Accelerating and stabilizing the vapor-liquid equilibrium (VLE) calculation in compositional simulation of unconventional reservoirs using deep learning based flash calculation. (1st October 2019)

• Record Type: Journal Article
• Authors: Wang, Shihao; Sobecki, Nicolas; Ding, Didier; Zhu, Lingchen; Wu, Yu-Shu
• Is Part Of: Fuel. Volume 253(2019)
• Page Start: 209
• Page End: 219
• Publication Date: 2019-10-01
• Subjects: Flash calculation -- Unconventional reservoirs -- Deep learning -- Proxy calculation -- Reservoir simulation; Fuel -- Periodicals; Coal -- Periodicals; Coal; Fuel; Periodicals; 662.6
• DOI: 10.1016/j.fuel.2019.05.023
• Languages: English
• ISSNs: 0016-2361

Abstract

Highlights: A deep learning based flash calculation module with large capillary pressure has been developed. The proxy flash calculation module has been trained with accuracy up to 97%. The proxy flash calculation module effectively accelerates and stabilizes flash calculation. The proxy flash calculation module has been implemented in a reservoir simulator. Abstract: 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.