanics,2021, 25(1):16-28.
[13] Lu Y., Yu Z.C., Ma Y.X., et al. Fatigue damage characteristics of a flexible cylinder under concomitant excitation of time-varying axial tension and VIV[J]. Ocean Engineering, 2023, 288:116079.
[14] Miwa S., Liu Y., Hibiki T., et al. Study of unsteady gas-liquid two-phase flow induced force fluctuation part1: evaluation and modeling of two-phase flow induced force fluctuation[J]. Transactions of the JSME (in Japanese), 2014, 80(809):1-11.
[15] Liang W.X., Luo M., Zhang C., et al. Experimental investigation and phenomenological modeling of fatigue crack growth in X80 pipeline steel under random loading[J]. International Journal of Fatigue, 2024, 182:108169.
[16] Zhu H.J., Gao Y., Zhao H.L.. Experimental investigation of slug flow-induced vibration of a flexible riser[J]. Ocean Engineering, 2019, 189:106370.
[17] 袁海燕. 提升管道系统固液两相流工程应用研究[D]. 长沙: 湖南大学硕士学位论文, 2012.
[18] 刘磊. 深海采矿水力提升固液两相流动力学特性研究[D]. 上海: 上海交通大学博士学位论文, 2019.
[19] Guo X.Q., Chen X.H., Zhao L.B., et al. Multi-field coupling multiple nonlinear vibration model and fatigue failure mechanism of deep-ocean mining hydraulic lifting pipe[J]. Nonlinear Dynamics, 2023, 111(18):16777-16811.
[20] Voulodimos A., Doulamis N., Doulamis A., et al. Deep learning for computer vision: A brief review[J]. Computational intelligence and neuroscience, 2018, 2018(1): 7068349.
[21] Holm E.A., Cohn R., Gao N., et al. Overview: computer vision and machine learning for microstructural characterization and analysis[J]. Metallurgical and Materials Transactions A, 2020, 51(12): 5985-5999.
[22] Shamshad F., Khan S., Waqas Z.S., et al. Transformers in Medical Imaging: A Survey[J]. Medical Image Analysis, 2022, 88: 102802.
[23] Sarvamangala D.R., Kulkarni R.V.. Convolutional neural networks in medical image understanding: a survey[J]. Evolutionary intelligence, 2022, 15(1): 1-22.
[24] Areekul P., Senjyu T., Toyama H., et al. Price Forecasting using a Hybrid ARIMA and Neural Network Model[J]. Neurocomputing, 2009, 50 :159-175.
[25] Mohamed A.R., Dahl G., Hinton G.. Deep belief networks for phone recognition[C].Nips workshop on deep learning for speech recognition and related applications. 2009, 1(9): 39.
[26] Yu Y., Si X.S., Hu C.H., et al. A review of recurrent neural networks: LSTM cells and network architectures[J]. Neural Computation, 2019, 31(7): 1235-1270.
[27] Sherstinsky A.. Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) network[J].Physica D: Nonlinear Phenomena, 2020, 404: 132306.
[28] Shewalkar A., Nyavanandi D., Ludwig S.A.. Performance evaluation of deep neural networks applied to speech recognition: RNN, LSTM and GRU[J]. Journal of Artificial Intelligence and Soft Computing Research, 2019, 9(4): 235-245.
[29] Siłka J., Wieczorek M., Woźniak M.. Recurrent neural network model for high-speed train vibration prediction from time series[J]. Neural Computing and Applications, 2022, 34(16): 13305-13318.
[30] Zha W.S., Liu Y.P., Wan Y.J., et al. Forecasting monthly gas field production based on the CNN-LSTM model[J]. Energy, 2022, 260: 124889.
[31] Zhang J.X., Li S.Y.. Air quality index forecast in Beijing based on CNN-LSTM multi-model[J]. Chemosphere, 2022, 308: 136180.
[32] Shen Z.P., Fan X.C., Zhang L.Y., et al. Wind speed prediction of unmanned sailboat based on CNN and LSTM hybrid neural network[J]. Ocean Engineering, 2022, 254: 111352.
[33] Zhang W.Y., Zhou H.Y., Bao X.H., et al. Outlet water temperature prediction of energy pile based on spatial-temporal feature extraction through CNN–LSTM hybrid model[J]. Energy, 2023, 264: 126190.
[34] Lin J., Ma J., Zhu J.G., et al. Short-term load forecasting based on LSTM networks considering attention mechanism[J]. International Journal of Electrical Power & Energy Systems, 2022, 137: 107818.
[35] Cho K., Kim Y.. Improving streamflow prediction in the WRF-Hydro model with LSTM networks[J]. Journal of Hydrology, 2022, 605: 127297.
[36] Huang R.J., Wei C.J., Wang B.H., et al. Well performance prediction based on Long Short-Term Memory (LSTM) neural network[J]. Journal of Petroleum Science and Engineering, 2022, 208: 109686.
[37] Stefenon S.F., Seman L.O., Aquino L.S., et al. Wavelet-Seq2Seq-LSTM with attention for time series forecasting of level of dams in hydroelectric power plants[J]. Energy, 2023, 274: 127350.
[38] Huang X.Q., Li Q., Tai Y.H., et al. Time series forecasting for hourly photovoltaic power using conditional generative adversarial network and Bi-LSTM[J]. Energy, 2022, 246: 123403.
[39] Li X.M., Chen Y.K., Zou C., et al. Building coupling loss measurement and prediction due to train-induced vertical vibrations[J]. Soil Dynamics and Earthquake Engineering, 2023, 164: 107644.
[40] Guo X.Q., Li X., He Y.F., et al. Investigation on three-dimensional vibration model and response characteristics of deep-water riser-test pipe system[J]. Communications in Nonlinear Science and Numerical Simulation, 2022, 109:106296.
[41] Facchinetti M.L., Langre E.D., Biolley F.. Coupling of structure and wake oscillators in vortex-induced vibrations[J]. Journal of Fluids and Structures, 2004, 19(2): 123 - 140.
[42] Violette R., Langre E.D., Szydlowski J.. Computation of vortex-induced vibrations of long structures using a wake oscillator model: Comparison with DNS and experiments[J]. Computers and Structures, 2007, 85(11-14): 1135-1141.
[43] Guo X.Q., Chen X.H., Xu J., et al. Investigation on gas-liquid-solid three-phase flow model and flow characteristics in mining riser for deep-sea gas hydrate exploitation[J]. Physics of Fluids, 2024, 36(7): 075193.
[44] 夏建新. 大洋多金属结核水力提升两相流体动力学及应用研究[D]. 北京: 中国矿业大学, 2000.