A Review of the Application Progress of Machine Learning in Oil and Gas Industry

doi:10.11885/j.issn.1674-5086.2020.06.05.03

Abstract

Abstract: With the rise of deep learning in recent years, machine learning has been further developed in the oil and gas field. However, due to the particularity and complexity of the oil and gas industry, there is no training sample base suitable for deep learning, nor a targeted model establishment and selection method system. In addition, the uninterpretability of methods such as deep learning leads to the high dependence of learning models on the environment, which restricts the popularization and application of machine learning in the oil and gas industry. Starting from the development stage of machine learning, this paper introduces the major breakthroughs and problems in the application of machine learning in various fields of oil and gas industry. Then, suggestions are given on the processing methods and sample building of different types of data in the oil and gas industry, and how to carry out model adaptability analysis, etc. Finally, the development potential and research direction of machine learning in oil and gas artificial intelligence are proposed.

Key words: artificial intelligence, machine learning, deep learning, oil and gas industry, review

CLC Number:

TE19

MIN Chao, DAI Boren, ZHANG Xinhui, DU Jianping. A Review of the Application Progress of Machine Learning in Oil and Gas Industry[J]. Journal of Southwest Petroleum University(Science & Technology Edition), 2020, 42(6): 1-15.

0
/ / Recommend

Add to citation manager EndNote|Ris|BibTeX

URL: http://journal15.magtechjournal.com/Jwk_xnzk/EN/10.11885/j.issn.1674-5086.2020.06.05.03

http://journal15.magtechjournal.com/Jwk_xnzk/EN/Y2020/V42/I6/1

References

[1] 陈仲为. 深度学习的发展以及应用[J]. 现代计算机, 2019(17):46-50. doi:10.3969/j.issn.1007-1423.2019.17.010 CHEN Zhongwei. Development and application of deep learning[J]. Modern Computer, 2019(17):46-50. doi:10.3969/j.issn.1007-1423.2019.17.010
[2] 骞宇澄,刘昭策. 深度学习的实现与发展——从神经网络到机器学习[J]. 电子技术与软件工程, 2017(11):30-31. QIAN Yucheng, LIU Zhaoce. Realization and development of deep learning:From neural network to machine learning[J]. Electronic Technology and Software Engineering, 2017(11):30-31.
[3] 王斌. 人工智能技术在石油工程领域的最新应用[J]. 信息系统工程, 2018(10):95. WANG Bin. The latest application of artificial intelligence technology in the field of petroleum engineering[J]. Information System Engineering, 2018(10):95.
[4] 佩德罗·多明戈斯. 终极算法:机器学习和人工智能如何重塑世界[M]. 黄方萍,译. 北京:中信出版社, 2017. DOMINGOS P. Ultimate algorithms:How machine learning and artificial intelligence are reshaping the world[M]. HUANG Fangping, Trans.. Beijing:Citic Press, 2017.
[5] 刘伟,闫娜. 人工智能在石油工程领域应用及影响[J]. 石油科技论坛, 2018, 37(4):32-40. doi:10.3969/j.issn.1002-302x.2018.04.006 LIU Wei, YAN Na. Application and influence of artificial intelligence in the field of petroleum engineering[J]. Petroleum Science and Technology Forum, 2018, 37(4):32-40. doi:10.3969/j.issn.1002-302x.2018.04.006
[6] 陈强,李晓磊. 国际石油工业界POCS及其相关项目的进展[J]. 石油地球物理勘探, 1995, 30(2):223-229. CHEN Qiang, LI Xiaolei. Progress of POCS and related projects in international petroleum industry[J]. Petroleum Geophysical Exploration, 1995, 30(2):223-229.
[7] MCCORMACK M P. Neural networks in the petroleum industry[C]. SEG Technical Program Expanded Abstracts, 1991. doi:10.1190/1.1889172
[8] GUO Yi, HANSEN R O, HARTHILL N. Feature recognition from potential fields using neural networks[C]. SEG Technical Program Expanded Abstracts, 1992. doi:10.1190/1.1822039
[9] NAZI G M, ASHENAYI K, LEA J F, et al. Application of artificial neural network to pump card diagnosis[C]. SPE 25420-PA, 1994. doi:10.2118/25420-PA
[10] ALI J K. Neural networks:A new tool for the petroleum industry?[C]. SPE 27561-MS, 1994. doi:10.2118/27561 MS
[11] 鲍慎毅,高朝晖. 人工智能注采调配及其在孤东油田开发中的应用[J]. 石油工业计算机应用,1995(1):45-51. BAO Shenyi, GAO Zhaohui. Artificial intelligence injection, production and deployment and its application in Gudong Oilfield development[J]. Computer Application in Petroleum Industry, 1995(1):45-51.
[12] MOHAGHEGH S. Virtual-intelligence applications in petroleum engineering:Part 1-Artificial neural networks[C]. SPE 58046-JPT, 2000. doi:10.2118/58046-JPT
[13] MOHAGHEGH S. Virtual-intelligence applications in petroleum engineering:Part 2-Evolutionary computing[C]. SPE 61925-JPT, 2000. doi:10.2118/61925-JPT
[14] MOHAGHEGH S. Virtual-intelligence applications in petroleum engineering:Part 3-Fuzzy logic[C]. SPE 62415-JPT, 2000. doi:10.2118/62415-JPT
[15] 林伯韬,郭建成. 人工智能在石油工业中的应用现状探讨[J]. 石油科学通报, 2019, 4(4):403-413. doi:10.3969/j.issn.2096-1693.2019.04.036 LIN Botao, GUO Jiancheng. Application of artificial intelligence in petroleum industry[J]. Chinese Petroleum Science Bulletin, 2019, 4(4):403-413. doi:10.3969/j.issn.2096-1693.2019.04.036
[16] HANSEN K V. Neural networks for primary reflection identification[C]. SEG Technical Program Expanded Abstracts, 1993. doi:10.1190/1.1822450
[17] FOGG A N. Petro-seismic classification using neural networks:UK onshore[C]. SEG Technical Program Expanded Abstracts, 2000. doi:10.1190/1.1815670
[18] CLIFFORD A, AMINZADEH F. Gas detection from absorption attributes and amplitude versus offset with artificial neural networks in grand bay field[C]. SEG Technical Program Expanded Abstracts, 2011. doi:10.1190/1.3627988
[19] OGIESOBA O, AMBROSE W. Seismic attributes investigation of depositional environments and hydrocarbon sweet-spot distribution in Serbin Field, Taylor Group, Central Texas[C]. SEG Technical Program Expanded Abstracts, 2017. doi:10.1190/segam2017-17559583.1
[20] RICHARDSON A. Generative adversarial networks for model order reduction in seismic full-waveform inversion[C]. arXiv:1806.00828v1, 2018.
[21] LUKAS M, OLIVIER D, MARTIN J. Blunt, Stochastic seismic waveform inversion using generative adversarial networks as a geological prior[C]. arXiv:1806.03720v1, 2018. doi:10.3997/2214-4609.201803018
[22] ZHANG Tuanfeng, 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, 16:541-549. doi:10.1007/s12182-019-0328-4
[23] LI Shucai, LIU Bin, REN Yuxiao, et al. Deep-learning inversion of seismic data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(3):2135-2149. doi:10.1109/TGRS.2019.2953473
[24] GUPTA K D, VALLEGA V, MANIAR H, et al. A deeplearning approach for borehole image interpretation[C]. SPWLA 60th Annual Symposium, 2019. doi:10.30632/T60ALS-2019_BB
[25] ERTEKIN T, SUN Qian. Artificial intelligence applica-tions in reservoir engineering:A status check[J]. Energies, 2019, 12(15):2897. doi:10.3390/en12152897
[26] NAZARI S, KUZMA H A, RECTOR J W. Predicting permeability from well log data and core measurements using support vector machines[C]. SEG Technical Program Expanded Abstracts, 2011. doi:10.1190/1.3627601
[27] ZHAO Tao, VERMA S, DEVEGOWDA D, et al. TOC estimation in the barnett shale from triple combo logs using support vector machine[C]. Society of Exploration Geophysicists International Exposition and 85th Annual Meeting, 2015. doi:10.1190/segam2015-5922788.1
[28] SCHLANSER K, GRANA D, CAMPBELL-STONE E. Petro-elastic facies classification in the marcellus shale by applying expectation maximization to measured well logs[C]. SEG Technical Program Expanded Abstracts, 2014. doi:10.1190/segam2014-0939.1
[29] ZHAO Tao, VERMA S, QI Jie, et al. Supervised and unsupervised learning:How machines can assist quantitative seismic interpretation[C]. SEG Technical Program Expanded Abstracts, 2015. doi:10.1190/segam2015-5924540.1
[30] BESTAGINI P, LIPARI V, TUBARO S. A machine learning approach to facies classification using well logs[C]. SEG Technical Program Expanded Abstracts, 2017. doi:10.1190/segam2017-17729805.1
[31] AKINNIKAWE O, LYNE S, ROBERTS J. Synthetic well log generation using machine learning techniques[C]. Unconventional Resources Technology Conference, 2018. doi:10.15530/urtec-2018-2877021
[32] GUPTA I, RAI C, SONDERGELD C H, et al. Rock typing in eagle ford, barnett, and woodford formations[C]. SPE 189968-PA, 2018. doi:10.2118/189968-PA
[33] AGAR S, GOTETI R, JOBE D, et al. Geologic risking with bayesian methods:Fracture case study in an unconventional setting[C]. GEO 2018 Conference, 2018.
[34] JOBE T D, VITAL-BRAZIL E, KHAIT M. Geological feature prediction using image-based machine learning[C]. Society of Petrophysicists and Well-Log Analysts, 2018. doi:10.30632/PJV59N6-2018a1
[35] TSAI K C, HU Wenyi, WU Xuqing, et al. First-break automatic picking with deep semisupervised learning neural network[C]. SEG Technical Program Expanded Abstracts, 2018. doi:10.1190/segam2018-2998106.1
[36] ALQAHTANI N, ARMSTRONG R T, MOSTAGHIMI P. Deep learning convolutional neural networks to predict porous media properties[C]. SPE 191906-MS, 2018. doi:10.2118/191906-MS
[37] ALFARRAJ M, ALREGIB G. Petrophysical property estimation from seismic data using recurrent neural networks[C]. SEG Technical Program Expanded Abstracts, 2018. doi:10.1190/segam2018-2995752.1
[38] LI Hao, MISRA S. Prediction of subsurface NMR T₂ distribution from formation-mineral composition using variational autoencoder[C]. Society of Exploration Geophysicists, 2017. doi:10.1190/segam2017-17798488.1
[39] LI Hao, HE Jiabo, MISRA S. Data-driven in-situ geomechanical characterization in shale reservoirs[C]. SPE 191400-MS, 2018. doi:10.2118/191400-MS
[40] AREHART R A. Drill-bit diagnosis with neural networks[C]. SPE 191400-MS. doi:10.2118/19558-PA
[41] BILGESU H I, AL-RASHIDI A F, AMINIAN K, et al. An unconventional approach for drill-bit selection[C]. SPE 68089-MS, 2001. doi:10.2118/68089-MS
[42] WANG Yanfang, SALEHI S. Drilling hydraulics optimization using neural networks[C]. SPE 173420-MS, 2015. doi:10.2118/173420-MS
[43] MORAN D P, IBRAHIM H F, PURWANTO A, et al. Sophisticated ROP prediction technology based on neural network delivers accurate resultssophisticated rop prediction technology based on neural network delivers accurate results[C]. SPE 132010-MS, 2010. doi:10.2118/132010-MS
[44] LIND Y B, KABIROVA A R. Artificial neural networks in drilling troubles prediction[C]. SPE 171274-MS, 2014. doi:10.2118/171274-MS
[45] 丁昕炜,胡泽,葛亮,等. 基于压力传感器阵列的智能井水平段油管泄漏定位技术研究[J]. 仪表技术与传感器, 2016(3):79-82. DING Xinwei, HU Ze, GE Liang, et al. Research on oil pipe leak location technology in horizontal section of intelligent well based on pressure sensor array[J]. Instrumentation Technology and Sensors, 2016(3):79-82.
[46] CAO Dingzhou, LOESEL C, PARANJI S. Rapid development of real-time drilling analytics system[C]. SPE 189595-MS, 2018. doi:10.2118/189595-MS
[47] BEN Yuxing, JAMES C, CAO Dingzhou. Development and application of a real-time drilling state classification algorithm with machine learning[C]. URTEC-2019-253-MS, 2019. doi:10.15530/urtec-2019-253
[48] ALIYEV R, PAUL D. A novel application of artificial neural networks to predict rate of penetration[C]. SPE 195268-MS, 2019. doi:10.2118/195268-MS
[49] AL-KHDHEEAWI E A, MAHDI D S, FENG Runhua. Lithology determination from drilling data using artificial neural network[C]. 53rd U S Rock Mechanics/Geomechanics Symposium, 2019.
[50] ALARFAJ I, KHOUKHI A, EREN T. Application of advanced computational intelligence to rate of penetration prediction[C]. Sixth UKSim/AMSS European Symposium on Computer Modeling and Simulation, 2012. doi:10.1109/EMS.2012.79
[51] ELKATATNY S M. Determination the rheological properties of invert emulsion based mud on real time using artificial neural network[C]. SPE 182801-MS, 2016. doi:10.2118/182801-MS
[52] LEITE C R A, LONGHIN G A, DE Sá C H M, et al. Artificial intelligence strategy minimizes lost circulation nonproductive time in Brazilian deep water pre-salt[C]. OTC-28034-MS, 2017. doi:10.4043/28034-MS
[53] LIANG Haibo, LI Guoliang, LIANG Wenlong. Intelligent early warning model of early-stage overflow based on dynamic clustering[J]. Cluster Computing, 2017(3):1-12. doi:10.1007/s10586-017-1214-8
[54] LIANG Haibo, WANG Zhi. Application of an intelligent early-warning method based on DBSCAN clustering for drilling overflow accident[J]. Cluster Computing, 2018(1):1-10. doi:10.1007/s10586-017-1687-5
[55] HOFFIMANN J, MAO Youli, WESLEY A, et al. Sequence mining and pattern analysis in drilling reports with deep natural language processing[C]. arXiv:1712.01476v1, 2017.
[56] XU Yankai, SUN Keli, XIE Hui, et al. Borehole resistivity measurement modeling using machine-learning techniques[J]. Petrophysics, 2018, 59(6):778-785. doi:10.30632/PJV59N6-2018a3
[57] SHEN Qiuyang, CHEN Jiefu, WANG Hanming. Datadriven interpretation of ultradeep azimuthal propagation resistivity measurements:Transdimensional stochastic inversion and uncertainty quantification[C]. SPWLA-2018-v59n6a4, 2018.
[58] HAN Jiahang, SUN Yanji, ZHANG Shaoning. A data driven approach of ROP prediction and drilling performance estimation[C]. IPTC-19430-MS, 2019. doi:10.2523/IPTC-19430-MS
[59] GAN Chao, CAO Weihua, WU Min, et al. Two-level intelligent modeling method for the rate of penetration in complex geological drilling process[J]. Applied Soft Computing, 2019.
[60] DENNEY D. Artificial neural networks identify restimulation candidates[C]. SPE 0200-0044-JPT, 2000. doi:10.2118/0200-0044-JPT
[61] 曾德仁,彭妥,黄诚,等. 试井设计风险评价[J]. 西南石油学院学报, 2001, 23(4):23-25. ZENG Deren, PENG Tuo, HUANG Cheng, et al. The well test design risk assessment[J]. Journal of Southwest Petroleum Institute, 2001, 23(4):23-25.
[62] FAGA A T, OYENEYIN B M. Application of neural networks for improved gravel-pack design[C]. SPE 58722-MS, 2000. doi:10.2118/58722-MS
[63] AL-FATTAH S M, STARTZMAN R A. Predicting natural gas production using artificial neural network[C]. SPE 68593-MS, 2001. doi:10.2118/68593-MS
[64] SALEHI S, HARELAND G, DEHKORDI K K, et al. Casing collapse risk assessment and depth prediction with a neural network system approach[J]. Journal of Petroleum Science and Engineering, 2009, 69(1):156-162. doi:10.1016/j.petrol.2009.08.011
[65] ADEYEMI B J, SULAIMON A A. Predicting wax formation using artificial neural network[C]. SPE 163026-MS, 2012. doi:10.2118/163026-MS
[66] RANJAN A, VERMA S, SINGH Y. Gas lift optimization using artificial neural network[C]. SPE 172610-MS, 2015. doi:10.2118/172610-MS
[67] CHU Hongyang, LIAO Xinwei, ZHANG Wenlong, et al. Applications of artificial neural networks in gas injection[C]. SPE 191606-18RPTC-MS, 2018. doi:10.2118/191606-18RPTC-MS
[68] KISS A, FRUHWIRTH R K, PONGRATZ R, et al. Formation breakdown pressure prediction with artificial neural networks[C]. SPE 191391-18IHFT-MS, 2018. doi:10.2118/191391-18IHFT-MS
[69] BRUYELLE J, GUÉRILLOT D. Optimization of waterflooding strategy using artificial neural networks[C]. SPE 196643-MS, 2019. doi:10.2118/196643-MS
[70] 邴绍强. 基于人工智能的抽油机井结蜡预警方法[J]. 石油钻探技术, 2019, 47(4):97-103. doi:10.11911/syztjs.20190937103. BING Shaoqiang. Early warning method of paraffin deposit in pumping wells based on artificial intelligence[J]. Oil Drilling Technology, 2019, 47(4):97-103. doi:10.11911/syztjs.2019093
[71] 樊浩杰. 基于人工智能算法的示功图智能识别研究[D]. 洛阳:河南科技大学, 2019. FAN Haojie. Research on intelligent recognition of indicator graph based on artificial intelligence algorithm[D]. Luoyang:Henan University of Science and Technology, 2019.
[72] 侯春华. 基于长短期记忆神经网络的油田新井产油量预测方法[J]. 油气地质与采收率, 2019, 26(3):105-110. doi:10.13673/j.cnki.cn37-1359/te.2019.03.014 HOU Chunhua. Prediction method of oil production in new wells based on long and short term memory neu-ral network[J]. Oil and Gas Geology and Recovery, 2019, 26(3):105-110. doi:10.13673/j.cnki.cn37-1359/te.2019.03.014
[73] YANG Zhaozhong, YANG Chenxi, LI Xiaogang, et al. Pattern recognition of the vertical hydraulic fracture shapes in coalbed methane reservoirs based on hierarchical bilstm network[J]. Complexity, 2020(9):1-12. doi:10.1155/2020/1734048
[74] SALEHI S, HARELAND G, DEHKORDI K K, et al. Casing collapse risk assessment and depth prediction with a neural network system approach[J]. Journal of Petroleumence & Engineering, 2009, 69(1-2):156-162. doi:10.1016/j.petrol.2009.08.011
[75] NIETO J, JANEGA G, BATLAI B, et al. An integrated approach to optimizing completions and protecting parent wells in the Montney Formation, N E B C[C]. 6th Unconventional Resources Technology Conference, 2018. doi:10.15530/urtec-2018-2902707
[76] YANG H S, KIM N S. Determination of rock properties by accelerated neural network[C]. ARMA-96-1567, 1996.
[77] DENNEY D. Neural network for time-lapse seismic reservoir monitoring[C]. SPE 0801-0044-JPT, 2001. doi:10.2118/0801-0044-JPT
[78] ELSHAFEI M, HAMADA G M. Neural network identification of hydrocarbon potential of shaly sand reservoirs[C]. SPE 110959-MS, 2007. doi:10.2118/110959 MS
[79] AL-BULUSHI N, ARAUJO M, KRAAIJVELD M, et al. Predicting water saturation using artificial neural networks (ANNs)[C]. SPWLA Middle East Regional Symposium, 2007.
[80] KOHLI A, ARORA P. Application of artificial neural networks for well logs[C]. International Petroleum Technology Conference, 2014. doi:10.2523/IPTC-17475-MS
[81] 贾虎,邓力珲. 基于流线聚类人工智能方法的水驱油藏流场识别[J]. 石油勘探与开发, 2018, 45(2):312-319. doi:10.11698/PED.2018.02.14 JIA Hu, DENG Lihui. Flow field identification of water drive reservoirs based on streamline clustering artificial intelligence[J]. Oil Exploration and Development, 2018, 45(2):312-319. doi:10.11698/PED.2018.02.14
[82] ALCOCER Y, RODRIGUES P. Neural networks models for estimation of fluid properties[C]. SPE 69624-MS, 2001. doi:10.2118/69624-MS
[83] AYOUB M A, RAJA A I, ALMARHOUN M. Evaluation of below bubble point viscosity correlations & construction of a new neural network model[C]. SPE 108439-MS, 2007. doi:10.2118/108439-MS
[84] HEGEMAN P S, DONG Chengli, VAROTSIS N, et al. Application of artificial neural networks to downhole fluid analysis[C]. SPE 123423-PA, 2009. doi:10.2118/123423-PA
[85] DENNEY D. Improved production-testing performance:Deepwater West Africa[C]. SPE 0603-0043-JPT, 2003. doi:10.2118/0603-0043-JPT
[86] DANG C, NGHIEM L, FEDUTENKO E, et al. Application of artificial intelligence for mechanistic modeling and probabilistic forecasting of hybrid low salinity chemical flooding[C]. SPE 191474-MS, 2018. doi:10.2118/191474-MS
[87] RASHIDI M, HAJIPOUR M, ASADI A. Correlation between static and dynamic elastic modulus of limestone formations using artificial neural networks[C]. 52nd U. S. Rock Mechanics/Geomechanics Symposium, 2018.
[88] RASHIDI M, ASADI A. An artificial intelligence approach in estimation of formation pore pressure by critical drilling data[J]. 52nd U.S. Rock Mechanics/Geomechanics Symposium, 2018.
[89] HAMAM H, ERTEKIN T. A Generalized continuous carbon dioxide injection design and screening tool for naturally fractured reservoirs of varying oil compositions[C]. SPE 190371-MS, 2018. doi:10.2118/190371-MS
[90] KHAN M R, TARIQ Z, ABDULRAHEEM A. Machine learning derived correlation to determine water saturation in complex lithologies[C]. SPE 192307-MS, 2018. doi:10.2118/192307-MS
[91] WANG Kun, LUO Jia, YAN Lin, et al. Artificial neural network accelerated flash calculation for compositional simulations[C]. SPE 193896-MS, 2019. doi:10.2118/193896-MS
[92] VENNA A R, LU Yinghui, WALTERS D, et al. Supportvector-machine phase classification of downhole leak flows based on acoustic signals[J]. Petrophysics, 2018, 59(6):841-848. doi:10.30632/PJV59N6-2018a8
[93] ZIMMERMANN T. Machine-learning-based automatic well-log depth matching[J]. Petrophysics, 2018, 59(6):863-872. doi:10.30632/PJV59N6-2018a10
[94] CADEI L, MONTINI M, LANDI F, et al. Big data advanced analytics to forecast operational upsets in upstream production system[C]. SPE 193190-MS, 2018. doi:10.2118/193190-MS
[95] MULUNJKAR A M, DESHPANDE A P, STEINKE S, et al. Operational excellence and product reliability enhancement through big data analytics[C]. OTC-29513-MS, 2019. doi:10.4043/29513-MS
[96] BHOWMIK S. Digital twin of subsea pipelines:Concep-tual design integrating iot, machine learning and data analytics[C]. OTC-29455-MS, 2019. doi:10.4043/29455-MS
[97] 吴钧,于晓红. 大庆油田生产经营管理与辅助决策系统设计与实施[J]. 大庆石油地质与开发, 2019, 38(5):294300. doi:10.19597/j.issn.1000-3754.201907023 WU Jun, YU Xiaohong. Design and implementation of production management and decision support system for Daqing Oilfield[J]. Daqing Petroleum Geology and Development, 2019, 38(5):294-300. doi:10.19597/j.issn.1000-3754.201907023