A prediction method of fracture aperture based on hierarchical expert committee machine model for tight reservoirs
ZHOU You1,2, ZHANG Guangzhi1,2, ZHANG Shengze1,2, LIU Junzhou3, HAN Lei3
1. Key Laboratory of Deep Oil and Gas, China University of Petroleum (East China), Qingdao, Shandong 266580, China; 2. School of Geosciences, China University of Petroleum (East China), Qingdao, Shandong 266580, China; 3. SINOPEC Petroleum Exploration and Production Research Institute, Beijing 100083, China
Abstract：Fracture aperture is a key parameter for cha-racterizing the quality of tight reservoirs and evalua-ting oil and gas productivity. Tight reservoirs have strong heterogeneity due to the influences of sedimentation, diagenesis, and tectonism, resulting in complex and irregular logging response characteristics. Consequently, it is difficult to accurately predict reservoir fracture aperture by the conventional logging interpretation method or with a single machine learning model. To solve this problem, this paper proposes a prediction method of fracture aperture based on the hierarchical expert committee machine model for tight reservoirs. Firstly, the parameters of reservoir fracture aperture are obtained from core and imaging logging data, and sensitive logging data at same depth are selected as characteristic variables to construct a sample set. Secondly, the kernel ridge regression, support vector regression, and BP neural network are used as the basic expert network units to train and learn the sample set. Thirdly, the initial weight of each basic expert network unit is adaptively generated by hierarchical network modules built with the hierarchical structure model and the gated neural network model. Lastly, the prediction performance of each basic expert network unit is comprehensively considered. The contribution of each basic expert network to the final output is determined by alternating conditional expectation transform, and the fracture aperture of the reservoir is thereby accurately predicted. The practical application shows that this method can effectively quantitatively characterize the reservoir fracture aperture in a well and provide reliable geophysical information for the evaluation of tight reservoirs.
孙龙德,邹才能,贾爱林,等.中国致密油气发展特征与方向[J].石油勘探与开发,2019,46(6):1015-1026.SUN Longde,ZOU Caineng,JIA Ailin,et al.Development characteristics and orientation of tight oil and gas in China[J].Petroleum Exploration and Development,2019,46(6):1015-1026.
[2]
贾承造,邹才能,杨智,等.陆相油气地质理论在中国中西部盆地的重大进展[J].石油勘探与开发,2018,45(4):546-560.JIA Chengzao,ZOU Caineng,YANG Zhi,et al.Signi-ficant progress of continental petroleum geology theory in basins of Central and Western China[J].Petroleum Exploration and Development,2018, 45(4):546-560.
[3]
邹才能,朱如凯,吴松涛,等.常规与非常规油气聚集类型、特征、机理及展望——以中国致密油和致密气为例[J].石油学报,2012,33(2):173-187.ZOU Caineng,ZHU Rukai,WU Songtao,et al.Types,characteristics,genesis and prospects of conventional and unconventional hydrocarbon accumulations:taking tight oil and tight gas in China as an instance[J].Acta Petrolei Sinica,2012,33(2):173-187.
[4]
吕文雅,曾联波,刘静,等.致密低渗透储层裂缝研究进展[J].地质科技情报,2016,35(4):74-83.LYU Wenya,ZENG Lianbo,LIU Jing,et al.Fracture research progress in low permeability tight reservoirs[J].Geological Science and Technology Information,2016,35(4):74-83.
[5]
吕文雅,苗凤彬,张本键,等.四川盆地剑阁地区须家河组致密砾岩储层裂缝特征及对天然气产能的影响[J].石油与天然气地质,2020,41(3):484-491.LYU Wenya,MIAO Fengbin,ZHANG Benjian,et al.Fracture characteristics and their influence on natural gas production:A case study of the tight conglome-rate reservoir in the Upper Triassic Xujiahe Formation in Jian'ge area,Sichuan Basin[J].Oil&Gas Geo-logy,2020,41(3):484-491.
[6]
PONZIANI M,ESLOB E, LUTHI S,et al.Experimental validation of fracture aperture determination from borehole electric microresistivity measurements[J].Geophysics,2015,80(3):D175-D181.
[7]
VAN STAPPEN J F, MEFTAH R, BOONE M A,et al.In situ triaxial testing to determine fracture permeability and aperture distribution for CO2 sequestration in Svalbard,Norway[J].Environmental Science&Technology,2018,52(8):4546-4554.
[8]
丁文龙,曾维特,王濡岳,等.页岩储层构造应力场模拟与裂缝分布预测方法及应用[J].地学前缘,2016,23(2):63-74.DING Wenlong,ZENG Weite,WANG Ruyue,et al.Method and application of tectonic stress field simulation and fracture distribution prediction in shale reservoir[J].Earth Science Frontiers,2016,23(2):63-74.
[9]
BOADU F K.Relating the hydraulic properties of a fractured rock mass to seismic attributes:Theory and numerical experiments[J].International Journal of Rock Mechanics and Mining Sciences,1997,34(6):885-895.
[10]
AGHLI G,MOUSSAVI-HARAMI R,MOHAMMADIAN R.Reservoir heterogeneity and fracture parameter determination using electrical image logs and petrophysical data (a case study,carbonate Asmari Formation,Zagros Basin,SW Iran)[J].Petroleum Science,2020,17(1):51-69.
[11]
孙致学,姜宝胜,肖康,等.基于新型集成学习算法的基岩潜山油藏储层裂缝开度预测算法[J].油气地质与采收率,2020,27(3):32-38.SUN Zhixue,JIANG Baosheng,XIAO Kang,et al.Prediction of fracture aperture in bedrock buried hill oil reservoir based on novel ensemble learning algorithm[J].Petroleum Geology and Recovery Efficiency, 2020,27(3):32-38.
[12]
项云飞,康志宏,郝伟俊,等.基于线性回归与神经网络的储层参数预测复合方法[J].科学技术与工程,2017,17(31):46-52.XIANG Yunfei,KANG Zhihong,HAO Weijun,et al.A composite method of reservoir parameter prediction based on linear regression and neural network[J].Science Technology and Engineering,2017,17(31):46-52.
[13]
闫星宇,顾汉明,肖逸飞,等.XGBoost算法在致密砂岩气储层测井解释中的应用[J].石油地球物理勘探,2019,54(2):447-455.YAN Xingyu,GU Hanming,XIAO Yifei,et al.XGBoost algorithm applied in the interpretation of tight-sand gas reservoir on well logging data[J].Oil Geophysical Prospecting,2019,54(2):447-455.
[14]
王俊,曹俊兴,尤加春.基于GRU神经网络的测井曲线重构[J].石油地球物理勘探,2020,55(3):510-520.WANG Jun,CAI Junxing,YOU Jiachun.Reconstruction of logging traces based on GRU neural network[J].Oil Geophysical Prospecting,2020,55(3):510-520.
[15]
何健,文晓涛,聂文亮,等.利用随机森林算法预测裂缝发育带[J].石油地球物理勘探,2020,55(1):161-166.HE Jian,WEN Xiaotao,NIE Wenliang,et al.Fracture zone prediction based on random forest algorithm[J].Oil Geophysical Prospecting,2020,55(1):161-166.
[16]
匡立春,刘合,任义丽,等.人工智能在石油勘探开发领域的应用现状与发展趋势[J].石油勘探与开发,2021, 48(1):1-11.KUANG Lichun,LIU He,REN Yili,et al.Application and development trend of artificial intelligence in petroleum exploration and development[J].Petroleum Exploration and Development,2021,48(1):1-11.
[17]
ZERROUKI A A, AÏFA T, BADDARI K.Prediction of natural fracture porosity from well log data by means of fuzzy ranking and an artificial neural network in Hassi Messaoud oil field,Algeria[J].Journal of Petroleum Science and Engineering,2014,115:78-89.
[18]
CRANGANU C,BREABAN M.Using support vector regression to estimate sonic log distributions:A case study from the Anadarko Basin,Oklahoma[J].Journal of Petroleum Science and Engineering,2013,103:1-13.
[19]
谷宇峰,张道勇,鲍志东.测井资料PSO-XGBoost渗透率预测[J].石油地球物理勘探,2021,56(1):26-37.GU Yufeng,ZHANG Daoyong,BAO Zhidong.Permeability prediction using PSO-XGBoost based on logging data[J].Oil Geophysical Prospecting,2021,56(1):26-37.
[20]
秦敏,胡向阳,梁玉楠,等.利用Stacking模型融合法识别高温、高压储层流体[J].石油地球物理勘探,2021,56(2):364-371.QIN Min,HU Xiangyang,LIANG Yunan,et al.Using stacking model fusion to identify fluid in high tempe-rature and high-pressure reservoir[J].Oil Geophysical Prospecting,2021,56(2):364-371.
[21]
ASOODEH M,BAGHERIPOUR P,GHOLAMI A.NMR parameters determination through ACE committee machine with genetic implanted fuzzy logic and genetic implanted neural network[J].Acta Geophysica,2015,63(3):735-760.
[22]
ANSARI H R.Use seismic colored inversion and power law committee machine based on imperial competitive algorithm for improving porosity prediction in a he-terogeneous reservoir[J].Journal of Applied Geophy-sics,2014,108(9):61-68.
[23]
ZHOU Z H,WU J X,TANG W.Ensembling neural networks:Many could be better than all[J].Artificial Intelligence,2002,137(1/2):239-263.
[24]
GOLSANAMI N,KADKHODAIE-ILKHCHIA,SH-ARGHI Y,et al.Estimating NMR T2 distribution data from well log data with the use of a committee machine approach:A case study from the Asmari formation in the Zagros Basin,Iran[J].Journal of Petroleum Science and Engineering,2014,114:38-51.
[25]
JAFARI K S A,MASHOHOR S.Robust committee machine for water saturation prediction[J].Journal of Petroleum Science and Engineering,2013,104:1-10.
[26]
白洋,谭茂金,肖承文,等.致密砂岩气藏动态分类委员会机器测井流体识别方法[J].地球物理学报,2021,64(5):1745-1758.BAI Yang,TAN Maojin,XIAO Chengwen,et al.Dynamic classification committee machine-based fluid typing method from wireline logs for tight sandstone gas reservoir[J].Chinese Journal of Geophysics,2021,64(5):1745-1758.
[27]
TAN M J,BAI Y,ZHANG H T,et al.Fluid typing in tight sandstone from wireline logs using classification committee machine[J].Fuel,2020,271:117601.
万方.基于生命周期的产业集群综合竞争力研究[D].浙江金华:浙江师范大学,2014.WAN Fang.Study on the Comprehensive Competitiveness of Industrial Clusters Based on Life Cycle[D].Zhejiang Normal University,Jinhua,Zhejiang,2014.
[30]
张小东,张硕,孙庆宇,等.基于AHP和模糊数学评价地质构造对煤层气产能的影响[J].煤炭学报,2017,42(9):2385-2392.ZHANG Xiaodong,ZHANG Shuo,SUN Qingyu,et al.Evaluating the influence of geological structure to CBM productivity based on AHP and fuzzy mathematics[J].Journal of China Coal Society,2017,42(9):2385-2392.
[31]
GHOLAMI A,MOHAMMADZADEH O,KORD S, et al.Improving the estimation accuracy of titration-based asphaltene precipitation through power-law committee machine (PLCM) model with alternating conditional expectation (ACE) and support vector regression (SVR) elements[J].Journal of Petroleum Exploration and Production Technology,2016,6(2):265-277.
[32]
李蒙,商晓飞,赵华伟,等.基于likelihood地震属性的致密气藏断裂预测——以四川盆地川西坳陷新场地区须二段为例[J].石油与天然气地质,2020,41(6):1299-1309.LI Meng,SHANG Xiaofei,ZHAO Huawei,et al.Prediction of fractures in tight gas reservoirs based on likelihood attribute:A case study of the 2nd member of Xujiahe Formation in Xinchang area, Western Sichuan Depression,Sichuan Basin[J].Oil&Gas Geo-logy,2020,41(6):1299-1309.
[33]
刘冬冬,杨东旭,张子亚,等.基于常规测井和成像测井的致密储层裂缝识别方法——以准噶尔盆地吉木萨尔凹陷芦草沟组为例[J].岩性油气藏,2019,31(3):76-85.LIU Dongdong,YANG Dongxu,ZHANG Ziya,et al.Fracture identification for tight reservoirs by conventional and imaging logging:a case study of Permian Lucaogou Formation in Jimsar Sag,Junggar Basin[J].Lithologic Reservoirs,2019,31(3):76-85.
[34]
周游,张广智,高刚,等.核主成分分析法在测井浊积岩岩性识别中的应用[J].石油地球物理勘探,2019,54(3):667-675.ZHOU You,ZHANG Guangzhi,GAO Gang,et al.Application of kernel principal component analysis in well logging turbidite lithology identification[J].Oil Geophysical Prospecting,2019,54(3):667-675.
[35]
EZATI M,AZIZZADEH M,RIAHI M A,et al.Cha-racterization of micro-fractures in carbonate Sarvak reservoir, using petrophysical and geological data,SW Iran[J].Journal of Petroleum Science and Engineering,2018,170:675-695.
