1.中国石油大学(华东)机电工程学院
2.中海油田服务股份有限公司
赵荣根,生于2000年,现为在读硕士研究生,研究方向为海洋隔水管/立管作业安全监测预警。地址:(266580)山东省青岛市。email:zhaoronggen0@163.com。
刘秀全,教授。 email:lxqmcae@163.com。
收稿:2025-06-23,
修回:2026-07-06,
录用:2025-11-14,
纸质出版:2026-10-25
移动端阅览
赵荣根,贾国乐,金学义,等.基于有限监测数据的深水钻井隔水管系统状态预测方法[J].石油机械,2026,54(10):71-78.
Zhao Ronggen,Jia Guole,Jin Xueyi,et al.State Prediction method for deepwater drilling riser system based on limited monitoring data[J].China Petroleum Machinery,2026,54(10):71-78.
赵荣根,贾国乐,金学义,等.基于有限监测数据的深水钻井隔水管系统状态预测方法[J].石油机械,2026,54(10):71-78. DOI: 10.12473/CPM.202506065.
Zhao Ronggen,Jia Guole,Jin Xueyi,et al.State Prediction method for deepwater drilling riser system based on limited monitoring data[J].China Petroleum Machinery,2026,54(10):71-78. DOI: 10.12473/CPM.202506065.
深水钻井隔水管系统是海洋油气钻探的关键设备,其动力响应特性直接关系到整个钻井作业的安全性。然而,由于深海环境复杂多变且监测数据有限,在有限数据下实现系统全状态动态响应的实时准确预测面临重大挑战。针对这一问题,提出了一种有限监测数据下深水钻井隔水管系统动力响应实时状态预测方法。该方法使用上部挠性接头转角及平台升沉、横荡和垂荡监测数据预测深水钻井隔水管系统动力响应状态。根据设计海况进行深水钻井隔水管全耦合系统动力响应分析,以得到的时序数据为基础,利用蚁群算法优化门控循环神经网络(GRU)建立系统状态预测模型,并对预测模型进行验证。研究结果表明:该隔水管系统状态响应参数预测模型的准确度较高,其决定系数大于0.97,显示出较高的预测精度与稳定性,可使用GRU进行深水钻井隔水管系统动力响应状态预测。研究结果可为深水钻井隔水管系统动力响应状态实时预测提供理论依据及技术支撑。
Deepwater drilling riser system is a critical component for offshore oil and gas drilling, and its dynamic response characteristics are directly related to the overall safety of drilling operations. However, due to the complex and variable deep-sea environment and limited monitoring data, real-time and accurate prediction of the system's full-state dynamic responses is highly chal
lenging. This paper proposes a real-time state prediction method for the dynamic response of deepwater drilling riser system based on limited monitoring data. This method uses the monitoring data of the upper flexible joint rotation angle and the platform heave, surge, and sway motions, to predict the system's dynamic response state. The dynamic response analysis of the fully-coupled deepwater drilling riser system was conducted depending on designed sea conditions. Based on the time-series data obtained from the analysis, the gated recurrent unit (GRU) neural network optimized by the ant colony algorithm was employed to establish the system state prediction model. Finally, the prediction model was validated. The results show that the proposed model achieves accurate prediction, with the coefficient of determination (
R
2
) exceeding 0.97, indicating high accuracy and stability, and that GRU can be used to predict the dynamic response states of deepwater drilling riser systems. The study provides a theoretical basis and technical support for real-time prediction of deepwater drilling riser system's dynamic response state.
ISO 3421:2022 Petroleum and natural gas industries-drilling and production equipment [S].
Qin Ken , Di Qinfeng , Zhou Xing , et al . Nonlinear dynamic characteristics of the drill-string for deep-water and ultra-deep water drilling [J]. Journal of Petroleum Science and Engineering , 2022 , 209 : 109905 .
Gao Deli , Wang Yanbin . Some research progress in deepwater drilling mechanics and control technology [J]. Acta Petrolei Sinica , 2019 , 40 ( S2 ): 102 - 115 .
Guimarães F . Dynamics of the system drilling riser-bop-well casing-wellhead casing fatigue analysis [J]. Journal of Offshore Mechanics and Arctic Engineering , 2024 , 146 ( 2 ): 021401 .
Liu Kang , Chen Guoming , Zhu Gaogeng , et al . Nonlinear self-induced vibration and operability envelope analysis of production strings in marine natural gas development [J]. International Journal of Naval Architecture and Ocean Engineering , 2019 , 11 ( 1 ): 344 - 352 .
Liu Xiuquan , Sun Hexiang , Yu Mengru , et al . Mechanical analysis of deepwater drilling riser system based on multibody system dynamics [J]. Petroleum Science , 2021 , 18 ( 2 ): 603 - 617 .
鞠少栋 , 陈国明 , 宋林松 , 等 . 深水钻井隔水管事故类型及对策分析 [J]. 石油机械 , 2011 , 39 ( 5 ): 83 - 87 .
Ju Shaodong , Chen Guoming , Song Linsong , et al . Analysis of deepwater drilling marine riser accident types and countermeasures [J]. China Petroleum Machinery , 2011 , 39 ( 5 ): 83 - 87 .
Sidarta D E , Kyoung J , O Sullivan J , et al . Prediction of offshore platform mooring line tensions using artificial neural network [C]∥ Proceedings of the ASME 2017 36th International Conference on Ocean, Offshore and Arctic Engineering , Trondheim, Norway , 2017 : V001T01A079 .
Chaves V , Sagrilo L V S , Da Silva V R M , et al . Artificial neural networks applied to flexible pipes fatigue calculations [C]∥ Proceedings of the ASME 2015 34th International Conference on Ocean , Newfoundland, Canada , 2015 : V05BT04A022 .
Chaves V , Sagrilo L V S , Da Silva V R M . Optimization of flexible pipes dynamic analysis using artificial neural networks [C]∥ Proceedings of the ASME 2016 35th International Conference on Ocean, Offshore and Arctic Engineering , Busan, South Korea , 2016 : V003T02A058 .
Akinsete O , Adesiji B A . Bottom-hole pressure estimation from wellhead data using artificial neural network [C]∥ The SPE Nigeria Annual International Conference and Exhibition , Lagos, Nigeria , 2019 : SPE-198762-MS.
Srikonda R , Haakonsen R , Russo M , et al . Real-time wellhead bending moment measurement using motion reference unit(MRU) sensors and machine learning [C]∥ The ASME 2018 37th International Conference on Ocean, Offshore and Arctic Engineering , Madrid,Spain . 2018 : V003T02A095 .
Wong E W C , Choi H S , Hashim F M . Development of ANN model for the prediction of VIV fatigue damage of top-tensioned riser [C]∥ 2018 International Conference on Civil, Offshore and Environmental Engineering 2018 , Shanghai,China , 2018 : 01013 .
朱高庚 , 陈国明 , 刘康 . 深水钻井隔水管下放作业可靠性智能评估方法 [J]. 船舶力学 , 2025 , 29 ( 1 ): 123 - 133 .
Zhu Gaogeng , Chen Guoming , Liu Kang . Intelligent assessment method of reliability for deepwater riser deployment [J]. Journal of Ship Mechanics , 2025 , 29 ( 1 ): 123 - 133 .
王金龙 , 李凡鹏 , 胡鹏基 , 等 . 基于深度学习的水下井口弯曲应力预测方法 [J]. 石油机械 , 2023 , 51 ( 8 ): 64 - 72 .
Wang Jinlong , Li Fanpeng , Hu Pengji , et al . A method for predicting bending stress of subsea wellhead based on deep learning [J]. China Petroleum Machinery , 2023 , 51 ( 8 ): 64 - 72 .
李家仪 , 刘秀全 , 许亮斌 , 等 . 深水水下井口全钻井过程波激疲劳精细化评估 [J]. 石油机械 , 2024 , 52 ( 9 ): 74 - 80 .
Li Jiayi , Liu Xiuquan , Xu Liangbin , et al . Fine evaluation on wave induced fatigue of deepwater subsea wellhead in full drilling process [J]. China Petroleum Machinery , 2024 , 52 ( 9 ): 74 - 80 .
李彦伟 . 深水钻井隔水管系统新型悬挂动力学特性及应用研究 [D]. 青岛 : 中国石油大学(华东) , 2022 .
Li Yanwei . Research on dynamic characteristics and application of deepwater drilling risers in new hang-off mode [D]. Qingdao : China University of Petroleum (East China) , 2022 .
许伟 . 基于监测数据的水下井口疲劳寿命计算方法研究 [D]. 青岛 : 中国石油大学(华东) , 2021 .
Xu Wei . Research on calculating method of subsea wellhead fatigue life based on monitoring data [D]. Qingdao : China university of petroleum (East China) , 2021 .
Li Yanwei , Liu Xiuquan , Wang Jinlong , et al . Dynamic analysis of a deepwater drilling riser with a new hang-off system [J]. China Ocean Engineering , 2024 , 38 ( 1 ): 29 - 41 .
Li Wenlong , Gao Deli , Yang Jin , et al . Subsea wellhead stability study of composite casing for deepwater drilling [J]. Ocean Engineering , 2020 , 214 : 107780 .
Hochreiter S , Schmidhuber J . Long short-term memory [J]. Neural Computation , 1997 , 9 ( 8 ): 1735 - 1780 .
Cho K , Merrienboer B , Gulcehre C , et al . Learning phrase representations using RNN encoder-decoder for statistical machine translation [PP/OL]. arXiv ( 2014-09-03 ) [ 2025-12-20 ]. https:∥doi.org/10.48550/arXiv.1406.1078 https://doi.org/10.48550/arXiv.1406.1078 .
Willmott C J , Matsuura K . Advantages of the mean absolute error( MAE) over the root mean square error(RMSE) in assessing average model performance [J]. Climate Research , 2005 , 30 ( 1 ): 79 - 82 .
0
浏览量
6
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621