注水开发油田注水通道状态辨识及预测方法

doi:10.7623/syxb202108009

石油学报 ›› 2021, Vol. 42 ›› Issue (8): 1081-1090.DOI: 10.7623/syxb202108009

注水开发油田注水通道状态辨识及预测方法

赵艳红^1,2,3, 姜汉桥¹, 李洪奇^2,3

1. 中国石油大学(北京)石油工程学院北京 102249;
2. 石油数据挖掘北京市重点实验室北京 102249;
3. 中国石油大学(北京)人工智能学院北京 102249

收稿日期:2021-01-08 修回日期:2021-06-06 出版日期:2021-08-25 发布日期:2021-08-31
通讯作者: 赵艳红,女,1986年1月生,2009年获中国石油大学(北京)学士学位,2016年获中国石油大学(北京)博士学位,现为中国石油大学(北京)石油与天然气工程学院博士后,主要从事石油数据智能化分析与挖掘技术研究等。
作者简介:赵艳红,女,1986年1月生,2009年获中国石油大学(北京)学士学位,2016年获中国石油大学(北京)博士学位,现为中国石油大学(北京)石油与天然气工程学院博士后,主要从事石油数据智能化分析与挖掘技术研究等。Email:yh_zhao@126.com
基金资助:
国家自然科学基金项目"复杂油气藏核磁共振测井新理论与新方法研究"（No.41130417）资助。

Identification and predictions of water injectivity for water injection channels in water injection development oilfield

Zhao Yanhong^1,2,3, Jiang Hanqiao¹, Li Hongqi^2,3

1. College of Petroleum Engineering, China University of Petroleum, Beijing 102249, China;
2. Beijing Key Laboratory of Petroleum Data Mining, Beijing 102249, China;
3. College of Artificial Intellectual, China University of Petroleum, Beijing 102249, China

Received:2021-01-08 Revised:2021-06-06 Online:2021-08-25 Published:2021-08-31

摘要/Abstract

摘要： 为研究注水开发油田注水通道的状态，通过将油田动、静态数据分析与机器学习算法相结合，提出了一种基于油田勘探开发动、静态数据进行注水井地层吸水状态预测的新方法。首先利用高斯混合模型完成地层吸水状态分类；然后结合动、静态数据生成机器学习样本，采用随机森林算法构建地层吸水状态预测模型，并对影响地层吸水状态的地质因素和开发因素进行重要性分析；最后将模型应用于研究工区，给出了所有井、不同层段、不同时期的吸水状态。实际应用表明，预测结果与示踪剂监测结果、吸水剖面测试结果一致，验证了该方法的可行性。该方法克服了理想条件假设、经验假设、参数假设等与实际状况不符等问题，提出了面向历史数据挖掘注水井地层吸水状态的新模式，对注水开发油田调剖堵水具有一定指导意义。

关键词: 大孔道, 地层吸水状态预测, 高斯混合模型, 随机森林, 样本均衡化

Abstract: This paper presents a new method for predicting water injectivity of the well formation based on dynamic and static data of oilfield exploration and development. Initially, the water injectivity was classified using Gaussian Mixture Model (GMM). On this basis, machine learning samples were generated using dynamic and static data, and further a prediction model of water injectivity was established using the random forest algorithm. Moreover, the importance of geological factors and development factors affecting water injectivity was also analyzed. Finally, the model has been applied to the study area, providing the water injectivity of all wells in different sections and different periods. The predicted results are consistent with the tracer monitoring results and the water absorption profile test results, thus verifying the feasibility of the method proposed in this study. The method overcomes the disadvantages of traditional methods, such as the hypotheses of ideal conditions, experience and parameters, and explores the water injectivity by historical data mining. It has an important guiding significance for profile control and water plugging in water injection development oilfield.

Key words: high capacity channel, prediction for water injectivity of well formations, Gaussian mixture model, random forest, sample equalization

中图分类号:

TE312

赵艳红, 姜汉桥, 李洪奇. 注水开发油田注水通道状态辨识及预测方法[J]. 石油学报, 2021, 42(8): 1081-1090.

Zhao Yanhong, Jiang Hanqiao, Li Hongqi. Identification and predictions of water injectivity for water injection channels in water injection development oilfield[J]. Acta Petrolei Sinica, 2021, 42(8): 1081-1090.

参考文献

[1] 周丽清, 熊琦华, 吴胜和.大孔道诊断和描述技术研究[J].石油勘探与开发, 2001, 28(1):75-77.
ZHOU Liqing, XIONG Qihua, WU Shenghe.Research on the diagnosis and description of wormhole[J].Petroleum Exploration and Development, 2001, 28(1):75-77.
[2] 彭仕宓, 史彦尧, 韩涛, 等.油田高含水期窜流通道定量描述方法[J].石油学报, 2007, 28(5):79-84.
PENG Shimi, SHI Yanyao, HAN Tao, et al.A quantitative description method for channeling-path of reservoirs during high water cut period[J].Acta Petrolei Sinica, 2007, 28(5):79-84.
[3] 冯其红, 齐俊罗, 尹晓梅, 等.大孔道形成与演化过程流固耦合模拟[J].石油勘探与开发, 2009, 36(4):498-502.
FENG Qihong, QI Junluo, YIN Xiaomei, et al.Simulation of fluid-solid coupling during Formation and evolution of high-permeability channels[J].Petroleum Exploration and Development, 2009, 36(4):498-502.
[4] 林承焰, 孙廷彬, 董春梅, 等.基于单砂体的特高含水期剩余油精细表征[J].石油学报, 2013, 34(6):1131-1136.
LIN Chengyan, SUN Tingbin, DONG Chunmei, et al.Fine characterization of remaining oil based on a single sand body in the high water cut period[J].Acta Petrolei Sinica, 2013, 34(6):1131-1136.
[5] 商晓飞, 侯加根, 孙福亭, 等.砂质滩坝储集层内部结构特征及构型模式——以黄骅坳陷板桥油田古近系沙河街组为例[J].石油学报, 2014, 35(6):1160-1171.
SHANG Xiaofei, HOU Jiagen, SUN Futing, et al.Architectural characteristics and sedimentary models of beach-bar sandstone reservoirs:a case study of the Paleogene Shahejie Formation in Banqiao oilfield, Huanghua depression[J].Acta Petrolei Sinica, 2014, 35(6):1160-1171.
[6] 崔传智, 李松, 杨勇, 等.特高含水期油藏平面分区调控方法[J].石油学报, 2018, 39(10):1155-1161.
CUI Chuanzhi, LI Song, YANG Yong, et al.Planar zoning regulation and control method of reservoir at ultra-high water cut stage[J].Acta Petrolei Sinica, 2018, 39(10):1155-1161.
[7] 史有刚, 曾庆辉, 周晓俊.大孔道试井理论解释模型[J].石油钻采工艺, 2003, 25(3):48-50.
SHI Yougang, ZENG Qinghui, ZHOU Xiaojun.Interpreting model of large pore well testing theory[J].Oil Drilling & Production Technology, 2003, 25(3):48-50.
[8] 冯其红, 史树彬, 王森, 等.利用动态资料计算大孔道参数的方法[J].油气地质与采收率, 2011, 18(1):74-76.
FENG Qihong, SHI Shubin, WANG Sen, et al.Identification of thief zones based on dynamic data[J].Petroleum Geology and Recovery Efficiency, 2011, 18(1):74-76.
[9] YOUSEF A A, GENTIL P H, JENSEN J L, et al.A capacitance model to infer interwell connectivity from production and injection rate fluctuations[J].SPE Reservoir Evaluation & Engineering, 2006, 9(6):630-646.
[10] KARAMBEIGI M S, ZABIHI R, HEKMAT Z.Neuro-simulation modeling of chemical flooding[J].Journal of Petroleum Science and Engineering, 2011, 78(2):208-219.
[11] BHATTACHARYA S, MISHRA S.Applications of machine learning for facies and fracture prediction using Bayesian network theory and random forest:case studies from the Appalachian Basin, USA[J].Journal of Petroleum Science and Engineering, 2018, 170:1005-1017.
[12] AO Yile, LI Hongqi, ZHU Liping, et al.The linear random forest algorithm and its advantages in machine learning assisted logging regression modeling[J].Journal of Petroleum Science and Engineering, 2019, 174:776-789.
[13] XIANG Min, QIN Pengbo, ZHANG Fengwei.Research and application of logging lithology identification for igneous reservoirs based on deep learning[J].Journal of Applied Geophysics, 2020, 173:103929.
[14] DE OLIVEIRA L A B, DE CARVALHO CARNEIRO C.Synthetic geochemical well logs generation using ensemble machine learning techniques for the Brazilian pre-salt reservoirs[J].Journal of Petroleum Science and Engineering, 2021, 196:108080.
[15] ALZUBAIDI F, MOSTAGHIMI P, SWIETOJANSKI P, et al.Automated lithology classification from drill core images using convolutional neural networks[J].Journal of Petroleum Science and Engineering, 2021, 197:107933.
[16] 李大伟, 石广仁.油气勘探开发常用数据挖掘算法优选[J].石油学报, 2018, 39(2):240-246.
LI Dawei, SHI Guangren.Optimization of common data mining algorithms for petroleum exploration and development[J].Acta Petrolei Sinica, 2018, 39(2):240-246.
[17] 杨笑, 王志章, 周子勇, 等.基于参数优化AdaBoost算法的酸性火山岩岩性分类[J].石油学报, 2019, 40(4):457-467.
YANG Xiao, WANG Zhizhang, ZHOU Ziyong, et al.Lithology classification of acidic volcanic rocks based on parameter-optimized AdaBoost algorithm[J].Acta Petrolei Sinica, 2019, 40(4):457-467.
[18] DJURAEV U, JUFAR S R, VASANT P.A review on conceptual and practical oil and gas reservoir monitoring methods[J].Journal of Petroleum Science and Engineering, 2017, 152:586-601.
[19] JIA Deli, LIU He, ZHANG Jiqun, et al.Data-driven optimization for fine water injection in a mature oil field[J].Petroleum Exploration and Development, 2020, 47(3):674-682.
[20] ANIFOWOSE F A, LABADIN J, ABDULRAHEEM A.Ensemble machine learning:an untapped modeling paradigm for petroleum reservoir characterization[J].Journal of Petroleum Science and Engineering, 2017, 151:480-487.
[21] ANIFOWOSE F, ABDULRAHEEM A, AL-SHUHAIL A.A parametric study of machine learning techniques in petroleum reservoir permeability prediction by integrating seismic attributes and wireline data[J].Journal of Petroleum Science and Engineering, 2019, 176:762-774.
[22] SONG Xuanyi, LIU Yuetian, XUE Liang, et al.Time-series well performance prediction based on long short-term memory (LSTM)neural network model[J].Journal of Petroleum Science and Engineering, 2020, 186:106682.
[23] 徐宝昌, 周家立, 刘伟, 等.基于数据驱动的钻井过程气侵工况预测方法[J].石油学报, 2019, 40(10):1263-1269.
XU Baochang, ZHOU Jiali, LIU Wei, et al.Data driven prediction method for gas cut in drilling process[J].Acta Petrolei Sinica, 2019, 40(10):1263-1269.
[24] 周斌, 王延江, 刘伟锋, 等.基于Hessian正则化支持向量机的多视角协同识别抽油机井工况方法[J].石油学报, 2018, 39(12):1429-1436.
ZHOU Bin, WANG Yanjiang, LIU Weifeng, et al.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.
[25] KHLAIFI H, ISTRATE D, DEMONGEOT J, et al.Swallowing sound recognition at home using GMM[J].IRBM, 2018, 39(6):407-412.
[26] VU T K, HOANG M K, LE H L.An EM algorithm for GMM parameter estimation in the presence of censored and dropped data with potential application for indoor positioning[J].ICT Express, 2019, 5(2):120-123.
[27] CHAWLA N V, BOWYER K W, HALL L O, et al.SMOTE:synthetic minority over-sampling technique[J].Journal of Artificial Intelligence Research, 2002, 16(1):321-357.
[28] 钟大康, 朱筱敏, 吴胜和, 等.注水开发油藏高含水期大孔道发育特征及控制因素——以胡状集油田胡12断块油藏为例[J].石油勘探与开发, 2007, 34(2):207-211.
ZHONG Dakang, ZHU Xiaomin, WU Shenghe, et al.Characteristics and controlling factors of high capacity channels of reservoirs at high water cut stage:a case from Block Hu 12 of Huzhuangji oilfield[J].Petroleum Exploration and Development, 2007, 34(2):207-211.
[29] 崔传智, 杨勇, 曹刚, 等.疏松砂岩油藏大孔道中高速非达西渗流对产能的影响分析[J].石油天然气学报, 2009, 31(3):122-125.
CUI Chuanzhi, YANG Yong, CAO Gang, et al.Effect of high velocity non-Darcy flow on productivity in wormhole of unconsolidated sandstone reservoirs[J].Journal of Oil and Gas Technology, 2009, 31(3):122-125.

注水开发油田注水通道状态辨识及预测方法

Identification and predictions of water injectivity for water injection channels in water injection development oilfield

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价