油井地热开发的数值模拟与回归预测研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
在常规资源匮乏情况日益加重的今天,清洁、绿色、可再生能源的使用成为新一轮能源调整的重点,受到世界各国的重视。其中,地热资源以其资源储备量雄厚,方便开发利用,可持续性,而受到人们的高度关注。我国油田的油井伴生地热资源丰富,目前主要的采热手段为注水采热,二氧化碳羽流系统作为一种新的采热方法,以其更强的采热效果和对于二氧化碳地质封存的潜在能力,一经提出就成为研究的热点。但不论是哪种注入流体采热的方式,部分储层参数和注入条件对于采热效果的影响和原因,以及智能算法对采热效果的回归预测,尚未见详细报导。
     本文首先利用数值模拟的方法,分别对注入水和超临界二氧化碳开采油井地热进行建模,通过改变相应的储层参数和注入条件,分析其对采热效果的影响,并根据影响的时间、大小、方式分析成因。根据数字模拟的结果,找出对于注入不同流体采热的相应影响因子,通过智能算法中的深度学习方法对多井采热、单井采热和采热趋势变化进行回归预测。通过上述模拟和回归预测实验,得到以下几点的认识:
     1.通过对注水采热和注入超临界二氧化碳采热系统的数值模拟,可以看出后者在井下具有超强的流动性,虽然热晗值低于水,但总体的采热效果将近注水采热的一倍。
     2.对注水地热开采来说,储层温度、注水量、注水速度、储层岩石比热容、注入井和生产井井径、流体注入温度的升高,会提高注水采热的效果;储层初始盐度的升高会降低注水采热的影响效果;储层岩石渗透率、储层岩石导热系数和储层压力对采热效果影响不大。
     3.对于注入超临界二氧化碳采热来说,储层温度、储层岩石渗透率、注入量、注入速度、储层岩石导热系数、储层岩石比热容、初始注入温度的升高能够提高采热效果。该方法对储层压力变化非常敏感,会使得采热效率发生很大变化。储层初始盐度在水和二氧化碳两相流阶段的升高会降低采热效果,注入井和生产井井径对于采热的作用需根据地层压力来确定。
     4.经过实验和与传统人工神经网络的比较,采用DBNs+SVM模型,对多井采热、单井采热和采热变化趋势进行回归预测的效果相对较好,能够从样本数据的抽象特征中找出规律,并进行回归预测,预测数据与原始数据的拟合效果良好。从实验结果来说,该方法比较灵活,能够自适应的建立网络模型,适合于储层条件和初始注入条件的随时变化,相对于传统数值模拟软件来说,具有一定的优势。
With scarcity of conventional resources becoming more and more serious, the usage ofclean, green and renewable energy becomes the focus of next energy construction adjustment,which obtains attention all over the world. Among those new energy resources, the geothermalresource become a real priority because of its high reserves, convenient utilization and strongsustainability. Geothermal exploitation means of oil wells at present are water injection andCO2plume system. The latter, as a new method, get the attention of industry because of itsability of strong heat getting and potential advantage for CO2sequestration. But no matter whatkind of heating method, thermal effect and cause of some reservoir parameters and injectionconditions, and regression prediction with intelligent algorithm for thermal effect, has not beenreported.
     The thesis was written as follows: firstly, modeling for geothermal development of oilwells with injecting water and supercritical carbon dioxide with numerical simulation method;by changing the corresponding reservoir parameters and injection conditions, we computed itsinfluences on geothermal development of oil wells and analyzed its causes according to timepoint, degree and style of influences; secondly, according to the simulation result, we find outthe corresponding influencing factors of different fluid for geothermal development of oil wells;and then using deep learning as the method to predict thermal efficiency of multi-wells model,single well model and change trend of thermal efficiency. Through the experiment of numericalsimulation and intelligent regression, the following conclusions were reached:
     1. Through numerical Simulation of water and supercritical carbon dioxide injectiongeothermal exploitation system, we can see that the latter has superior buoyant, thoughenthalpy is lower than the water, its overall thermal efficiency nearly doubled to water.
     2. Improvement of parameters like reservoir temperature, injection volume, injectionrate, specific heat capacity of reservoir rock, diameter of injection well and production well,fluid injection temperature will increase thermal efficiency of water injection; Improvementof initial salt concentration of reservoir will reduce thermal efficiency of water injection; pressure, permeability and thermal conductivity of reservoir rock has little effect onthermal efficiency of water injection.
     3. Improvement of parameters like reservoir temperature, permeability of reservoirrock, injection volume, injection rate, thermal conductivity of reservoir rock, specific heatcapacity of reservoir rock, initial temperature of injected fluid can increase thermalefficiency of scCO2injection. Supercritical carbon dioxide injection geothermalexploitation system is very sensitive to the change of reservoir pressure, which will lead itto change a lot. Increasing initial level of reservoir salinity will reduce thermal efficiency ofscCO2injection in two-phase flow of water and CO2. Affection of diameter of injection andproduction well on thermal efficiency of scCO2injection should be depended on reservoirpressure.
     4. Deep belief network can complete the high dimensional feature extraction. Throughthe comparison between it and traditional artificial neural network, it was found that DBNshad been effective enough in regression prediction for multi-wells model, single-wellmodel and change trend of thermal efficiency, and could find rules from abstractcharacteristics of sample data, then predict thermal effect. The result proved thatforecasting data fitted well with the original data, but the side effect is time-consuming ifthe amount of hidden layer nodes was too big. All in all, intelligent prediction forgeothermal development of oil wells with injecting water and scCO2is more flexible, andable to build an adaptive network model, which is suitable for changes of initial injectionconditions and reservoir conditions at any time. Compared with the traditional numericalsimulation software, this method has certain advantages in some aspects, and has valuablereference for the future production.
引文
[1]董华松,黄文辉.利用遗传算法优化的小波神经网络实现地热资源预测[J].资源与产业.2014(6)
    [2]李克文.利用油气田伴生中低温地热资源发电的可行性研究[C].2010年中国地球物理年会,浙江宁波,2010-10-17—20
    [3] Brown D. A hot dry rock geothermal energy concept utilizing supercritical CO2instead ofwater[C]. Proceedings of the Twenty-Fifth Workshop on Geothermal ReservoirEngineering. Stanford, CA, USA: Stanford University.2000(6)
    [4] Milliken M. Geothermal resources at Naval petroleum reserve-3(NPR-3), Wyoming[C].Proceedings of Thirty-second Workshop on Geothermal Reservoir Engineering, Stanford,CA: Stanford University, January22-24,2007, SGP-TR-183
    [5] JIMMY B RANDOLPH, MARTIN O SAAR. Coupling carbon dioxide sequestration withgeothermal energy capture in naturally permeable, porous geologic formations:Implications for CO2sequestration [J]. Energy Procedia,2011(4):2206-2213
    [6] Randolph J, Saar M O. Coupling carbon dioxide sequestration with geothermal energycapture in naturally permeable, porous geological formations: Implications forCO2sequestration[J]. Energy Procedia,2011,4:2206-2213
    [7]张国骏.关于加快大庆地热资源开发利用的调查与思考[J].大庆社会科学.2012(04)
    [8] Li K, Zhang L, Ma Q, Liu M, et al. Low Temperature Geothermal Resources at HuabeiOilfield, China. GRC Trans.2007
    [9] Xin S, Liang H, Hu B, et al. A400kW geothermal power generator using co-producedfluids from Huabei Oilfield[J]. Geothermal Resources Council Transactions,2012,36:219-223
    [10] Erkan K, Holdman G, Blackwell D, et al. Thermal characteristics of the Chena hot springsAlaska geothermal system [C]. Proceedings of Thirtysecond Workshop on GeothermalReservoir Engineering, Stanford, CA: Stanford University.2007-1-22—24
    [11] Johnson L A, Simon D L. Electrical Power from an Oil Production Waste Stream[C].Thirty-Forth Workshop on Geothermal Reservoir Engineering Stanford University,Stanford, CA, USA.2009(2)
    [12] Johnson L A, Walker E. Oil Production Waste Stream, a Source of Electrical Power[C].Thirty-Fifth Workshop on Geothermal Reservoir Engineering Stanford University,Stanford, CA, USA.2010(2)
    [13]罗兰德·洪恩,李克文.世界地热能发电新进展[J].科技导报.2012(32)
    [14]柳清峰.昆明地热田Ⅱ块段地下热水系统渗流场的数值模拟及应用分析[硕士学位论文].昆明:昆明理工大学.2009
    [15]王月.昆明地热田Ⅱ块段地下热水系统溶质运移的数值模拟[硕士学位论文].昆明:昆明理工大学.2009
    [16]王洋,张可霓, Allan D. Woodbury等.加拿大温尼伯IKEA场地开环地热系统数值模拟[J].可再生能源.2013(8)
    [17]赵阳升,王瑞凤,胡耀青等.高温岩体地热开发的块裂介质固流热耦合三维数值模拟[J].岩石力学与工程学报.2002(12).
    [18]王贵玲,刘志明,刘庆宣等.西安地热田地热弃水回灌数值模拟研究[J].地球学报.2002(02)
    [19] Pruess K. Enhanced geothermal systems(EGS)using CO2as working fluid: A novelapproach for generating renewable energy with simultaneous sequestration of carbon[J].Ceothermics.2006(35):351-367
    [20] Pruess K, Azaroual M. On the feasibility of using supercritical CO2as heat transmissionfluid in an engineered hot dry rock geothermal system[C]. Proceedings of the Thirty-FirstWorkshop on Geothermal Reservoir Engineering. Stanford, CA, USA: Stanford University.2006(8).
    [21] Pruess K. On production behavior of enhanced geothermal systems with CO2as workingfluid[J]. Energy Conversion and Management.2008(49):1446-1454.
    [22] Atrens A D, Gurgenri H, Rudolph V. CO2thermosiphon for competitive geothermalpower generation[J].Energy&Fuels.2009(23):553-557
    [23] Atrens A D, Gurgenri H, Rudolph V. Electricity generation using a carbon-dioxidethermosiphon[J].Geothermics.2010(39):161-169
    [24] McGrail B P,Schaef H T, Glezakou V A, et al. Water reactivity in the liquid andsupercritical CO2phase:Has half the story been neglected?[J]. Energy Procedia.2009(1):3415-3419
    [25] Jacquemet N, Pironon J, Saint-Marc J. Mineralogical changes of a well cement in variousH2S-CO2(-brine)fluids at high pressure and temperature[J]. Environmental Science&Technology.2007(42):282-288
    [26] Apps J, Pruess K. Modeling geochemical processes in enhanced geothermal systems withCO2as heat transfer fluid[C]. Proceedings of the Thirty-Sixth Workshop on GeothermalReservoir Engineering. Stanford, CA, USA: Stanford University,2011(8)
    [27] Ueda A, Nakatsuka Y, Kunieda M, et al. Laboratory and field tests of CO2-water injectioninto the Ogachi hot dry rock site, Japan [J]. Energy Procedia.2009(1):3669-3674
    [28] Wakahama H, Mito S, Ohsumi T, et al. A concept of CO2georeactor sequestration at theOgachi HDR site, NE Japan[J]. Energy Procedia.2009(1):3683-3689
    [29] Rosenbaruer, R. J., T. Koksalan, et al. Experimental investigation of CO2-brine-rockinteractions at elevated temperature and pressure: implication for CO2sequestration indeep-saline aquifers [J]. Fuel Process.2005(86):1581-1597
    [30] Kaszuba, J.P., D.R.Janecky, et al. Experimental evaluation of mixed fluid reactionsbetween supercritical carbon dioxide and NaCl brine: Relevance to the integrity of ageologic carbon repository[J]. Chemical Geology.2005(217):277-293
    [31] Sugama T., L. Ecker, and T. Butcher. Carbonation of rock minerals by supercritical carbondioxide at250C[R]. Report BNL-93722-2010-IR, Energy Science and TechnologyDepartment, Brookhaven National Laboratory.2010(7)
    [32] Ott. H, K.e. Kloe, C. Taberner, et al. Rock/fluid interactions by injected of supercriticalCO2/H2S: Investigation of dry-zone formation near the injection well[J]. Society of CoreAnalysis, Halifax, Nova Scotia.2010-8-4—7
    [33] Magliocco M, Kneafsey T J, Pruess K, et al. Laboratory experimental study of hearextraction from porous media by means of CO230[C]. Proceedings of the Thirty-SixthWorkshop on Geothermal Reservoir Engineering. Stanford, CA, USA: Stanford University.2011(7)
    [34] Wakahama H, Mito S, Ohsumi T, et al. A concept of CO2georeactor sequestration at theOgachi HDR site, NE Japan [J]. Energy Procedia.2009(1):3683-3689
    [35] Ueda A, Nakatsuka Y, Kunieda M, et al. Laboratory and field tests of CO2-water injectioninto the Ogachi hot dry rocksite, Japan [J]. Energy Procedia.2009(1):3669-3674
    [36]候光武,丁信伟,陈彦泽,等.超临界二氧化碳传热特性的研究[J].化工装备技术.2006,27(1):25-29.
    [37]诸凯,侯晓飞,秦娜,等.超临界二氧化碳水平管内传热得数值模拟及与实验对比[J].热科学与技术,2008,7(1):17-21
    [38]王在明,邱正松,朱宽亮.超临界二氧化碳钻井流体井筒温度传递特性[J].钻井液与完全液.2010,27(6):1-3
    [39] Hinton, G. E. and Salakhutdinov, R. R. Reducing the dimensionality of data with neuralnetworks. Science,2006,7(313):504-507
    [40] Bengio Y, Lamblin P, Popovici D, et al. Greedy layer-wise training of deep networks[C].Advances in Neural Information Processing Systems19: Proceedings of the2006Conference.2007(19):153
    [41] Bengio Y. Learning deep architectures for AI [J]. Foundations and Trends in MachineLearning.2009,2(1):1–127
    [42]刘景旺,顾炳鸿.超临界二氧化碳流体[J].化学教学.2001(06):21-22
    [43]张宝胜,张淑洁,钟玲.喇萨杏油田各类油层水洗状况[J].大庆石油地质与开发.2002,21(06):40-43
    [44]李志勇,艾颖.大庆喇嘛甸油田剩余油分布规律口[J].大庆石油学院学报.2007(31):176-178
    [45]于生云.喇嘛甸油田北北块河流相储层流动单元划分[硕士学位论文].大庆:大庆石油学院石油工程系.2004
    [46]林玉保,张江,刘先贵,周洪涛.喇嘛甸油田高含水后期储集层孔隙结构特征[J].石油勘探与开发.2008(02)
    [47]福超.大庆喇嘛甸油田北西块储层非均质性研究[硕士学位论文].杭州:浙江大学.2009
    [48]刘钰铭,侯加根,宋保全,周新茂,陈宏魁,张腊梅.辫状河厚砂层内部夹层表征——以大庆喇嘛甸油田为例[J].石油学报.2011(05)
    [49]黄伏生.喇嘛甸油田低效无效循环带识别方法研究及其应用[博士学位论文].青岛:中国海洋大学.2008
    [50]赵云飞,胡广斌.喇嘛甸油田不同时期油层动用状况评价[J].大庆石油地质与开发.2006(03)
    [51]计秉玉,李彦兴.喇萨杏油田高含水期提高采收率的主要技术对策[J].大庆石油地质与开发.2004(05)
    [52]盖玉国.喇嘛甸油田特高含水期开发潜力分析[J].大庆石油学院学报.2009(01)
    [53]李传亮.岩石压缩系数与孔隙度的关系[J].中国海上油气(地质).2003.17(5)
    [54] Baria R, Michelet S, Baumg rtner J, Dyer B, Nicholls J, et al. Creation and mapping of5000m deep HDR/HFR reservoir to produce electricity[C]. World Geothermal Congress2005, Antalya, Turkey.2005-5-24—29
    [55] Dezayes C, Genter A, Hooijkaas, GR. Deep-seated geology and fracture system of theEGS Soultz reservoir (France) based on recent5km depth boreholes[C]. WorldGeothermal Congress2005, Antalya, Turkey.2005-5-24—29
    [56] Brill, J.P., H. Mukherjee. Multiphase Flow in Wells[J]. SPE Monograph, Society ofPetroleum Engineers, Richardson, TX.1999(17)
    [57] W. D. Gunter, B. Wiwehar, E. H. Perkins. Aquifer disposal of CO2-rich greenhouse gases:Extension of the time scale of experiment for CO2-sequestering reactions by geochemicalmodelling [J]. Mineralogy and Petrology.1997(1-2)
    [58] Bando S, Takemura F, Nishio M, Hihara E, Akai M. Solubility of CO2in aqueous solutionsof NaCl at(30to60)℃and (10to20)MPa[J]. Chemical Engineering.2003
    [59] Bachu S, Gunter W D, Perkins E H. Aquifer disposal of CO2: Hydrodynamic and mineraltrapping[J]. Energy Converse Management.1994
    [60] D.H.S. Law, S. Bachu. Hydrogeological and numerical analysis of CO2disposal in deepaquifers in the Alberta sedimentary basin[J]. Energy Convers. Manag.1996
    [61] Hitchon,B. Aquifer disposal of carbon dioxide: hydro-dynamic and mineral trapping-proofof concept[J].1996
    [62] Bergman P D, Winter E M. Disposal of Carbon-Dioxide in Aq-uifers in the US[J]. EnergyConversion and Management.1995
    [63] S. Holloway, D. Savage. The potential for aquifer disposal of carbon dioxide in the UK[J].Energy Conversion.1993
    [64] Ide S T, Jessen K, Orr F M Jr. Storage of CO2in saline aqui-fers: Effects of gravity,viscous, and capillary forces on a-mount and timing of trapping[J]. International Journal ofGreenhouse Gas Control.2007
    [65] Lindeberg E, Bergmo P. The long term fate of CO2injected into an aquifer[C].Proceedings of the6th International Conference on Greenhouse Gas Control Technology.2002
    [66] Pruess K, Xu T, Apps J. et al. Numerical Modeling of Aquifer Disposal of CO2[J]. Societyof Petroleum Engineers Journal.2003
    [67] Z.-H. Zhou and M. Li. Tri-training: Exploiting unlabeled data using three classifiers[J].IEEE Transactions on Knowledge and Data Engineering,2005,17(11):1529–1541
    [68] T. G. Dietterich. Ensemble methods in machine learning[J]. Proceedings of the1stInternational Workshop on Multiple Classifier Systems (MCS’00), Cagliari, Italy, LNCS1867,2000:1-15
    [69] M. Li, Z.-H. Zhou. Improve computer-aided diagnosis with machine learning techniquesusing undiagnosed samples[J]. IEEE Transactions on Systems, Man and Cybernetics–Part A, in press
    [70] LEE T S, MUMFORD D, ROMERO R, et al. The role of the primary visual cortex inhigher level vision [J]. Vision research,1998,38(15):2429-2454
    [71] BRAVKRMAN M. Poly-logarithmic independence fools bounded-depth boolean circuits[J]. Communications of the ACM,2011,54⑷:108-115
    [72] Hinton G E, Dayan P, Frey B J, et al. The "wake-sleep" algorithm for unsupervised neuralnetworks [J]. Science.1995,268(5214):1158–1161
    [73] HINTON G, OSINDERO S, THE Y. A fast learning algorithm for deep belief nets [J].Netural computation.2006,18(7):1527-1554
    [74] VINCENT P, LAROCHELLE H, BENGIO Y, et al. Extracting and composing robustfeatures with denoising autoencoders[C]. Proceedings of the25th international conferenceon Machine learning.2008:1096–1103
    [75] ACKLEY H, HINTON E, SEJNOWSKI J. A learning algorithm for Boltzmannmachines[J]. Cognitive Science.1985:147–169
    [76] SMOLENSKY P. Information processing in dynamical systems: Foundations of harmonytheory[J]. D. E. Rumelhart and J. L. McClelland (Eds.), Parallel distributed processing.1986,1:194–281
    [77] HINTON G. Training Products of Experts by Minimizing Contrastive Divergence[J].Neural Computation.2000(14):1771–1800
    [78] TIELEMAN T. Training restricted Boltzmann machines using approximations to thelikelihood gradient[C]. Proceedings of the25th international conference on Machinelearning.2008:1064–1071
    [79] LIU J S. Monte Carlo Strategies in Scientific Computing[M]. Corrected, Springer.2008
    [80] CARREIRA-PERPINAN M A, HINTON G E. On Contrastive Divergence Learning[M].Artificial Intelligence and Statistics, Barbados,2005
    [81] SUTSKEVER I, TIELEMAN T. On the Convergence Properties of ContrastiveDivergence[J]. Journal of Machine Learning Research-Proceedings Track.2010(9):789–795
    [82] TIELEMAN T, HINTON G. Using fast weights to improve persistent contrastivedivergence[C]. Proceedings of the26th Annual International Conference on MachineLearning.2009
    [83] SALAKHUTDINOV R. Learning Deep Boltzmann Machines using Adaptive MCMC[C].Proceedings of the27th International Conference on Machine Learning.2010b
    [84] DESJARDINS G, COURVILLE A, BENGIO Y. Adaptive Parallel Tempering forStochastic Maximum Likelihood Learning of RBMs[C]. NIPS2010Workshop on DeepLearning and Unsupervised.2010b
    [85] MARINARI E, PARISI G. Simulated Tempering: A New Monte Carlo Scheme[J]. EPL(Europhysics Letters),1992,19(6):451–458
    [86]谢云,尤矢勇.一种并行模拟退火算法——加温退火算法.武汉大学学报(并行计算专刊)[J].1991:49-59
    [87]王子才,张彤,王宏伟.基于混沌变量的模拟退火优化方法[J].控制与决策.1999(04)
    [88] Szu H, Telfer B and Kadambe S. Neural network adaptive wave lets for signalrepresentation and classification [J]. Optical Engineering,1992,36(9):1907~1916
    [89] HINTON G. A Practical Guide to Training Restricted Boltzmann Machines[R].http://www.cs.toronto.edu/~hinton/absps/guideTR.pdf,2010
    [90] NEAL R M. Annealed Importance Sampling [J]. Statistics and computing.1998(11):125–139
    [91] HINTON G E. Distributed representations [R]. Tech. Report, University of Toronto.1984
    [92] Su C T, Yang C H. Feature selection for the SVM: anapplication to hypertension diagnosis[J]. E xpert Systems with Application.2008,34(1):754-763
    [93]张学工.关于统计学习理论与支持向量机[J].自动化学报.2000,26(1):34-39
    [94] Liu Xianglou, JIA Dongxu, LI Hui. Research on Kernel parameter optimization of supportvector machine in speaker recognition[J]. Science Technology and Engineering.2010,10(7):1669-1673
    [95]王兴玲,李占斌.基于网格搜索的支持向量机核函数参数的确定[J].中国海洋大学学报.2005,35(5):859-862
    [96]王健峰等.基于改进的网格搜索法的SVM参数优化[J].应用科技,2012,6,39(3):28-31
    [97] Chen P W, Wang J Y, Lee H. Model selection of SVMs using GA approach[C]. Proc of2004IEEE Int Int Joint Conf on Neural Networks. Piscataway, USA.2004:2035-2040
    [98] Eberhart R, Kenney J. A new optimizer using particle swrm theory[C]. Proc of thesixth International Symposium on Micro Machine and Human Science. Piscataway, USA.1995:39-43
    [99]郭晓蕊,王德意,杨国清,景敏,李琼.基于改进粒子群优化算法的风电场最大接入容量计算[J].中国电力.2011(01)
    [100]刘华蓥.粒子群优化算法的改进研究及在石油工程中的应用[博士学位论文].大庆:东北石油大学.2012
    [101]赵晶.量子行为粒子群优化算法及其应用中的若干问题研究[博士学位论文].无锡:江南大学.2013
    [102] Shi Y, Eberhart R C. A modified particle swarm optimizer[C]. Proc. of the IEEE Int'lConf. of Evolutionary Computation. Piscataway:IEEE Press.1998:69-73
    [103]魏漪,赵国玺,周雯鸽,韩发俊,李涛低.模糊数学方法在长庆油田低渗透储层综合评价中的应用[J].石油天然气学报.2011(01)
    [104] Erkan K, Holdman G, Blackwell D, et al. Thermal characteristics of the Chena hotsprings Alaska geothermal system [C]. Proceedings of Thirtysecond Workshop onGeothermal Reservoir Engineering, Stanford, CA:Stanford University.2007-1-22—24
    [105] Lyle A, Johnson P E, Everett D W. Oil production waste stream: A source of electricalpower [C]. Proceedings of Thirty-fifth Workshop on Geothermal Reservoir Engineering,Stanford, CA: Stanford University.2010-2-1—3
    [106] Cubric S. Recovery of geothermal energy from oil reservoir aquifers[R]. AmericanInstitute of Mining, Metallurgical and Petroleum Engineers. SPE6976,1977
    [107] Zhang L, Yuan J, Liang H, et al. Energy from Abandoned oil and gas reservoirs [C]. The2008SPE Asia Pacific Oil&Gas Conference and Exhibition, Perth, Australia.2008-10-20-22,SPE115055
    [108] Joost J, Brasz J B, Bruce P B, et al. Power production from a moderate temperaturegeothermal resource [C]. M J8IBNIGeothermal Resources Council Annual Meeting, Reno,NV, USA, September25-28,2005
    [109] McKenna J R, Blackwell D D, Moyes C P. et al. Geothermal electric power supplypossible from Gulf Coast, Midcontinent oil field waters[J]. Oil&Gas Journal,2005,103(33):34-40
    [110] Zhang L, Liu M, Li K. Estimation of geothermal reserves in oil and gas reservoirs [C].2009SPE Western Regional Meeting, San Jose, CA,USA, March24-26,2009:120031-MS
    [111]Gong B, Xin S, Li K. Numerical studies on power generation from coproducedgeothermal resources in oil fields and change in reservoir temperature[J]. RenewableEnergy,2012
    [112]李苏武.变废为宝、综合利用开发地热资源、发展新型产业[C].21世纪中国地热可持续发展论文集,北京,2002:140-145
    [113]陈墨香,汪集旸.中国地热资源[M].北京:科学出版社,1994
    [114]Xin S, Liang H, Hu B, et al. A400kW geothermal power generator using co-producedfluids from Huabei Oilfield [J]. Geothermal Resources Council Transactions,2012,36:219-223
    [115]雷群,王红岩,魏伟,等.油气田地热开发前景潜力分析[J].天然气工业,2008,28(12):127-129
    [116]Sarikaya, R., Hinton, G. E. and Deoras, A. Application of Deep Belief Networks forNatural Language Understanding. IEEE Transactions on Audio, Speech and LanguageProcessing.2014
    [117]Graves, A., Mohamed, A. and Hinton, G. E. Speech Recognition with Deep RecurrentNeural Networks. In IEEE International Conference on Acoustic Speech and SignalProcessing (ICASSP2013) Vancouver,2013
    [118]Graves, A., Mohamed, A. and Hinton, G. E. Speech Recognition with Deep RecurrentNeural Networks. In IEEE International Conference on Acoustic Speech and SignalProcessing (ICASSP2013) Vancouver,2013
    [119]Deng, L., Hinton, G. E. and Kingsbury, B. New types of deep neural network learning forspeech recognition and related applications: An overview. In IEEE InternationalConference on Acoustic Speech and Signal Processing (ICASSP2013) Vancouver,2013

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700