An accurate gas transport model is of vital importance to the simulation and production optimization of unconventional gas reservoirs. Although great success has been achieved in the development of single-component transport models, limited progress has been made in multicomponent systems. The major challenge of developing non-empirical multicomponent gas transport models lies in the absence of the quantification of the concentration impact on the fluid dynamic properties. To fill such a gap, this work presents a comprehensive transport model for multicomponent gas transport in shale and tight reservoirs. In developing the model, we first conducted molecular dynamic simulations to qualitatively understand the differential release of hydrocarbons from unconventional shale and tight reservoirs. It is found that the gas slippage, differential adsorption and surface diffusion are the primary transport mechanism in the working range of Knudsen number during reservoir production. Based upon the molecular dynamic study, a quantitative transport model has been developed and validated, which extends existing models from single-component systems to multiple-component systems. The kinetic theory of gases is adopted and modified to model the multicomponent slippage effect. A Generalized Maxwell-Stefan formulation with extended Langmuir adsorption isotherm is used to model the multicomponent surface diffusion process. The accuracy of the proposed model is above 90% for low to moderate Knudsen numbers in modeling the differential release phenomenon in unconventional reservoirs.
The flash calculation with large capillary pressure often turns out to be time-consuming and unstable. Consequently, the compositional simulation of unconventional oil/gas reservoirs, where large capillary pressure exists on the vapor-liquid phase interface due to the narrow pore channel, becomes a challenge to traditional reservoir simulation techniques. In this work, we try to resolve this issue by combining deep learning technology with reservoir simulation. We have developed a compositional simulator that is accelerated and stabilized by stochastically-trained proxy flash calculation.We first randomly generated 300,000 data samples from a standalone physical flash calculator.We have constructed a two-step neural network, in which the first step is the classify the phase condition of the system and the second step is to predict the concentration distribution among the determined phases. Each network consists of four hidden layers in between the input layer and the output layer. The network is trained by Stochastic Gradient Descent (SGD) method with 100 epochs.With given temperature, pressure, feed concentration pore radius, the trained network predicts the phases and concentration distribution in the system with very low computational cost. Our results show that the accuracy of the network is above 97% in the metric of mean absolute percentage error.The predicted result is used as the initial guess of the flash calculation module in the reservoir simulator. With the implementation of the deep learning based flash calculation module, the speed of the simulator has been effectively increased and the stability (in the manner of the ratio of convergence) has been improved as well.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.