A novel method for predicting wellbore trajectory based on support vector machine

doi:10.7623/syxb200505022

Editorial office of ACTA PETROLEI SINICA ›› 2005, Vol. 26 ›› Issue (5): 98-101.DOI: 10.7623/syxb200505022

• Petroleum Engineering • Previous Articles Next Articles

A novel method for predicting wellbore trajectory based on support vector machine

WANG Yan-jiang^1,2, YANG Pei-jie¹, SHI Ging-jiang¹, SUN Zheng-yi²

1. College of Information and Control Engineering, China University of Petroleum, Dongying 257061, China;
2. Drilling Information Center of Drilling Technology Research Institute, Sinopec Shengli Oilfield, Dongying 257017, China

Received:2004-11-22 Revised:2005-04-11 Online:2005-09-25 Published:2010-05-21

一种基于支撑向量机学习预测井眼轨迹的新方法

王延江^1,2, 杨培杰¹, 史清江¹, 孙正义²

1. 中国石油大学信息与控制工程学院, 山东, 东营, 257061;
2. 胜利油田钻井工艺研究院钻井信息中心, 山东, 东营, 257017

作者简介:王延江,男,1966年9月生,2001年获北方交通大学博士学位,现为中国石油大学(华东)信息与控制工程学院教授,胜利油田钻井工艺研究院在站博士后,主要从事智能信息处理及其在石油勘探、开发中的应用研究.E-mail:yjwang@hdpu.edu.cn
基金资助:
中国石油化工集团公司科技攻关项目“地质导向钻井工艺技术研究”(JP03009)资助

Abstract

Abstract: The main factors affecting well trajectory during drilling were analyzed.A novel method for predicting well trajectory by using support vector machine(SVM)based on small samples of statistical learning theory is presented.The basic principles of support vector for regression(SVR)is introduced.A prediction model for well trajectory was established by training the SVR using the data of wellbore trajectory,drilling mode and the structural parameters for the bottom hole assembly of one or several drilled wells.The proposed prediction model was verified with the trajectory data of a number of drilled wells.This model has higher prediction precision than geometric method.

Key words: wellboret rajectory, prediction model, support vector machine, structural parameters, statistical learning theory

摘要： 对影响井眼轨迹的几个主要因素进行了分析,提出了一种利用小样本统计学习理论中的支撑向量机来进行井眼轨迹预测的新方法,介绍了用于非线性回归估计的支撑向量机的基本原理,通过对一口或几口已钻井的轨迹数据、钻进方式和底部钻具组合结构参数进行学习训练支撑向量机,建立了井眼轨迹的支撑向量机预测模型,并利用多口实钻井的轨迹数据进行了验证。结果表明,这种新方法的预测精度远高于传统的定曲率几何预测方法。

关键词: 井眼轨迹, 预测模型, 支撑向量机, 结构参数, 统计学习理论

CLC Number:

TE23

WANG Yan-jiang, YANG Pei-jie, SHI Ging-jiang, SUN Zheng-yi. A novel method for predicting wellbore trajectory based on support vector machine[J]. Editorial office of ACTA PETROLEI SINICA, 2005, 26(5): 98-101.

王延江, 杨培杰, 史清江, 孙正义. 一种基于支撑向量机学习预测井眼轨迹的新方法[J]. 石油学报, 2005, 26(5): 98-101.

[1]	Yang Jiaosheng, Feng Peng, Tang Shuling, Tang Dazhen, Wang Meizhu, Li Song, Zhao Yang, Li Zhanwei. Phase control factors and content prediction model of deep coalbed methane in Daning-Jixian block [J]. Acta Petrolei Sinica, 2023, 44(11): 1879-1891.
[2]	Song Chuang, Zhang Xiaocheng, Xie Tao, Huo Hongbo, Wang Wen. Prediction of early annular trap pressure of three-high gas wells in Bohai Sea [J]. Acta Petrolei Sinica, 2022, 43(5): 694-707.
[3]	Wang Jiangshuai, Li Jun, Liu Gonghui, Chen Anming, Luo Kuidong, Huang Tao, Wang Wei. Prediction of annulus pressure in variable pressure gradients drilling [J]. Acta Petrolei Sinica, 2020, 41(4): 497-504.
[4]	Gao Yonghai, Meng Wenbo, Cui Yanchun, Zhang Chong, Chen Ye, Dong Zhao, Sun Jinsheng, Sun Baojiang. A new prediction model for hydrate deposition in deepwater gas well [J]. Acta Petrolei Sinica, 2019, 40(8): 975-982.
[5]	Zhou Bin, Wang Yanjiang, Liu Weifeng, Liu Baodi. A working condition recognition method of sucker-rod pumping wells based on Hessian-regularized SVM and multi-view co-training algorithm [J]. Acta Petrolei Sinica, 2018, 39(12): 1429-1436.
[6]	Zhao Xin, Qiu Zhengsong, Huang Weian, Zhou Guowei, Zhang Yongjun. Inhibition mechanism and optimized design of thermodynamic gas hydrate inhibitors [J]. Acta Petrolei Sinica, 2015, 36(6): 760-766.
[7]	Xing Haiyan, Dang Yongbin, Wang Ben, Ge Hua, Wang Zunce. Q uantitative MMM identification of damage levels based on KNN FSVM for remanufactured sucker rod [J]. Acta Petrolei Sinica, 2015, 36(11): 1427-1432,1456.
[8]	Wang Gang, Qin Yong, Shen Jian, Zhao Lijuan, Zhao Jincheng, Li Yepeng. Experimental studies of deep low-rank coal reservoirs’ permeability based on variable pore compressibility [J]. ACTA PETROLEI SINICA, 2014, 35(3): 462-468.
[9]	WANG Yuming, WANG Jiaying, KANG Hongqing, SUN Qiang, CHAI Fangyuan, ZHAO Qiyue. Establishment and application of a prediction model for enhanced oil recovery in polymer flooding [J]. Editorial office of ACTA PETROLEI SINICA, 2013, 34(3): 513-517.
[10]	ZHU Yixiang SHI Guangren. Identification of lithologic characteristics of volcanic rocks by support vector machine [J]. Editorial office of ACTA PETROLEI SINICA, 2013, 34(2): 312-322.
[11]	LI Li　LIU Jianyi　ZHANG Wei　ZHANG Guangdong　LI Chao　YE Changqing. An influence of phase behavior changes on scale formation in fluids of gas reservoirs [J]. Editorial office of ACTA PETROLEI SINICA, 2012, 33(5): 864-870.
[12]	JU Binshan　QIN Jishun　LI Zhiping　CHEN Xinglong. A prediction model for the minimum miscibility pressure of the CO₂-crude oil system [J]. Editorial office of ACTA PETROLEI SINICA, 2012, 33(2): 274-277.
[13]	YU Deliang QI Weigui DENG Shengchuan ZHANG Yongming ZHANG Fengwu. Submergence forecasting of a submersible plunger pump based on the support vector machine [J]. Editorial office of ACTA PETROLEI SINICA, 2011, 32(3): 534-538.
[14]	YI Fang LI Zhuxin LU Hongqing MA Weiping. Defect recognition by metal magnetic memory detection of pipelines based on the fuzzy kernel function SVM [J]. Editorial office of ACTA PETROLEI SINICA, 2010, 31(5): 863-866.
[15]	WANG Yi WANG Zhiyin ZENG Zhihua MA Lanping. The application of the method of uniform design response surface in inclined shaft traversing engineering of pipeline [J]. Editorial office of ACTA PETROLEI SINICA, 2010, 31(4): 645-648.

A novel method for predicting wellbore trajectory based on support vector machine

一种基于支撑向量机学习预测井眼轨迹的新方法

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

Comments