[1]王文东,石梦翮,庄新宇,等.基于机器学习的井位及注采参数联合优化方法[J].深圳大学学报理工版,2022,39(2):126-133.[doi:10.3724/SP.J.1249.2022.02126]
 WANG Wendong,SHI Menghe,ZHUANG Xinyu,et al.Joint optimization method of well location and injection-production parameters based on machine learning[J].Journal of Shenzhen University Science and Engineering,2022,39(2):126-133.[doi:10.3724/SP.J.1249.2022.02126]
点击复制

基于机器学习的井位及注采参数联合优化方法()
分享到:

《深圳大学学报理工版》[ISSN:1000-2618/CN:44-1401/N]

卷:
第39卷
期数:
2022年第2期
页码:
126-133
栏目:
环境与能源
出版日期:
2022-03-15

文章信息/Info

Title:
Joint optimization method of well location and injection-production parameters based on machine learning
文章编号:
202202003
作者:
王文东1 石梦翮1 庄新宇1 卜亚辉2 苏玉亮1
1)中国石油大学(华东)非常规油气开发教育部重点实验室,中国石油大学(华东)石油工程学院,山东青岛 266580
2)中石化胜利油田勘探开发研究院,山东东营 257015
Author(s):
WANG Wendong1SHI Menghe1ZHUANG Xinyu1BU Yahui2 and SU Yuliang1
1) Key Laboratory of Unconventional Oil & Gas Development, Ministry of Education, School of Petroleum Engineering, China University of Petroleum (East China), Qingdao 266580, Shandong Province, P. R. China
2) Sinopec Shengli Oilfield Exploration and Development Research Institute, Dongying 257015, Shandong Province, P. R. China
关键词:
油田开发 水驱油藏 注采井网 机器学习 智能优化 代理模型 随机森林 径向基神经网络
Keywords:
oilfield development water-flooding reservoir injection-production well pattern machine learning intelligent optimization proxy model random forest radial basis function neural network
分类号:
TE341;TE324
DOI:
10.3724/SP.J.1249.2022.02126
文献标志码:
A
摘要:
针对水驱油藏传统优化方法过于依赖人为经验及顺序优化难以求得全局最优解等问题,提出一种基于机器学习的井位及注采参数联合优化方法.基于水驱油藏特征,利用随机森林算法筛选影响注水开发效果的主控因素,以井网形式、产量和注采比等作为输入参数,累计产油量为输出参数,通过流线数值模拟方法构建机器学习预测样本集,综合径向基函数神经网络预测水驱开发效果.基于粒子群算法建立优化数学模型,以最大化产油量作为目标对井网形式和注采参数进行联合优化求解.结果表明,与传统优化方法相比,联合优化方法能够自动同步优化井网形式、井位和注采比等参数,优化后开发效果提升约12%,为水驱油藏的智能高效开发奠定基础.
Abstract:
To solve the problems of excessive reliance on human experience in traditional optimization methods and difficulty in obtaining the global optimal solution for sequence optimization in water-flooding reservoirs, we propose a joint optimization method of well location and injection-production parameters based on machine learning theory. Firstly, based on the characteristics of the water-flooding reservoir, the random forest algorithm is used to screen the main controlling factors affecting the oil production effect of water flooding. Then, taking well pattern form, production, injection-production ratio, etc. as input parameters, the cumulative oil production as the model output parameters, the machine learning prediction sample set is constructed through streamline numerical simulation method, and the comprehensive radial basis function (RBF) neural network is utilized to predict the development effect of water flooding. Finally, the particle swarm optimizer algorithm is applied for the joint optimization for well pattern and injection-production parameters by maximizing oil production as the optimization goal. Results show that compared with the traditional optimization methods, the new joint optimization method could automatically and synchronously optimize parameters, including well pattern form, well position, injection-production ratio, etc. The optimization scheme is better than the original ones. The water flooding performance is improved by about 12% using the new optimization method, laying a solid foundation for the intelligent and efficient development of water flooding reservoirs.

参考文献/References:

[1] 王相.水驱油田井网及注采优化方法研究[D].青岛:中国石油大学(华东),2016.
WANG Xiang. Well placement and production optimization well placement and production optimization for water-flooding oil fields [D]. Qingdao: China University of Petroleum (East China), 2016.(in Chinese)
[2] 袁向春,杨凤波.高含水期注采井网的重组调整[J].石油勘探与开发,2003,30(5):94-96.
YUAN Xiangchun, YANG Fengbo. Regrouping adjusting of the producer-injector well-pattern in the high aquifer period of oilfield development [J]. Petroleum Exploration and Development, 2003, 30(5): 94-96.(in Chinese)
[3] 曹仁义,程林松,薛永超,等.低渗透油藏井网优化调整研究[J].西南石油大学学报,2007,29(4):67-69.
CAO Renyi, CHENG Linsong, XUE Yongchao, et al.Well pattern optimization adjustment for low permeability oilfield [J]. Journal of Southwest Petroleum University, 2007, 29(4): 67-69.(in Chinese)
[4] 孙致学,苏玉亮,聂海峰,等.基于生产潜力的深水油田井位优化方法及应用[J].断块油气田,2013, 20(4):473-476.
SUN Zhixue, SU Yuliang, NIE Haifeng, et al.Method and application of well location optimization in deepwater oilfield based on productivity potential [J]. Fault-Block Oil and Gas Field, 2013, 20(4): 473-476.(in Chinese)
[5] WANG Chunhong, LI Gaoming, REYNOLDS A C. Optimal well placement for production optimization [C]// Proceedings of the Eastern Regional Meeting. Lexington, USA: Society of Petroleum Engineers, 2007: SPE-111154-MS. doi:10.2118/111154-MS
[6] 姜瑞忠,刘明明,徐建春,等.遗传算法在苏里格气田井位优化中的应用[J].天然气地球科学,2014,25(10):1603-1609.
JIANG Ruizhong, LIU Mingming, XU Jianchun, et al. Application of genetic algorithm for well placement optimization in Sulige Gasfield [J]. Natural Gas Geoscience,2014, 25(10): 1603-1609.(in Chinese)
[7] 张凯,姚军,张黎明,等.水驱高效开发注采策略优化[J].系统工程理论与实践,2010,30(8):1506-1513.
ZHANG Kai, YAO Jun, ZHANG Liming, et al. Injection-production strategies optimization for efficient development of water flooding [J]. Systems Engineering-Theory & Practice, 2010, 30(8): 1506-1513.(in Chinese)
[8] EMERICK A A, SILVA E, MESSER B, et al. Well placement optimization using a genetic algorithm with nonlinear constraints [C]// Proceedings of the SPE Reservoir Simulation Symposium. The Woodlands, USA: Society of Petroleum Engineers, 2009: SPE-118808-MS. doi: 10.2118/118808-MS
[9] 冯其红,王波,王相,等.基于油藏流场强度的井网优化方法研究[J].西南石油大学学报自然科学版,2015,37(4):181-186.
FENG Qihong, WANG Bo, WANG Xiang, et al. Optimization of well patterns based on flow field intensity [J]. Journal of Southwest Petroleum University Science & Technology Edition, 2015, 37(4): 181-186.(in Chinese)
[10] BELLOUT M C, ECHEVERR?A CIAURRI D, DURLOFSKY L J, et al. Joint optimization of oil well placement and controls [J]. Computational Geosciences, 2012, 16(4): 1061-1079.
[11] HUMPHRIES T D, HAYNES R D, JAMES L A.Simultaneous and sequential approaches to joint optimization of well placement and control [J]. Computational Geosciences,2014, 18(3): 433-448.
[12] 刘巍,刘威,谷建伟.基于机器学习方法的油井日产油量预测[J].石油钻采工艺,2020,42(1):70-75.
LIU Wei, LIU Wei, GU Jianwei.Oil production prediction based on a machine learning method [J]. Oil Drilling & Production Technology, 2020, 42(1): 70-75.(in Chinese)
[13] 马俊修,石胜男,陈进,等.基于机器学习的玛湖地区水平井压裂设计优化[J].深圳大学学报理工版,2021,38(6):621-627.
MA Junxiu, SHI Shengnan, CHEN Jin, et al. Optimization of fracture design for horizontal wells in Mahu region based on machine learning [J]. Journal of Shenzhen University Science and Engineering, 2021, 38(6): 621-627.(in Chinese)
[14] EBERHART R, KENNEDY J. A new optimizer using particle swarm theory [C]// MHS’95. Proceedings of the Sixth International Symposium on Micro Machine and Human Science. Nagoya, Japan: IEEE. 1995: 5297172. doi: 10.1109/MHS.1995.494215
[15] SHAO Wei, CHEN Songhua, CHENG Yuesheng, et al. Improved RBF-based NMR pore-throat size, pore typing, and permeability models for middle east carbonates [C]// SPE Annual Technical Conference and Exhibition. Dubai, UAE: Society of Petroleum Engineers, 2016: SPE-181448-MS. doi: 10.2118/181448-MS
[16] NWACHUKWU A, JEONG H, SUN A, et al. Machine learning-based optimization of well locations and WAG parameters under geologic uncertainty [C]// SPE Improved Oil Recovery Conference. Tulsa, USA: Society of Petroleum Engineers, 2018:1-18. doi: 10.2118/190239-MS
[17] 杨旭.基于RBF神经网络的工业过程建模与优化研究[D].哈尔滨:哈尔滨理工大学,2009.
YANG Xu. Research on industry process modeling and optimization based on RBF neural network [D].Harbin: Harbin University of Science and Technology, 2009.(in Chinese)

相似文献/References:

[1]陈民锋,赵晶,赵梦盼,等.低渗透稠油油藏储量有效动用界限研究[J].深圳大学学报理工版,2013,30(No.2(111-220)):210.[doi:10.3724/SP.J.1249.2013.02210]
 Chen Minfeng,Zhao Jing,Zhao Mengpan,et al.Study on limits of effective drive in low-permeability heavy-oil reservoirs[J].Journal of Shenzhen University Science and Engineering,2013,30(2):210.[doi:10.3724/SP.J.1249.2013.02210]
[2]陈民锋,李晓风,王敏,等.深水油田高饱和油藏能量合理补充时机研究[J].深圳大学学报理工版,2013,30(No.6(551-660)):649.[doi:10.3724/SP.J.1249.2013.06649]
 Chen Minfeng,Li Xiaofeng,Wang Min,et al.Reasonable opportune moment of energy supplement of high saturation reservoirs in deepwater oilfield[J].Journal of Shenzhen University Science and Engineering,2013,30(2):649.[doi:10.3724/SP.J.1249.2013.06649]
[3]廉培庆,陈志海,董广为,等.水平井与非均质盒式油藏耦合模型[J].深圳大学学报理工版,2015,32(3):266.[doi:10.3724/SP.J.1249.2015.03266]
 Lian Peiqing,Chen Zhihai,Dong Guangwei,et al.A coupling model for horizontal well in heterogeneous box-shaped reservoir[J].Journal of Shenzhen University Science and Engineering,2015,32(2):266.[doi:10.3724/SP.J.1249.2015.03266]
[4]李帅,丁云宏,刘广峰,等.致密储层体积改造润湿反转提高采收率的研究[J].深圳大学学报理工版,2017,34(1):98.[doi:10.3724/SP.J.1249.2017.01098]
 Li Shuai,Ding Yunhong,Liu Guangfeng,et al.Enhancing oil recovery by wettability alteration during fracturing in tight reservoirs[J].Journal of Shenzhen University Science and Engineering,2017,34(2):98.[doi:10.3724/SP.J.1249.2017.01098]
[5]陈民锋,王兆琪,张琪琛,等.启动压力影响下注采井间有效驱替规律[J].深圳大学学报理工版,2017,34(1):91.[doi:10.3724/SP.J.1249.2017.01091]
 Chen Minfeng,Wang Zhaoqi,Zhang Qichen,et al.Effective displacement rules for interwell with threshold pressure[J].Journal of Shenzhen University Science and Engineering,2017,34(2):91.[doi:10.3724/SP.J.1249.2017.01091]
[6]张贤松,谢晓庆,康晓东,等.非均质油藏聚合物驱注入参数优化方法改进与应用[J].深圳大学学报理工版,2018,35(4):362.[doi:10.3724/SP.J.1249.2018.04362]
 ZHANG Xiansong,XIE Xiaoqing,KANG Xiaodong,et al.An improved optimization method and application for injection parameter of polymer flooding for heterogeneous reservoir[J].Journal of Shenzhen University Science and Engineering,2018,35(2):362.[doi:10.3724/SP.J.1249.2018.04362]
[7]张继成,范佳乐,匡力,等.一种预测特高含水期开发指标的联解法[J].深圳大学学报理工版,2018,35(6):558.[doi:10.3724/SP.J.1249.2018.06574]
 ZHANG Jicheng,FAN Jiale,KUANG Li,et al.An integrated method for predicting the development index of extra-high water cut period[J].Journal of Shenzhen University Science and Engineering,2018,35(2):558.[doi:10.3724/SP.J.1249.2018.06574]
[8]苏泽中,林加恩,柏明星,等.天然能量开发阶段的缝洞型油藏井间连通性分析[J].深圳大学学报理工版,2020,37(6):645.[doi:10.3724/SP.J.1249.2020.06645]
 SU Zezhong,LIN Jiaen,BAI Mingxing,et al.Inter-well connectivity analysis in carbonate fracture-vuggy reservoir in natural energy development stage[J].Journal of Shenzhen University Science and Engineering,2020,37(2):645.[doi:10.3724/SP.J.1249.2020.06645]
[9]刘旭鹏,袁彬,戴彩丽,等.低渗油藏活性纳米颗粒减阻增注解析模拟方法[J].深圳大学学报理工版,2021,38(6):563.[doi:10.3724/SP.J.1249.2021.06563]
 LIU Xupeng,YUAN Bin,,et al.A novel analytical simulation method of utilization of surfactant-active nanoparticles for well injection enhancement in low-permeability reservoirs[J].Journal of Shenzhen University Science and Engineering,2021,38(2):563.[doi:10.3724/SP.J.1249.2021.06563]
[10]毛新军,胡广文,张晓文,等.双重介质致密油藏油水两相瞬态流动模拟方法[J].深圳大学学报理工版,2021,38(6):572.[doi:10.3724/SP.J.1249.2021.06572]
 MAO Xinjun,HU Guangwen,ZHANG Xiaowen,et al.Simulation method of oil-water two-phase transient flow in dual-porosity system in tight reservoir[J].Journal of Shenzhen University Science and Engineering,2021,38(2):572.[doi:10.3724/SP.J.1249.2021.06572]

备注/Memo

备注/Memo:
Received: 2021-10-18;Accepted: 2021-12-03; Online (CNKI): 2022-01-24
Foundation: National Natural Science Foundation of China (51804328); The National Science and Technology Major Project of CNPC (ZD2019-183-007)
Corresponding author: Associate professor WANG Wendong. E-mail: wwdong@upc.edu.cn
Citation: WANG Wendong,SHI Menghe,ZHUANG Xinyu, et al.Joint optimization method of well location and injection-production parameters based on machine learning [J]. Journal of Shenzhen University Science and Engineering, 2022, 39(2): 126-133.(in Chinese)
基金项目:国家自然科学基金资助项目(51804328);中国石油天然气集团有限公司重大科技项目(ZD2019-183-007)
作者简介:王文东(1986 —),中国石油大学(华东)副教授、博士.研究方向:水驱提高采收率和非常规地质资源开发等.E-mail: wwdong@upc.edu.cn
引 文:王文东,石梦翮,庄新宇,等.基于机器学习的井位及注采参数联合优化方法[J].深圳大学学报理工版,2022,39(2):126-133.
更新日期/Last Update: 2022-03-30