基于数据驱动的钻井过程气侵工况预测方法

doi:10.7623/syxb201910011

石油学报 ›› 2019, Vol. 40 ›› Issue (10): 1263-1269.DOI: 10.7623/syxb201910011

基于数据驱动的钻井过程气侵工况预测方法

徐宝昌¹, 周家立¹, 刘伟², 付加胜²

1. 中国石油大学(北京)信息学院北京 102249;
2. 中国石油集团钻井工程技术研究院北京 102206

收稿日期:2018-10-20 修回日期:2019-07-25 出版日期:2019-10-25 发布日期:2019-11-09
通讯作者: 徐宝昌,男,1974年8月生,1997年获东北石油大学学士学位,2005年获北京航空航天大学博士学位,现为中国石油大学(北京)信息科学与工程学院副院长、副教授、硕士生导师,主要从事系统辨识及控压钻井方面研究工作。Email:xbcyl@163.com
作者简介:徐宝昌,男,1974年8月生,1997年获东北石油大学学士学位,2005年获北京航空航天大学博士学位,现为中国石油大学(北京)信息科学与工程学院副院长、副教授、硕士生导师,主要从事系统辨识及控压钻井方面研究工作。Email:xbcyl@163.com
基金资助:
国家重点研发计划项目（2016YFC0303700）资助。

Data driven prediction method for gas cut in drilling process

Xu Baochang¹, Zhou Jiali¹, Liu Wei², Fu Jiasheng²

1. College of Geophysics and Information Engineering, China University of Petroleum, Beijing 102249, China;
2. CNPC Drilling Engineering Research Institute, Beijing 102206, China

Received:2018-10-20 Revised:2019-07-25 Online:2019-10-25 Published:2019-11-09

摘要/Abstract

摘要：

钻井过程中异常工况的及时诊断是保证快速安全钻井的重要手段。笔者以提前预判气侵工况为目标，应用自适应观测器，以实际立压回压数据作为观测器输入，对未知的井底流量、井底压力数据进行估计。井底压力数据估计值与实际测得的井底压力数据吻合良好。将井底流量数据的估计值与井口实际出口流量数据做差，对该差值和实际立压、回压以及入口流量数据一起进行独立主元分析，提取该组数据的独立元、确定正常工况下的统计量控制限，并提取工作状态下的数据独立元的统计量，将该统计量数值与控制限进行对比，用于气侵工况诊断。经过实际钻井数据验证，该方法能够更准确判断正常工况及异常工况、并判断气侵的发生。

关键词: 工况诊断, 自适应观测器, 独立主元分析, 气侵, 预测

Abstract:

Timely diagnosis of abnormal working conditions in drilling process is an important means of ensuring fast and secure drilling. Aiming at predicting the gas cut in advance, a self-adaptive observer is used to estimate the unknown bottom hole flow rate and pressure data by inputting the actual standpipe pressure and return pressure data into the observer. The estimated bottom hole pressure data is well consistent with the actual measured bottom hole pressure data; the difference between the estimated bottom hole flow data and the actual wellhead flow data can be obtained; an independent component analysis is performed on such a difference, the actual standpipe pressure and return pressure, and the wellhead flow data. This study extracts independent elements of the data set, determines the statistical control limit under normal working conditions, obtains the statistics of independent elements in the working state, and performs a comparison between the statistics and the statistical control limit, aiming to detect the work conditions for gas cut. Verified by the real drilling data, the above method can accurately judge the normal or abnormal working conditions; compared with traditional methods, it can more timely and precisely predict the occurrence of gas cut.

Key words: condition diagnosis, adaptive observer, independent component analysis, gas cut, prediction

中图分类号:

TE258

徐宝昌, 周家立, 刘伟, 付加胜. 基于数据驱动的钻井过程气侵工况预测方法[J]. 石油学报, 2019, 40(10): 1263-1269.

Xu Baochang, Zhou Jiali, Liu Wei, Fu Jiasheng. Data driven prediction method for gas cut in drilling process[J]. Acta Petrolei Sinica, 2019, 40(10): 1263-1269.

参考文献

[1] 王明波,郭亚亮,方明君,等.裂缝性地层钻井液漏失动力学模拟及规律[J].石油学报,2017,38(5):597-606.
WANG Mingbo,GUO Yaliang,FANG Mingjun,et al.Dynamics simulation and laws of drilling fluid loss in fractured formations[J].Acta Petrolei Sinica,2017,38(5):597-606.
[2] 中国石油天然气集团公司工程技术与市场部,中国石油天然气集团公司石油工程技术承包商协会.中国石油天然气集团公司井喷事故案例汇编[M].北京:石油工业出版社,2006.
China Petroleum and Natural Gas Corporation Engineering and Marketing Department,China Petroleum and Natural Gas Corporation Petroleum Engineering and Technology Contractor Association.China petroleum and natural gas corporation blowout accident case compilation[M].Beijing:Petroleum Industry Press,2006.
[3] 卓鲁斌,葛云华,汪海阁.深水钻井早期井涌检测方法及其未来趋势[J].石油钻采工艺,2009,31(1):22-26.
ZHUO Lubin,GE Yunhua,WANG Haige.Early kick detection methods for deepwater drilling and its future development[J].Petroleum Drilling & Production Technology, 2009,31(1):22-26.
[4] 陈庭根,管志川.钻井工程理论与技术[M].东营:石油大学出版社,2000.
CHEN Tinggen,GUAN Zhichuan.Drilling engineering theory and technology[M].Dongying:Petroleum University Press,2000.
[5] 李相方,管丛笑,隋秀香,等.气侵检测技术的研究[J].天然气工业,1995,15(4):19-22.
LI Xiangfang,GUAN Congxiao,SUI Xiuxiang,et al.Research on gas cut detecting technology[J].Natural Gas Industry,1995,15(4):19-22.
[6] 任美鹏,李相方,刘书杰,等.深水钻井井筒气液两相溢流特征及其识别方法[J].工程热物理学报,2011,32(12):2068-2072.
REN Meipeng,LI Xiangfang,LIU Shujie,et al.The characteristics and identification method of gas-liquid two flow overflow in deepwater drilling[J].Journal of Engineering Thermophysics,2011,32(12):2068-2072.
[7] Nas S.Kick detection and well control in a closed wellbore[R].SPE 143099,2011.
[8] Tseytlin S.Methods and devices for determination of gas-kick parameters and prevention of well explosion[R].SPE 166871,2013.
[9] 徐加放,丁廷稷,张瑞,等.水基钻井液低温流变性调控用温敏聚合物研制及性能评价[J].石油学报,2018,39(5):597-603.
XU Jiafang,DING Tingji,ZHANG Rui,et al.Development and performance evaluation of thermo-sensitive polymer for low-temperature rheology control of water-based drilling fluid[J].Acta Petrolei Sinica,2018,39(5):597-603.
[10] 徐春露,孙建孟,董旭,等.页岩气储层孔隙压力测井预测新方法[J].石油学报,2017,38(6):666-676.
XU Chunlu,SUN Jianmeng,DONG Xu,et al.A new pore pressure logging prediction method in shale gas reservoirs[J].Acta Petrolei Sinica,2017,38(6):666-676.
[11] GE Zhiqiang,SONG Zhihua,GAO Furong.Review of recent research on data-based process monitoring[J].Industrial & Engineering Chemistry Research,2013,52(10):3543-3562.
[12] QIN S J.Survey on data-driven industrial process monitoring and diagnosis[J].Annual Reviews in Control,2012,36(2):220-234.
[13] ZHANG Yingwei,ZHANG Yang.Process monitoring,fault diagnosis and quality prediction methods based on the multivariate statistical techniques[J].IETE Technical Review,2010,27(5):406-420.
[14] CHO Y M,RAJAMANI R.A systematic approach to adaptive observer synthesis for nonlinear systems[J].IEEE Transactions on Automatic Control,1997,42(4):534-537.
[15] BESANÇON G.Remarks on nonlinear adaptive observer design[J].Systems & Control Letters,2000,41(4):271-280.
[16] ZHOU J,STAMNES O N,AAMOL O M,et al.Observer-based control of a managed pressure drilling system[C]//2008 Chinese Control and Decision Conference.Yantai,Shandong,China:IEEE,2008:3475-3480.
[17] ZHANG Q.Adaptive observer for multiple-input-multiple-output (MIMO)linear time-varying systems[J].IEEE Transactions on Automatic Control,2002,47(3):525-529.
[18] XU Aiping,ZHANG Qinghua.Nonlinear system fault diagnosis based on adaptive estimation[M].Tarrytown,NY,USA:Pergamon Press,Inc.,2004.
[19] 郭江维,缑林峰,时培燕,等.基于自适应观测器的故障检测方法研究[J].计算机仿真,2014,31(2):136-139.
GUO Jiangwei,GOU Linfeng,SHI Peiyan,et al.Research on fault detection method based on adaptive observer[J].Computer Simulation,2014,31(2):136-139.
[20] LEE J M,YOO C K,LEE I B.Statistical process monitoring with independent component analysis[J].Process Control,2004,14(5):467-485.
[21] 陈国金,梁军,钱积新.独立元分析方法(ICA)及其在化工过程监控和故障诊断中的应用[J].化工学报,2003,54(10):1474-1477.
CHEN Guojin,LIANG Jun,QIAN Jixin.ICA and its application to chemical process monitoring and fault diagnosis[J].Journal of Chemical Industry and Engineering (China),2003,54(10):1474-1477.
[22] 陆宁云,王磊,姜斌.基于时延SDG和ICA的多工况过程故障预测方法[J].控制工程,2011,18(4):632-635.
LU Ningyun,WANG Lei,JIANG Bin.A fault prognosis method based on time-delayed SDG and ICA for multi-mode industrial processes[J].Control Engineering of China,2011,18(4):632-635.
[23] 邓晓刚,徐莹.基于贝叶斯ICA的多工况非高斯过程故障检测[J].控制工程,2018,25(3):402-407.
DENG Xiaogang,XU Ying.Multimode non-gaussian process fault detection based on Bayesian-ICA[J].Control Engineering of China,2018,25(3):402-407.
[24] GODHAVN J M.Control requirements for high-end automatic MPD operations[R].SPE 119442,2009.
[25] KAASA G O.A simple dynamic model of drilling for control[R].Porsgrunn:StatoilHydro Research Centre,2007.
[26] 王果,范红康,牛新明,等.控压钻井线性节流阀及其控制[J].石油学报,2017,38(8):105-112.
WANG Guo,FAN Hongkang,NIU Xinming,et al.Linear choke valve and its control technology for managed pressure drilling[J].Acta Petrolei Sinica,2017,38(8):105-112.
[27] NYGAARD O G H.Multivariable process control in high temperature and high pressure environment using non-intrusive multi sensor data fusion[D]. Trondheim Norway:Norwegian University of Science and Technology,2006.
[28] XU Aiping,ZHANG Qinghua.Nonlinear system fault diagnosis based on adaptive estimation[J].Automatica,2004,40(7):1181-1193.
[29] FARZA M,M'SAAD M,MAATOUG T,et al.Adaptive observers for nonlinearly parameterized class of nonlinear systems[J].Automatica,2009,45(10):2292-2299.
[30] HYVÄRINEN A,HURRI J,HOYER P O.Independent component analysis[M]//Natural Image Statistics.London:Springer,2009:529-529.
[31] KANO M,HASEBE S,HASHIMOTO I,et al.Evolution of multivariate statistical process control:application of independent component analysis and external analysis[J].Computers & Chemical Engineering,2004,28(6/7):1157-1166.
[32] 周照明.欠平衡随钻气侵规律及运移模型研究[D].大庆:东北石油大学,2010.
ZHOU Zhaoming.Study of gas kick rule and migration model during underblance drilling[D].Daqing:Northeast Petroleum University,2010.
[33] 白丽丽,孙文峰,高金兰,等.基于多参数控制的钻井事故监测预警系统[J].化工自动化及仪表,2017,44(7):643-647.
BAI Lili,SUN Wenfeng,GAO Jinlan,et al.Drilling accident monitoring and early-warning system based on multi-parameter control[J].Chemical and Automations in Chemical Industry,2017,44(7):643-647.

基于数据驱动的钻井过程气侵工况预测方法

Data driven prediction method for gas cut in drilling process

PDF

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]	徐宝昌, 尤香凝, 孟卓然, 刘伟, 尹士轩. 基于回压激励响应的实时地层压力反演方法[J]. 石油学报, 2024, 45(6): 1009-1018.
[2]	李祯, 郭奇, 卜亚辉, 胡慧芳. 基于深度学习的饱和度场样本库建立及预测[J]. 石油学报, 2024, 45(4): 698-707.
[3]	王立歆, 李弘, 刘小民, 胡华锋. 中国海相页岩气地震勘探技术及其发展方向[J]. 石油学报, 2024, 45(1): 261-275.
[4]	郭秋麟, 黄少英, 卢玉红, 王建, 吴晓智, 陈宁生. 塔里木盆地台盆区下古生界油气系统模拟及资源分布预测[J]. 石油学报, 2023, 44(9): 1459-1471.
[5]	崔传智, 孙莲婷, 单高军, 杨勇, 吴义志. 多层合采油井的多措施同步优化方法[J]. 石油学报, 2023, 44(8): 1356-1364,1381.
[6]	徐宝昌, 张学智, 王雅欣, 刘伟, 孟卓然. 用于两相流环空压力预测的自适应物理信息神经网络模型[J]. 石油学报, 2023, 44(3): 545-555.
[7]	刘喜武, 王心宇, 刘宇巍, 张金强, 刘炯, 刘倩. 中国陆相页岩油地震勘探技术现状及发展方向[J]. 石油学报, 2023, 44(12): 2270-2285.
[8]	桑树勋, 郑司建, 王建国, 周效志, 刘世奇, 韩思杰, 赵伟光, 黄华州, 王冉, 汪吉林, 张志镇, 赵立明, 潘冬明, 陈同俊. 岩石力学地层新方法在深部煤层气勘探开发“甜点”预测中的应用[J]. 石油学报, 2023, 44(11): 1840-1853.
[9]	杨焦生, 冯鹏, 唐淑玲, 汤达祯, 王玫珠, 李松, 赵洋, 李站伟. 大宁—吉县区块深部煤层气相态控制因素及含量预测模型[J]. 石油学报, 2023, 44(11): 1879-1891.
[10]	刘致水, 王康宁, 包乾宗, 李之旭. 致密砂岩储层岩石物理横波速度预测方法 ——以鄂尔多斯盆地延长组为例[J]. 石油学报, 2022, 43(9): 1284-1294.
[11]	王珂, 张荣虎, 唐永, 余朝丰, 杨钊, 唐雁刚, 周露. 库车坳陷北部构造带侏罗系阿合组构造成岩作用与储层预测[J]. 石油学报, 2022, 43(7): 925-940.
[12]	姜晓宇, 宋涛, 甘利灯, 李贤兵, 杜文辉, 周晓越, 丁骞. 全方位叠前道集在花岗岩基岩潜山缝洞型储层预测中的应用——以乍得Bongor盆地Baobab潜山为例[J]. 石油学报, 2022, 43(7): 969-976.
[13]	赵辉, 李伯英, 周玉辉, 张琪, 刘洪发, 王文才, 王晓龙. 基于高速非达西渗流的断溶体油藏连通性预测模型[J]. 石油学报, 2022, 43(7): 1026-1034.
[14]	金国文, 王堂宇, 刘忠华, 谢然红, 邵亮, 李博宇. 基于核磁共振测井的砂砾岩储层分类与产能预测方法[J]. 石油学报, 2022, 43(5): 648-657.
[15]	宋闯, 张晓诚, 谢涛, 霍宏博, 王文. 渤海“三高”气井环空早期圈闭压力预测[J]. 石油学报, 2022, 43(5): 694-707.