«Automation and Informatization of the fuel and energy complex»

Estimation of heterogeneous porous media permeability by 3D U-Net based on Minkowski functional fields

UDC: 681.5:622.276+622.279
DOI: -

Authors:

¹ National University of Oil and Gas "Gubkin University", Moscow, Russia

Keywords: permeability component tensor, 3D U-Net, binary porous medium digital model, Minkowski functionals, lattice Boltzmann method, diagonalization of the permeability tensor, Euler angles

Annotation:

The authors of the article present an alternative method for determining the components of the permeability coefficient tensor for anisotropic heterogeneous porous media from 3D images of core samples obtained by X-ray microcomputer tomography. The procedure is based on the application of image preprocessing using four fields of Minkowski functionals – morphological descriptors that take into account the geometry and topology of the skeleton structure and void space of the porous medium. Numerical modeling of a single-phase fluid flow on homogeneously averaged areas of the digital model is performed by lattice Boltzmann method (LBM). The obtained data is used to train a 3D U-Net convolutional neural network. An algorithm is proposed for converting the permeability coefficient tensor to the main components using a rotation matrix, based on which Euler angles are obtained, indicating the main directions of fluid filtration in a porous medium.

Bibliography:

1. Arsen'ev-Obraztsov S.S., Volkov E.A. Klasterizatsiya tsifrovogo 3D-obraztsa kerna s ispol'zovaniem funktsionalov Minkovskogo // Avtomatizatsiya i informatizatsiya TEK. – 2023. – № 8(601). – S. 13–22. – DOI: 10.33285/2782-604X-2023-8(601)-13-22
2. Arsen'ev-Obraztsov S.S., Volkov E.A. Mul'tiklassovaya segmentatsiya geterogennykh poristykh sred s ispol'zovaniem 3D U-Net i poley funktsionalov Minkovskogo // Avtomatizatsiya i informatizatsiya TEK. – 2024. – № 3(608). – S. 32–43.
3. Chen Beifang. A Simplified Elementary Proof of Hadwiger's Volume Theorem // Geometriae Dedicata. – 2004. – Vol. 105. – P. 107–120. – DOI: 10.1023/B:GEOM.0000024665.02286.46
4. Downscaling-Based Segmentation for Unresolved Images of Highly Heterogeneous Granular Porous Samples / S.V. Korneev, Yang Xiaofan, J.M. Zachara [et al.] // Water Resources Research. – 2018. – Vol. 54, Issue 4. – P. 2871–2890. – DOI: 10.1002/2018WR022886
5. Han Jiang, Arns C.H. Fast Fourier transform and support-shift techniques for pore-scale microstructure classification using additive morphological measures // Physical Review E. – 2020. – Vol. 101, Issue 3. – P. 033302. – DOI: 10.1103/PhysRevE.101.033302
6. Arsen'ev-Obraztsov S.S., Volkov E.A. Razrabotka kontseptsii sistemy mnogourovnevogo masshtabirovaniya petrofizicheskikh svoystv kollektora // Gubkinskiy un-t v reshenii voprosov neftegazovoy otrasli Rossii: tez. dokl. VI Region. nauch.-tekhn. konf., posvyashch. 100-letiyu M.M. Ivanovoy, M., 19–21 sent. 2022 g. – M.: RGU nefti i gaza (NIU) im. I.M. Gubkina, 2022. – S. 734–735.
7. Accurate and versatile 3D segmentation of plant tissues at cellular resolution / A. Wolny, L. Cerrone, A. Vijayan [et al.] // Elife. – 2020. – Vol. 9. – DOI: 10.7554/eLife.57613
8. Arsen'ev-Obraztsov S.S. Opredelenie tenzora koeffitsientov pronitsaemosti chislennym modelirovaniem techeniya flyuida na tsifrovoy modeli poristoy sredy // Tr. RGU nefti i gaza im. I.M. Gubkina. – 2015. – № 4(281). – S. 64–77.
9. Ronneberger O., Fischer P., Brox T. U-net: Convolutional Networks for Biomedical Image Segmentation // Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015: 18th Int. Conf., Munich, Germany, Oct. 5–9, 2015. – Springer Int. Publishing, 2015. – P. 234–241. – (Lecture Notes in Computer Science, Vol. 9351). – DOI: 10.1007/978-3-319-24574-4_28
10. Deep learning based atomic defect detection framework for two-dimensional materials / Chen Fu-Xiang Rikudo, Lin Chia-Yu, Siao Hui-Ying [et al.] // Scientific Data. – 2023. – Vol. 10, Issue 1. – P. 91. – DOI: 10.1038/s41597-023-02004-6
11. Bear J. Dynamics of Fluids in Porous Media. – Dover Publications Inc., 2013. – 800 p.
12. Nicholson W.K. Linear Algebra with Applications. – Lyryx Learning Inc., 2020. – 663 p.
13. Gill F., Myurrey U., Rayt M. Prakticheskaya optimizatsiya / per. s angl. V.Yu. Lebedeva. – M.: Mir, 1985. – 509 s.