吴佳忆,王加强,宋玉婷,朱丽旭,董晶
WU Jiayi,WANG Jiaqiang,SONG Yuting,ZHU Lixu,DONG Jing

• 1:国家能源陆相砂岩老油田持续开采研发中心
• 2:中国石油大庆油田有限责任公司勘探开发研究院
• 3:中国石油大庆油田有限责任公司第六采油厂
• 4:中国石油大庆油田有限责任公司第七采油厂

摘要(Abstract)：

大庆长垣萨、葡、高油层作为河流-三角洲相砂岩储层的典型代表，是大庆油田产量和效益的“压舱石”。由于储层砂体类型多样、非均质性强，沉积微相描述面临手工绘图依赖专家经验、工作效率低以及自动成图缺乏沉积模式约束、砂体边界刻画精度不高等难题，难以满足剩余油实时精准挖潜的需求。为此，提出一种基于沉积模式约束的智能沉积微相工业制图方法：通过构建密井网条件下的多尺度地质样本库，融合边界信息输入，改进Pix2Pix生成对抗网络（GAN）模型，引入沉积模式约束提升砂体边界的刻画精度；建立基于边缘信息共享的沉积相带图拼接方法，突破传统模型中固定图像尺寸输出的限制，实现万井级储层整体沉积微相一次性成图。在萨南开发区的工业化应用表明，该方法单层沉积微相制图效率较传统方法提升了20倍，沉积微相组合结果符合不同沉积环境的砂体展布规律。研究成果为强非均质性储层的高质量开发提供了快速工业制图手段，推动沉积微相绘图从传统手工刻画向智能工业制图迈进。
As typical representatives of fluvial-delta facies sandstone reservoirs, Sa-Pu-Gao reservoirs in Daqing Placanticline serve as the “ballast stone” for production and benefit of Daqing Oilfield. Due to the diverse types and high heterogeneity of reservoir sand bodies, the sedimentary micro-facies characterization faces challenges such as manual mapping relying on expert experience, low work efficiency and automatic mapping lacking sedimentary pattern constraints, resulting in low accuracy of sand body boundaries characterization, making it difficult to meet the requirement of real-time and accurate potential tapping of remaining oil. Therefore, an intelligent sedimentary micro-facies industrial mapping method based on sedimentary pattern constraints is proposed. By constructing the multi-scale geological sample library in condition of dense well patterns and integrating boundary information input, the Pix2Pix generative adversarial network(GAN) model is improved, and sedimentary pattern constraints are introduced to improve the accuracy of sand body boundary characterization. A method for sedimentary facies belt maps splicing based on edge information sharing is established, breaking through the fixed image size output limitations of traditional models and realizing one-time mapping of overall micro-facies for reservoirs with tens of thousands of wells. The industrial application in Sanan development zone indicates that, the efficiency of single-layer sedimentary micro-facies mapping using this method is 20 times higher than that of traditional methods, with sedimentary micro-facies combination results consistent with the extention laws of sand bodies in different sedimentary environments. The research provides a rapid industrial mapping method for high-quality development of reservoirs with high heterogeneity, and promotes the development of sedimentary micro-facies mapping from traditional manual characterization to intelligent industrial mapping.

关键词(KeyWords)： 河流-三角洲相储层;沉积微相;智能工业制图;沉积模式约束;生成对抗网络;大庆长垣
fluvial-delta facies reservoir;sedimentary micro-facies;intelligent industrial mapping;sedimentary pattern constraint;generative adversarial networks;Daqing Placanticline

Abstract:

Keywords:

基金项目(Foundation): 中国石油天然气股份有限公司攻关性应用型科技专项“中高渗油田特高含水期大幅度提高采收率技术研究”(2023ZZ22)

作者(Author): 吴佳忆,王加强,宋玉婷,朱丽旭,董晶
WU Jiayi,WANG Jiaqiang,SONG Yuting,ZHU Lixu,DONG Jing

DOI: 10.19597/J.ISSN.1000-3754.202505005

参考文献(References)：

• [1]赵翰卿.大庆油田精细储层沉积学研究[M].北京：石油工业出版社，2012.ZHAO Hanqing. Study on fine reservoir sedimentology in Daqing Oilfield[M]. Beijing:Petroleum Industry Press,2012.
• [2]刘合，杜庆龙，高兴军，等.高含水老油田深度开发面临挑战及发展方向[J].大庆石油地质与开发，2024,43(4):15-24.LIU He, DU Qinglong, GAO Xingjun, et al. Challenges and development direction for deep development of high water-cut mature oilfields[J]. Petroleum Geology&Oilfield Development in Daqing,2024,43(4):15-24.
• [3]袁庆峰，李斌会，赵云飞，等.大庆油田油藏工程技术的创新发展与攻关方向[J].大庆石油地质与开发，2024,43(4):116-124.YUAN Qingfeng, LI Binhui, ZHAO Yunfei, et al. Innovative development and research direction of reservoir engineering technology in Daqing Oilfield[J]. Petroleum Geology&Oilfield Development in Daqing,2024,43(4):116-124.
• [4]王广昀，王凤兰，赵波，等.大庆油田公司勘探开发形势与发展战略[J].中国石油勘探，2021,26(1):55-73.WANG Guangyun,WANG Fenglan,ZHAO Bo,et al. Exploration and development situation and development strategy of Daqing Oilfield Company[J]. China Petroleum Exploration,2021,26(1):55-73.
• [5]白振国，姜雪岩，杨光耀，等.大庆油田水驱开发技术及其发展方向[J].大庆石油地质与开发，2024,43(4):25-33.BAI Zhenguo,JIANG Xueyan,YANG Guangyao,et al. Water flooding development technology in Daqing Oilfield and its development direction[J]. Petroleum Geology&Oilfield Development in Daqing,2024,43(4):25-33.
• [6]陈欢庆.中国石油精细油藏描述技术新进展与展望[J].世界石油工业，2024,31(3):17-25.CHEN Huanqing. New progress and prospect of fine reservoir description of PetroChina[J]. World Petroleum Industry,2024,31(3):17-25.
• [7]郭军辉，郑宪宝，王治国，等.大庆长垣油田水驱开发技术智能化实践与展望[J].大庆石油地质与开发，2024,43(3):203-213.GUO Junhui, ZHENG Xianbao, WANG Zhiguo, et al. Intelligent practice and prospects of water flooding development technology in Daqing Placanticline oilfield[J]. Petroleum Geology&Oilfield Development in Daqing,2024,43(3):203-213.
• [8]张赫，单高军，杜庆龙，等.大庆长垣油田特高含水后期水驱开发技术难题及其对策[J].大庆石油地质与开发，2022,41(4):60-66.ZHANG He, SHAN Gaojun, DU Qinglong, et al. Technical challenges and solutions of water flooding development in late stage of ultra-high water cut in Placanticline oilfield in Daqing[J]. Petroleum Geology&Oilfield Development in Daqing,2022,41(4):60-66.
• [9]裘亦楠.储层沉积学研究工作流程[J].石油勘探与开发，1990,17(1):85-90.QIU Yi’nan. A proposed flow-diagram for reservoir sedimentological study[J]. Petroleum Exploration and Development,1990,17(1):85-90.
• [10]吕晓光，李长山，蔡希源，等.松辽大型浅水湖盆三角洲沉积特征及前缘相储层结构模型[J].沉积学报，1999,17(4):572-577.LüXiaoguang,LI Changshan,CAI Xiyuan,et al. Depositional characteristics and front facies reservoir framework model in Songliao shallow lacustrine delta[J]. Acta Sedimentologica Sinica,1999,17(4):572-577.
• [11]赵翰卿，付志国，吕晓光.储层分层次分析和模式预测描述法[J].大庆石油地质与开发，2004,23(5):74-77.ZHAO Hanqing, FU Zhiguo, LüXiaoguang. Reservoir type analysis and model prediction description method[J]. Petroleum Geology&Oilfield Development in Daqing, 2004, 23(5):74-77.
• [12]何宇航，宋保全，白振强.大庆油田河流相储层精细描述技术发展及应用[J].大庆石油地质与开发，2011,30(1):63-69.HE Yuhang,SONG Baoquan,BAI Zhenqiang. Development and application of fine reservoir description technology in fluvial reservoirs in Daqing Oilfield[J]. Petroleum Geology&Oilfield Development in Daqing,2011,30(1):63-69.
• [13]杨会东，黄伏生，赵翰卿.沉积相带图计算机绘制方法研究[J].石油工业计算机应用，1999,7(3):18-22.YANG Huidong, HUANG Fusheng, ZHAO Hanqing. Study on computer rendering method of sedimentary facies zone map[J].Computer Applications in Petroleum Industry, 1999, 7(3):18-22.
• [14]孔凡立.河流沉积微相自动识别方法研究与算法设计[D].杭州：浙江大学，2011.KONG Fanli. Method and arithmetic design of automatic identification of river sedimentary microfacies[D]. Hangzhou:Zhejiang University,2011.
• [15]冀宇.河流三角洲沉积的沉积相带图绘制方法研究[D].大庆：东北石油大学，2014.JI Yu. Research on the drawing method of the sedimentary facies belt maps of the river delta deposits[D]. Daqing:Northeast Petroleum University,2014.
• [16]赵翰卿，付志国，吕晓光，等.大型河流-三角洲沉积储层精细描述方法[J].石油学报，2000,31(4):109-113.ZHAO Hanqing,FU Zhiguo,LüXiaoguang,et al. Methods for detailed description of large fluvial-delta depositional reservoir[J]. Acta Petrolei Sinica,2000,31(4):109-113.
• [17]吕晓光，赵翰卿，付志国，等.河流相储层平面连续性精细描述[J].石油学报，1997,18(2):66-71.LüXiaoguang, ZHAO Hanqing, FU Zhiguo, et al. A detailed description of area continuity of fluvial reservoir[J]. Acta Petrolei Sinica,1997,18(2):66-71.
• [18]何宇航，宋保全，张春生.大庆长垣辫状河砂体物理模拟实验研究与认识[J].地学前缘，2012,19(2):41-48.HE Yuhang, SONG Baoquan, ZHANG Chunsheng. A study of braided river sand deposit in Changyuan,Daqing through physical simulation experiments[J]. Earth Science Frontiers,2012,19(2):41-48.
• [19]周新茂，高兴军，季丽丹，等.曲流河废弃河道的废弃类型及机理分析[J].西安石油大学学报（自然科学版），2010,25(1):19-23.ZHOU Xinmao,GAO Xingjun,JI Lidan,et al. Analysis on the types and the sedimentation mechanism of the abandoned channel in meandering river[J]. Journal of Xi’an Shiyou University(Natural Science Edition),2010,25(1):19-23.
• [20]文慧俭，范广平，马世忠，等.大庆萨尔图油田北部萨一油层组沉积微相再认识[J].科技导报，2012,33(7):39-43.WEN Huijian,FAN Guangping,MA Shizhong,et al. Study of sedimentary microfacies of Sayi reservoir in north Saertu oilfield[J]. Science&Technology Review,2012,33(7):39-43.
• [21]于德水，何宇航，邢宝荣，等.大庆长垣高台子油层沉积演化分布及沉积模式[J].沉积学报，2024,42(1):238-250.YU Deshui,HE Yuhang,XING Baorong,et al. Study of evolution,distribution and sedimentary model of Gaotaizi reservoir in Daqing Placanticline[J]. Acta Sedimentologica Sinica,2024,42(1):238-250.
• [22] GOODFELLO I J,POUGET-ABADIE J,MIRZA M,et al. Generative adversarial nets[C]. Montreal:28th Annual Conference on Neural Information Processing Systems,2014.
• [23] ZHANG T F,TILKE P,DUPONT E,et al. Generating geologically realistic 3D reservoir facies models using deep learning of sedimentary architecture with generative adversarial networks[J]. Petroleum Science,2019,16(3):541-549.
• [24] SONG S H, MUKERJI T, HOU J G. GANSim:Conditional facies simulation using an improved progressive growing of generative adversarial networks(GANs)[J]. Mathematical Geosciences,2021,53(7):1413-1444.
• [25]李少华，史敬华，于金彪，等.基于单一图像生成对抗神经网络方法在沉积相建模中的应用[J].油气地质与采收率，2022,29(1):37-45.LI Shaohua,SHI Jinghua,YU Jinbiao,et al. Application of SinGAN method in sedimentary facies modeling[J]. Petroleum Geology and Recovery Efficiency,2022,29(1):37-45.
• [26]王志腾，冒添逸，张昕，等.基于U型生成对抗网络的编码孔径CT成像方法[J]. CT理论与应用研究，2022,31(3):317-327.WANG Zhiteng,MAO Tianyi,ZHANG Xin,et al. Coded aperture computed tomography via generative adversarial U-net[J].Computerized Tomography Theory and Applications, 2022, 31(3):317-327.
• [27] ISOLA P,ZHU J Y,ZHOU T H,et al. Image-to-image translation with conditional adversarial networks[C]. Honolulu:30th IEEE Conference on Computer Vision and Pattern Recognition,2017.
• [28]马岽奡，唐娉，赵理君，等.深度学习图像数据增广方法研究综述[J].中国图象图形学报，2021,26(3):487-502.MA Dongao, TANG Ping, ZHAO Lijun, et al. Review of data augmentation for image in deep learning[J]. Journal of Image and Graphics,2021,26(3):487-502.
• [29]马世忠，李杭，张斌驰.储层平面沉积相带图的动态修正方法[J].黑龙江科技大学学报，2017,27(5):499-502.MA Shizhong,LI Hang,ZHANG Binchi. Reservoir plane sedimentary facies corrected using dynamic data[J]. Journal of Heilongjiang University of Science&Technology, 2017, 27(5):499-502.