Effect of Pc and MW C6- on the accuracy of Gas Condensate Dewpoint Pressure estimation using Neural network modelling
2021
Dewpoint pressure (DPP) is one of the most important factors to be evaluated by reservoir
engineers while planning the development of a gas condensate reservoir. Below the
dewpoint pressure, liquid condenses out of the gaseous phase. This liquid condensate
forms a “ring” or “bank” around the producing well in the near-well region. Normally
this liquid will not flow until its saturation exceeds the critical condensate saturation
(Scc) due to the capillary pressure and relative permeability of the porous medium.
Hence it is very essential to accurately predict the dewpoint pressure of the reservoir
fluid.Numerous studies have been done on predicting dewpoint pressure using neural
networks. All of these studies focus on four key input parameters: Reservoir Temperature,
Specific gravity, Compressibility factor and Molecular weight of heavier components
(C7+). However, in this study, two multi-layer perception neural networks (MLPNN)
were built. In developing the MLPNN models two new input parameters were introduced;
Critical pressure and Molecular weight of lighter components (C6-).
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
0
References
0
Citations
NaN
KQI