Drilling Speed Enhancement Method for Extended Reach Wells Based on Machine Learning and Bayesian Optimization
-
摘要:
海上大位移井的井眼轨迹复杂和水平位移较大，导致井下摩阻增加，严重影响钻井效率。根据钻井数据和录井数据等，提出了一种基于机器学习钻速预测与钻井参数优化的大位移井钻井提速方法。首先，对现场原始数据进行滤波、归一化等预处理，进行了相关性分析，得出钻压、转盘转速等钻井参数及井斜角、水平位移等井眼轨迹参数与钻速有显著的相关性；然后，构建了基于BP神经网络、随机森林和支持向量机的钻速预测模型，预测精度评价结果表明，BP神经网络模型表现最优，可以较为准确地预测海上大位移钻井的机械钻速；最后，采用贝叶斯优化算法，以提高钻速为目标进行了钻压、转盘转速和排量等参数优化。优化结果表明，钻井参数优化后，机械钻速平均提升了18.86%。研究结果揭示了钻井参数和井眼轨迹参数对大位移井钻速的影响，为大位移井钻井提速提供了理论依据。
Abstract:The wellbore trajectories of offshore extended reach wells are complex and characterized by large horizontal displacements, leading to increased downhole friction and subsequently affecting drilling efficiency. This paper introduces a novel method for rate of penetration prediction and drilling parameter optimization in extended reach wells using machine learning, based on drilling and logging data. Initially, raw field data were preprocessed and subjected to correlation analysis, revealing significant correlations between drilling parameters such as bit pressure and rotary speed, as well as wellbore trajectory parameters like hole deviation angle and horizontal displacement, with rate of penetration. Based on these findings, rate of penetration prediction models were developed using BP neural networks, random forests, and support vector machines. The prediction accuracy of these models was evaluated using four performance indicators, with the results showing that the BP neural network model outperformed the others, providing relatively accurate rate of penetration predictions for offshore extended reach wells. Furthermore, the Bayesian optimization algorithm was employed to adjust controllable parameters such as bit pressure, rotary speed, and pump rate, resulting in an average increase in rate of penetration by 18.86%. This study elucidates the impact of drilling parameters and wellbore trajectory parameters on rate of penetration; in extended reach wells and provides theoretical evidence for enhancing drilling efficiency.
-
-
![]()
图 1 贝叶斯优化算法的采集函数迭代过程
Figure 1. Iteration Process of Acquisition Function in Bayesian Optimization Algorithm
![]()
图 5 钻速优化前后对比
Figure 5. Comparison of Rate of Penetration Before and After Optimization
![]()
图 6 不同深度下的钻速提升效果
Figure 6. Enhancement Effect of Rate of Penetration at Different Depths
表 1 预测模型评价指标
Table 1 Evaluation Metrics for Prediction Models
算法 决定系数 平均绝对误差 均方误差 均方根误差 BP神经网络 0.883 4.81 57.64 7.59 随机森林 0.838 5.59 69.95 8.36 支持向量机 0.680 8.79 215.25 14.67 
下载: 导出CSV
-
[1] 高德利,黄文君,李鑫. 大位移井钻井延伸极限研究与工程设计方法[J]. 石油钻探技术,2019,47(3):1–8. GAO Deli, HUANG Wenjun, LI Xin. Research on extension limits and engineering design methods for extended reach drilling[J]. Petroleum Drilling Techniques, 2019, 47(3): 1–8.
[2] 张剑,肖禹涵,周忠易,等. 基于TDCSO优化CNN-Bi-LSTM网络的井底钻压预测方法[J]. 石油钻探技术,2024,52(5):82–90. ZHANG Jian, XIAO Yuhan, ZHOU Zhongyi, et al. Downhole WOB prediction method based on CNN-Bi-LSTM network optimized by TDCSO[J]. Petroleum Drilling Techniques, 2024, 52(5): 82–90.
[3] 李乾,王磊,王喜杰,等. 东海大位移水平井降摩减阻技术研究与实践[J]. 中国海上油气,2022,34(6):149–156. LI Qian, WANG Lei, WANG Xijie, et al. Research and practice of friction and drag reduction technology for extended reach horizontal wells in the East China Sea[J]. China Offshore Oil and Gas, 2022, 34(6): 149–156.
[4] 纪国栋,陈畅畅,郭建华,等. 万米深井钻柱减振增能提速方法研究[J]. 石油钻探技术,2024,52(2):100–107. doi: 10.11911/syztjs.2024038 JI Guodong, CHEN Changchang, GUO Jianhua, et al. Research on vibration reduction, energy enhancement, and acceleration methods for drilling strings of 10000-meter deep wells[J]. Petroleum Drilling Techniques, 2024, 52(2): 100–107. doi: 10.11911/syztjs.2024038
[5] 呼怀刚,黄洪春,汪海阁,等. 国内外PDC钻头新进展与发展趋势展望[J]. 石油机械,2024,52(2):1–10. HU Huaigang, HUANG Hongchun, WANG Haige, et al. New progress and development trends of PDC bits in China and Abroad[J]. China Petroleum Machinery, 2024, 52(2): 1–10.
[6] 佘朝毅. 四川盆地超深层钻完井技术进展及其对万米特深井的启示[J]. 天然气工业,2024,44(1):40–48. doi: 10.3787/j.issn.1000-0976.2024.01.004 SHE Zhaoyi. Progress in ultra-deep drilling and completion technology in the Sichuan Basin and its implications for extra-deep wells of more than ten thousand meters in depth[J]. Natural Gas Industry, 2024, 44(1): 40–48. doi: 10.3787/j.issn.1000-0976.2024.01.004
[7] 李中. 渤海深层探井钻井关键技术现状及展望[J]. 钻采工艺,2024,47(2):35–41. doi: 10.3969/J.ISSN.1006-768X.2024.02.05 LI Zhong. Challenges and technology trends prediction of deep exploration well drilling in Bohai Sea[J]. Drilling & Production Technology, 2024, 47(2): 35–41. doi: 10.3969/J.ISSN.1006-768X.2024.02.05
[8] HEGDE C, GRAY K. Evaluation of coupled machine learning models for drilling optimization[J]. Journal of Natural Gas Science and Engineering, 2018, 56: 397–407. doi: 10.1016/j.jngse.2018.06.006
[9] 郑双进,江厚顺,熊梦园,等. 基于数据驱动和机理模型的机械钻速预测[J]. 钻采工艺,2025,48(1):78–87. doi: 10.3969/J.ISSN.1006-768X.2025.01.10 ZHENG Shuangjin, JIANG Houshun, XIONG Mengyuan, et al. Data driven and mechanistic model based prediction of rate of penetration[J]. Drilling & Production Technology, 2025, 48(1): 78–87. doi: 10.3969/J.ISSN.1006-768X.2025.01.10
[10] 伊鹏,刘衍聪,郭欣,等. 基于改进自适应遗传算法的钻井参数优化设计[J]. 石油机械,2010,38(2):30–33. YI Peng, LIU Yancong, GUO Xin, et al. Optimized design of drilling darameters based on enhanced adaptive genetic algorithm[J]. China Petroleum Machinery, 2010, 38(2): 30–33.
[11] 刘光星,李巧花. 基于改进蚁群算法的钻进参数优化[J]. 西安石油大学学报(自然科学版),2019,34(4):31–36. doi: 10.3969/j.issn.1673-064X.2019.04.006 LIU Guangxing, LI Qiaohua. Optimization of drilling parameters based on improved ant colony algorithm[J]. Journal of Xi’an Shiyou University(Natural Science Edition), 2019, 34(4): 31–36. doi: 10.3969/j.issn.1673-064X.2019.04.006
[12] 刘兆年,赵颖,孙挺. 渤海区域基于数据驱动的钻井提速[J]. 西南石油大学学报(自然科学版),2020,42(6):35–41. LIU Zhaonian, ZHAO Ying, SUN Ting. Data-driven drilling acceleration in Bohai XX Block[J]. Journal of Southwest Petroleum University(Science & Technology Edition), 2020, 42(6): 35–41.
[13] GAN Chao, CAO Weihua, WU Min, et al. Prediction of drilling rate of penetration (ROP) using hybrid support vector regression: a case study on the Shennongjia Area, Central China[J]. Journal of Petroleum Science and Engineering, 2019, 181: 106200.
[14] SOARES C, GRAY K. Real-time predictive capabilities of analytical and machine learning rate of penetration (ROP) models[J]. Journal of Petroleum Science and Engineering, 2019, 172: 934–959. doi: 10.1016/j.petrol.2018.08.083
[15] NAJJARPOUR M, JALALIFAR H, NOROUZI-APOURVARI S. Half a century experience in rate of penetration management: Application of machine learning methods and optimization algorithms: a review[J]. Journal of Petroleum Science and Engineering, 2022, 208(Part D): 109575.
[16] FENG Hao, ZHOU Yadong, ZENG Weili, et al. A physics-based PSO-BPNN model for civil aircraft noise assessment[J]. Applied Acoustics, 2024, 221: 109992. doi: 10.1016/j.apacoust.2024.109992
[17] 苏兴华,孙俊明,高翔,等. 基于GBDT算法的钻井机械钻速预测方法研究[J]. 计算机应用与软件,2019,36(12):87–92. doi: 10.3969/j.issn.1000-386x.2019.12.014 SU Xinghua, SUN Junming, GAO Xiang, et al. Prediction method of drilling rate of penetration based on GBDT algorithm[J]. Computer Applications and Software, 2019, 36(12): 87–92. doi: 10.3969/j.issn.1000-386x.2019.12.014
[18] 张宏韬,唐芳,吴坤,等. 基于粒子群优化BP神经网络的激光扫描投影系统畸变预测方法[J]. 光子学报,2024,53(6):0611001. doi: 10.3788/gzxb20245306.0611001 ZHANG Hongtao, TANG Fang, WU Kun, et al. Distortion prediction method of laser scanning projection system based on PSO-BP neural network[J]. Acta Photonica Sinica, 2024, 53(6): 0611001. doi: 10.3788/gzxb20245306.0611001
[19] 陈亮,郝祎纯,李巧茹,等. 改进SSA优化的BP神经网络交通量预测模型[J]. 哈尔滨工业大学学报,2024,56(7):94–101. CHEN Liang, HAO Yichun, LI Qiaoru, et al. Traffic volume forecast model based on BP neural network optimized by improved sparrow search algorithm[J]. Journal of Harbin Institute of Technology, 2024, 56(7): 94–101.
[20] 邹红梅,朱成涛. 基于LSTM和BP神经网络的水库入库径流中长期预测比较研究[J]. 水文,2024,44(4):27–31. ZOU Hongmei, ZHU Chengtao. Comparative study on mid-long term prediction of reservoir inflow based on LSTM and BP neural network[J]. Journal of China Hydrology, 2024, 44(4): 27–31.
[21] 秦长坤,赵武胜,贾海宾,等. 基于模态分解和深度学习的煤矿微震时序预测方法[J]. 煤炭学报,2024,49(9):3781–3797. QIN Changkun, ZHAO Wusheng, JIA Haibin, et al. A method for predicting the time series of microseismic events in coal mines based on modal decomposition and deep learning[J]. Journal of China Coal Society, 2024, 49(9): 3781–3797.
[22] 盖建. 基于自动机器学习的采油井压裂效果预测方法[J]. 油气地质与采收率,2023,30(1):161–170. GE Jian. Prediction method for hydraulic fracturing effect of oil production well based on automatic machine learning technology[J]. Petroleum Geology and Recovery Efficiency, 2023, 30(1): 161–170.
[23] 郝杨杨,邹宇. 基于BP神经网络的上海生鲜农产品物流需求预测[J]. 上海海事大学学报,2024,45(1):39–45. HAO Yangyang, ZOU Yu. Logistics demand forecast of fresh agricultural products in Shanghai based on BP neural network[J]. Journal of Shanghai Maritime University, 2024, 45(1): 39–45.
[24] 雍锐. 智能钻井多目标协同优化系统研究与应用[J]. 钻采工艺,2024,47(3):9–14. YONG Rui. Research and application of intelligent drilling advisory system[J]. Drilling & Production Technology, 2024, 47(3): 9–14.
[25] 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. 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.
[26] 高云伟,罗利民,薛凤龙,等. 基于Stacking集成学习的机械钻速预测方法[J]. 石油机械,2024,52(5):17–24. GAO Yunwei, LUO Limin, XUE Fenglong, et al. ROP prediction method based on stacking ensemble learning[J]. China Petroleum Machinery, 2024, 52(5): 17–24.
[27] 姜宝胜,白玉湖,徐兵祥,等. 基于集成学习的致密气藏产能预测新方法[J]. 中国海上油气,2024,36(5):120–127. JIANG Baosheng, BAI Yuhu, XU Bingxiang, et al. A novel approach for predicting production capacity of tight gas reservoirs based on ensemble learning[J]. China Offshore Oil and Gas, 2024, 36(5): 120–127.
[28] CHEN Xuyue, WENG Chengkai, DU Xu, et al. Prediction of the rate of penetration in offshore large-scale cluster extended reach wells drilling based on machine learning and big-data techniques[J]. Ocean Engineering, 2023, 285(part 2): 115404.
[29] 汤明,王汉昌,何世明,等. 基于PCA-BP算法的机械钻速预测研究[J]. 石油机械,2023,51(10):23–31. TANG Ming, WANG Hanchang, HE Shiming, et al. Prediction for rate of penetration based on PCA-BP algorithm[J]. China Petroleum Machinery, 2023, 51(10): 23–31.
[30] 黄哲. 探管式智能钻头参数测量装置研制与现场试验[J]. 石油钻探技术,2024,52(4):34–43. doi: 10.11911/syztjs.2024004 HUANG Zhe. Development and field test of probe-type intelligent bit parameter measurement device[J]. Petroleum Drilling Techniques, 2024, 52(4): 34–43. doi: 10.11911/syztjs.2024004
-
期刊类型引用(3)
1. 张文锐，代玉杰，刘贵满. 环形井网稠油渗流压力场数值模拟. 当代化工. 2022(01): 196-201+205 . 
百度学术
2. 李瑞轩，黄云龙，李源. 油藏渗流模型与数值模拟技术研究进展. 石油化工应用. 2021(07): 11-15+29 . 百度学术
3. 房娜，姜光宏，程奇，李广龙，王双龙. 裂缝性油藏不同见水模式下的注水优化. 断块油气田. 2020(05): 633-637 . 百度学术
其他类型引用(2)
计量
- 文章访问数: 1
- HTML全文浏览量: 0
- PDF下载量: 0
- 被引次数: 5
