基于大数据的测井智能解释系统开发与应用

doi:10.3969/j.issn.1672-7703.2021.02.012

摘要/Abstract

摘要： 人工智能技术在测井解释中的应用由来已久，但单方法应用研究多，系统集成应用少。当今云计算、大数据和人工智能技术的规模应用，再次推动了测井解释智能化发展。以多学科数据融合的数据湖为基础，在专业软件的基础上进行智能解释模块开发，将测井智能解释引入到传统的解释流程中，辅助测井分析人员快速挖掘隐藏的高价值信息。利用大数据治理工具将数据湖连接到智能模型，实现大数据与智能算法融合。通过系统开发实现基于大数据的智能解释模型和传统专业软件的集成，搭建基于地质图件导航的测井智能解释环境，形成地质、油藏背景下的智能化测井解释工作模式，增强测井评价复杂储层的能力，提高工作效率。

关键词: 大数据, 智能算法, 测井解释, 智能解释环境

Abstract: Artificial intelligence technology has been used in well logging interpretation for a long time, but there are more researches
on single model interpretation and less on application of system integration. Nowadays, large-scale application of cloud
computing, big data and artificial intelligence technology has promoted the intelligent development of logging interpretation once
again. Based on the data lake of multidisciplinary data fusion, intelligent interpretation module is developed in the logging interpretation software. That is, the intelligent logging interpretation method is introduced into the traditional interpretation process to assist logging analysts to quickly mine the hidden high-value information. Big data governance tools are used to connect data lake to intelligent model, so that big data and intelligent algorithm are integrated. The system integrates intelligent interpretation model based on big data with traditional professional software and builds an intelligent logging interpretation environment based on geological map navigation, realizing intelligent logging interpretation working mode with integration of geology and reservoir,strengthening the ability of complex reservoir evaluation, and improving the working efficiency.

中图分类号:

P631.9

石玉江, 刘国强, 钟吉彬, 王娟, 张文静. 基于大数据的测井智能解释系统开发与应用[J]. 中国石油勘探, 2021, 26(2): 113-126.

Shi Yujiang, Liu Guoqiang, Zhong Jibin, Wang Juan, Zhang Wenjing. Development and application of intelligent logging interpretation system based on big data#br#[J]. China Petroleum Exploration, 2021, 26(2): 113-126.

参考文献

[1] 曾文冲．现代测井技术发展趋势的分析[J]．测井技术，1989,13(1):1-11. Zeng Wenchong. An analysis of the development trend of modern logging technique[J]. Well Logging Technology, 1989,13(1):1-11.
[2] 李乐中，张立．斯伦贝谢公司解释系统及软件介绍[J]．国外测井技术， 1992,7(1):111-113. Li Lezhong, Zhang Li. Introduction to interpretation system and software of schlumberger[J]. World Well Logging Technology, 1992,7(1):111-113.
[3] 陆大卫，张世刚．测井软件走集成化道路[J]．测井技术，1996,20(1):5-11. Lu Dawei, Zhang Shigang. On integration of well logging software[J]. Well Logging Technology, 1996,20(1):5-11.
[4] 李浩，刘双莲，魏修平．浅析我国测井解释技术面临的问题与对策[J]．地球物理学进展，2010,25(6):2084-2090. Li Hao, Liu Shuanglian, Wei Xiuping. Analysis of the problem and strategys in logging interpretation techniques in our country[J]. Progress in Geophysics，2010,25(6):2084-2090.
[5] 谭廷栋．中国石油测井学科的发展及展望[J]．地球物理学报，1997 ( 增刊1）:344-350. Tan Tingdong. Prospect and development for petroleum well logging science in China[J]. Chinese Journal of Geophysics, 1997(S1):344-350.
[6] 石玉江，王娟，程启贵，等．数字化油藏研究理念与实践[M]．北京：石油工业出版社，2020. Shi Yujiang,Wang Juan,Cheng Qigui, et al . Concept and practice of digital reservoir research[M]. Beijing: Petroleum Industry Press, 2020.
[7] 赵丽莎，史永彬，金玮，等．基于梦想云的测井智能化解释应用研究[J]．中国石油勘探，2020,25(5):97-103. Zhao Lisha, Shi Yongbin, Jin Wei, et al . Application research on intelligent logging interpretation based on E&P Dream Cloud[J]. China Petroleum Exploration, 2020,25(5):97-103.
[8] 邹德江，谢关宝．大数据时代的现代测井解释技术探讨[J]．石油地质与工程，2016,30(6):51-54. Zou Dejiang, Xie Guanbao. Exploration of modern logging interpretation technology in the era of big data[J]. Petroleum Geology and Engineering, 2016,30(6):51-54.
[9] 白云程，何川．人工智能专家系统在测井综合解释中的应用[J]．测井技术，1984,8(4):16-32. Bai Yuncheng, He Chuan. Application of artificial intelligence expert system in logging comprehensive interpretation[J]. Well Logging Technology, 1984,8(4):16-32.
[10] 伊广林，吕健儒，吴付东，等．石油储集层评价专家系统[J]．测井技术，1986,10(1):1-8. Yi Guanglin, Lü Jianru, Wu Fudong, et al . Expert system for oil reservoir evaluation[J]. Well Logging Technology, 1986,10(1):1-8.
[11] 袁祖贵．砂泥岩地层测井解释专家系统在孤岛油田的应用[J]．测井技术，1988,12(3):74-79. Yuan Zugui. Application of sand shale formation logging interpretation expert system in Gudao Oilfield[J]. Well Logging Technology, 1988,12(3):74-79.
[12] 胡克珍，王继贤，詹晓君，等．利用测井曲线进行小层对比的专家系统[J]．测井技术，1989,13(4):71-76. Hu Kezhen, Wang Jixian, Zhan Xiaojun, et al . An expert system for detailed correlation of well logs[J]. Well Logging Technology, 1989,13(4):71-76.
[13] 夏宏泉，刘红岐．BP 神经网络在测井资料标准化中的应用[J]．测井技术，1996,20(3):201-206. Xia Hongquan, Liu Hongqi. Application of BP neural network to normalization of logging data[J]. Well Logging Technology, 1996,20(3):201-206.
[14] 陈遵德．测井数据模式识别中的信息优化方法[J]．测井技术，1998, 22(6):43-46. Chen Zunde. A method for information optimization in pattern recognition with log data[J]. Well Logging Technology, 1998,22(6):43-46.
[15] 宋子齐，谭成仟，吴少波，等．灰色系统与神经网络技术分析软件在油田勘探开发中的应用[J]. 测井技术，2000,24(6):423-427. Song Ziqi, Tan Chengqian, Wu Shaobo, et al . Application of grey system & neural network analysis software in oilfield exploration and exploitation[J]. Well Logging Technology, 2000,24(6):423-427.
[16] 李洪奇，李雄炎，谭锋奇，等．基于数据挖掘技术的测井评价方法[J]. 测井技术，2009,33(1):16-21. Li Hongqi, Li Xiongyan, Tan Fengqi, et al . A log evaluation method based on the data mining technique[J]. Well Logging Technology, 2009,33(1):16-21.
[17] 李洪奇，谭锋奇，徐长福，等．基于决策树方法的砾岩油藏岩性识别[J]．测井技术，2010,34(1):16-21. Li Hongqi, Tan Fengqi, Xu Changfu, et al . Lithology identification of conglomerate reservoir based on decision tree method[J]. Well Logging Technology, 2010,34(1):16-21.
[18] 杨莉娜，杨斌，鲁洪江，等．五百梯气田长兴组储层裂缝发育程度的常规测井神经网络预测[J]. 中国石油勘探,2011, 16(1):10,63-69. Yang Lina, Yang Bin, Lu Hongjiang, et al . Prediction of fracture development in Changxing Formation reservoir of Wubaiti Gas Field from conventional logging data using neural Networks[J]. China Petroleum Exploration, 2011,16(1):10,63-69.
[19] 李虎，范宜仁，丛云海，等．基于改进SADE 算法的神经网络预测储层物性[J]．测井技术，2012,36(6):585-589. Li Hu, Fan Yiren, Cong Yunhai, et al . A new method predicting reservoir properties with neural network based on SADE algorithm[J]. Well Logging Technology, 2012,36(6): 585-589.
[20] 李艳华，王红涛，王鸣川，等．基于PCA 和KNN 的碳酸盐岩沉积相测井自动识别[J]．测井技术，2017,41(1):57-63. Li Yanhua, Wang Hongtao, Wang Mingchuan, et al . Automatic identification of carbonate sedimentary facies based on PCA and KNN using logs[J]. Well Logging Technology, 2017,41(1): 57-63.
[21] 石玉江，周金昱，钟吉彬，等．重构电阻率曲线识别水淹层的方法及应用[J]．测井技术，2018,42(1):42-48. Shi Yujiang, Zhou Jinyu, Zhong Jibin, et al . Method and application for identifying waterflooded layer with reconstructed resistivity curves[J]. Well Logging Technology, 2018,42(1):42-48.
[22] 谭茂金，白洋，王谦，等．当非常规油气遇到人工智能：多源数据驱动下非常规油气测井智能解释方法研究进展[C] .2019 年油气地球物理学术年会, 2019. Tan Maojin, Bai Yang, Wang Qian, et al .When unconventional oil and gas meet artificial intelligence：progress of intelligent interpretation methods for unconventional oil and gas logging driven by multi-source data[C]. Proceedings of 2019 Annual Meeting of Oil and Gas Geophysics, 2019.
[23] 杨华，石玉江，王娟，等．油气藏研究与决策一体化信息平台的构建与应用[J]．中国石油勘探，2015,20(5):1-8. Yang Hua, Shi Yujiang, Wang Juan, et al . Construction and application of reservoir research and decision-making integrated information platform[J]. China Petroleum Exploration, 2015, 20(5):1-8.
[24] 石玉江，王娟，魏红芳，等．基于梦想云的油气藏协同研究环境构建与应用[J]．中国石油勘探，2020,25(5):15-22. Shi Yujiang, Wang Juan, Wei Hongfang, et al . Construction and application of oil and gas reservoir collaborative research environment based on E&P Dream Cloud[J]. China Petroleum Exploration, 2020,25(5):15-22.
[25] 付金华，石玉江，王娟，等．长庆油田勘探开发服务型共享数据中心构建研究[J]．中国石油勘探，2017,22(6):1-8. Fu Jinhua, Shi Yujiang, Wang Juan, et al . Construction of service-oriented shared data center for exploration and development of Changqing Oilfield[J]. China Petroleum Exploration, 2017,22(6):1-8.
[26] 杨勇，黄文俊，王铁成，等．梦想云数据连环湖建设研究[J]．中国石油勘探，2020,25(5):82-88. Yang Yong, Huang Wenjun, Wang Tiecheng, et al . Research on construction of Data Interlinked Lakes of E&P Dream Cloud[J]. China Petroleum Exploration, 2020,25(5):82-88.
[27] 杜金虎，时付更，杨剑锋，等．中国石油上游业务信息化建设总体蓝图[J]．中国石油勘探，2020,25(5):1-8. Du Jinhu, Shi Fugeng, Yang Jianfeng, et al . Overall blueprint of information construction of PetroChina upstream business[J]. China Petroleum Exploration, 2020,25(5):1-8.
[28] 王同良．油气行业数字化转型实践与思考[J]．石油科技论坛，2020, 39(1):29-33. Wang Tongliang. Practice and thinking of oil and gas industrial digitalization transformation[J]. Petroleum Science and Technology Forum, 2020,39(1):29-33.
[29] 付锁堂，石玉江，丑世龙，等．长庆油田数字化转型智能化发展成效与认识[J]．石油科技论坛，2020,39(5):9-15. Fu Suotang, Shi Yujiang, Chou Shilong, et al . Achievements from digital transformation and intelligent development of Changqing Oilfield[J]. Petroleum Science and Technology Forum, 2020,39(5):9-15.
[30] 徐鹏，高健祎，陈溯，等．勘探开发数据资产化管理实践与思考[J]．石油科技论坛，2020,39(5):34-40. Xu Peng, Gao Jianyi, Chen Su, et al . Research and practice o f a s s e t m a n a g e m e n t o f e x p l o r a t i o n a n d d e v e l o p m e n t data[J]. Petroleum Science and Technology Forum, 2020,39(5):34-40.
[31] Andreas Müller, Sarah Guido. Introduction to machine learning with Python-a guide for data scientists[M]. California:O’Reilly Media, 2016.
[32] Aurélien Géron. Hands-on machine learning with scikit-learn and tensor flow-concepts, tools, and techniques for building intelligent systems[M]. California: O’Reilly Media, 2019.
[33] Sinan Ozdemir, Divya Susarla. Feature engineering made easy[M]. Birmingham: Packt Publishing, 2018.
[34] 周志华．机器学习[M]．北京：清华大学出版社，2016. Zhou Zhihua. Machine learning[M]. Beijing: Tsinghua University Press, 2016.
[35] 贾俊平，何晓群，金勇进．统计学[M]．北京：中国人民大学出版社, 2014. Jia Junping, He Xiaoqun, Jin Yongjin. Statistics[M].Beijing: China Renmin University Press, 2014.