Lost Circulation Prediction Based on Long Short-Term Memory Network and Random Forest Algorithm

CAI Aiting; SU Junlin; DAI Kun; ZHAO Han; WANG Jiayi

Article Contents

Article Navigation > DRILLING FLUID & COMPLETION FLUID > 2025 > Accepted Manuscript

CAI Aiting, SU Junlin, DAI Kun, et al.Lost circulation prediction based on long short-term memory network and random forest algorithm[J]. Drilling Fluid & Completion Fluid，2025, 42（6）：1-9

Citation:

CAI Aiting, SU Junlin, DAI Kun, et al.Lost circulation prediction based on long short-term memory network and random forest algorithm[J]. Drilling Fluid & Completion Fluid，2025, 42（6）：1-9

CAI Aiting, SU Junlin, DAI Kun, et al.Lost circulation prediction based on long short-term memory network and random forest algorithm[J]. Drilling Fluid & Completion Fluid，2025, 42（6）：1-9

Citation:

CAI Aiting, SU Junlin, DAI Kun, et al.Lost circulation prediction based on long short-term memory network and random forest algorithm[J]. Drilling Fluid & Completion Fluid，2025, 42（6）：1-9

PDF( 5349 KB)

Lost Circulation Prediction Based on Long Short-Term Memory Network and Random Forest Algorithm

CAI Aiting^1
,,
SU Junlin^{1, 2
,
,},
DAI Kun³,
ZHAO Han³,
WANG Jiayi³

1.
Petroleum Engineering School, Southwest Petroleum University, Chengdu, Sichuan 610500
2.
State Key Laboratory of Oil and Gas Reservoir Geology and Development, Southwest Petroleum University, Chengdu, Sichuan 610500
3.
Shale Gas Exploration and Development Department, CNPC Chuanqing Drilling Engineering Company Limited, Chengdu, Sichuan 610051

Received Date: 2025-05-06
Rev Recd Date: 2025-06-27

Available Online: 2025-09-02

Abstract

Abstract

Lost circulation is one of the key factors restricting drilling safety and efficiency. To realize accurate prediction of lost circulation, a hybrid model for the prediction of lost circulation is presented based on long short-term memory (LSTM) and random forest (RF) algorithm. The LSTM model, the RF model and the LSTM-RF hybrid model are constructed based on algorithm principle. Fourteen lost circulation characteristic parameters are selected using correlation analysis method, and are input into three lost circulation prediction models for training. The performance and lost circulation prediction accuracy of the three models are then analyzed and compared. The experimental results show that the root mean square error (RMSE) of the hybrid model on the test dataset is 0.11, the mean absolute error (MAE) is 0.22, the coefficient of determination (R²) is 0.95, and the overall accuracy reaches 84.2%, each indicator is better than that of the single model. Furthermore, hybrid model has successfully predicted 5 times of lost circulation in field application. The results of this study show that LSTM-RF hybrid model is a model with optimal comprehensive performance in lost circulation prediction, it can predict lost circulation more precisely, and can provide reference for the prevention of lost circulation and for the decision making in drilling operation.
- Lost circulation prediction,
- Characteristic parameter,
- Long short-term memory network,
- Random forest,
- Hybrid model

FullText(HTML)

References(14)

References

[1]	李根生, 宋先知, 祝兆鹏, 等. 智能钻完井技术研究进展与前景展望[J]. 石油钻探技术, 2023, 51(4): 35-47. doi: 10.11911/syztjs.2023040 LI Gensheng, SONG Xianzhi, ZHU Zhaopeng, et al. Research progress and the prospect of intelligent drilling and completion technologies[J]. Petroleum Drilling Techniques, 2023, 51(4): 35-47. doi: 10.11911/syztjs.2023040
[2]	陈林, 陆海瑛, 王泽华, 等. 融合LightGBM和SHAP的井漏类型判断及主控因素分析[J]. 钻井液与完井液, 2023, 40(6): 771-777. doi: 10.12358/j.issn.1001-5620.2023.06.011 CHEN Lin, LU Haiying, WANG Zehua, et al. Identifying types and analyzing main controlling factors of mud losses using a method integrating LightGBM algorithm and SHAP[J]. Drilling Fluid & Completion Fluid, 2023, 40(6): 771-777. doi: 10.12358/j.issn.1001-5620.2023.06.011
[3]	孙伟峰, 卜赛赛, 张德志, 等. 基于DCC—LSTM的钻井液微量漏失智能监测方法[J]. 天然气工业, 2023, 43(9): 141-148. doi: 10.3787/j.issn.1000-0976.2023.09.014 SUN Weifeng, BU Saisai, ZHANG Dezhi, et al. DCC-LSTM based intelligent minor lost circulation monitoring method[J]. Natural Gas Industry, 2023, 43(9): 141-148. doi: 10.3787/j.issn.1000-0976.2023.09.014
[4]	孙金声, 刘凡, 程荣超, 等. 机器学习在防漏堵漏中研究进展与展望[J]. 石油学报, 2022, 43(1): 91-100. doi: 10.7623/syxb202201008 SUN Jinsheng, LIU Fan, CHENG Rongchao, et al. Research progress and prospects of machine learning in lost circulation control[J]. Acta Petrolei Sinica, 2022, 43(1): 91-100. doi: 10.7623/syxb202201008
[5]	HOU X X, YANG J, YIN Q S, et al. Lost circulation prediction in South China sea using machine learning and big data technology[C]//Offshore Technology Conference. Houston, Texas, USA, 2020: OTC-30653-MS.
[6]	万康, 马志超, 郭青松, 等. 人工智能技术在石油钻井工程事故预警中的应用[J]. 录井工程, 2022, 33(2): 24-29. doi: 10.3969/j.issn.1672-9803.2022.02.005 WAN Kang, MA Zhichao, GUO Qingsong, et al. Application of artificial intelligence on petroleum drilling engineering accident early warning[J]. Mud Logging Engineering, 2022, 33(2): 24-29. doi: 10.3969/j.issn.1672-9803.2022.02.005
[7]	PANG H W, MENG H, WANG H Q, et al. Lost circulation prediction based on machine learning[J]. Journal of Petroleum Science and Engineering, 2022, 208, Part A: 109364.
[8]	罗鸣, 李盛阳, 彭巍, 等. 基于深度卷积特征重构的井漏事故预测[J]. 计算机仿真, 2023, 40(7): 82-88. doi: 10.3969/j.issn.1006-9348.2023.07.015 LUO Ming, LI Shengyang, PENG Wei, et al. Lost circulation accident forewarning based on deep convolutional feature reconstruction network[J]. Computer Simulation, 2023, 40(7): 82-88. doi: 10.3969/j.issn.1006-9348.2023.07.015
[9]	孙伟峰, 刘凯, 张德志, 等. 结合钻井工况与Bi-GRU的溢流与井漏监测方法[J]. 石油钻探技术, 2023, 51(3): 37-44. doi: 10.11911/syztjs.2023043 SUN Weifeng, LIU Kai, ZHANG Dezhi, et al. A kick and lost circulation monitoring method combining Bi-GRU and drilling conditions[J]. Petroleum Drilling Techniques, 2023, 51(3): 37-44. doi: 10.11911/syztjs.2023043
[10]	SHERSTINSKY A. Fundamentals of recurrent neural network (RNN) and long Short-Term memory (LSTM) network[J]. Physica D. Nonlinear Phenomena, 2020, 404: 132306. doi: 10.1016/j.physd.2019.132306
[11]	HOCHREITER S, SCHMIDHUBER J. Long Short-Term memory[J]. Neural Computation, 1997, 9(8): 1735-1780. doi: 10.1162/neco.1997.9.8.1735
[12]	杨丽, 吴雨茜, 王俊丽, 等. 循环神经网络研究综述[J]. 计算机应用, 2018, 38(S2): 1-6,26. YANG Li, WU Yuqian, WANG Junli, et al. Research on recurrent neural network[J]. Journal of Computer Applications, 2018, 38(S2): 1-6,26.
[13]	BREIMAN L. Random forests[J]. Machine Learning, 2001, 45(1): 5-32. doi: 10.1023/A:1010933404324
[14]	ABBAS A K, BASHIKH A A, ABBAS H, et al. Intelligent decisions to stop or mitigate lost circulation based on machine learning[J]. Energy, 2019, 183: 1104-1113. doi: 10.1016/j.energy.2019.07.020

Relative Articles

Supplements(0)

Cited By

Proportional views

Proportional views

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

Figures(10) / Tables(6)

Get Citation

PDF

XML

Article Metrics

Article views (341) PDF downloads(8)

Lost Circulation Prediction Based on Long Short-Term Memory Network and Random Forest Algorithm

Abstract

References

Proportional views

Catalog

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Proportional views

Related

Lost Circulation Prediction Based on Long Short-Term Memory Network and Random Forest Algorithm

Abstract

References

Proportional views

Catalog

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Proportional views

Related

Export File

Citation

Format

Content