Method and application of homogeneous digital core permeability prediction based on TensorFlow

被引：0

作者：

Jing W. ^{[1
]}

Li B. ^{[1
]}

Yang S. ^{[1
]}

Zhang L. ^{[1
]}

Sun H. ^{[1
]}

Yang Y. ^{[1
]}

Li A. ^{[1
]}

机构：

[1] School of Petroleum Engineering in China University of Petroleum (East China), Qingdao

来源：

Li, Aifen (aifenli@upc.edu.cn) | 1600年 / University of Petroleum, China卷 / 45期

关键词：

BP artificial neural network; Digital core; Permeability prediction; TensorFlow;

D O I：

10.3969/j.issn.1673-5005.2021.04.013

中图分类号：

学科分类号：

摘要：

The permeability of core samples is usually measured in laboratory using conventional techniques, which is inefficient, tedious and time-consuming. In this study, a permeability prediction method for homogeneous digital cores was proposed based on machine learning. Firstly, a large number of homogeneous digital cores were randomly generated. Their porosity and permeability were calculated by a pore network model, and the results were taken as the sample database for establishing a machine learning model. Then, based on the BP artificial neural network method, the porosity and permeability data of the cores were extracted and analyzed, and used for training the corresponding machine learning model. The accuracy of the machine learning model was verified in comparison with laboratory experiments. The results show that the machine learning model can provide an accurate and efficient method for permeability prediction. The error between the permeability calculated by the model and that measured by experiment is only 3. 1%. The machine learning method can be applied in oilfield for core analysis, which can avoid a large number of core testing, and improve the calculation efficiency of core permeability. © 2021, Editorial Office of Journal of China University of Petroleum(Edition of Natural Science). All right reserved.

引用

页码：108 / 113

页数：5

共 19 条

[1] SHIRANGI M., Applying machine learning algorithms to oil reservoir production optimization, (2012)
[2] DENG S, SAKURAI A., Crude oil spot price forecasting based on multiple crude oil markets and time flames, Energies, 7, 5, pp. 2761-2779, (2014)
[3] KIDD J., Detecting surface oil using unsupervised learning techniques on MODIS satellite data, (2012)
[4] CHAKI S., Reservoir characterization: a machine learning approach, (2015)
[5] GUO Changjie, WANG Haoxiang, LIU Xiao, Et al., Analysis of the application scenario of machine learning technology in oil and gas industry, Information System Engineering, 5, pp. 100-103, (2017)
[6] LI Junjian, CHENG Baoyang, LIU Renjing, Et al., Micro mechanism of pore scale glutenite water sensitivity based on digital core, Acta Petrolei Sinica, 40, 5, pp. 595-602, (2019)
[7] KNACKSTEDT M, ARNS C, GHOUS A, Et al., 3D imaging and characterization of the pore space of carbonate core: implications to single and two phase flow properties: the International Symposium of the Society of Core Analysts, (2006)
[8] KNACKSTEDT M A, ARNS C H, SOK R M, Et al., 3D pore scale characterisation of carbonate core: relating pore types and interconnectivity to petrophysical and multiphase flow properties: the International Petroleum Technology Conference, (2007)
[9] ZHANG Lei, YAO Jun, SUN Hai, Et al., Permeability calculation in shale using lattice Boltzmann method, Journal of China University of Petroleum(Edition of Natural Science), 38, 1, pp. 87-91, (2014)
[10] SUN Hai, YAO Jun, ZHANG Lei, Et al., A computing method of shale permeability based on pore structures, Journal of China University of Petroleum(Edition of Natural Science), 38, 2, pp. 92-98, (2014)

← 1 2 →