基于ANN算法的微纳米水气分散体系驱产油量预测方法

Abstract

Abstract: The Micro-nano water-gas dispersion system drive (MNWDS) is a new type of low permeability reservoir technology to improve the recovery rate of low permeability reservoirs, which improves the mobility of the drive system and the efficiency of the drive through the injection of micro-nanometer scale gas and water dispersed phases, and it is especially suitable for low permeability reservoirs where the effect of the conventional water drive is poor, and the mine experiments have been carried out one after another. At present, this method has been carried out in the experimental area of Wuliwan Chang6. When using numerical simulation methods to predict the oil yield driven by the micro-nano water-air dispersion system, it is necessary to consider multiple parameters such as bubble size, gas-liquid ratio, fluid properties and complex gas-liquid interactions. The process is complex and time-consuming, and it is impossible to quickly simulate the oil production driven by the micro-nano water-gas dispersion system. In order to accurately predict the production of oil wells after injecting the micro-nano water-gas dispersion system, this paper establishes a production prediction model of micro-nano water-gas dispersion system based on the actual production data of the test area and the parameters of the geological model, and utilizes the artificial neural network (ANN) algorithm. The model takes the oil production data of the wells in the test area, water content, injection volume, water-driven reserves, reservoir thickness, permeability and porosity as input parameters, and the oil production 12 months after implementation as output, and establishes the training sample set of the model. Through K-Means clustering analysis of the sample set, invalid samples were eliminated, and a training set of 59 samples was finally formed. In the model training, an optimization algorithm was introduced to automatically adjust the model parameters, which significantly improved the test set prediction accuracy of the model. Based on this model, the oil production prediction was carried out for 21 well groups to be driven by the micro-nano water-gas dispersion system, and the comparison between the prediction results and with the numerical simulation results showed that the compliance rate of the two was as high as 95%, which verified the accuracy of the current model. The model provides a new way for the oil production prediction of micro-nano water-gas dispersion system drive.

Key words: Micro-nano-water-gas dispersion system flooding, machine learning, K-Means clustering analysis, artificial neural network, Levenberg-Maquardt

CLC Number:

TE348

FENG GUOQING,CHANG HAILING,WANG KEYU, et al. Prediction method of oil production driven by micro-nano water and gas dispersion system based on ANN algorithm[J]. Petroleum Reservoir Evaluation and Development, 0, (): 2024601-2024601.

References

[1] 葛罗. 新型水-气分散体系提高低渗透油藏采收率的实验研究[J]. 精细石油化工, 2023, 40(1): 9-13.
GE Luo.Application and research of new Water-Gas dispersion system in low permeability reservoir[J]. Speciality Petrochemicals, 2023, 40(1): 9-13.
[2] 潘铎. 低渗透油藏地质特征与开发对策分析[J]. 石化技术, 2023, 30(6): 194-196.
PAN Duo.Analysis of geological characteristics and development countermeasures of low permeability reservoir[J]. Petrochemical Industry Technology, 2023, 30(6): 194-196.
[3] XIAN B H, HAO H D, DENG S, et al.Laboratory experiments of CO₂ flooding and its influencing factors on oil recovery in a low permeability reservoir with medium viscous oil[J]. Fuel, 2024, 371: 131871.
[4] 王哲, 曹广胜, 白玉杰, 等. 低渗透油藏提高采收率技术现状及展望[J]. 特种油气藏, 2023, 30(1): 1-13.
WANG Zhe, CAO Guangsheng, BAI Yujie, et al.Development Status and Prospect of EOR Technology in Low-Permeability Reservoirs[J]. Special Oil & Gas Reservoirs, 2023, 30(1): 1-13.
[5] 王宇. 致密储层气驱提高采收率研究[D]. 北京: 中国石油大学(北京), 2022.
WANG Yu.Study on enhanced oil recovery by gas flooding in tight reservoirs[D]. Beijing: China University of Petroleum(Beijing), 2022.
[6] 李勇, 周楚艺. J油田采用气驱方式提高采收率方法研究[C]//陕西省石油学会. 2023油气田勘探与开发国际会议论文集Ⅰ. 大庆油田勘探开发研究院, 2023: 6.
LI Yong, ZHOU Chuyi.Research on the method of improving oil recovery by gas drive in J Oilfield[C]//Shaanxi petroleum society. Collection I of international field exploration and development conference 2023. Research Institute of Exploration and Development of Daqing Oilfield Company Ltd. 2023: 6.
[7] 王涛, 于海洋, 朱旭晨, 等. 水气交替CO₂咸水层地质封存数值模拟研究[J]. 中国海上油气, 2023, 35(4): 198-204.
WANG Tao, YU Haiyang, ZHU Xuchen, et al.Numerical simulation study on geological storage of CO₂ in saline aquifers assisted by water alternating gas[J]. China Offshore Oil and Gas, 2023, 35(4): 198-204.
[8] 汤瑞佳, 王贺谊, 余华贵, 等. 水气交替注入对CO₂驱油效果的影响[J]. 断块油气田, 2016, 23(3): 358-362.
TANG Ruijia,WANG Heyi,YU Huagui, et al.Effect of water and gas alternate injection on CO₂ flooding[J]. Fault-Block Oil and Gas Field , 2016, 23(3): 358-362.
[9] 潘佳莹, 闫健, 佀彬凡, 等. 水气交替提高采收率技术进展[J]. 精细石油化工进展, 2024, 25(1): 15-22.
PAN Jiaying, YAN Jian, SI Binfan, et al.Advances in water-gas alternation technology for enhanced recovery[J]. Progress of Fine Petrochemicals, 2024, 25(1): 15-22.
[10] 伍家忠, 韩海水, 王秉合, 等. 低渗透储层油/水/岩相互作用机制及离子匹配提高采收率方法[J]. 中国石油大学学报(自然科学版), 2023, 47(1): 116-124.
WU Jiazhong, HAN Haishui, WANG Binghe, et al.Interaction of reservoir oil/water/rock and EOR method of ion matching in low permeability reservoir[J]. Journal of China University of Petroleum (Edition of Natural science), 2023, 47(1): 116-124.
[11] 陈兴隆, 伍家忠, 韩海水, 等. 水气分散体系的超声波振荡生成方法及驱油实验研究[J]. 天然气与石油, 2021, 39(4): 48-52.
CHEN Xinglong, WU Jiazhong, HAN Haishui, et al.Formation of gas bubble-water dispersion system using ultrasonic vibration method and research on its impact on ultimate oil recovery[J]. Natural Gas and Oil, 2021, 39(4): 48-52.
[12] 尚祯浩, 伍家忠, 熊伟, 等. 水气分散体系驱油微观机理研究[J/OL]. 西南石油大学学报(自然科学版), 1-12[2024-06-21]. http://kns.cnki.net/kcms/detail/51.1718.te.20240325.1037.012.html.
SHANG Zhenhao, WU Jiazhong, XIONG Wei, et al. Micro Mechanism of Oil Displacement by Water Gas Dispersion System[J/OL]. Journal of Southwest Petroleum University(Science & Technology Edition), 1-12[2024-06-21]. http://kns.cnki.net/kcms/detail/51.1718.te.20240325.1037.012.html.
[13] 许世京, 伍家忠, 陈兴隆, 等. 离子匹配精细水驱提高采收率机理研究[J]. 西南石油大学学报(自然科学版), 2022, 44(5): 105-112.
XU Shijing, WU Jiazhong, CHEN Xinglong, et al.A study on mechanism of EOR by ion matching water injection[J]. Journal of Southwest Petroleum University(Science & Technology Edition), 2022, 44(5): 105-112.
[14] ZHAI H, XUE Z, PARK H, et al.Migration characteristics of supercritical CO₂ microbubble flow in the Berea sandstone revealed by voxel-based X-ray computed tomography imaging analysis(Article)[J]. Journal of Natural Gas Science and Engineering, 2020, 77: 103233.
[15] PATMONOAJI A, ZHANG Y, XUE Z Q, et al.Experimental and numerical simulation of supercritical CO₂ microbubble injection into a brine-saturated porous medium[J]. International Journal of Greenhouse Gas Control, 2019, 91: 1750-5836.
[16] JIANG L L, XUE Z Q, PARK H.Enhancement of CO₂ dissolution and sweep efficiency in saline aquifer by micro bubble CO₂ injection[J]. International Journal of Heat and Mass Transfer, 2019, 138: 1211-1221.
[17] MANOR O, CHAN D Y C. Terminal velocity and mobile surface species in rising microbubbles[J]. Langmuir, 2009, 25(16): 8899-8902.
[18] BJORNDALEN N, KURU E.Stability of microbubble-based drilling fluids under downhole conditions[J]. Journal of Canadian Petroleum Technology, 2008, 47(6): 40-47.
[19] SHAMS M M.A Study on the Flow Behavior of Microbubbles in Capillary Tubes[D]. Calgary: University of Calgary, 2014
[20] 卢帆. 数据驱动SAGD生产过程产量预测方法研究[D]. 青岛: 中国石油大学(华东), 2021.
LU Fan, Research on Data-driven Approaches for Production Prediction of SAGD Process[D]. Qingdao: China University of Petroleum(East China), 2021.
[21] 刁凤琴. 石油储量动态经济评价研究[D]. 武汉: 中国地质大学, 2007.
DIAO Fengqin, Study on dynamic economic evaluation of petroleum reserves[D]. Wuhai: China University of Geosciences, 2007.
[22] 苏恺明, 徐耀辉, 徐旺林, 等. 鄂尔多斯盆地延长组多油源贡献比例与分布规律:基于机器学习与可解释性研究[J]. 地学前缘, 2024, 31(3): 530-540.
SU Kaiming, XU Yaohui, XU Wanglin, et al.Contribution ratio and distribution patterns of multiple oil sources in the Yan-chang Formation of the Ordos Basin: A study utilizing machine learning and interpretability techniques[J]. Earth Science Frontiers, 2024, 31(3): 530-540.
[23] NIU X X, SUEN C Y.A novel hybrid CNN-SVM classifier for recognizing handwritten digits[J]. Pattern Recognition, 2012, 45(4): 1318-1325.
[24] 林景栋, 吴欣怡, 柴毅, 等. 卷积神经网络结构优化综述[J]. 自动化学报, 2020, 46(1): 24-37.
LIN Jingdong, WU Xinyi, CHAI Yi, et al.Structure optimization of convolutional neural networks: a survey[J]. Acta Automatica Sinica, 2020, 46(1): 24-37.
[25] 周永章, 陈烁, 张旗, 等. 大数据与数学地球科学研究进展——大数据与数学地球科学专题代序[J]. 岩石学报, 2018, 34(2): 255-263.
ZHOU Yongzhang, CHEN Shuo, ZHANG Qi, et al.Advances and prospects of big data and mathematical geoscience[J]. Acta Petrologica Sinica, 34(2): 255-263.
[26] BARROW H.Chapter 5 - Connectionism and Neural Networks[M]//BODEN M A. Handbook of Perception and Cognition. Academic Press, 1996: 135-155.
[27] HEFFER K J, FOX R J, MCGILL C A, et al.Novel techniques show links between reservoir flow directionality, earth stress, fault structure and geomechanical changes in mature waterfloods[C], SPE Journal, 1997, 2(2): 91-98.
[28] 王柏力, 冯乔, 江海英, 等. 水驱特征曲线在低渗透油藏开发中的应用[J]. 特种油气藏, 2019, 26(6): 82-87.
WANG Baili, FENG Qiao, JIANG Haiying, et al.Application of Waterflooding Characteristic Curve in the Development of Low-Permeability Oil Reservoir[J]. Special Oil & Gas Reservoirs, 2019, 26(6): 82-87.
[29] VUCIRI Isaac.基于ANN代理模型的致密油压裂裂缝参数优化[D]. 青岛: 中国石油大学(华东), 2018.
VUCIRI Isaac.Optimization of fracture parameters for tight oil fracturing based on ANN agent model[D]. Qingdao: China University of Petroleum (East China), 2018.
[30] 林魂, 孙新毅, 宋西翔, 等. 基于改进人工神经网络的页岩气井产量预测模型研究[J]. 油气藏评价与开发, 2023, 13(4): 467-473.
LIN Hun, SUN Xinyi, SONG Xixiang, et al.A model for shale gas well production prediction based on improved artificial neural network[J]. Petroleum Reservoir Evaluation and Development, 2023, 13(4): 467-473.

Prediction method of oil production driven by micro-nano water and gas dispersion system based on ANN algorithm

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 7

Metrics

Comments

Recommended 0

[1]	ZHANG Zhang, MENG Peng, YANG Wei, ZHANG Xiaolong, HUANG Qi, WANG Haoran. Characterization of braided river reservoir architecture based on seismic attribute stacking ensemble learning: A case study of the C-2 oilfield in the Bohai Bay Basin [J]. Petroleum Reservoir Evaluation and Development, 2025, 15(1): 64-72.
[2]	LIN Hun, SUN Xinyi, SONG Xixiang, MENG Chun, XIONG Wenxin, HUANG Junhe, LIU Hongbo, LIU Cheng. A model for shale gas well production prediction based on improved artificial neural network [J]. Petroleum Reservoir Evaluation and Development, 2023, 13(4): 467-473.
[3]	NIE Yunli, GAO Guozhong. Classification of shale gas “sweet spot” based on Random Forest machine learning [J]. Petroleum Reservoir Evaluation and Development, 2023, 13(3): 358-367.
[4]	ZHANG Qing,HE Feng,HE Youwei. Well interference evaluation and prediction of shale gas wells based on machine learning [J]. Petroleum Reservoir Evaluation and Development, 2022, 12(3): 487-495.
[5]	HUANG Jiachen,ZHANG Jinchuan. Overview of oil and gas production forecasting by machine learning [J]. Petroleum Reservoir Evaluation and Development, 2021, 11(4): 613-620.
[6]	LI Chang,SHEN Anjiang,CHANG Shaoying,LIANG Zhengzhong,LI Zhenlin,MENG He. Application and contrast of machine learning in carbonate lithofacies log identification: A case study of Longwangmiao Formation of MX area in Sichuan Basin [J]. Petroleum Reservoir Evaluation and Development, 2021, 11(4): 586-596.
[7]	ZHANG Jinchuan,CHEN Shijing,LI Zhongming,LANG Yue,WANG Chunyan,WANG Dongsheng,LI Zhen,TANG Xuan,LIU Yang,LI Pei,TONG Zhongzheng. Intelligent evaluation of shale gas resources [J]. Petroleum Reservoir Evaluation and Development, 2021, 11(4): 476-486.