Rapid evaluation of capillary pressure and relative permeability for oil-water flow in tight sandstone based on a physics-informed neural network

被引:6
作者
Ji, Lili [1 ,2 ]
Xu, Fengyang [3 ]
Lin, Mian [1 ,2 ]
Jiang, Wenbin [1 ,2 ]
Cao, Gaohui [1 ]
Wu, Songtao [4 ]
Jiang, Xiaohua [4 ]
机构
[1] Chinese Acad Sci, Inst Mech, Key Lab Mech Fluid Solid Coupling Syst, Beijing 100190, Peoples R China
[2] Univ Chinese Acad Sci, Sch Engn Sci, Beijing 100190, Peoples R China
[3] China France Bohai Geoserv Co Ltd, Tianjin 300456, Peoples R China
[4] PetroChina, Res Inst Petr Explorat & Dev, Beijing 100083, Peoples R China
基金
中国国家自然科学基金;
关键词
Two-phase flow; Capillary pressure curve; Relative permeability curve; Tight sandstone; Physics-informed neural network; 2-PHASE FLOW; POROUS-MEDIA; PORE; CURVES; WETTABILITY; RESERVOIRS; BEHAVIOR; VOLUME; AREA; PART;
D O I
10.1007/s13202-023-01682-7
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
Efficient and accurate evaluation of capillary pressure and relative permeability of oil-water flow in tight sandstone with limited routinely obtainable parameters is a crucial problem in tight oil reservoir modeling and petroleum engineering. Due to the multiscale pore structure, there is complex nonlinear multiphase flow in tight sandstone. Additionally, wetting behavior caused by mineral components remarkably influences oil-water displacement in multiscale pores. All this makes predicting capillary pressure and relative permeability in tight sandstone extremely difficult. This paper proposes a physics-informed neural network, integrating five important physical models, the improved parallel genetic algorithm (PGA), and the neural network to simulate the two-phase capillary pressure and relative permeability of tight sandstone. To describe the nonlinear multiphase flow and the wettability behavior, five physical models, including the non-Darcy liquid flow rate formula, apparent permeability (AP) formula, and contact angle-capillary pressure relationship, are coupled into the neural network to improve the prediction accuracy. In addition, the input parameters and the structure of the physics-informed neural network are simplified based on analyzing the change rule of the oil-water flow with the main controlling factors, which can also save training time and improve the accuracy of the neural network. To obtain the data for training the coupled neural network, the dataset of tight sandstone in Ordos Basin is constructed with experimentally measured data and various fluid flow properties as constraints. The test results demonstrate that the estimated capillary pressure and relative permeability from the physics-informed neural network are in good agreement with the test ones. Finally, we have compared the physics-informed neural network with the quasi-static pore network model (QSPNM), dynamic pore network model (DPNM), and conventional artificial neural network (ANN). The calculation time of QSPNM and DPNM are hundreds of times longer than that of the physics-informed neural network. The coupled neural network has also performed much better than the conventional ANN. As the heterogeneity of pore spaces in tight sandstone increases, the advantages of the physics-informed neural network over ANN are more prominent. The prediction models generated in this study can estimate the capillary pressure and relative permeability based on only four routine parameters in a few seconds. Therefore, the physics-informed neural network in this paper can provide the potential parameters for large-scale reservoir simulation.
引用
收藏
页码:2499 / 2517
页数:19
相关论文
共 40 条
[1]   Liquid slip flow in a network of shale noncircular nanopores [J].
Afsharpoor, Ali ;
Javadpour, Farzam .
FUEL, 2016, 180 :580-590
[2]   Dynamic network modeling of two-phase drainage in porous media [J].
Al-Gharbi, MS ;
Blunt, MJ .
PHYSICAL REVIEW E, 2005, 71 (01)
[3]   Real-time relative permeability prediction using deep learning [J].
Arigbe, O. D. ;
Oyeneyin, M. B. ;
Arana, I. ;
Ghazi, M. D. .
JOURNAL OF PETROLEUM EXPLORATION AND PRODUCTION TECHNOLOGY, 2019, 9 (02) :1271-1284
[4]  
Blunt MJ., 2017, MULTIPHASE FLOW PERM
[5]  
BURDINE NT, 1953, T AM I MIN MET ENG, V198, P71
[6]   Inertial effects during irreversible meniscus reconfiguration in angular pores [J].
Ferrari, Andrea ;
Lunati, Ivan .
ADVANCES IN WATER RESOURCES, 2014, 74 :1-13
[7]   Synthesis of capillary pressure curves from post-stack seismic data with the use of intelligent estimators: A case study from the Iranian part of the South Pars gas field, Persian Gulf Basin [J].
Golsanami, Naser ;
Kadkhodaie-Ilkhchi, Ali ;
Erfani, Amir .
JOURNAL OF APPLIED GEOPHYSICS, 2015, 112 :215-225
[8]   Two-Phase Relative Permeability of Rough-Walled Fractures: A Dynamic Pore-Scale Modeling of the Effects of Aperture Geometry [J].
Gong, Yanbin ;
Sedghi, Mohammad ;
Piri, Mohammad .
WATER RESOURCES RESEARCH, 2021, 57 (12)
[9]   Dynamic Pore-Scale Modeling of Residual Trapping Following Imbibition in a Rough-walled Fracture [J].
Gong, Yanbin ;
Sedghi, Mohammad ;
Piri, Mohammad .
TRANSPORT IN POROUS MEDIA, 2021, 140 (01) :143-179
[10]   Quantitative Prediction Model for the Water Oil Relative Permeability Curve and Its Application in Reservoir Numerical Simulation. Part 1: Modeling [J].
Hou, Jian ;
Luo, Fuquan ;
Wang, Chuanfei ;
Zhang, Yanhui ;
Zhou, Kang ;
Pan, Guangming .
ENERGY & FUELS, 2011, 25 (10) :4405-4413