Adaptive weight combination forecast of rock mechanical parameters in the Fengcheng Formation of Mahu Sag
TANG Junfang1, XIONG Jian1,2, LIU Xiangjun1, GAN Renzhong3, LUO Dejiang4, LIANG Lixi1
1. National Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Southwest Petroleum University, Chengdu, Sichuan 610500, China; 2. National Center for International Research on Deep Earth Drilling and Resource Development, Ministry of Science and Technology China University of Geosciences (Wuhan), Wuhan, Hubei 430074, China; 3. PetroChina Xinjiang Oilfield Company, Karamay, Xinjiang 834000, China; 4. Geomathematics Key Laboratory of Sichuan Province, Chengdu University of Technology, Chengdu, Sichuan 610059, China
Abstract:The lithology of the Fengcheng Formation in Mahu Sag, Junggar Basin is complex. To accurately predict its rock mechanical parameters, this paper proposes an adaptive weight combination forecast method. Firstly, the paper analyzes and compares the predictive performance of traditional methods and different machine learning algorithms (BP neural network,XGBoost,support vector machine (SVM), random forest(RF), convolutional neural network(CNN), Classifation and regression tree(CART), long-short term memory neural(LSTM) network, etc.). Traditional methods are difficult to achieve accurate forecasts of rock mechanical parameters, while different machine learning algorithms have different predictive effects. The optimal machine learning algorithm model for predicting compressive strength, tensile strength, and brittleness index is SVM. The optimal models for predicting elastic modulus, Poisson’s ratio, and cohesion are BP, RF, and XGBoost, respectively. The optimal model for predicting internal friction angle and fracture toughness is LSTM network. A single machine learning algorithm is difficult to achieve synchronous and accurate forecasts of multiple rock mechanical parameters. On this basis, adaptive weight combination forecast is carried out by selecting different forecast base models for different rock mechanical parameters, assigning weights based on the forecast effect of the base models, and combining them. The results show that this method can effectively improve the forecast accuracy and generalization performance of machine learning algorithms and can achieve synchronous and accurate forecasts of multiple rock mechanical parameters in complex lithological formations.
任岩,曹宏,姚逢昌,等.吉木萨尔致密油储层脆性及可压裂性预测[J].石油地球物理勘探,2018,53(3):511-519.REN Yan, CAO Hong, YAO Fengchang, et al. Brittleness and fracability prediction for tight oil reservoir in Jimsar Sag, Junggar Basin[J]. Oil Geophysical Prospecting, 2018, 53(3): 511-519.
[2]
YONG R, CHANG C, ZHANG D, et al. Optimization of shale-gas horizontal well spacing based on geology-engineering-economy integration:A case study of Well Block Ning 209 in the National Shale Gas Development Demonstration Area[J]. Natural Gas Industry B, 2021, 8(1): 98-104.
[3]
石林,史璨,田中兰,等.中石油页岩气开发中的几个岩石力学问题[J].石油科学通报,2019,4(3):223-232.SHI Lin, SHI Can, TIAN Zhonglan, et al. Several rock mechanics problems in the development of shale gas in PetroChina[J]. Petroleum Science Bulletin, 2019, 4(3): 223-232.
[4]
熊健,林海宇,唐勇,等.砂砾岩油藏影响压裂效果关键地质力学因素研究及应用[J].石油地球物理勘探,2021,56(5):1048-1059.XIONG Jian, LIN Haiyu, TANG Yong, et al. A case study of key geomechanical factors affecting fracturing effect in sandy conglomerate reservoirs[J]. Oil Geophysical Prospecting, 2021, 56(5): 1048-1059.
[5]
朱海燕,宋宇家,唐煊赫.页岩气储层四维地应力演化及加密井复杂裂缝扩展研究进展[J].石油科学通报,2021,6(3):396-416.ZHU Haiyan, SONG Yujia, TANG Xuanhe. Research progress on 4-dimensional stress evolution and complex fracture propagation of infill wells in shale gas reservoirs[J]. Petroleum Science Bulletin,2021, 6(3): 396-416.
[6]
任岩,曹宏,姚逢昌,等.岩石脆性评价方法进展[J].石油地球物理勘探,2018,53(4):875-886.REN Yan, CAO Hong, YAO Fengchang, et al. Review of rock brittleness evaluation methods[J]. Oil Geophysical Prospecting, 2018, 53(4): 875-886.
[7]
钟自强,刘向君,刘诗琼,等.砾岩地层岩石力学参数测井预测模型构建与应用[J].科学技术与工程,2018,18(8):181-186.ZHONG Ziqiang, LIU Xiangjun, LIU Shiqiong, et al. Logging prediction model of rock mechanical parameters and its applications in conglomerate formation[J]. Science Technology and Engineering, 2018, 18(8): 181-186.
[8]
CHEN L, CHEN X, YANG Y, et al. Cuttings-test method for predicting rock strength[J]. Energy Reports, 2022, 8: 3964-3969.
[9]
GUI J, GUO J, SANG Y, et al. Evaluation on the anisotropic brittleness index of shale rock using geophysical logging[J/OL].Petroleum,2022[2022-06-08].https://www.sciencedirect.com/science/article/pii/S2405656122000463.
[10]
王英伟,王林生,覃建华,等.致密砾岩储层岩石力学参数及地应力测井评价方法研究[J].测井技术,2021,45(6):624-629.WANG Yingwei, WANG Linsheng, QIN Jianhua, et al. Log evaluation method of rock mechanics and in-situ stress characteristics of tight conglomerate formations[J]. Well Logging Technology, 2021, 5(6): 624-629.
[11]
郭思强.大庆油田T30井区扶余油层致密储层岩石力学参数建模[J].大庆石油地质与开发,2020,39(5):169-174.GUO Siqiang. Rock mechanical parameter modeling of Fuyu tight oil reservoir in Well Block T30 of Daqing Oilfield[J]. Petroleum Geology & Oilfield Development in Daqing, 2020, 39(5): 169-174.
[12]
邓晗,孟召兰,王尧,等.渤海油田砂岩储层岩石力学参数预测经验公式研究[J].海洋石油, 2020,40(2):61-66, 95.DENG Han, MENG Zhaolan, WANG Yao, et al. Study on empirical formulas for predicting rock mechanical parameters of sandstone reservoirs in Bohai Oilfield[J]. Offshore Oil, 2020, 40(2): 61-66, 95.
[13]
孙佳成,高向东.基于测井曲线的临兴区块致密砂岩力学性质研究[J].内蒙古石油化工,2020,46(5):96-99.SUN Jiacheng, GAO Xiangdong. Study on the mechanical properties for the tight sandstone in Linxing block-area based on logging curve[J]. Inner Mongulia Petrochemical Industry, 2020, 46(5): 96-99.
[14]
WAN Y, ZHANG H, LIU X, et al. Prediction of mechanical parameters for low-permeability gas reservoirs in the Tazhong Block and its applications[J]. Advances in Geo-Energy Research,2020, 4(2): 219-228.
[15]
KHOSRAVI M, TABASI S, HOSSAM ELDIEN H, et al. Evaluation and prediction of the rock static and dynamic parameters[J]. Journal of Applied Geophysics, 2022, 199: 104581.
[16]
MOHAMMAD M I. Predictive models and feature ranking in reservoir geomechanics: A critical review and research guidelines[J]. Journal of Natural Gas Science and Engineering, 2020, 82: 103493.
[17]
CHANG C, ZOBACK M, KHAKSAR A. Empirical relations between rock strength and physical properties in sedimentary rocks[J]. Journal of Petroleum Science and Engineering, 2006, 51(3/4): 223-237.
[18]
MOHAMAD E T, JAHED ARMAGHANI D, MOMENI E, et al. Prediction of the unconfined compressive strength of soft rocks: a PSO-based ANN approach[J]. Bulletin of Engineering Geology and the Environment, 2015, 74(3): 745-757.
[19]
姚军,刘磊,杨永飞,等.基于多实验成像和机器学习的页岩多尺度孔隙结构表征新方法[J].天然气工业,2023,43(1):36-46.YAO Jun, LIU Lei, YANG Yongfei, et al. A new method for characterizing multi-scale shale pore structure based on multi-experimental imaging and machine learning[J].Natural Gas Industry,2023, 43(1): 36-46.
[20]
王斌,魏柳斌,于小伟,等.不同孔隙结构碳酸盐岩的岩石物理响应特征及储层预测新方法——以鄂尔多斯盆地奥陶系马家沟组四段为例[J].天然气工业,2023,43(3):46-58.WANG Bin, WEI Liubin, YU Xiaowei, et al. Petrophysical response characteristics of carbonate rocks with different pore structures and new reservoir prediction method: A case study of the fourth member of Ordovician Majiagou Formation in the Ordos Basin[J]. Natural Gas Industry, 2023, 43(3): 46-58.
[21]
陈超,印兴耀,陈祖庆,等.基于页岩岩石物理等效模型的地层压力系数预测方法[J].石油地球物理勘探, 2022, 57(2):367-376, 394.CHEN Chao, YIN Xingyao, CHEN Zuqing, et al. Prediction for formation pressure coefficients based on an equivalent petrophysical model of shale[J]. Oil Geophysical Prospecting, 2022, 57(2): 367-376, 394.
[22]
LI Z, ZHANG L, YUAN W, et al. Logging identification for diagenetic facies of tight sandstone reservoirs: A case study in the Lower Jurassic Ahe Formation, Kuqa Depression of Tarim Basin[J]. Marine and Petroleum Geology, 2022, 139: 105601.
[23]
ASADI A. Application of artificial neural networks in prediction of uniaxial compressive strength of rocks using well logs and drilling data[J]. Procedia Engineering, 2017, 191: 279-286.
[24]
MATIN S S, FARAHZADI L, MAKAREMI S, et al. Variable selection and prediction of uniaxial compressive strength and modulus of elasticity by random forest[J].Applied Soft Computing,2018,70: 980-987.
[25]
BARZEGAR R, SATTARPOUR M, NIKUDEL M R, et al. Comparative evaluation of artificial intelligence models for prediction of uniaxial compressive strength of travertine rocks, case study: Azarshahr area, NW Iran[J]. Modeling Earth Systems and Environment, 2016, 2(2): 76.
[26]
HE M, ZHANG Z, LI N. Deep convolutional neural network-based method for strength parameter prediction of jointed rock mass using drilling logging data[J]. International Journal of Geomechanics, 2021, 21(7): 04021111.
[27]
MAHMOODZADEH A, MOHAMMADI M, GHA FOOR SALIM S, et al. Machine learning techniques to predict rock strength parameters[J]. Rock Mechanics and Rock Engineering, 2022, 55(3): 1721-1741.
[28]
ZHANG Y, WANG J, YU L, et al. An extreme bias-penalized forecast combination approach to commodity price forecasting[J]. Information Sciences, 2022, 615: 774-793.
[29]
NASIRI H, HOMAFAR A, CHELGANI C. Prediction of uniaxial compressive strength and modulus of elasticity for Travertine samples using an explainable artificial intelligence[J]. Results in Geophysical Sciences, 2021, 8: 100034.
[30]
MARYAM M, MAHMOUD B. Comparison of LLNF,ANN,and COA-ANN techniques in modeling the uniaxial compressive strength and static Young’s modulus of limestone of the Dalan Formation[J]. Natural Resources Research,2019,28:223-239.
[31]
张文扬,汪凯,袁宏俊.安徽省城镇居民人均可支配收入组合预测[J].重庆工商大学学报(自然科学版),2022,39(5):93-104.ZHANG Wenyang, WANG Kai, YUAN Hongjun. Combination forecast of per capita disposable income of urban residents in Anhui province[J]. Journal of Chongqing Technology and Business University (Natural Science Edition), 2022, 39(5): 93-104.
[32]
唐小我.最优组合预测方法及其应用[J].数理统计与管理,1992,11(1):31-35.TANG Xiaowo. Optimal combination prediction method and its application[J].Jouranl of Applied Statistics and Management, 1992, 11(1): 31-35.
[33]
冯有良,杨智,张洪,等.咸化湖盆细粒重力流沉积特征及其页岩油勘探意义——以准噶尔盆地玛湖凹陷风城组为例[J].地质学报,2023,97(3):839-863.FENG Youliang, YANG Zhi, ZHANG Hong, et al. Fine-grained gravity flow sedimentary features and their petroleum significance within saline lacustrine basins: A case study of the Fengcheng Formation in Mahu depression, Junnggar basin, China[J]. Acta Geologica Sinica, 2023, 97(3): 839-863.
[34]
邹阳,韦盼云,曹元婷,等.碱湖型页岩油“甜点”分类与主控因素——以准噶尔盆地风城组为例[J].石油学报,2023,44(3):458-470.ZOU Yang, WEI Panyun, CAO Yuanting, et al. Classification and main controlling factors of sweet spots of alkaline lake type shale oil: a case study of Fengcheng Formation in Junggar Basin[J]. Acta Petrolei Sinica, 2023, 44(3): 458-470.
[35]
LIANG L, LIU X, XIONG J, et al. New model to evaluate the brittleness in shale formation[C]. SPG/SEG 2017 International Geophysical Conference, 2017, 1248-1251.