基于多维时序LSTM的超深井机械钻速预测方法

doi:10.11885/j.issn.1674-5086.2024.01.08.01

西南石油大学学报(自然科学版) ›› 2025, Vol. 47 ›› Issue (5): 121-133.DOI: 10.11885/j.issn.1674-5086.2024.01.08.01

基于多维时序LSTM的超深井机械钻速预测方法

刘阳^1,2, 陈思彤¹, 向幸运³, 沈明华⁴, 马天寿²

1. 西南石油大学机电工程学院, 四川成都 610500;
2. 油气藏地质及开发工程全国重点实验室·西南石油大学, 四川成都 610500;
3. 中国石化华北石油工程有限公司西部分公司, 新疆轮台 841600;
4. 中国石油川庆钻探工程有限公司钻采工程技术研究院, 四川广汉 618300

收稿日期:2024-01-08 发布日期:2025-11-04
通讯作者: 刘阳，E-mail:liuyang2013swpu@163.com
作者简介:刘阳，1989年生，男，汉族，甘肃平凉人，助理研究员，博士（后），主要从事油气井力学与控制工程、智能钻井理论与方法等方面的教学与科研工作。E-mail:liuyang2013swpu@163.com
陈思彤，1999年生，男，汉族，四川成都人，硕士研究生，主要从事智能钻井与过程控制方面的研究。E-mail: 980953951@qq.com
向幸运，1990年生，男，汉族，四川岳池人，高级工程师，主要从事特殊工艺井钻井理论与应用技术研究。E-mail: xiangxy.oshb@sinopec.com
沈明华，1985年生，男，汉族，四川达州人，工程师，主要从事固井、欠平衡钻井以及井控工艺技术研究及应用。E-mail: shenmhu_gcy@cnpc.com.cn
马天寿，1987年生，男，汉族，四川绵阳人，研究员，博士研究生导师，主要从事油气井工程教学与科研工作。E-mail: matianshou@126.com
基金资助:
国家自然科学基金青年基金（52204016）；中国博士后科学基金面上项目（2020M673576XB）；西南石油大学启航计划（2021QHZ027）

Prediction of Penetration Rate Method for Ultra-deep Well Based on Multi-dimensional Time Series LSTM

LIU Yang^1,2, CHEN Sitong¹, XIANG Xingyun³, SHEN Minghua⁴, MA Tianshou²

1. School of Mechatronic Engineering, Southwest Petroleum University, Chengdu, Sichuan 610500, China;
2. National Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Southwest Petroleum University, Chengdu, Sichuan 610500, China;
3. West Branch of Sinopec North China Petroleum Engineering Co. Ltd., Luntai, Xinjiang 841600, China;
4. Drilling & Production Technology Research Institute, CCDC, Guanghan, Sichuan 618300, China

Received:2024-01-08 Published:2025-11-04

摘要/Abstract

摘要： 为解决复杂深井钻井过程中机械钻速影响因素多、机理复杂且存在非线性、强耦合等特征的难题，提出了一种基于多维时序长短期记忆神经网络的机械钻速预测方法。根据新疆X-1井实际测录井数据，通过分析特征相关性和传统钻速方程的物理意义，优选工程参数、水力学参数、岩性参数和其他参数作为模型输入，分析多维特征在不同参数组合模式下的钻速预测效果。研究表明，机械钻速与转速、扭矩、立管压力呈正相关关系，与垂深、大钩载荷、比钻压、钻井液电导率、出口钻井液温度、出口排量、PDC可钻性极值呈负相关关系，与泵冲、钻井液密度相关性较弱；不同特征参数组合的机械钻速预测精度不同，其中，最优参数组合为比钻压、转速、扭矩、大钩载荷、立管压力、钻井液电导率、出口钻井液温度、出口排量、垂深、PDC可钻性极值，机械钻速预测的平均绝对误差为0.30 m/h，平均绝对百分比误差为11.35%，拟合优度为0.93；采用正交实验法确定了模型的最优超参数组合方案，预测效果提升较好，预测的绝对系数可提高0.06。

关键词: 超深井, 机械钻速, LSTM, 超参数组合, 正交实验

Abstract: In order to solve the problems of multiple factors, complex mechanism, nonlinear, strong coupling and other characteristics of rate of penetration in the process of complex deep drilling, this paper proposes a method of ROP prediction based on multi-dimensional time series long short-term memory neural network. Based on the actual logging data of Well X-1 in Xinjiang, this paper selects engineering parameters, hydraulics parameters, lithology parameters and other parameters as model inputs through the feature correlation analysis and the physical meaning of traditional ROP equation, and analyzes the ROP prediction effect of multi-dimensional features under different parameter combination modes. The results show that ROP is positively correlated with rotational speed, torque and riser pressure, but negatively correlated with vertical depth, hook load, specific weight on bit, drilling fluid conductivity, outlet drilling fluid temperature, outlet displacement and PDC drill ability, while weakly correlated with pump stroke and drilling fluid density; different characteristic parameter combinations have different prediction accuracy on ROP, among which the optimal parameter combinations are specific weight on bit, rotational speed, torque, hook load, riser pressure, drilling fluid conductivity, outlet drilling fluid temperature, outlet displacement, vertical depth and PDC drillability extreme value. MAE of ROP prediction is 0.30 m/h, MAPE is 11.35% and R² is 0.93; The optimal hyperparameter combination scheme of the model was determined by orthogonal experiment. The R² was increased by 0.06.

Key words: ultra-deep well, rate of penetration, LSTM, hyperparameter combination, orthogonal experiment

中图分类号:

TE29

刘阳, 陈思彤, 向幸运, 沈明华, 马天寿. 基于多维时序LSTM的超深井机械钻速预测方法[J]. 西南石油大学学报(自然科学版), 2025, 47(5): 121-133.

LIU Yang, CHEN Sitong, XIANG Xingyun, SHEN Minghua, MA Tianshou. Prediction of Penetration Rate Method for Ultra-deep Well Based on Multi-dimensional Time Series LSTM[J]. Journal of Southwest Petroleum University(Science & Technology Edition), 2025, 47(5): 121-133.

0
/ / 推荐

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://journal15.magtechjournal.com/Jwk_xnzk/CN/10.11885/j.issn.1674-5086.2024.01.08.01

http://journal15.magtechjournal.com/Jwk_xnzk/CN/Y2025/V47/I5/121

参考文献

[1] 李阳,薛兆杰,程喆,等. 中国深层油气勘探开发进展与发展方向[J]. 中国石油勘探, 2020, 25(1):45-57. doi:10.3969/j.issn.1672-7703.2020.01.005 LI Yang, XUE Zhaojie, CHENG Zhe, et al. Progress and development direction of deep oil and gas exploration and development in China[J]. China Petroleum Exploration, 2020, 25(1):45-57. doi:10.3969/j.issn.1672- 7703.2020.01.005
[2] 孙腾飞,李永安,张杨,等. 基于多相压力波响应图版识别超深井气侵位置[J]. 中国石油大学学报(自然科学版), 2024, 48(2):83-91.doi:10.3969/j.issn.1673- 5005.2024.02.009 SUN Tengfei, LI Yongan, ZHANG Yang, et al. Identification of gas invasion location in ultra-deep wells based on multiphase pressure wave response chart[J]. Journal of China University of Petroleum (Edition of Natural Science),2024, 48(2):83-91. doi:10.3969/j.issn.1673-5005.2024.02.009
[3] 闵超,代博仁,张馨慧,等. 机器学习在油气行业中的应用进展综述[J]. 西南石油大学学报(自然科学版), 2020, 42(6):1-15. doi:10.11885/j.issn.1674- 5086.2020.06.05.03 MIN Chao, DAI Boren, ZHANG Xinhui, et al. Application progress of machine learning in oil and gas industry[J]. Journal of Southwest Petroleum University (Natural Science Edition), 2020, 42(6):1-15. doi:10.11885/j.issn.1674-5086.2020.06.05.03
[4] MAURER W C. The "perfect-cleaning" theory of rotary drilling[J]. Journal of Petroleum Technology, 1962, 14(11):1270-1274. doi:10.2118/408-PA
[5] WARREN T M. Penetration-rate performance of rollercone bits[J]. SPE Drilling Engineering, 1987, 2(1):9-18. doi:10.2118/13259-PA
[6] BOURGOYNE A T, YOUNG F S. A multiple regression approach to optimal drilling and abnormal pressure detection[J]. SPE Journal, 1974, 14(4):371-384. doi:10.2118/4238-PA
[7] HARELAND G, RAMPERSAD P R. Drag-bit model including wear[C]. SPE 26957-MS, 1994. doi:10.2118/26957-MS
[8] DETOURNAY E, RICHARD T, SHEPHERD M. Drilling response of drag bits:Theory and experiment[J]. International Journal of Rock Mechanics and Mining Sciences, 2008, 45(8):1347-1360.
[9] 李根生,宋先知,田守嶒. 智能钻井技术研究现状及发展趋势[J]. 石油钻探技术, 2020, 48(1):1-8. doi:10.11911/syztjs.2020001 LI Gensheng, SONG Xianzhi, TIAN Shouceng. Intelligent drilling technology research status and development trends[J]. Petroleum Drilling Techniques, 2020, 48(1):1-8. doi:10.11911/syztjs.2020001
[10] 王果,许博越. 理论模型与机器学习融合的PDC钻头钻速预测方法[J]. 石油钻探技术, 2024, 52(5):117-123. doi:10.11911/syztjs.2024094 WANG Guo, XU Boyue. The method to predict ROP of PDC bits based on fusion of theoretical model and machine learning[J]. Petroleum Drilling Techniques, 2024, 52(5):117-123. 10.11911/syztjs.2024094
[11] 王贺强,郭海涛,马翠岩,等. 智能钻井系统在赵东油田的应用[J]. 世界石油工业, 2024, 31(3):59-67. doi:10.20114/j.issn.1006-0030.20240319001 WANG Heqiang, GUO Haitao, MA Cuiyan, et al. Field application of automated drilling system in Zhaodong Oilfield[J]. World Petroleum Industry, 2024, 31(3):59-67. doi:10.20114/j.issn.1006-0030.20240319001
[12] OSSAI C I, DURU U I. Applications and theoretical perspectives of artificial intelligence in the rate of penetration[J]. Petroleum, 2022, 8(2):237-251.
[13] AMER M M, DAHAB A S, EL-SAYED A A H. An ROP predictive model in nile delta area using artificial neural networks[C]. SPE 187969-MS, 2017. doi:10.2118/187969-MS
[14] AHMED O S, ADENIRAN A A, SAMSURI A. Computational intelligence based prediction of drilling rate of penetration:A comparative study[J]. Journal of Petroleum Science and Engineering, 2019, 172:1-12.
[15] ZHANG C, SONG X, SU Y, et al. Real-time prediction of rate of penetration by combining attention-based gated recurrent unit network and fully connected neural networks[J]. Journal of Petroleum Science and Engineering, 2022, 213:110396.
[16] BRENJKAR E, DELIJANI E B. Computational prediction of the drilling rate of penetration (ROP):A comparison of various machine learning approaches and traditional models[J]. Journal of Petroleum Science and Engineering, 2022, 210:110033.
[17] 李玥洋,任静思,张苏,等. 智能气田一体化模型数据共享平台建设与实践[J]. 西南石油大学学报(自然科学版), 2023, 45(1):155-162. doi:10.11885/j.issn.1674- 5086.2020.11.19.01 LI Yueyang, REN Jingsi, ZHANG Su, et al. Construction and application of intelligent gas field integrated model data sharing platform[J]. Journal of Southwest Petroleum University (Science & Technology Edition), 2023, 45(1):155-162. doi:10.11885/j.issn.1674-5086.2020.11.19.01
[18] 檀朝东,贺甲元,周彤,等. 基于PCA-BNN的页岩气压裂施工参数优化[J]. 西南石油大学学报(自然科学版), 2020, 42(6):56-62. doi:10.11885/j.issn.1674- 5086.2020.05.12.05 TAN Chaodong, HE Jiayuan, ZHOU Tong, et al. A study on the optimization of fracturing operation parameters based on PCA-BNN[J]. Journal of Southwest Petroleum University (Science & Technology Edition), 2020, 42(6):56-62. doi:10.11885/j.issn.1674-5086.2020.05.12.05
[19] 李元,刘雨田,冯立伟. 基于斯皮尔曼相关分析的非线性动态过程特征提取与故障检测[J]. 山东科技大学学报(自然科学版), 2023, 42(2):98-107. doi:10.16452/j.cnki.sdkjzk.2023.02.011 LI Yuan, LIU Yutian, FENG Liwei. Feature extraction and fault detection of non-linear dynamic process via Spearman correlation analysis[J]. Journal of Shandong University of Science and Technology (Natural Science Edition), 2023, 42(2):98-107. doi:10.16452/j.cnki.sdkjzk.2023.02.011
[20] 侯勋,方刚. 基于肯德尔系数的改进ID3算法[J]. 科学技术创新, 2021(22):21-22. doi:10.3969/j.issn.1673- 1328.2021.22.011 HOU Xun, FANG Gang. Improved ID3 algorithm based on Kendall coefficient[J]. Science and Technology Innovation, 2021(22):21-22. doi:10.3969/j.issn.1673-1328.2021.22.011
[21] 葛亮,滕怡,肖国清,等. 基于井下环空参数的溢流智能预警技术研究[J]. 西南石油大学学报(自然科学版), 2023, 45(2):126-134. doi:10.11885/j.issn.1674- 5086.2021.03.12.03 GE Liang, TENG Yi, XIAO Guoqing, et al. Research on overflow intelligent warning technology based on downhole annulus parameters[J]. Journal of Southwest Petroleum University (Science & Technology Edition), 2023, 45(2):126-134. doi:10.11885/j.issn.1674-5086.2021.03.12.03
[22] 李春生,邹林浩,张可佳,等. 基于 BP神经网络的录井异常数据检测方法研究[J]. 计算机技术与发展, 2022, 32(6):173-178. doi:10.3969/j.issn.1673- 629X.2022.06.029 LI Chunsheng, ZOU Linhao, ZHANG Kejia, et al. Research on abnormal data detection method of logging based on BP neural network[J]. Journal of Computer Technology and Development, 2022, 32(6):173-178. doi:10.3969/j.issn.1673-629X.2022.06.029
[23] LIU Xinkai, JI Lingyun, ZHANG Chen, et al. A method for reconstructing NDVI time-series based on envelope detection and the Savitzky-Golay filter[J]. International Journal of Digital Earth, 2022, 15(1):533-584.
[24] 宋先知,姚学喆,李根生,等. 基于LSTM-BP神经网络的地层孔隙压力计算方法[J]. 石油科学通报, 2022, 7(1):12-23. doi:10.3969/j.issn.2096-1693.2022.01.002 SONG Xianzhi, YAO Xuezhe, LI Gensheng, et al. A novel method to calculate formation pressure based on the LSTM-BP neural network[J]. Petroleum Science Bulletin, 2022, 7(1):12-23. doi:10.3969/j.issn.2096-1693.2022.01.002
[25] 张鹏,杨涛,刘亚楠,等. 基于CNN-LSTM的QAR数据特征提取与预测[J]. 计算机应用研究, 2019, 36(10):2958-2961. doi:10.19734/j.issn.1001-3695.2018.04.0214 ZHANG Peng, YANG Tao, LIU Yanan, et al. Feature extraction and prediction of QAR data based on CNN-LSTM[J]. Application Research of Computers, 2019, 36(10):2958-2961. doi:10.19734/j.issn.1001-36- 95.2018.04.0214
[26] DAVTYAN A, RODIN A, MUCHNIK I, et al. Oil production forecast models based on sliding window regression[J]. Journal of Petroleum Science and Engineering, 2020, 195:107916.
[27] SCHUSTER M, PALIWAL K K. Bidirectional recurrent neural networks[J]. IEEE Transactions on Signal Processing, 1997, 45(11):2673-2681.
[28] SHAN L Q, LIU Y C, TANG M, et al. CNN-BiLSTM hybrid neural networks with attention mechanism for well log prediction[J]. Journal of Petroleum Science and Engineering, 2021, 205:108838.
[29] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8):1735-1780.
[30] 马乔雨,张欣,张春雷,等. 基于一维卷积神经网络的横波速度预测[J]. 岩性油气藏, 2021, 33(4):111-120. doi:10.12108/yxyqc.20210412 MA Qiaoyu, ZHANG Xin, ZHANG Chunlei, et al. Shear wave velocity prediction based on one-dimensional convolutional neural network[J]. Lithologic Reservoirs, 2021, 33(4):111-120. doi:10.12108/yxyqc.20210412
[31] 马天寿,向国富,石榆帆,等. 基于双向长短期记忆神经网络的水平地应力预测方法[J]. 石油科学通报, 2022, 7(4):487-504. doi:10.3969/j.issn.2096- 1693.2022.04.042 MA Tianshou, XIANG Guofu, SHI Yufan, et al. Horizontal in-situ stress prediction method based on the bidirectional long short-term memory neural network[J]. Petroleum Science Bulletin, 2022, 7(4):487-504. doi:10.3969/j.issn.2096-1693.2022.04.042
[32] 马天寿,张东洋,杨赟,等. 基于机器学习模型的斜井坍塌压力预测方法[J]. 天然气工业, 2023, 43(9):119-131. doi:10.3787/j.issn.1000-0976.2023.09.012 MA Tianshou, ZHANG Dongyang, YANG Yun, et al. Machine learning model based collapse pressure prediction method for inclined wells[J]. Natural Gas Industry, 2023, 43(9):119-131. doi:10.3787/j.issn.1000- 0976.2023.09.012
[33] 刘均荣,韩艳慧,王哲,等. 基于分布式光纤声波监测数据和机器学习的井筒流体类型识别方法[J]. 中国石油大学学报(自然科学版), 2023, 47(3):107-114. doi:10.3969/j.issn.1673-5005.2023.03.012 LIU Junrong, HAN Yanhui, WANG Zhe, et al. Identification of fluid type in wellbore based on distributed acoustic sensing data and machine learning[J]. Journal of China University of Petroleum (Edition of Natural Science), 2023, 47(3):107-114. doi:10.3969/j.issn.1673-50- 05.2023.03.012
[34] 刘学锋,张晓伟,曾鑫,等. 采用机器学习分割算法和扫描电镜分析页岩微观孔隙结构[J]. 中国石油大学学报(自然科学版), 2022, 46(1):23-33. doi:10.3969/j.issn.1673-5005.2022.01.003 LIU Xuefeng, ZHANG Xiaowei, ZENG Xin, et al. Pore structure characterization of shales using SEM and machine learning-based segmentation method[J]. Journal of China University of Petroleum (Edition of Natural Science), 2022, 46(1):23-33. doi:10.3969/j.issn.1673- 5005.2022.01.003
[35] ZHANG P. A novel feature selection method based on global sensitivity analysis with application in machine learning-based prediction model[J]. Applied Soft Computing, 2019, 85:105859.
[36] 钟功祥,申伟,雷鹏燕,等. 基于正交实验的井下直线发电机设计与分析[J]. 西南石油大学学报(自然科学版), 2023, 45(3):154-162. doi:10.11885/j.issn.1674-5086.2020.11.06.01 ZHONG Gongxiang, SHEN Wei, LEI Pengyan, et al. Design and optimization analysis of downhole linear generator based on orthogonal test[J]. Journal of Southwest Petroleum University (Science & Technology Edition), 2023, 45(3):154-162. doi:10.11885/j.issn.1674-5086.2020.11.06.01

基于多维时序LSTM的超深井机械钻速预测方法

Prediction of Penetration Rate Method for Ultra-deep Well Based on Multi-dimensional Time Series LSTM

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	邱恩喜, 赵剑杰, 万旭升, 王知深, 刘君. 碎屑堆积体基岩-覆土接触面剪切实验研究[J]. 西南石油大学学报(自然科学版), 2025, 47(5): 151-165.
[2]	汤明, 王双宁, 何世明, 张光福, 刘晓森. 超深井高钢级厚壁套管开窗研究及应用[J]. 西南石油大学学报(自然科学版), 2025, 47(4): 177-188.
[3]	任今明, 潘昭才, 黄锟, 冯少波, 张宝. 关于超深油气井完井工程与油气藏采收率的思考[J]. 西南石油大学学报(自然科学版), 2024, 46(4): 169-177.
[4]	练章华, 万智勇, 宋琳, 赵朝阳, 林铁军. 超深井套管卡瓦效应的拉伸极限载荷理论计算[J]. 西南石油大学学报(自然科学版), 2024, 46(2): 155-163.
[5]	邓虎, 唐贵, 张林. 超深井高温高压井筒复杂流动压力演变规律研究[J]. 西南石油大学学报(自然科学版), 2023, 45(4): 111-120.
[6]	钟功祥, 申伟, 雷鹏燕, 宋华, 钟升级. 基于正交实验的井下直线发电机设计与分析[J]. 西南石油大学学报(自然科学版), 2023, 45(3): 154-162.
[7]	杨洋, 程悦菲, 谯英, 刘炯. 基于时序动态分析的油井产量预测研究[J]. 西南石油大学学报(自然科学版), 2020, 42(6): 82-88.
[8]	钟原, 刘小溶, 王杰, 陈雁, 张泰. 基于NER的石油非结构化信息抽取研究[J]. 西南石油大学学报(自然科学版), 2020, 42(6): 165-173.
[9]	董广建1 *，陈平1，邓元洲2，郭昭学1. 钻柱振动与冲击抑制技术研究现状[J]. 西南石油大学学报(自然科学版), 2016, 38(3): 121-134.
[10]	李洪建1 *，孙建波1，孟雪2，唐鑫3，王德玉3. 碳酸钙阻垢效果影响因素实验研究[J]. 西南石油大学学报(自然科学版), 2016, 38(2): 143-148.
[11]	刘月娥1，杨雯雯1，邬国栋2，阿不都维力·阿不力米提2，徐向红1. 抗油抗高矿化度泡沫排水剂的室内研究[J]. 西南石油大学学报(自然科学版), 2014, 36(3): 146-150.
[12]	王世洁1，杨志2，赵金洲2，王雷3，张建军3. 塔河超深裸眼分层注水管柱变形计算与对策[J]. 西南石油大学学报(自然科学版), 2014, 36(1): 163-169.
[13]	杨宇平;孙金声;杨枝;卢运虎;江四清. 快速钻井剂稳定井壁快速钻进作用机理研究[J]. 西南石油大学学报(自然科学版), 2010, 32 (1): 165-169.
[14]	林玉龙. 龙岗地区121/4英寸泥浆钻进井段机械钻速分析[J]. 西南石油大学学报(自然科学版), 2009, 31(6): 161-165.
[15]	郭建春;辛军;赵金洲;等. 酸处理降低地层破裂压力的计算分析[J]. 西南石油大学学报(自然科学版), 2008, 30(2): 83-86.