【摘要】 本文详细论述了利用全卷积神经网络建立三维数字岩心的完整过程,以大量的砂岩CT图像为输入,成功地训练了全卷积神经网络模型,随后利用该模型以少量Berea砂岩的CT图像为基础构建了Berea砂岩的三维数字岩心。采用闵可夫斯基函数分别计算了Berea砂岩实际CT扫描结果和采用FCN生成的三维数字岩心的孔隙度、孔隙的比表面积、平均曲率和连通性,随后计算了两者之间的相对误差分别为6.26%,1.40%,6.06%,4.91%,同时汉明距离为0.04479。研究结果表明利用FCN重建的三维数字岩心不仅能重建真实砂岩的物性特征,还能还原真实砂岩内孔隙分布特征,能很好地保留实际岩石的孔隙结构。为刻画岩石内部微观结构提供了一种新途径。更多还原

【Abstract】 In this paper, the complete process of constructing 3 D digital core by full convolutional neural network is described carefully. A large number of sandstone computed tomography(CT) images are used as training input for a fully convolutional neural network model. This model is used to reconstruct the three-dimensional(3 D) digital core of Berea sandstone based on a small number of CT images. The Hamming distance together with the Minkowski functions for porosity, average volume specific surface area, average curvature, and connectivity of both the real core and the digital reconstruction are used to evaluate the accuracy of the proposed method. The results show that the reconstruction achieved relative errors of 6.26%, 1.40%, 6.06%, and 4.91% for the four Minkowski functions and a Hamming distance of 0.04479. This demonstrates that the proposed method can not only reconstruct the physical properties of real sandstone but can also restore the real characteristics of pore distribution in sandstone, is the ability to which is a new way to characterize the internal microstructure of rocks.更多还原