Accelerating flash calculations in unconventional reservoirs considering capillary pressure using an optimized deep learning algorithm
KAUST DepartmentComputational Transport Phenomena Lab
Computational Transport Phenomena Laboratory (CTPL), King Abdullah University of Science and Technology (KAUST), Thuwal, 23955-6900, Saudi Arabia
Earth Science and Engineering Program
Physical Science and Engineering (PSE) Division
KAUST Grant NumberBAS/1/1351-01-01
Online Publication Date2020-09-15
Print Publication Date2020-12
Embargo End Date2022-09-18
Permanent link to this recordhttp://hdl.handle.net/10754/665295
MetadataShow full item record
AbstractAn increasing focus was placed in the past few decades on accelerating flash calculations and a variety of acceleration strategies have been developed to improve its efficiency without serious compromise in accuracy and reliability. Recently, as machine learning becomes a powerful tool to handle complicated and time-consuming problems, it is increasingly appealing to replace the iterative flash algorithm, due to the strong nonlinearity of flash problem, by a neural network model. In this study, an NVT flash calculation scheme is established with a thermodynamically stable evolution algorithm to generate training and testing data for the proposed deep neural network. With a modified network structure, the deep learning algorithm is optimized by carefully tuning neural network hyperparameters. Numerical tests indicate that the trained model is capable of accurately estimating phase compositions and states for complex reservoir fluids under a wide range of environmental conditions, while the effect of capillary pressure can be captured well. Thermodynamic rules are preserved well through our algorithm, and the trained model can be used for various fluid mixtures, which significantly accelerates flash calculations in unconventional reservoirs.
CitationZhang, T., Li, Y., Sun, S., & Bai, H. (2020). Accelerating flash calculations in unconventional reservoirs considering capillary pressure using an optimized deep learning algorithm. Journal of Petroleum Science and Engineering, 195, 107886. doi:10.1016/j.petrol.2020.107886
SponsorsThe authors thank for the support from the National Natural Science Foundation of China (No. 51874262,51936001) and the Research Funding from King Abdullah University of Science and Technology (KAUST) through the grants BAS/1/1351-01-01.