在传统的数值模拟及优化算法基础上,结合分层注采实时监测与自动控制工艺技术所监测的“硬数据”,提出了一套大数据驱动下的精细注水方案优化方法。首先在动态观测数据的约束下,通过数据同化算法实现地质模型参数的自动拟合;根据分层注采流动关系自动识别方法计算区块分层注采井间的流动关系;采用多层多向产量劈分技术计算采油井分层分方向的产液量与产油量,量化注水效果指标;进一步通过机器学习算法评价多井分层的注水效果、分析注水调整方向;通过智能优化算法求解最优注水调整方案,进行产量预测。该方法和流程充分利用了数据驱动和机器学习算法的自动化、智能化优势,应用于中国东部某复杂断块油藏,数据模拟的拟合率可达85%,示例区块优化后12个月内的累计产油量与未优化时相比增加8.2%,能够精准指导老油田精细注水方案的设计和实施。图13表2参16
贾德利
,
刘合
,
张吉群
,
龚斌
,
裴晓含
,
王全宾
,
杨清海
. 大数据驱动下的老油田精细注水优化方法[J]. 石油勘探与开发, 2020
, 47(3)
: 629
-636
.
DOI: 10.11698/PED.2020.03.19
Based on the traditional numerical simulation and optimization algorithms, in combination with the layered injection and production "hard data" monitored at real time by automatic control technology, a systematic approach for detailed water injection design using data-driven algorithms is proposed. First the data assimilation technology is used to match geological model parameters under the constraint of observed well dynamics; the flow relationships between injectors and producers in the block are worked out based on automatic identification method for layered injection-production flow relationship; multi-layer and multi-direction production splitting technique is used to calculate the liquid and oil production of producers in different layers and directions and obtain quantified indexes of water injection effect. Then, machine learning algorithms are adopted to evaluate the effectiveness of water injection in different layers of wells and find out the direction of water injection adjustment. Finally, the particle swarm algorithm is used to optimize the detailed water injection plan and predict production. This method and procedure make full use of the automation and intelligence of data-driven and machine learning algorithms. This method was used to match the data of a complex fault block reservoir in eastern China, achieving a fitting rate of 85%. The cumulative oil production in the example block for 12 months after optimization is 8.2% higher than before. This method can help design detailed water injection program for mature oilfields.
[1] 黄昌武. 2012年中国石油十大科技进展[J]. 石油勘探与开发, 2013, 40(2): 208.
HUANG Changwu.The 10 great advances of petroleum science and technology of CNPC in 2012[J]. Petroleum Exploration and Development, 2013, 40(2): 208.
[2] 刘合, 裴晓含, 罗凯, 等. 中国油气田开发分层注水工艺技术现状与发展趋势[J]. 石油勘探与开发, 2013, 40(6): 733-737.
LIU He, PEI Xiaohan, LUO Kai, et al.Current status and trend of separated layer water flooding in China[J]. Petroleum Exploration and Development, 2013, 40(6): 733-737.
[3] 杨国庆, 侯宪文, 刘玉龙. 萨北油田注水工艺技术发展方向及评价[J]. 大庆石油地质与开发, 2006, 25(s1): 51-53.
YANG Guoqing, HOU Xianwen, LIU Yulong.Development and evaluation of water injection technology in north Saertu oilfield[J]. Petroleum Geology & Oilfield Development in Daqing, 2006, 25(s1): 51-53.
[4] 谭文斌. 油田注水开发的决策部署研究[M]. 北京: 石油工业出版社, 2000.
TAN Wenbin.Decisions and arrangements of oilfield water-injection development[M]. Beijing: Petroleum Industry Press, 2000.
[5] 宋新民, 李勇. 中东碳酸盐岩油藏注水开发思路与对策[J]. 石油勘探与开发, 2018, 45(4): 679-689.
SONG Xinmin, LI Yong.Optimum development options and strategies for water injection development of carbonate reservoirs in the Middle East[J]. Petroleum Exploration and Development, 2018, 45(4): 679-689.
[6] 吴奇. 提高注水开发效果工艺配套技术文集[M]. 北京: 中国石化出版社, 2010.
WU Qi.Matching technology for improving the effect of water injection[M]. Beijing: China Petrochemical Press, 2010.
[7] 刚振宝, 卫秀芬. 大庆油田机械分层注水技术回顾与展望[J]. 特种油气藏, 2006, 13(5): 4-9.
GANG Zhenbao, WEI Xiufen.Review and outlook of separate layer water injection technology in Daqing[J]. Special Oil & Gas Reservoirs, 2006, 13(5): 4-9.
[8] 王玉普, 王广昀, 王林, 等. 大庆油田高含水期注采工艺技术[M]. 北京: 石油工业出版社, 2001.
WANG Yupu, WANG Guangyun, WANG Lin, et al.Injection production technology in high water cut stage in Daqing Oilfield[M]. Beijing: Petroleum Industry Press, 2001.
[9] 刘合, 裴晓含, 贾德利, 等. 第四代分层注水技术内涵、应用与展望[J]. 石油勘探与开发, 2017, 44(4): 608-614.
LIU He, PEI Xiaohan, JIA Deli, et al.Connotation, application and prospect of the fourth-generation separated layer water injection technology[J]. Petroleum Exploration and Development, 2017, 44(4): 608-614.
[10] 贾德利, 王凤山, 徐建, 等. 变论域自适应模糊的分层注水工艺控制[J]. 电机与控制学报, 2012, 16(2): 66-70.
JIA Deli, WANG Fengshan, XU Jian, et al.Variable-universe adaptive fuzzy control of layered water injection technique[J]. Electric Machines and Control, 2012, 16(2): 66-70.
[11] 贾德利, 于泳, 陈召, 等. 分层注水工艺中涡街流量计信号处理方法研究[J]. 传感技术学报, 2015, 28(10): 1513-1519.
JIA Deli, YU Yong, CHEN Zhao, et al.Research on processing methods of vortex flowmeter signal processing in layered water injection technology[J]. Chinese Journal of Sensors and Actuators, 2015, 28(10): 1513-1519.
[12] 王洪亮, 穆龙新, 时付更, 等. 分散存储油气生产动态大数据的优化管理与快速查询[J]. 石油勘探与开发, 2019, 46(5): 959-965.
WANG Hongliang, MU Longxin, SHI Fugeng, et al.Management and instant query of distributed oil and gas production dynamic data[J]. Petroleum Exploration and Development, 2019, 46(5): 959-965.
[13] NEJADI S, LEUNG J, TRIVEDI J.Characterization of non-Gaussian geologic facies distribution using ensemble Kalman filter with probability weighted re-sampling[J]. Mathematical Geosciences, 2015, 47(2): 193-225.
[14] ZHANG Jiqun, HU Chungjin, DENG Baorong, et al.The application of computational geometry algorithms in discriminating direct injection-production connections[C]//International Conference on Materials Engineering and Information Technology Applications (MEITA 2015). Paris: Atlantis Press, 2015: 635-642.
[15] DENG B, ZHANG J, CHANG J, et al.A new production splitting method based on discrimination of injection-production relation[C]//Proceedings of the International Field Exploration and Development Conference 2017. Singapore: Springer, 2017: 303-315.
[16] KENNEDY J, EBERHART R.Particle swarm optimization[R]. Perth, Australia: IEEE International Conference on Neural Networks, 1995.
