基于驱替匹配性评价的水驱油藏注采参数智能协同优化方法

Intelligent collaborative optimization of injection-production parameters for waterflooding reservoirs based on displacement matching evaluation

摘要

受储层非均质性及注采制度不合理等因素影响,水驱油藏开发过程中常出现窜流、驱替不均等问题,严重制约了采收率的提升。基于区域过水量与可动油储量的空间匹配关系,构建驱替均衡性表征指标,定量评价储层内部的注入水驱替匹配程度。在此基础上,构建以驱替匹配度最大化为目标的注采参数协同优化模型,并优选霜冰优化算法进行求解,形成基于驱替匹配性评价的注采参数智能协同优化方法,将其应用于埕岛中区油藏的开发实践中。结果表明,通过协同调配各井的注采液量,油藏整体注入水的驱替匹配性显著提高,有效改善水驱开发效果,预测生产5 a累积增油量达到146.53×10⁴ m³,综合含水率下降1.7%,可为同类水驱油藏的效益开发提供切实可行的技术支撑。

Abstract

Due to reservoir heterogeneity and suboptimal injection-production schemes, waterflooding reservoirs often suffer from issues such as water channeling and displacement imbalance, which can significantly constrain oil recovery in high water cut stage. In this study, a novel displacement equilibrium indicator was proposed based on the spatial matching relationship between regional injected water volumes and movable oil reserves, enabling quantitative evaluation of the injection-displacement matching performance within the reservoir. A coordinated optimization model for injection-production parameters was established with the objective of maximizing spatial displacement matching. A reptile-inspired metaheuristic optimization algorithm (RIME) was selected and adopted to solve the model, forming an intelligent coordinated optimization method for injection-production parameters guided by displacement matching evaluation. The method has been applied to the Chengdao central block for a case study. The results demonstrate that the coordinated adjustment of injection and production rates across wells can significantly enhance the overall displacement matching performance, effectively improving the waterflooding effect. Over a predicted production period of five years, the cumulative oil increment reaches 146.53×10 ⁴ m ³, and the average water cut is reduced by 1.7%, providing a practical and effective technical solution for efficient development of similar waterflooding reservoirs.

关键词

水驱油藏 / 余弦相似度 / 可动油储量 / 协同优化 / 霜冰优化算法

Key words

waterflooding oil reservoir / cosine similarity / movable oil reserves / collaborative optimization / reptile-inspired metaheuristic optimization algorithm

参考文献

[1] 李阳, 赵清民, 薛兆杰. 新一代油气开发技术体系构建与创新实践[J]. 中国石油大学学报(自然科学版), 2023, 47(5): 45-54.

[2] LI Yang, ZHAO Qingmin, XUE Zhaojie. Construction and innovative practice of new generation oil and gas development technology system[J]. Journal of China University of Petroleum(Edition of Natural Science), 2023, 47(5): 45-54.

[3] 孙焕泉, 杨勇, 王海涛, 等 . 特高含水油藏剩余油分布特征与提高采收率新技术[J]. 中国石油大学学报(自然科学版), 2023, 47(5): 90-102.

[4] SUN Huanquan, YANG Yong, WANG Haitao, et al. Distribution characteristics of remaining oil in extra-high water cut reservoirs and new technologies for enhancing oil recovery[J]. Journal of China University of Petroleum(Edition of Natural Science), 2023, 47(5): 90-102.

[5] AZAMIPOUR V, ASSAREH M, MITTERMEIR G M . An improved optimization procedure for production and injection scheduling using a hybrid genetic algorithm[J]. Chemical Engineering Research and Design, 2018, 131: 557-570.

[6] 张益, 宁崇如, 陈亚舟, 等 . 致密油藏大排量注水吞吐技术及参数优化研究[J]. 油气藏评价与开发, 2024, 14(5): 727-733.

[7] ZHANG Yi, NING Chongru, CHEN Yazhou, et al. Huff-n-puff technology and parameter optimization of large displacement water injection in tight oil reservoir[J]. Petroleum Reservoir Evaluation and Development, 2024, 14(5): 727-733.

[8] CHEN G, ZHANG K, XUE X, et al. Surrogate-assisted evolutionary algorithm with dimensionality reduction method for water flooding production optimization[J]. Journal of Petroleum Science and Engineering, 2020, 185: 106633.

[9] 李梦云, 张贵才, 裴海华, 等 . 非均质水驱油藏层间弱水驱带分布预测新模型与应用研究[J]. 断块油气田, 2025, 32(6): 1011-1017.

[10] LI Mengyun, ZHANG Guicai, PEI Haihua, et al. New model and application research on distribution prediction of interlayer weak waterflooded zones in heterogeneous waterflooded reservoirs[J]. Fault-Block Oil and Gas Field, 2025, 32(6): 1011-1017.

[11] WANG Z Z, ZHANG K, CHEN G D, et al. Evolutionary-assisted reinforcement learning for reservoir real-time production optimization under uncertainty[J]. Petroleum Science, 2023, 20(1): 261-276.

[12] RODRIGUEZ C A X, GILDIN E, CABRALES S A, et al. A novel decision-making framework for waterflooding optimization using long and short-term memory models and metaheuristics[R]. SPE 213154-MS, 2023.

[13] ABDALLA R, AGBAN N, LÜDDEKE C, et al. Multi agent physics informed reinforcement learning for waterflooding optimization[J]. Franklin Open, 2025, 10: 100229.

[14] 范昭宇, 宋兆杰, 朱绍鹏, 等 . 水驱气藏水侵及开发效果主控因素数值模拟研究[J]. 断块油气田, 2025, 32(1): 141-146.

[15] FAN Zhaoyu, SONG Zhaojie, ZHU Shaopeng, et al. Numerical simulation study on main controlling factors of water invasion and development effect of water-driven gas reservoirs[J]. Fault-Block Oil and Gas Field, 2025, 32(1): 141-146.

[16] FENG Q H, LI S S, ZHANG X M, et al. Well production optimization using streamline features-based objective function and Bayesian adaptive direct search algorithm[J]. Petroleum Science, 2022, 19(6): 2879-2894.

[17] AL-AGHBARI M, AL-WADHAHI M, GUJARATHI A M . Multi-objective optimization of Brugge field for short-term and long-term waterflood management[J]. Arabian Journal for Science and Engineering, 2022, 47(9): 11069-11087.

[18] LI X, ZHANG J, LIU H, et al. A comprehensive machine learning algorithm based methodology for intelligent water injection optimization - case study of D field in Asia[R]. SPE 221340-MS, 2024.

[19] 吴宽宽, 冯其红, 张先敏, 等 . 多层水驱油藏均衡驱替注采参数协同优化方法[J]. 油气地质与采收率, 2023, 30(5): 67-75.

[20] WU Kuankuan, FENG Qihong, ZHANG Xianmin, et al. Collaborative optimization method of injection and production parameters for multi-layer reservoirs based on balanced water flooding[J]. Petroleum Geology and Recovery Efficiency, 2023, 30(5): 67-75.

[21] ISLAM M, ZUNAIR H, MOHAMMED N . CosSIF: cosine similarity-based image filtering to overcome low inter-class variation in synthetic medical image datasets[J]. Computers in Biology and Medicine, 2024, 172: 108317.

[22] LI D, LI J, FAN Y, et al. Printed label defect detection using twice gradient matching based on improved cosine similarity measure[J]. Expert Systems with Applications, 2022, 204: 117372.

[23] NAVEED J M, SAEED M, SAEED A, et al. Cosine and cotangent similarity measures for intuitionistic fuzzy hypersoft sets with application in MADM problem[J]. Heliyon, 2024, 10(7): e27886.

[24] RINJENI T P, INDRIAWAN A, RAKHMAWATI N A . Matching scientific article titles using cosine similarity and jaccard similarity algorithm[J]. Procedia Computer Science, 2024, 234: 553-560.

[25] HAN Y, LI Y . Image cascade matching method based on an improved random sampling consistency algorithm[J]. Journal of Radiation Research and Applied Sciences, 2023, 16: 100698.

[26] JIANG W, SHEN H, XU Z, et al. A feature compression method based on similarity matching[J]. Displays, 2024, 83: 102728.

[27] ZHOU M, DUAN M . A research method based on POI similarity and translation machine matching recommendation algorithm[J]. Procedia Computer Science, 2024, 247: 2-9.

[28] LIU X, TENG X, LUO J, et al. Robust multi-sensor image matching based on normalized self-similarity region descriptor[J]. Chinese Journal of Aeronautics, 2024, 37(1): 271-286.

[29] FLYNN R, OLUKOYA O . Using approximate matching and machine learning to uncover malicious activity in logs[J]. Computers & Security, 2025, 151: 104312.

[30] 苏峰山, 禄小敏, 叶云会, 等 . 基于图卷积自编码器的道路网相似度计算方法[J]. 武汉大学学报(信息科学版), 2026, 51(2): 391-402.

[31] SU Fengshan, LU Xiaomin, YE Yunhui, et al. A road network similarity calculation method based on graph convolutional autoencoder[J]. Geomatics and Information Science of Wuhan University, 2026, 51(2): 391-402.

[32] 徐传丽, 周世杰, 吴春江. 深度学习中文本相似度计算研究综述[J]. 计算机应用与软件, 2024, 41(11): 1-14.

[33] XU Chuanli, ZHOU Shijie, WU Chunjiang. Review of textual similarity calculation in deep learning[J]. Computer Applications and Software, 2024, 41(11): 1-14.

[34] 陈红伟. 水驱油田井网加密矢量化优化方法研究[D]. 青岛: 中国石油大学(华东), 2019.

[35] CHEN Hongwei. The vectorial optimization method of well pattern infilling in waterflooding oilfield[D]. Qingdao: China University of Petroleum(East China), 2019.

[36] 马晓丽, 毕永斌, 蒋明洁, 等 . 中低渗油藏高倍数水驱过程中水相渗透率变化特征[J]. 油气藏评价与开发, 2025, 15(1): 103-109.

[37] MA Xiaoli, BI Yongbin, JIANG Mingjie, et al. Characteristics of water phase permeability variation in medium-low permeability oil reservoirs during high multiple waterflooding[J]. Petroleum Reservoir Evaluation and Development, 2025, 15(1): 103-109.

[38] 姜汉桥 . 油藏工程原理与方法[M]. 东营: 石油大学出版社, 2000: 181-185.

[39] 郝少璞, 刘全, 徐平安, 等 . 基于余弦相似度的多模态模仿学习方法[J]. 计算机研究与发展, 2023, 60(6): 1358-1372.

[40] HAO Shaopu, LIU Quan, XU Ping̍an, et al. Multi-modal imitation learning method with cosine similarity[J]. Journal of Computer Research and Development, 2023, 60(6): 1358-1372.

[41] KIM J, YANG H, CHOE J . Robust optimization of the locations and types of multiple wells using CNN based proxy models[J]. Journal of Petroleum Science and Engineering, 2020, 193: 107424.

[42] AMIRI M H, MEHRABI H N, MONTAZERI M, et al. Hippopotamus optimization algorithm: a novel nature-inspired optimization algorithm[J]. Scientific Reports, 2024, 14: 5032.

[43] WANG J, WANG W C, HU X X, et al. Black-winged kite algorithm: a nature-inspired meta-heuristic for solving benchmark functions and engineering problems[J]. Artificial Intelligence Review, 2024, 57(4): 98.

[44] SU H, ZHAO D, HEIDARI A A, et al. RIME: a physics-based optimization[J]. Neurocomputing, 2023, 532: 183-214.

[45] NOMAN N, BOLLEGALA D, IBA H . An adaptive differential evolution algorithm[C]// 2011 IEEE Congress of Evolutionary Computation(CEC), New Orleans, LA, USA, 2011: 2229-2236.

基金资助

油气重大专项课题(2025ZD1406103)

中国石化科技攻关项目(P22094)