Modeling study of sandstone permeability under true triaxial stress based on backpropagation neural network, genetic programming, and multiple regression analysis

Yu，Beichen1,2; Zhao，Honggang1,2; Tian，Jiabao5; Liu，Chao1,2,3,4; Song，Zhenlong6; Liu，Yubing1,2; Li，Minghui1,2

2021-02-01

10.1016/j.jngse.2020.103742

Journal of Natural Gas Science and Engineering   影响因子和分区

1875-5100

2212-3865

Permeability evolution of sandstone is of great significance in the development of tight sandstone gas reservoirs. Traditional laboratory tests have the disadvantages of high cost and long testing time. Therefore, the present study employed use artificial intelligence systems, i.e., backpropagation neural network (BPNN), genetic programming (GP), and multiple regression analysis to construct prediction models of sandstone permeability based on the coupling effect of true triaxial stress field and pore pressure. The results showed that the permeability prediction obtained from the systems fit well with the experimental data, and evidenced that permeability increased with pore pressure and decreased with increase in principal stress. Sensitivity analysis showed that the pore pressure has the greatest influence on sandstone permeability under different true triaxial stress. The effect of anisotropic principal stress on permeability exhibited σ > σ > σ under fixed pore pressure. Further assessment based on a combination of five evaluation indexes showed that the prediction accuracy of the BPNN model was better.

Artificial intelligence systems Permeability Pore pressure True triaxial stress

EI ; SCI

英语

其他

National Natural Science Foundation of China[51874053] ; Graduate Research and Innovation Foundation of Chongqing, China["CYS19013","CYB19046","CYB 19045"]

Energy & Fuels ; Engineering

Energy & Fuels ; Engineering, Chemical

WOS:000606642600001

ELSEVIER SCI LTD

20205109658933

Sandstone ; Neural networks ; Petroleum reservoir engineering ; Backpropagation ; Sensitivity analysis ; Forecasting ; Genetic algorithms ; Regression analysis ; Genetic programming

Minerals:482.2 ; Soils and Soil Mechanics:483.1 ; Petroleum Deposits : Development Operations:512.1.2 ; Computer Programming:723.1 ; Artificial Intelligence:723.4 ; Mathematics:921 ; Mathematical Statistics:922.2

2-s2.0-85097771042

Scopus

1.State Key Laboratory of Coal Mine Disaster Dynamics and Control,Chongqing University,Chongqing,400030,China
2.School of Resources and Safety Engineering,Chongqing University,Chongqing,400030,China
3.State Key Laboratory for Geomechanics and Deep Underground Engineering,China University of Mining and Technology,Xuzhou,221116,China
4.School of Mechanics and Civil Engineerig,China University of Mining and Technology,Xuzhou,221116,China
5.Yanzhou Coal Mining Company Limited Jining No.3 Coal Mine,Jining,272000,China
6.Department of Earth and Space Sciences,Southern University of Science and Technology,Shenzhen,518055,China

Yu，Beichen,Zhao，Honggang,Tian，Jiabao,et al. Modeling study of sandstone permeability under true triaxial stress based on backpropagation neural network, genetic programming, and multiple regression analysis[J]. Journal of Natural Gas Science and Engineering,2021,86.

Yu，Beichen.,Zhao，Honggang.,Tian，Jiabao.,Liu，Chao.,Song，Zhenlong.,...&Li，Minghui.(2021).Modeling study of sandstone permeability under true triaxial stress based on backpropagation neural network, genetic programming, and multiple regression analysis.Journal of Natural Gas Science and Engineering,86.

Yu，Beichen,et al."Modeling study of sandstone permeability under true triaxial stress based on backpropagation neural network, genetic programming, and multiple regression analysis".Journal of Natural Gas Science and Engineering 86(2021).