Discover the SciOpen Platform and Achieve Your Research Goals with Ease.
Search articles, authors, keywords, DOI, etc.
Shale gas flow equations are characterized by source-sink terms, adsorption terms and pressure-dependent fluid properties, resulting in strong nonlinearity. To the best of our knowledge, no existing deep learning study has solved shale gas flow equations without labeled data and grid. To address this gap, this study proposes an asymptotic solution network with a Gaussian modulation factor. The proposed network combines an asymptotic network, constructed from the asymptotic solution of a well in a homogeneous infinite-acting reservoir, with a correction network to correct the output of the asymptotic network. A Gaussian modulation factor is further introduced to enable the neural network to concentrate on regions with large pressure gradients and strong nonlinearity. Additionally, linear interpolation is employed to decrease the learning difficulty caused by the nonlinearity of the gas formation volume factor and viscosity. Numerical results demonstrate that the solutions of the proposed network closely match numerical simulations, demonstrating the effectiveness of the proposed model. Ablation studies reveal that the Gaussian modulation factor significantly accelerates convergence and improves the solution accuracy.
This article is distributed under the terms and conditions of the Creative Commons Attribution (CC BY-NC-ND) license, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Comments on this article