DL-KF modeling for acceleration of flash calculations in phase equilibrium using deep learning methods
SSRN Electronic Journal(2023)
Abstract
Improving the robustness and efficiency of flash calculations in phase equilibrium is crucial for reservoir simulation. DL-KF (Deep Learning for K-values and Fugacity Calculation) modeling is proposed to accelerate phase equilibrium calculation using deep learning methods, in which the three-steps neural networks are included: ANN-STAB (Artificial Neural Network for Stability Test) model, ANN-KV (Artificial Neural Network for K-values Calculation) model and ANN-FUG (Artificial Neural Network for Fugacity Calculation) model respectively. The ANN-STAB model is generated to test phase stability. When temperature, pressure and feed composition are given, the phase classification is obtained directly with very low computation cost. In the ANN-KV model, initial K-values are determined by trained networks instead of employing Wilson equation employed in traditional flash calculation. Its initial estimations of K-values significantly reduce the number of iterations and avoid converging to incorrect or unphysical solutions. The ANN-FUG model is built to replace the fugacity coefficient calculation in traditional flash calculation algorithms, and simplifies the nonlinear calculation of internal iterative calculation. These three artificial neural network models are embedded into the traditional algorithms to accelerate flash calculations. The framework considers the complete physical process of the algorithms of flash calculations in phase equilibrium calculations using deep learning methods, and it can also guarantee the conservation of component mass, which is crucial for phase equilibrium calculations and reservoir simulation. The proposed DL-KF modeling is validated and compared with the original equation of state modeling and three other deep learning methods using two typical hydrocarbon fluid cases. A sample of C3H8-CO2-heavy oil systems from Huabei oilfield and a PVT experiment in Tahe oilfield are used to examine the DL-KF modeling. The physical properties of oil sample of Bakken reservoir with CO2 injection are also investigated. These results reveal that the DL-KF methoding is accurate and efficient for accelerating phase equilibrium calculations of reservoir fluids.
MoreTranslated text
Key words
deep learning methods,phase equilibrium,flash calculation,phase stability test,Kvalues,fugacity coefficient,conservation of component mass
AI Read Science
Must-Reading Tree
Example
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined