![]() ![]() To address the above issue, physical experimental methods and numerical reconstruction methods are developed to obtain or reconstruct the structures of porous media (Zhang et al. The study about the structures of porous media is quite meaningful for the research of fluids flow, but the extremely complex structures of pore space have caused a great challenge for the accurate acquisition or reconstruction of such structures. Seepage mechanics studies the motion pattern and law of fluids flow in porous media (Okabe and Blunt 2005 Singh and Mohanty 2000), which is not only related to the properties of the fluids themselves, but also influenced by the internal structures of porous media since the topological structure and geometric characteristics of pore space directly affect the flow of fluids in porous media. Seepage is a very common natural phenomenon existing in porous media. Porous media are widely found in soil, rocks, plants, animals and other substances. Experimental comparison with some typical methods proves that this method can reconstruct HR images with favorable quality. In this paper, a method is proposed based on multistage concurrent GAN to learn the structural features of porous media from one low-resolution 3D image and then stochastically reconstruct larger-sized porous media images. However, in real experiments, constrained by the resolution of physical equipment and the size of samples, it is difficult to physically obtain a large-scale image of porous media with high-resolution (HR) since HR and large field of view are usually contradictory for physical equipment. As a typical branch of deep learning methods, generative adversarial network (GAN) can simulate a two-person zero-sum game through confrontation between a generator and a discriminator. ![]() Porous media reconstruction has been greatly developed and benefited by applying current flourishing deep learning to its simulation process thanks to the strong capability of extracting features by deep learning. The traditional methods such as multi-point statistics perform porous media reconstruction based on the statistical features of training images, but the process is possibly cumbersome and the result is less effective. ![]() Accurate porous media reconstruction has always been one of the significant research hotspots in the numerical simulation of reservoirs. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |