|本期目录/Table of Contents|

[1]赵 颖 孙 挺 杨 进 李炎军 黄 熠 闫宇龙.基于极限学习机的海上钻井机械钻速监测及实时优化[J].中国海上油气,2019,31(06):138-142.[doi:10.11935/j.issn.1673-1506.2019.06.018]
 ZHAO Ying SUN Ting YANG Jin LI Yanjun HUANG Yi YAN Yulong.Extreme learning machine-based offshore drilling ROP monitoring and real-time optimization[J].China Offshore Oil and Gas,2019,31(06):138-142.[doi:10.11935/j.issn.1673-1506.2019.06.018]
点击复制

基于极限学习机的海上钻井机械钻速监测及实时优化()

《中国海上油气》[ISSN:1673-1506/CN:11-5339/TE]

卷:
第31卷
期数:
2019年06期
页码:
138-142
栏目:
钻采工程
出版日期:
2019-11-21

文章信息/Info

Title:
Extreme learning machine-based offshore drilling ROP monitoring and real-time optimization
文章编号:
1673-1506(2019)06-0138-05
作者:
赵 颖1 孙 挺1 杨 进1 李炎军2 黄 熠2 闫宇龙3
(1. 中国石油大学(北京)北京 102249; 2. 中海石油(中国)有限公司湛江分公司 广东湛江 524057; 3. 北京航空航天大学 北京 100191)
Author(s):
ZHAO Ying1 SUN Ting1 YANG Jin1 LI Yanjun2 HUANG Yi2 YAN Yulong3
(1. China University of Petroleum, Beijing 102249, China; 2. CNOOC China Limited, Zhanjiang Branch, Zhanjiang, Guangdong 524057, China; 3. Beihang University, Beijing 100191, China)
关键词:
极限学习机 海上钻井 机械钻速 实时优化 钻井效率
Keywords:
extreme learning machine offshore drilling ROP real-time optimization drilling efficiency
分类号:
TE242
DOI:
10.11935/j.issn.1673-1506.2019.06.018
文献标志码:
A
摘要:
海上钻井作业环境恶劣,作业风险和费用高,如何提高钻井效率、降低钻井成本一直是倍受关注的问题。基于极限学习机,建立了海上钻井机械钻速预测模型,并以南海YL8-3-1井为例进行了验证与钻井参数实时优化。结果表明,基于极限学习机的海上钻井机械钻速预测模型预测结果与实测结果较为吻合,可以对机械钻速进行实时监测并通过优化钻井参数实现钻井事故预警及有效预防,进而提高钻井效率。本文研究可对海上安全高效钻井作业及油田数字化、智能化发展提供借鉴。
Abstract:
Offshore drilling is subject to bad environmental and high risks and cost. How to improve the drilling efficiency and reduce drilling cost has always been a difficulty in offshore drilling. Based on the extreme learning machine, the prediction model of offshore drilling ROP has been established and verified on Well YL8-3-1 in the South China Sea. The results show that the prediction results of this mode are in good agreement with the measured results. Therefore, it is able to conduct the real-time monitoring of ROP and optimize the drilling parameters, and realize the drilling accident precaution and effective prevention, thus improving the drilling efficiency. This study can provide references for the safe and efficient offshore drilling as well as the digital and intelligent development of oilfields.

参考文献/References:

[1] ZHAO Ying,SUN Ting,YANG Jin,et al.Combining drilling big data and machine learning method to improve the timeliness of drilling[C].The Hague,The Netherlands:SPE/IADC International Drilling Conference and Exhibition,2019. [2] 张奇志,杨佳淼.随钻测量的钻进多参数模型建立[J].石油化工应用,2015,34(11):8-11. ZHANG Jizhi,YANG Jiamiao.Establishment of drilling multi-parameter model for MWD[J].Petrochemical Industry Application,2015,34(11):8-11. [3] 付志胜.钻井参数实时优化方法研究[D].成都:西南石油大学,2014. FU Zhisheng.Research on real-time optimization method of drilling parameters [D].Chengdu:Southwest Petroleum University,2014. [4] ZHAO Fei,WANG Haige,CUI Meng,et al.Monitoring and mitigating downhole vibration with MSE in Xinjiang oilfield of China[C].San Francisco,California,USA:51st US Rock Mechanics/Geomechanics Symposium,2017. [5] DUPRIEST F E,WITT J W,REMMERT S M.Maximizing ROP with real-time analysis of digital data and MSE[C].Doha,Qatar:International Petroleum Technology Conference,2005. [6] BOURGOYNE A T,YOUNG FS.A multiple regression approach to optimal drilling and abnormal pressure detection[J].Society of Petroleum Engineers Journal,1974,14(4):371-384. [7] RASTEGAR M,HARELAND G,NYGAARD R,et al.Optimization of multiple bit runs based on ROP models and cost equation:A new methodology applied for one of the Persian Gulf carbonate fields[J].Medical Physics,2008,36(6):2692-2692. [8] ROMMETVEIT R,BJRKEVOLL K,HALSEY G W,et al.Drilltronics:An integrated system for real-time optimization of the drilling process[C].Dallas,Texas:IADC/SPE Drilling Conference,2004. [9] BAHARI M,BAHARI A,NEJATI F,et al.Trust-region approach to find constants of Bourgoyne and Young penetration rate model in Khangiran Iranian gas field[C].Buenos Aires,Argentina:Latin American & Caribbean Petroleum Engineering Conference,2008. [10] KSHITIJ M,FARAAZ A and ROBELLO S.Tracking drilling efficiency using hydro-mechanical specific energy[C].Amsterdam,The Netherlands:SPE/IADC Drilling Conference and Exhibition,2009. [11] 王小川.MATLAB神经网络43个案例分析[M].北京:北京航空航天大学出版社,2013.

相似文献/References:

备注/Memo

备注/Memo:
*“十三五”国家科技重大专项“莺琼盆地高温高压天然气富集规律与勘探开发关键技术(三期)(编号:2016ZX05024-005)”、中国石油大学(北京)引进人才科研启动基金项目“页岩气藏单井最终可采储量计算(编号:2462017YJRC034)”部分研究成果。 第一作者简介: 赵颖,女,中国石油大学(北京)在读硕士研究生,主要研究方向为海洋钻完井工程以及石油钻完井大数据应用的研究工作。地址:北京市昌平区府学路18号中国石油大学(北京)安全与海洋工程学院安全与海洋工程学院(邮编:102249)。E-mail:
更新日期/Last Update: 1900-01-01