Big data intelligent platform and application analysis for oil and gas resource development
-
摘要: 油气资源大数据智能平台的总体框架应以数据资源为基础、大数据平台算力为支撑、人工智能算法为核心，面向油气行业生产需求，构建集勘探、开发、生产数据于一体的油气数据资源池，通过数据清洗与融合提升数据质量，整合物理模拟与数据挖掘等手段，实现服务功能模块化，并在PC端、管控大屏、手机移动APP等多维平台实现智能监测、预警与展示。通过对深度学习等人工智能方法在油气工业领域的应用案例分析，表明其具有较好的应用前景。未来石油公司应与科研院所通力合作，挖掘石油工业数据的巨大潜能，实现降本增效，建设全新的智能油气工业生态圈，完成产业升级。Abstract: With the rapid improvement of exploration and monitoring technologies, the oil and gas industry has accumulated a large amount of data in the fields of seismic exploration, logging, production, and development. How to transform the huge “data resources” into “data assets” and fully utilize data and tap their real value to better serve society is a main concern in the oil and gas industry today. Therefore, the oil industry needs to complete the industrial upgrading of “Smart Oilfield” through digital and intelligent transformation. In recent years, the rise of big data technology and artificial intelligence have allowed international oil companies and oil service giants to accelerate the construction of digital and intelligent oil fields. The overall framework of the big data intelligent platform of oil and gas resources should be based on data resources with big data platform computing power as the support and artificial intelligence algorithms as the core. To meet the production needs of the oil and gas industry, it is of great urgency to build an oil and gas data resource pool that integrates exploration, development, and production data. The data quality can be improved via data cleaning and fusion. Physical simulations, data mining, and other approaches should be combined to achieve the modularization of service functions. Additionally, the goals of intelligent monitoring, early warning, and display on multi-dimensional platforms such as PC, control screen, and mobile apps can also be achieved. The analysis of artificial intelligence methods such as deep learning in the context of the oil and gas industry shows that these methods have good application prospects. In the future, oil companies should work together with scientific research institutes to tap the huge potential of oil industry data, achieve cost reduction and efficiency increase, and build a new smart oil and gas industrial ecosystem to complete industrial upgrading.
-
Key words:
- petroleum /
- natural gas /
- big data /
- artificial intelligence /
- deep learning /
- machine learning
-
图 1 SPE-one petro（美国石油工程师协会）数据库中机器学习相关文章增长图
Figure 1. Graph depicting the increase in the number of machine learning-related articles in SPE-OnePetro
图 2 国内外油气大数据智能平台构建实例图
Figure 2. Construction and example of the intelligent platform for domestic and foreign oil and gas big data
图 3 国内外油气工业数字化转型发展历程
Figure 3. Development process of the digital transformation of the oil and gas industry at home and abroad
图 5 油气大数据智能平台基本流程与总体框架
Figure 5. Basic process and overall framework of oil and gas big data intelligent platform
图 6 油气大数据智能平台Hadoop、Spark及Storm混合存储计算架构
Figure 6. Oil and gas big data intelligent platform with Hadoop, Spark, and Storm hybrid storage computing architecture
图 7 油气工业多源异构数据体的清洗融合
Figure 7. Cleaning and fusion of multi-source data in the oil and gas industry
图 8 油气行业常用人工智能算法
Figure 8. Artificial intelligence algorithms commonly used in the oil and gas industry
图 9 基于卷积神经网络的储层物性预测流程
Figure 9. Reservoir property prediction process based on convolutional neural network
图 11 基于LSTM神经网络的产量与剩余油分布预测流程
Figure 11. Prediction process of production data and remaining oil distribution based on LSTM neural network
-
[1] Hassani H, Silva E S. Big Data: a big opportunity for the petroleum and petrochemical industry. OPEC Energy Rev, 2018, 42(1): 74 doi: 10.1111/opec.12118 [2] 李大伟, 熊华平, 石广仁, 等. 基于全球典型油气田数据库的数据挖掘预处理. 大庆石油地质与开发, 2016, 35(1):66 doi: 10.3969/J.ISSN.1000-3754.2016.01.013Li D W, Xiong H P, Shi G R, et al. Preprocessing of the data tapping based on global typical oil and gas field database. Pet Geol Oilfield Dev Daqing, 2016, 35(1): 66 doi: 10.3969/J.ISSN.1000-3754.2016.01.013 [3] Lynch C. How do your data grow? Nature, 2008, 455(7209): 28 doi: 10.1038/455028a [4] Los W, Wood J. Dealing with data: Upgrading infrastructure. Science, 2011, 331(6024): 1515 [5] 李大伟, 石广仁. 油气勘探开发常用数据挖掘算法优选. 石油学报, 2018, 39(2):240 doi: 10.7623/syxb201802013Li D W, Shi G R. Optimization of common data mining algorithms for petroleum exploration and development. Acta Pet Sinica, 2018, 39(2): 240 doi: 10.7623/syxb201802013 [6] 刘伟, 闫娜. 人工智能在石油工程领域应用及影响. 石油科技论坛, 2018, 37(4):32 doi: 10.3969/j.issn.1002-302x.2018.04.006Liu W, Yan N. Application and influence of artificial intelligence in petroleum engineering area. Oil Forum, 2018, 37(4): 32 doi: 10.3969/j.issn.1002-302x.2018.04.006 [7] 林伯韬, 郭建成. 人工智能在石油工业中的应用现状探讨. 石油科学通报, 2019, 4(4):403Lin B T, Guo J C. Discussion on current application of artificial intelligence in petroleum industry. Pet Sci Bull, 2019, 4(4): 403 [8] 曾涛, 张弼弛. 国际油服公司数字化转型经验与启示. 国际石油经济, 2019, 27(7):39 doi: 10.3969/j.issn.1004-7298.2019.07.006Zeng T, Zhang B C. Experiences and enlightenments of digital transformation of international oil service companies. Int Petrol Econom, 2019, 27(7): 39 doi: 10.3969/j.issn.1004-7298.2019.07.006 [9] Bravo C E. Digital transformation for oil & gas production operations: Voice of the Oilfield™ technology[J/OL]. Halliburton Landmark (2018)[2020-07-07]. https://innovationisrael.org.il/sites/default/files/04%20Sebastian%20Kroczka%20Halliburton.pdf [10] Bryant R E, Katz R H, Lazowska E D. Big-data computing: creating revolutionary breakthroughs in commerce, science and society[J/OL]. Computing Community Consortium (2008-12-22)[2020-07-07]. http://acrhive2.cra.org/ccc/files/docs/init/Big_Data.pdf [11] 孟小峰, 慈祥. 大数据管理: 概念, 技术与挑战. 计算机研究与发展, 2013, 50(1):146 doi: 10.7544/issn1000-1239.2013.20121130Meng X F, Ci X. Big data management: concepts, technology and challenges. J Comput Res Dev, 2013, 50(1): 146 doi: 10.7544/issn1000-1239.2013.20121130 [12] Baaziz A, Quoniam L. How to use big data technologies to optimize operations in upstream petroleum industry. Int J Innov, 2015, 1(1): 19 [13] Hamzeh H. Application of Big Data in Petroleum Industry[J/OL]. ResearchGate (2016-01-12)[2020-07-07]. https://www.academia.edu/27175616/Application_of_Big_Data_in_Petroleum_Industry_Application_of_Big_Data_in_Petroleum_Industry [14] 苏健, 刘合. 石油工程大数据应用的挑战与发展. 中国石油大学学报(社会科学版), 2020, 36(3):1Su J, Liu H. Challenges and development of big data application in petroleum engineering. J China Univ Petrol Ed Social Sci, 2020, 36(3): 1 [15] Jiang J M, Younis R M. Hybrid coupled discrete-fracture/matrix and multicontinuum models for unconventional-reservoir simulation. SPE J, 2016, 21(3): 1009 doi: 10.2118/178430-PA [16] Ghassemi A, Pak A. Numerical study of factors influencing relative permeabilities of two immiscible fluids flowing through porous media using lattice Boltzmann method. J Pet Sci Eng, 2011, 77(1): 135 doi: 10.1016/j.petrol.2011.02.007 [17] Wang S, Javadpour F, Feng Q H. Molecular dynamics simulations of oil transport through inorganic nanopores in shale. Fuel, 2016, 171: 74 doi: 10.1016/j.fuel.2015.12.071 [18] 廖方宇, 洪学海, 汪洋, 等. 数据与计算平台是驱动当代科学研究发展的重要基础设施. 数据与计算发展前沿, 2019, 1(1):2Liao F Y, Hong X H, Wang Y, et al. The data and computing platform is an important infrastructure which drives modern scientific research development. Front Data Comput, 2019, 1(1): 2 [19] Shvachko K, Kuang H R, Radia S, et al. The Hadoop distributed file system // 2010 IEEE 26th Symposium on Mass Storage Systems and Technologies (MSST). Incline Village, 2010: 1 [20] Vavilapalli V K, Murthy A C, Douglas C, et al. Apache Hadoop YARN: yet another resource negotiator // Proceedings of the 4th Annual Symposium on Cloud Computing. California, 2013: 5 [21] Moon S, Lee J, Kee Y S. Introducing SSDs to the Hadoop MapReduce framework // 2014 IEEE 7th International Conference on Cloud Computing. Anchorage, 2014: 272 [22] Zaharia M, Chowdhury M, Franklin M J, et al. Spark: Cluster computing with working sets. HotCloud. 2010: 95 [23] Toshniwal A, Taneja S, Shukla A, et al. Storm@ twitter // Proceedings of the 2014 ACM SIGMOD International Conference on Management of Data. Snowbird, 2014: 147 [24] da Silva Morais T. Survey on frameworks for distributed computing: Hadoop, spark and storm // Proceedings of the 10th Doctoral Symposium in Informatics Engineering-DSIE'15. Porto, 2015: 95 [25] 李国欣, 王峰, 皮学军, 等. 非常规油气藏地质工程一体化数据优化应用的思考与建议. 中国石油勘探, 2019, 24(2):147Li G X, Wang F, Pi X J, et al. Optimized application of geology-engineering integration data of unconventional oil and gas reservoirs. China Pet Explor, 2019, 24(2): 147 [26] Hao S, Tang N, Li G L, et al. A novel cost-based model for data repairing. IEEE Trans Knowl Data Eng, 2017, 29(4): 727 doi: 10.1109/TKDE.2016.2637928 [27] Wang J N, Tang N. Towards dependable data repairing with fixing rules // Proceedings of the 2014 ACM SIGMOD International Conference on Management of Data. Snowbird, 2014: 457 [28] Rekatsinas T, Chu X, Ilyas I F, et al. HoloClean: Holistic data repairs with probabilistic inference. arXiv preprint (2017-02-02)[2020-07-07]. https://arxiv.org/abs/1702.00820 [29] He J, Veltri E, Santoro D, et al. Interactive and deterministic data cleaning // Proceedings of the 2016 International Conference on Management of Data. San Francisco, 2016: 893 [30] Aliyuda K, Howell J, Humphrey E. Impact of geological variables in controlling oil-reservoir performance: An insight from a machine-learning technique. SPE Reservoir Eval Eng, 2020, 23(4): 1314 doi: 10.2118/201196-PA [31] Ahmadi M A, Bahadori A. A LSSVM approach for determining well placement and conning phenomena in horizontal wells. Fuel, 2015, 153: 276 doi: 10.1016/j.fuel.2015.02.094 [32] Al-anazi A F, Gates I D. Support-vector regression for permeability prediction in a heterogeneous reservoir: A comparative study. SPE Reservoir Eval Eng, 2010, 13(3): 485 doi: 10.2118/126339-PA [33] 石广仁. 支持向量机在裂缝预测及含气性评价应用中的优越性. 石油勘探与开发, 2008, 35(5):588 doi: 10.3321/j.issn:1000-0747.2008.05.010Shi G R. Superiorities of support vector machine in fracture prediction and gassiness evaluation. Pet Explor Dev, 2008, 35(5): 588 doi: 10.3321/j.issn:1000-0747.2008.05.010 [34] El-Sebakhy E A. Data mining in forecasting PVT correlations of crude oil systems based on Type1 fuzzy logic inference systems. Comput Geosci, 2009, 35(9): 1817 doi: 10.1016/j.cageo.2007.10.016 [35] Patel A N, Davis D, Guthrie C F, et al. Optimizing cyclic steam oil production with genetic algorithms // SPE Western Regional Meeting: Society of Petroleum Engineers. Irvine, 2005: SPE-93906-MS [36] 卞晓冰, 张士诚, 张景臣, 等. 压裂投产低—特低渗透油藏井排距设计. 石油勘探与开发, 2015, 42(5):646 doi: 10.1016/S1876-3804(15)30059-8Bian X B, Zhang S C, Zhang J C, et al. Well spacing design for low and ultra-low permeability reservoirs developed by hydraulic fracturing. Pet Explor Dev, 2015, 42(5): 646 doi: 10.1016/S1876-3804(15)30059-8 [37] Siavashi M, Tehrani M R, Nakhaee A. Efficient particle swarm optimization of well placement to enhance oil recovery using a novel streamline-based objective function. J Energy Resour Technol, 2016, 138(5): 052903 doi: 10.1115/1.4032547 [38] Ding S W, Jiang H Q, Li J J, et al. Optimization of well placement by combination of a modified particle swarm optimization algorithm and quality map method. Comput Geosci, 2014, 18(5): 747 doi: 10.1007/s10596-014-9422-2 [39] Ahmadi M A, Zendehboudi S, Lohi A, et al. Reservoir permeability prediction by neural networks combined with hybrid genetic algorithm and particle swarm optimization. Geophys Prospect, 2013, 61(3): 582 doi: 10.1111/j.1365-2478.2012.01080.x [40] 冉启全, 李士伦, 李元元. 用神经网络模式识别沉积微相. 石油勘探与开发, 1995, 22(2):59 doi: 10.3321/j.issn:1000-0747.1995.02.009Ran Q Q, Li S L, Li Y Y. Identification of sedimentary microfacies with an artificial neural network model. Pet Explor Dev, 1995, 22(2): 59 doi: 10.3321/j.issn:1000-0747.1995.02.009 [41] 吴新根, 葛家理. 应用人工神经网络预测油田产量. 石油勘探与开发, 1994, 21(3):75Wu X G, Ge J L. The application of artificial neural network in predicting output of oil fields. Pet Explor Dev, 1994, 21(3): 75 [42] 刘想平, 汪崎生, 汤军. 用神经网络建立自喷井井底流压预测模型. 石油勘探与开发, 1997, 24(5):92 doi: 10.3321/j.issn:1000-0747.1997.05.023Liu X P, Wang Q S, Tang J. An application of neural network in developing a model for predicting flowing bottomhole pressure of flowing wells. Pet Explor Dev, 1997, 24(5): 92 doi: 10.3321/j.issn:1000-0747.1997.05.023 [43] 宋子齐, 谭成仟, 吴少波, 等. 灰色系统与神经网络技术在水淹层测井评价中的应用. 石油勘探与开发, 1999, 26(3):110Song Z Q, Tan C Q, Wu S B, et al. Application of grey system theory and neural network technology to wateredout formation logging evaluation. Pet Explor Dev, 1999, 26(3): 110 [44] Negash B M, Yaw A D. 基于人工神经网络的注水开发油藏产量预测. 石油勘探与开发, 2020, 47(2):357 doi: 10.1016/S1876-3804(20)60052-0Negash B M, Yaw A D. Artificial neural network based production forecasting for a hydrocarbon reservoir under water injection. Pet Explor Dev, 2020, 47(2): 357 doi: 10.1016/S1876-3804(20)60052-0 [45] Carpenter C. Geology-driven estimated-ultimate-recovery prediction with deep learning. J Pet Technol, 2016, 68(5): 74 doi: 10.2118/0516-0074-JPT [46] Korjani M M, Popa A S, Grijalva E, et al. Reservoir characterization using fuzzy kriging and deep learning neural networks // SPE Annual Technical Conference and Exhibition: Society of Petroleum Engineers. Dubai, 2016: 15 [47] You L J, Tan Q G, Kang Y L, et al. Reconstruction and prediction of capillary pressure curve based on particle swarm optimization-back propagation neural network method. Petroleum, 2018, 4(3): 268 doi: 10.1016/j.petlm.2018.03.004 [48] 王安辉, 张英魁, 高景龙, 等. 应用人工神经网络方法确定岩石压缩系数. 石油勘探与开发, 2003, 30(4):105 doi: 10.3321/j.issn:1000-0747.2003.04.034Wang A H, Zhang Y K, Gao J L, et al. Predicting rock compressibility by artificial neural network. Pet Explor Dev, 2003, 30(4): 105 doi: 10.3321/j.issn:1000-0747.2003.04.034 [49] Wang S H, Chen Z, Chen S N. Applicability of deep neural networks on production forecasting in Bakken shale reservoirs. J Pet Sci Eng, 2019, 179: 112 doi: 10.1016/j.petrol.2019.04.016 [50] 李道伦, 刘旭亮, 查文舒, 等. 基于卷积神经网络的径向复合油藏自动试井解释方法. 石油勘探与开发, 2020, 47(3):583Li D L, Liu X L, Zha W S, et al. Automatic well test interpretation based on convolutional neural network for a radial composite reservoir. Pet Explor Dev, 2020, 47(3): 583 [51] Zhu L P, Li H Q, Yang Z G, et al. Intelligent logging lithological interpretation with convolution neural networks. Petrophysics, 2018, 59(6): 799 [52] Huang L, Dong X S, Clee T E. A scalable deep learning platform for identifying geologic features from seismic attributes. Lead Edge, 2017, 36(3): 249 doi: 10.1190/tle36030249.1 [53] He Y F, Liu Y L, Shao S, et al. Application of CNN-LSTM in gradual changing fault diagnosis of rod pumping system. Math Problems Eng, 2019, 2019: 4203821 [54] Wang X, He Y F, Li F J, et al. A working condition diagnosis model of sucker rod pumping wells based on big data deep learning // International Petroleum Technology Conference. Beijing, 2019: 10 [55] 张东晓, 陈云天, 孟晋. 基于循环神经网络的测井曲线生成方法. 石油勘探与开发, 2018, 45(4):598Zhang D X, Chen Y T, Meng J. Synthetic well logs generation via recurrent neural networks. Pet Explor Dev, 2018, 45(4): 598 [56] Tian C, Horne R N. Recurrent neural networks for permanent downhole gauge data analysis // SPE Annual Technical Conference and Exhibition: Society of Petroleum Engineers. San Antonio, 2017: 12 [57] Lu L, Zhang G Z, Zhao C. Reservoir thickness forecasting based on deep belief networks // International Geophysical Conference. Qingdao, 2017: 733 [58] Cao J X, Wu S K. Deep learning: Chance and challenge for deep gas reservoir identification // International Geophysical Conference. Qingdao, 2017: 711 [59] Carpenter C. Artificial intelligence improves seismic-image reconstruction. J Pet Technol, 2019, 71(10): 65 doi: 10.2118/1019-0065-JPT [60] Li Q X, Luo Y N. Using GAN priors for ultrahigh resolution seismic inversion // SEG International Exposition and Annual Meeting. San Antonio, 2019: SEG-2019-3215520 [61] Zhang H J, Wang W, Wang X K, et al. An implementation of the seismic resolution enhancing network based on GAN // SEG International Exposition and Annual Meeting. San Antonio, 2019: SEG-2019-3216229 [62] Shi X J, Chen Z R, Wang H, et al. Convolutional LSTM network: A machine learning approach for precipitation nowcasting // 29th Annual Conference on Neural Information Processing Systems (NIPS 2015). Montreal, 2015: 802 [63] Xu P, Du R, Zhang Z B. Predicting pipeline leakage in petrochemical system through GAN and LSTM. Knowl-Based Syst, 2019, 175: 50 doi: 10.1016/j.knosys.2019.03.013 [64] Alakeely A, Horne R N. Simulating the behavior of reservoirs with convolutional and recurrent neural networks. SPE Reservoir Eval Eng, 2020, 23(3): 992 doi: 10.2118/201193-PA [65] Lei L, Yu L, Xiong Z, et al. Convolutional recurrent neural networks based waveform classification in seismic facies analysis // SEG International Exposition and Annual Meeting. San Antonio, 2019: SEG-2019-3215237 [66] Anifowose F, Abdulraheem A. Fuzzy logic-driven and SVM-driven hybrid computational intelligence models applied to oil and gas reservoir characterization. J Nat Gas Sci Eng, 2011, 3(3): 505 doi: 10.1016/j.jngse.2011.05.002 [67] Amiri M, Ghiasi-Freez J, Golkar B, et al. Improving water saturation estimation in a tight shaly sandstone reservoir using artificial neural network optimized by imperialist competitive algorithm–A case study. J Pet Sci Eng, 2015, 127: 347 doi: 10.1016/j.petrol.2015.01.013 [68] Saemi M, Ahmadi M, Varjani A Y. Design of neural networks using genetic algorithm for the permeability estimation of the reservoir. J Pet Sci Eng, 2007, 59(1-2): 97 doi: 10.1016/j.petrol.2007.03.007 [69] LeCun Y, Bengio Y, Hinton G E. Deep learning. Nature, 2015, 521(7553): 436 doi: 10.1038/nature14539 [70] Wu J L, Yin X L, Xiao H. Seeing permeability from images: fast prediction with convolutional neural networks. Sci Bull, 2018, 63(18): 1215 doi: 10.1016/j.scib.2018.08.006 [71] Alqahtani N, Armstrong R T, Mostaghimi P. Deep learning convolutional neural networks to predict porous media properties // SPE Asia Pacific Oil and Gas Conference and Exhibition: Society of Petroleum Engineers. Brisbane, 2018: SPE-191906-MS [72] Du S Y, Wang R F, Wei C J, et al. The connectivity evaluation among wells in reservoir utilizing machine learning methods. IEEE Access, 2020, 8: 47209 doi: 10.1109/ACCESS.2020.2976910 [73] Zaremba W, Sutskever I, Vinyals O. Recurrent neural network regularization. arXiv preprint (2015-02-19)[2020-07-07]. https://arxiv.org/abs/1409.2329 [74] Zhang Q T, Wei C J, Wang Y H, et al. Potential for prediction of water saturation distribution in reservoirs utilizing machine learning methods. Energies, 2019, 12(19): 3597 doi: 10.3390/en12193597 -
下载:
点击查看大图
图(12)
计量
- 文章访问数: 636
- HTML全文浏览量: 343
- PDF下载量: 60
- 被引次数: 0
