A formation intelligent evaluation solution for geosteering
-
摘要:
地质导向系统基于井下实时测量的地质、地球物理和钻井参数，优化三维井轨迹到油气藏指定位置以获得最大的泄油面积和最佳的采收率，成为提高单井油气产量和油田开发效益的前沿技术，面临低孔-低渗-强非均质储层等地质难题和高温-高压-强振动等钻井工程难题.本文在梳理地质导向系统硬件、软件和人员等组成的基础上，将地质导向系统划分为基于地层构造的轨迹地质导向、识别储层岩性的油藏地质导向和面向地层成分的产能地质导向三个阶段；以分辨率更高、更直观的露头为例，阐述了地质导向系统"构造-岩性-成分"三个层次的逻辑关系.本文提出"数据采集-信息融合-态势感知-地层智能评价"的地质导向智能评价方案：按照学科门类，考虑数据的来源、采集时间和空间分辨率等因素，梳理出地层智能评价所需的数据类型与数据特征；提出地质导向多源异构数据"数据级-特征级-决策级"信息融合分类，并梳理了相关算法；根据数据模型与先验经验对当前钻井状态、地质环境进行态势评估，采用机器学习等算法对钻井模型和地质模型进行态势预测；提出"初导"和"精导"的理念，按照"构造-岩性-成分"三个层次厘定了地层智能评价的"精导"技术要点.该地质导向智能评价方案应用到实际油田的地质导向作业，验证了技术方案的可靠性和实用性，可为未来的井下智能闭环研究提供借鉴.
Abstract:Geosteering system is the optimal placement of a three-dimensional well trajectory based on the results of real-time downhole geological, geophysical and drilling parameters, aiming to obtain the largest oil drainage area and the best recovery factor. It has become the cutting-edge technology to improve the oil and gas production of a single well and the benefits of oilfield development, confronting geological problems such as low porosity, low permeability, and strong heterogeneous reservoir, combined with drilling engineering problems such as high temperature, high pressure, and strong vibration. Based on sorting out the hardware, software, and team of the geosteering system, this paper divided the geosteering system into three stages: trajectory geosteering based on formation structure, reservoir geosteering based on reservoir lithology, and productivity geosteering oriented to formation composition. Taking the outcrop with higher resolution and more intuitive as an example, the logical relationship in three levels of "structure-lithology-composition" for the geosteering system was expounded. In this paper, a formation intelligent evaluation solution for geosteering with the scheme of "data acquisition, information fusion, situational awareness, and formation intelligent evaluation" was proposed: According to the discipline categories, combined with the data sources, acquisition time and spatial resolution, the data types and characteristics required for formation intelligent evaluation were sorted; The information fusion classification of multi-source heterogeneous data of geosteering was proposed into "Data level-Feature level-Decision level", and the relevant algorithms were sorted out; According to the data model and prior experience, the situation assessment for the current drilling state and the geological environment was carried out, and the situation forecast for the next drilling state and the geological environment was carried out by machine learning algorithms; According to the "structure-lithology-composition" classification, the concepts of "Preliminary Geosteering" and "Fine Geosteering" was put forward, and the technical points of "Fine Geosteering" were also determined. An application of the geosteering intelligent evaluation solution to the actual oilfield geosteering operation was carried out, verifying its reliability and practicability, which can provide a reference for future downhole intelligent closed-loop research.
-
-
图 1
钻前预设井轨迹与实钻井轨迹对比
Figure 1.
Comparison of pre-drilling trajectory and actual trajectory
图 2
地质导向指导下实际井轨迹穿越储层时钻遇砂体的理想情况示意图
Figure 2.
Schematic diagram of the ideal situation of drilling sand bodies when the actual trajectory passes through the reservoir under the guidance of geosteering
图 3
面向地层成分的产能地质导向示意图
Figure 3.
Schematic diagram of productivity geosteering oriented to formation components
图 5
地质导向钻井过程中井轨迹与砂体、断层的接触关系，及对应的随钻测井图像方向和特征倾角模式
Figure 5.
The contact relationship between the well trajectory and the sand body and fault during the geosteering drilling process, and the corresponding LWD image orientation and characteristic dip pattern
图 6
F井地质导向所用的地震剖面与地层构造
Figure 6.
Seismic section and stratigraphic structure used for geosteering in Well F
图 7
地质导向信息融合采用的卷积神经网络
Figure 7.
Convolutional neural network used for geosteering information fusion
图 8
地质导向钻测录数据的一维编码解码神经网络
Figure 8.
One-dimensional coding decoding neural network of geosteering drilling, LWD, and mud logging data
图 9
基于随钻测井数据多尺度融合的岩性识别结果
Figure 9.
Lithology identification results based on multi-scale fusion of LWD data
图 10
F井基础地质-地球物理信息与地质导向剖面图
Figure 10.
Basic geological-geophysical information and geosteering profile of Well F
表 1
地质导向系统组成与仪器分类
Table 1.
Composition and instrument classification of geosteering system
类型 组成部分 具体分类 作用 硬件 定向钻井工具 旋转导向系统、螺杆 执行定向指令，实现井轨迹的调整 随钻测量和随钻测井仪器 随钻测量仪器(MWD)、随钻测井仪器(LWD)、随钻工程参数仪器 测量井下的工具姿态、地层性质、钻井状态等参数 井地传输仪器 脉冲式、旋转阀式、电磁波式 将井下参数实时传输到地面软件系统 软件 地面软件 地面解码软件、导向软件 信息实时解编与智能决策的平台 人员 地质导向团队 地球物理工程师、钻井工程师、定向井工程师、地质导向工程师和油藏工程师 地质导向作业的共同决策和执行者 
下载: 导出CSV
表 2
地质导向所需“地质-地球物理-钻井工程”的数据类型
Table 2.
Data types of "geology-geophysics-drilling engineering" required for geosteering
一级分类 二级分类 三级分类 地质数据 露头 储层岩性、构造、物性、连通性 岩心 岩性、岩石物理参数、流体含量、流体PVT参数 录井 井位、井深、钻时、延迟时间、全烃、C1、C2、C3、iC4、iC5、nC5、CO2、H2S 岩石学参数 岩石颜色、含油级别、岩石名称、岩性及含油性、荧光含量、岩石密度、碳酸钙含量、碳酸镁含量、其他矿物含量、K+、Na+、Mg2+等离子的含量、随钻压力检测、随钻温度检测 钻井地质分层 地层界面、分层数据、分层数据属性、层段属性 三维地质模型 构造模型、岩性模型、孔渗饱等属性模型 地球物理数据 电缆测井 岩性判别曲线：CAL、GR、SP、Pe物性判别曲线：AC、DEN、CNL电性判别曲线：Rt、Rs、RMSFL 随钻测井 随钻方位伽马、方位电阻率、核磁共振、中子和密度等 时深关系 单井时深关系、三维时深速度体、时深关系属性 地震数据 二维地震数据、二维地震测区、三维地震数据、三维地震测区 地震解释成果 二维地震解释成果、二维地震解释属性、三维地震解释网格、三维地震解释网格属性 钻井工程数据 井孔资料 井位、钻井时间、施工单位、井属性 井轨迹 井深、补心海拔、井斜角、方位角、三维井轨迹 钻井参数 钻时、钻压、悬重、钻速、扭矩、泵冲、立管压力、套管压力、地层压力、泥浆密度 井下钻具组合 钻头、旋转导向工具、钻铤、地质导向工具、钻杆、螺杆、扶正器、随钻震击器、水力振荡器 导向钻进参数 侧向力方向、侧向力大小、转角、趋势角、动态井斜角、动态方位角、测量深度
下载: 导出CSV
表 3
地质导向“数据级-特征级-决策级”信息融合算法表
Table 3.
"Data level-feature level-decision level" information fusion algorithm table of geosteering
数据级 特征级 决策级 加权融合法、乘积融合法、比值融合法、高通滤波融合法、小波变换融合法、彩色变换融合法、主成分分析融合法 多贝叶斯估计法、卡尔曼滤波法、支持向量机法、模糊逻辑推理、多核学习、人工神经网络法、聚类分析法、稀疏表示融合法 表决法、可靠性理论、基于知识的融合法、Dempster-shafer法、支持向量机法、集成学习法、梯度提升树、逻辑模板
下载: 导出CSV
-
Ao Y L, Lu W K, Xu P C, et al. 2022. Seismic dip estimation with a domain knowledge constrained transfer learning approach. IEEE Transactions on Geoscience and Remote Sensing, 60: 4501216, doi: 10.1109/TGRS.2021.3061438.
Chandola Y, Virmani J, Bhadauria H S, et al. 2021. Deep Learning for Chest Radiographs: Computer-Aided Classification. New York: Elsevier.
Di Q Y, Tian F, Suo Y H, et al. 2021. Linkage of deep lithospheric structures to intraplate earthquakes: A perspective from multi-source and multi-scale geophysical data in the South China Block. Earth-Science Reviews, 214: 103504, doi: 10.1016/j.earscirev.2021.103504.
Henrichs E, Lesch V, Straesser M, et al. 2022. A literature review on optimization techniques for adaptation planning in adaptive systems: State of the art and research directions. Information and Software Technology, 149: 106940, doi: 10.1016/J.INFSOF.2022.106940.
Hong D F, Tang X P, Gao W K, et al. 2021. Comprehensive solving method for arc-type well-path planning model. Acta Petrolei Sinica (in Chinese), 42(2): 226-232, doi: 10.7623/syxb202102007.
Jahani N, Ambia Garrido J, Alyaev S, et al. 2022. Ensemble-based well-log interpretation and uncertainty quantification for well geosteering. Geophysics, 87(3): IM57-IM66. doi: 10.1190/geo2021-0151.1
Jenakumo T, Adekoya O, Itua J, et al. 2022. Overcoming the late-stage development challenges of Bonga Turbidite reservoirs via Geosteering technology deployment. //SPE Nigeria Annual International Conference and Exhibition. Lagos, Nigeria: SPE.
Jia C Z. 2020. Development challenges and future scientific and technological researches in China's petroleum industry upstream. Acta Petrolei Sinica (in Chinese), 41(12): 1445-1464, doi: 10.7623/syxb202012001.
Jia J, Xia Z Y, Feng L, et al. 2022. Technological innovation and practice of geological engineering integration in Linxing block of Ordos basin. Petroleum Geology and Engineering (in Chinese), 36(2): 101-105, 112. doi: 10.3969/j.issn.1673-8217.2022.02.018
Kanfar M F. 2012. Real-time integrated petrophysics: Geosteering in challenging geology & fluid systems. //SPE Saudi Arabia Section Young Professionals Technical Symposium. Dhahran, Saudi Arabia: SPE.
Kolbikov S, Kuznetsov V, Karychev Y, et al. 2016. Integrated approach for the horizontal well design and geosteering in thin Jurassic sands. //SPE Russian Petroleum Technology Conference and Exhibition. Moscow, Russia: SPE, doi:
10.2118/182049-MS .Kolbjørnsen O, Buland A, Hauge R, et al. 2020. Bayesian seismic inversion for stratigraphic horizon, lithology, and fluid prediction. Geophysics, 85(3): R207-R221. doi: 10.1190/geo2019-0170.1
Kuang L C, Liu H, Ren Y L, et al. 2021. Application and development trend of artificial intelligence in petroleum exploration and development. Petroleum Exploration and Development (in Chinese), 48(1): 1-11, doi: 10.11698/PED.2021.01.01.
Kullawan K, Bratvold R B, Bickel J E. 2018. Sequential geosteering decisions for optimization of real-time well placement. Journal of Petroleum Science and Engineering, 165: 90-104. doi: 10.1016/j.petrol.2018.01.068
Leau Y B, Manickam S. 2015. Network security situation prediction: a review and discussion. //4th International Conference on Soft Computing, Intelligence Systems, and Information Technology. Bali, Indonesia: Springer, 424-435.
Li G S, Song X Z, Tian S C. 2020. Intelligent drilling technology research status and development trends. Petroleum Drilling Techniques (in Chinese), 48(1): 1-8, doi: 10.11911/syztjs.2020001.
Li L, Teng X M, Sheng L M, et al. 2014. Identification and ranging of reservoir boundary in horizontal well geo-steering. Petroleum Exploration and Development (in Chinese), 41(1): 108-111, doi: 10.11698/PED.2014.01.14.
Liang X, Xu Z Y, Zhang J H, et al. 2020. Key efficient exploration and development technologies of shallow shale gas: a case study of Taiyang anticline area of Zhaotong National Shale Gas Demonstration zone. Acta Petrolei Sinica (in Chinese), 41(9): 1033-1048.
Liang X, Shan C A, Jiang P, et al. 2021. Geology and engineering integration application in the whole life cycle of shallow shale gas wells. Journal of Southwest Petroleum University (Science & Technology Edition) (in Chinese), 43(5): 1-18.
Liu G D. 2002. The second round of oil & gas exploration of China. Marine Geology Letters (in Chinese), 18(11): 1-3.
Love A, Rabinovich M, Sayer Z, et al. 2018. Skewering the pancake: Geosteering challenges in a thinly bedded sandstone reservoir. //SPWLA 59th Annual Logging Symposium. London, UK: SPWLA.
Mahiout M S, Al Enezi F N, Santoso G I, et al. 2022. Artificial-intelligence-based well placement look ahead concept. //ADIPEC. Abu Dhabi, UAE: SPE, doi:
10.2118/211752-MS .Mukanov Y, Chzhen I, Tagirov A, et al. 2022. Geosteering a well in considerable structural and stratigraphic uncertainties environment, a case study from Kazakhstan. //SPE Annual Caspian Technical Conference. Nur-Sultan, Kazakhstan: SPE, doi:
10.2118/212081-MS .Ndokwu C N, Amadi K, Okowi V, et al. 2021. The synergy between borehole imaging and geosteering. //SPE Nigeria Annual International Conference and Exhibition. Lagos, Nigeria: SPE.
Ribeiro M T, da Costa V L F, Bomfim R A G, et al. 2011. Integrated petrophysics and geosteering reservoir characterization in the initial development phase of a carbonate reservoir-Campos Basin, Offshore Brazil. //OTC Brasil. Rio de Janeiro, Brazil: SPE.
Shao C R, Zhang P F, Ji J Q, et al. 2022. Identifying the carbonate interlayer using the horn response of electromagnetic wave resistivity logging while drilling combined with drilling and mud-logging data during geo-steering. Journal of Geophysics and Engineering, 19(4): 807-819. doi: 10.1093/jge/gxac054
Su Y N. 2005. Geosteering drilling technology and its development in China. Petroleum Exploration and Development (in Chinese), 32(1): 92-95.
Tian F, Jin Q, Lu X B, et al. 2016. Multi-layered Ordovician paleokarst reservoir detection and spatial delineation: A case study in the Tahe Oilfield, Tarim Basin, Western China. Marine and Petroleum Geology, 69: 53-73. doi: 10.1016/j.marpetgeo.2015.10.015
Tian F, Di Q Y, Jin Q, et al. 2019a. Multiscale geological-geophysical characterization of the epigenic origin and deeply buried paleokarst system in Tahe Oilfield, Tarim Basin. Marine and Petroleum Geology, 102: 16-32. doi: 10.1016/j.marpetgeo.2018.12.029
Tian F, Luo X R, Zhang W. 2019b. Integrated geological-geophysical characterizations of deeply buried fractured-vuggy carbonate reservoirs in Ordovician strata, Tarim Basin. Marine and Petroleum Geology, 99: 292-309. doi: 10.1016/j.marpetgeo.2018.10.028
Tian F, Wang Z X, Cheng F Q, et al. 2019c. Three-dimensional geophysical characterization of deeply buried paleokarst system in the Tahe oilfield, Tarim Basin, China. Water, 11(5): 1045, doi: 10.3390/w11051045.
Toader L, Bimastianto P A, Khambete S P, et al. 2021. Automated drilling variances detection through smart alarms system. //Abu Dhabi International Petroleum Exhibition & Conference. Abu Dhabi, UAE: SPE.
Wang M S, Guang X J. 2020. Status and development trends of intelligent drilling technology. Acta Petrolei Sinica (in Chinese), 41(4): 505-512, doi: 10.7623/syxb202004013.
Wiig M, Berg E, Kjærefjord J M, et al. 2005. Geosteering using new directional electromagnetic measurements and a 3D rotary steerable system on the Veslefrikk Field, North Sea. //SPE Annual Technical Conference and Exhibition. Dallas, Texas: SPE.
Wu Z G, Liang X, Dong J Y, et al. 2017. Application of 3D geosteering in geology-engineering integration practice. China Petroleum Exploration (in Chinese), 22(1): 89-98.
Wu Z G, Li H, Han Y J, et al. 2022. Effects of formation structure on directional electromagnetic logging while drilling measurements. Journal of Petroleum Science and Engineering, 211: 110118, doi: 10.1016/j.petrol.2022.110118.
Zhang J W, Wang G Y, He K, et al. 2019. Practice and understanding of sidetracking horizontal drilling in old wells in Sulige Gas Field. Petroleum Exploration and Development (in Chinese), 46(2): 370-377, doi: 10.11698/PED.2019.02.17.
Zhang Q S, Zhang W. 2022. An efficient diffraction stacking interferometric imaging location method for microseismic events. Geophysics, 87(3): KS73-KS82. doi: 10.1190/geo2021-0233.1
Zhang T, Li X F, Wang X Z, et al. 2018. Efficient mobilization method of stereoscopic well pattern in low-permeability complex superimposed tight reservoir: a case study of Yan'an gasfield. Acta Petrolei Sinica (in Chinese), 39(11): 1279-1291, doi: 10.7623/syxb201811008.
Zhao Y, Cheng Z G, Zhang S D, et al. 2021. Fine Description and application for reservoir with large well cluster based on logging data. Well Logging Technology (in Chinese), 45(2): 143-148, doi: 10.16489/j.issn.1004-1338.2021.02.006.
Zheng W H, Tian F, Di Q Y, et al. 2021. Electrofacies classification of deeply buried carbonate strata using machine learning methods: A case study on Ordovician paleokarst reservoirs in Tarim Basin. Marine and Petroleum Geology, 123: 104720, doi: 10.1016/j.marpetgeo.2020.104720.
Zhu D D, Dai X P, Liu Y, et al. 2022. Deep learning approach of drilling decision for subhorizontal drain geosteering based on APC-LSTM model. SPE Drilling & Completion, 38(1): 1-17, doi: 10.2118/210605-PA.
洪迪峰, 唐雪平, 高文凯等. 2021. 圆弧型井眼轨道设计模型的综合求解法. 石油学报, 42(2): 226-232. https://www.cnki.com.cn/Article/CJFDTOTAL-SYXB202102007.htm
贾承造. 2021. 中国石油工业上游发展面临的挑战与未来科技攻关方向. 石油学报, 41(12): 1445-1464, doi: 10.7623/syxb202012001.
贾佳, 夏忠跃, 冯雷等. 2022. 鄂尔多斯临兴区块地质工程一体化技术创新与实践. 石油地质与工程, 36(2): 101-105, 112. https://www.cnki.com.cn/Article/CJFDTOTAL-SYHN202202018.htm
匡立春, 刘合, 任义丽等. 2021. 人工智能在石油勘探开发领域的应用现状与发展趋势. 石油勘探与开发, 48(1): 1-11, doi: 10.11698/PED.2021.01.01.
李根生, 宋先知, 田守嶒. 2020. 智能钻井技术研究现状及发展趋势. 石油钻探技术, 48(1): 1-8, doi: 10.11911/syztjs.2020001.
李林, 滕鑫淼, 盛利民等. 2014. 水平井地质导向中储集层边界识别与测距. 石油勘探与开发, 41(1): 108-111, doi: 10.11698/PED.2014.01.14.
梁兴, 徐政语, 张介辉等. 2020. 浅层页岩气高效勘探开发关键技术——以昭通国家级页岩气示范区太阳背斜区为例. 石油学报, 41(9): 1033-1048. https://www.cnki.com.cn/Article/CJFDTOTAL-SYXB202009003.htm
梁兴, 单长安, 蒋佩等. 2021. 浅层页岩气井全生命周期地质工程一体化应用. 西南石油大学学报(自然科学版), 43(5): 1-18. https://www.cnki.com.cn/Article/CJFDTOTAL-XNSY202105003.htm
刘光鼎. 2002. 论中国油气二次创业. 海洋地质动态, 18(11): 1-3. https://www.cnki.com.cn/Article/CJFDTOTAL-HYDT200211002.htm
苏义脑. 2005. 地质导向钻井技术概况及其在我国的研究进展. 石油勘探与开发, 32(1): 92-95. https://www.cnki.com.cn/Article/CJFDTOTAL-SKYK200501027.htm
王敏生, 光新军. 2020. 智能钻井技术现状与发展方向. 石油学报, 41(4): 505-512, doi: 10.7623/syxb202004013.
吴宗国, 梁兴, 董健毅等. 2017. 三维地质导向在地质工程一体化实践中的应用. 中国石油勘探, 22(1): 89-98. https://www.cnki.com.cn/Article/CJFDTOTAL-KTSY201701011.htm
张金武, 王国勇, 何凯等. 2019. 苏里格气田老井侧钻水平井开发技术实践与认识. 石油勘探与开发, 46(2): 370-377, doi: 10.11698/PED.2019.02.17.
张涛, 李相方, 王香增等. 2018. 低渗致密复杂叠置储层组合立体井网高效动用方法——以延安气田为例. 石油学报, 39(11): 1279-1291, doi: 10.7623/syxb201811008.
赵毅, 成志刚, 张树东等. 2021. 大井丛测井油藏精细描述与应用. 测井技术, 45(2): 143-148, doi: 10.16489/j.issn.1004-1338.2021.02.006.
-
图(11)
表(3)
计量
- 文章访问数: 2565
- PDF下载数: 305
- 施引文献: 0