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.
- Article type
- Year
- Co-author
Open Access
Original Article
Issue
Open Access
Original Article
Issue
Generative Adversarial Networks (GANs),as most popular artificial intelligence models in the current image generation field,have excellent image generation capabilities. Based on Wasserstein GANs with gradient penalty,this paper proposes a novel digital core reconstruction method. First,a convolutional neural network is used as a generative network to learn the distribution of real shale samples,and then a convolutional neural network is constructed as a discriminative network to distinguish reconstructed shale samples from real ones. Through this confrontation training method,realistic digital core samples of shale can be reconstructed. The paper uses two-point covariance function,Frechet Inception ′ Distance and Kernel Inception Distance,to evaluate the quality of digital core samples of shale reconstructed by GANs. The results show that the covariance function can test the similarity between generated and real shale samples,and that GANs can efficiently reconstruct digital core samples of shale with high-quality. Compared with multiple point statistics,the new method does not require prior inference of the probability distribution of the training data,and directly uses noise vector to generate digital core samples of shale without using constraints of "hard data" in advance. It is easy to produce an unlimited number of new samples. Furthermore,the training time is also shorter,only 4 hours in this paper. Therefore,the new method has some good points compared with current methods.
京公网安备11010802044758号