ĭigital core reconstruction methods can be divided into two categories. 3D gray core CT images are of great significance for studying core compositions and their physical characteristics. Specifically, the core parameter characteristics, such as permeability, electrical conductivity, and elastic modulus, will also vary with the distribution of these components. Real rock samples are usually composed of multiple components, and these different components show different gray values under imaging equipment. Taking computed tomography (CT) as an example, the gray values of pixels in a 3D-core CT image comprehensively reflect the differences in the X-ray absorption coefficients of different rock components. The most commonly used method to solve this problem entails obtaining detailed information on the rock structure using physical imaging equipment. This proposed method can help us to understand and analyze various parameter characteristics in cores.Ĭurrent on-site geological monitoring approaches struggle to accurately understand and characterize the three-dimensional (3D) structural properties of rock mass. The reconstructed 3D results showed that the gray level information in the 2D image were accurately reflected in the 3D space. In addition, we used 3D convolution to determine the spatial characteristics of the core. Through the cascade of every single node network, we thus ensured continuity and variability between the reconstruction layers. Simultaneously, by adopting SD dimension promotion theory, we set the input and output of every single node of the CPGAN network to be deep gray-padding structures of equivalent size. Within this network, we propose a loss function based on the gray level distribution and pattern distribution to maintain the texture information of the reconstructed structure. Here, by combining the dimension promotion theory in super-dimension (SD) reconstruction and framework of deep learning, we propose a novel convolutional neural network framework, the cascaded progressive generative adversarial network (CPGAN), to reconstruct 3D grayscale core images. Furthermore, the reconstruction structure cannot reflect the gray level distribution of the core. However, traditional 2D–3D reconstruction methods are mostly designed for binary core images, rather than grayscale images. One important method for obtaining 3D core images involves reconstructing their 3D structure from two-dimensional (2D) core images. It is very challenging to accurately understand and characterize the internal structure of three-dimensional (3D) rock masses using geological monitoring and conventional laboratory measures. School of Information Engineering, North China University of Water Resources and Electric Power, Zhengzhou, China.
0 kommentar(er)
