Randomly generating realistic calcareous sand for directional seepage simulation using deep convolutional generative adversarial networks
Abstract
The issues of seepage in calcareous sand foundations and backfills have a potentially detrimental effect on the stability and safety of superstructures. Simplifying calcareous sand grains as spheres or ellipsoids in numerical simulations may lead to significant inaccuracies. In this paper, we present a novel intelligence framework based on a deep convolutional generative adversarial network (DCGAN). A DCGAN model was trained using a training dataset comprising 11,625 real particles for the random generation of three-dimensional calcareous sand particles. Subsequently, 3800 realistic calcareous sand particles with intra-particle voids were generated. Generative fidelity and validity of the DCGAN model were well verified by the consistency of the statistical values of nine morphological parameters of both the training dataset and the generated dataset. Digital calcareous sand columns were obtained through gravitational deposition simulation of the generated particles. Directional seepage simulations were conducted, and the vertical permeability values of the sand columns were found to be in accordance with the objective law. The results demonstrate the potential of the proposed framework for stochastic modeling and multi-scale simulation of the seepage behaviors in calcareous sand foundations and backfills.