English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Phase equilibrium calculation, also known as flash calculation, has beenextensively applied in petroleum engineering, not only as a standaloneapplication for separation process but also an integral component ofcompositional reservoir simulation. It is of vital importance to accelerateflash calculation without much compromise in accuracy and reliability, turningit into an active research topic in the last two decades. In this study, weestablish a deep neural network model to approximate the iterative NVT-flashcalculation. A dynamic model designed for NVT flash problems is iterativelysolved to produce data for training the neural network. In order to test themodel's capacity to handle complex fluid mixtures, three real reservoir fluidsare investigated, including one Bakken oil and two Eagle Ford oils. Compared toprevious studies that follow the conventional flash framework in whichstability testing precedes phase splitting calculation, we incorporatestability test and phase split calculation together and accomplish both twosteps by a single deep learning model. The trained model is able to identifythe single vapor, single liquid and vapor-liquid state under the subcriticalregion of the investigated fluids. A number of examples are presented to showthe accuracy and efficiency of the proposed deep neural network. It is foundthat the trained model makes predictions at most 244 times faster than theiterative flash calculation under the given cases. Even though training amulti-level network model does take a large amount of time that is comparableto the computational time of flash calculations, the one-time offline trainingprocess gives the deep learning model great potential to speed up compositionalreservoir simulation.

Acceleration of the NVT-flash calculation for multicomponent mixtures using deep neural network models