K-means聚类优化井底压力修正模型研究

doi:10.11885/j.issn.16745086.2019.01.14.03

摘要/Abstract

摘要： 在钻井过程中，由于井底压力计算模型误差大，而井下实测井底压力时数据容易失真、甚至无数据，因而不能准确测定井底压力，对钻井作业带来极大的安全风险。针对此类问题，提出了一种用K-means聚类方法优化朴素贝叶斯模型，结合井底压力监测原理，形成一套实现井底压力智能动态分析K-means聚类优化的朴素贝叶斯模型，利用该模型修正传统水力学模型井底压力计算值，根据修正结果与实测井底压力值进行对比，使得计算结果误差最小。利用现场数据进行对比分析，结果表明，应用基于K-means聚类的朴素贝叶斯模型修正井底压力计算值其误差较小，处于安全钻井压力监测误差范围内，能够满足现场正常钻井要求。

关键词: 井底压力, K-means 聚类, 朴素贝叶斯, 水力学模型, 压力修正

Abstract: In the process of drilling, owing to problems such as data distortion during the measurement of bottom-hole pressure, absence of return data, and incapacity of bottom-hole pressure calculation models to accurately reflect the measurements, the bottom-hole pressure cannot be accurately monitored, and this results in a substantial safety risk for drilling operations. To provide an effective overall monitoring of the bottom-hole pressure, a K-means clustering optimization method was established to improve the Naive Bayesian model. Combined with the principle of bottom-hole pressure monitoring, a Naive Bayesian model optimized by K-means clustering was designed, which could perform intelligent dynamic analysis of the bottom-hole pressure. This model was adopted to correct the bottom-hole pressure calculated by the traditional hydraulic model, and the results of both these models were compared to minimize the calculation error. Analysis of field data suggested that the calculated bottom-hole pressure corrected using the optimized model demonstrated a smaller error. This error was within the safe range of the pressure monitoring of drilling operation, indicating that the model was able to satisfy the requirements of regular drilling practices.

Key words: bottom hole pressure, K-means clustering, Naive Bayesian, hydraulic model, pressure correction

中图分类号:

TE12

张禾, 全锐. K-means聚类优化井底压力修正模型研究[J]. 西南石油大学学报(自然科学版), 2021, 43(3): 155-164.

ZHANG He, QUAN Rui. Optimization of a Bottom-hole Pressure Correction Model Using K-means Clustering[J]. Journal of Southwest Petroleum University(Science & Technology Edition), 2021, 43(3): 155-164.

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.16745086.2019.01.14.03

http://journal15.magtechjournal.com/Jwk_xnzk/CN/Y2021/V43/I3/155

参考文献

[1] 张红凤. 对油田井控技术的探索[J]. 中国新技术新产品,2012(7):127. doi:10.13612/j.cnki.cntp.2012.07.020 ZHANG Hongfeng. Exploration of well control technology in oilfield[J]. New Technologies and New Products in China, 2012(7):127. doi:10.13612/j.cnki.cntp.2012.07.020
[2] 李梦刚,万长根,白彬珍. 随钻压力测量技术现状及应用前景[J]. 断块油气田,2008,15(6):123-126. LI Menggang, WAN Changgen, BAI Binzhen. Present situation and application prospect of pressure measurement while drilling[J]. Fault Block Oil and Gas Field, 2008, 15(6):123-126.
[3] 梁海波,李欣嵘,王玉,等. 基于神经网络的井底压力模型修正技术应用[J]. 自动化与仪表,2012,27(11):9-11. dio:10.19557/j.cnki.1001-9944.2012.11.003 LIANG Haibo, LI Xinrong, WANG Yu, et al. Application of neural network-based bottom-hole pressure model revision technology[J]. Automation and Instruments, 2012, 27(11):9-11. dio:10.19557/j.cnki.1001-9944.2012.11.003
[4] 许珍萍,江乾锋,刘会会,等. 数值分析法在求解产水气井井底流压的应用[J]. 石油化工应用,2016,35(6):80-83. doi:10.3969/j.issn.16735285.2016.06.020 XU Zhenping, JIANG Qianfeng, LIU Huihui, et al. Application of numerical analysis method in solving bottom hole flowing pressure of water-producing gas wells[J]. Petrochemical Industry Application, 2016, 35(6):80-83. doi:10.3969/j.issn.16735285.2016.06.020
[5] 韩雄,何峰,王超. 酸化期间基于BP神经网络法的井底压力计算[J]. 天然气勘探与开发,2018,41(1):74-78. doi:10.12055/gaskk.issn.16733177.2018.01.012 HAN Xiong, HE Feng, WANG Chao. Calculation of bottomhole pressure during acidizing based on BP neural network method[J]. Natural Gas Exploration and Development, 2018, 41(1):74-78. doi:10.12055/gaskk.issn.16733177.2018.01.012
[6] 卢献健,刘海锋,蒋园园,等. 基于灰色遗传BP神经网络的大坝变形预测[J]. 桂林理工大学学报,2017,37(4):647-652. doi:10.3969/j.issn.1674-9057.2017.04. 015 LU Xianjian, LIU Haifeng, JIANG Yuanyuan, et al. Dam deformation prediction based on grey genetic BP neural network[J]. Journal of Guilin University of Technology, 2017, 37(4):647-652. doi:10.3969/j.issn.1674-9057.2017.04.015
[7] 韩家炜, MICHELINE K. 数据挖掘概念与技术[M]. 北京:机械工业出版社, 2001. HAN Jiawei, MICHELINE K. Data mining concept and technology[M]. Beijing:Machinery Industry Press, 2001.
[8] 毛国君,段立娟. 数据挖掘原理与算法[M]. 北京:清华大学出版社,2011. MAO Guojun, DUAN Lijuan. Principles and algorithms of data mining[M]. Beijing:Tsinghua University Press, 2011.
[9] 黄文秀,唐超尘,神显豪,等. 改进的k最邻近算法在海量数据挖掘中的应用[J]. 济南大学学报(自然科学版),2021,35(1):24-28. doi:10.13349/j.cnki.jdxbn.20200817.001 HUANG Wenxiu, TANG Chaochen, SHEN Xianhao, et al. Application of improved k-nearest neighbor algorithm in massive data mining[J]. Journal of University of Jinan (Science and Technology), 2021, 35(1):24-28. doi:10.13349/j.cnki.jdxbn.20200817.001
[10] PELIKAN M, SASTRY K, GOLDBERG D E. Scalability of the Bayesian optimization algorithm[J]. International Journal of Approximate Reasoning, 2002, 31(3):221-258. doi:10.1016/S0888-613X(02)00095-6
[11] CHEN M S, HAN J, YU P S. Data mining:An overview from a database perspective[J]. IEEE Transactions on Knowledge & Data Engineering, 1996, 8(6):866-883. doi:10.1109/69.553155
[12] 倪超武,许明标,陈斌. 钻井液水力学软件的编制与应用[J]. 长江大学学报(自科版),2009,6(4):186-188. doi:10.16772/j.cnki.16731409.2009.04.022 NI Chaowu, XU Mingbiao, CHEN Bin. Development and application of drilling fluid hydraulics software[J]. Journal of Changjiang University (Natural Science Edition), 2009, 6(4):186-188. doi:10.16772/j.cnki.16731409.2009.04.022
[13] 孙在. 随钻压力测量技术的研究与应用[J]. 中国科技信息,2011(19):81-82. doi:10.3969/j.issn.10018972.2011.19.033 SUN Zai. Research and application of pressure measurement while drilling technology[J]. Science and Technology Information in China, 2011(19):81-82. doi:10.3969/j.issn.10018972.2011.19.033
[14] 包富鹏,高瑞香,李三国. 随钻地层压力监测系统及其应用[J]. 内蒙古石油化工, 2010,36(15):33-35. doi:10.3969/j.issn.1006-7981.2010.15.010 BAO Fupeng, GAO Ruixiang, LI Sanguo. Pressure-monitoring system of drill ground and its application[J]. Inner Mongulia Petrochemical Industry, 2010, 36(15):33-35. doi:10.3969/j.issn.1006-7981.2010.15.010
[15] 马志勇,候满峰. 小井眼钻井水力学设计理论与应用研究[J]. 化工管理,2015(14):89. doi:10.3969/j.issn.1008-4800.2015.14.072 MA Zhiyong, HOU Manfeng. Study on hydraulic design theory and application of slim hole drilling[J]. Chemical Enterprise Management, 2015(14):89. doi:10.3969/j.issn.1008-4800.2015.14.072
[16] 毕春光,陈桂芬. 基于数据挖掘的贝叶斯算法应用研究[J]. 农业网络信息,2010(3):19-22. doi:10.3969/j.issn.1672-6251.2010.03.004 BI Chunguang, CHEN Guifen. Study on the naive bayes algorithm application based on data mining[J]. Agricultural Network Information, 2010(3):19-22. doi:10.3969/j.issn.1672-6251.2010.03.004
[17] 裴向杰,唐红昇,陈鹏. 一种改进的贝叶斯算法在短信过滤中的研究[J]. 计算机技术与发展,2015,25(9):89-93. doi:10.3969/j.issn.1673629X.2015.09.019 PEI Xiangjie, TANG Hongsheng, CHEN Peng. Research on optimized Naive Bayesian algorithm in SMS spam filtering[J]. Computer Technology and Development, 2015, 25(9):89-93. doi:10.3969/j.issn.1673629X.2015.09.019
[18] TAHERI S, YEARWOOD J, MAMMADOV M, et al. Attribute weighted Naive Bayes classifier using a local optimization[J]. Neural Computing & Applications, 2014, 24(5):995-1002.
[19] 秦怀强. 朴素贝叶斯分类算法浅析[J]. 福建质量管理,2017(17):235. QIN Huaiqiang. Analysis of Naive Bayesian classification algorithms[J]. Fujian Quality Management, 2017(17):235.
[20] 赵文涛,孟令军,赵好好,等. 朴素贝叶斯算法的改进与应用[J]. 测控技术,2016, 35(2):143-147. doi:10.3969/j.issn.10008829.2016.02.036 ZHAO Wentao, MENG Lingjun, ZHAO Haohao, et al. Improvement and application of Naive Bayesian algo-rithms[J]. Measurement & Control Technology, 2016, 35(2):143-147. doi:10.3969/j.issn.1000-8829.2016.02. 036
[21] HARTIGAN J A, WONG M A. Algorithm AS 136:A K-means clustering algorithm[J]. Journal of the Royal Statistical Society, 1979, 28(1):100-108.
[22] 程国建,赵倩倩. K-means聚类算法在Spark平台上的应用[J]. 软件导刊,2016,15(2):146-148. doi:10.11907/rjdk.1511517 CHENG Guojian, ZHAO Qianqian. Application of K-means clustering algorithms on spark platform[J]. Software Guide, 2016, 15(2):146-148. doi:10.11907/rjdk.1511517
[23] 王实,高文. 数据挖掘中的聚类方法[J]. 计算机科学,2000,27(4):42-45. doi:10.3969/j.issn.1002137X. 2000.04.012 WANG Shi, GAO Wen. Clustering method in data mining[J]. Computer Science, 2000, 27(4):42-45. doi:10.3969/j.issn.1002-137X.2000.04.012
[24] 王凡. 基于众包的数据库信息查询处理方法[J]. 电脑知识与技术,2016,12(16):25-27. doi:10.14004/j.cnki.ckt.2016.2787 WANG Fan. Database information query processing method based on the crowdsourcing[J]. Computer Know-ledge and Technology, 2016, 12(16):25-27. doi:10. 14004/j.cnki.ckt.2016.2787
[25] 黄韬,刘胜辉,谭艳娜. 基于K-means聚类算法的研究[J]. 计算机技术与发展,2011,21(7):54-57. doi:10.3969/j.issn.1673629X.2011.07.015 HUANG Tao, LIU Shenghui, TAN Yanna. Research on K-means clustering algorithm[J]. Computer Technology and Development, 2011, 21(7):54-57. doi:10.3969/j.issn.1673629X.2011.07.015
[26] 蔡瑞瑞. 改进K-means算法下大数据精准挖掘[J]. 新乡学院学报, 2021,38(3):27-31. CAI Ruirui. The use of improved K-means algorithm into accurate big data mining[J]. Journal of Xinxiang University, 2021, 38(3):27-31.
[27] 刘宇航,马慧芳,刘海姣,等. 一种可重叠子空间K-Means聚类算法[J]. 计算机工程,2020,46(8):58-63,71. doi:10.19678/j.issn.1000-3428.0054555 LIU Yuhang, MA Huifang, LIU Haijiao. et al. An overlapping subspace K-means clustering algorithm[J]. Computer Engineering, 2020, 46(8):58-63, 71. doi:10.19678/j.issn.1000-3428.0054555
[28] 张宇亭. K-means的应用混合数据算法[J]. 现代计算机,2020(13):22-25. doi:10.3969/j.issn.1007-1423.2020.13.004 ZHANG Yuting. Mixed data algorithm based on K-means[J]. Modern Computer, 2020(13):22-25. doi:10. 3969/j.issn.1007-1423.2020.13.004