0
Research Papers: Petroleum Engineering

Effective Prediction and Management of a CO2 Flooding Process for Enhancing Oil Recovery Using Artificial Neural Networks

[+] Author and Article Information
Si Le Van

Department of Energy Resources Engineering,
Inha University,
100 Inharo, Nam-gu,
Incheon 22212, South Korea
e-mail: slevansi_1190@inha.edu

Bo Hyun Chon

Professor
Department of Energy Resources Engineering,
Inha University,
100 Inharo, Nam-gu,
Incheon 22212, South Korea
e-mail: bochon@inha.ac.kr

1Corresponding author.

Contributed by the Petroleum Division of ASME for publication in the JOURNAL OF ENERGY RESOURCES TECHNOLOGY. Manuscript received May 27, 2017; final manuscript received September 15, 2017; published online October 19, 2017. Assoc. Editor: Esmail M. A. Mokheimer.

J. Energy Resour. Technol 140(3), 032906 (Oct 19, 2017) (14 pages) Paper No: JERT-17-1248; doi: 10.1115/1.4038054 History: Received May 27, 2017; Revised September 15, 2017

The injection of CO2 has been in global use for enhanced oil recovery (EOR) as it can improve oil production in mature fields. It also has environmental benefits for reducing greenhouse carbon by permanently sequestrating CO2 (carbon capture and storage (CCS)) in reservoirs. As a part of numerical studies, this work proposed a novel application of an artificial neural network (ANN) to forecast the performance of a water-alternating-CO2 process and effectively manage the injected CO2 in a combined CCS–EOR project. Three targets including oil recovery, net CO2 storage, and cumulative gaseous CO2 production were quantitatively simulated by three separate ANN models for a series of injection frames of 5, 15, 25, and 35 cycles. The concurrent estimations of a sequence of outputs have shown a relevant application in scheduling the injection process based on the progressive profile of the targets. For a specific surface design, an increment of 5.8% oil recovery and 4% net CO2 storage was achieved from 25 cycles to 35 cycles, suggesting ending the injection at 25 cycles. Using the models, distinct optimizations were also computed for oil recovery and net CO2 sequestration in various reservoir conditions. The results expressed a maximum oil recovery from 22% to 30% oil in place (OIP) and around 21,000–29,000 tons of CO2 trapped underground after 35 cycles if the injection began at 60% water saturation. The new approach presented in this study of applying an ANN is obviously effective in forecasting and managing the entire CO2 injection process instead of a single output as presented in previous studies.

FIGURES IN THIS ARTICLE
<>
Copyright © 2018 by ASME
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Fig. 1

Flow capacity of phases in the considered rock system used in the simulation: (a) water–oil relative permeabilities, (b) gas–liquid relative permeabilities, and (c) three-phase relative permeability

Grahic Jump Location
Fig. 2

Laboratory data and regression results simulated in WINPROP for a specific crude oil: (a) oil specific gravity—differential liberation test (DLT), (b)oil viscosity—DLT, (c) gas-to-oil ratio—DLT, (d) saturation pressure—ST, and (e) swelling factor—ST

Grahic Jump Location
Fig. 3

Schematic represents the structure of network models, whereas Y stands for oil recovery, CO2 production or net CO2 storage

Grahic Jump Location
Fig. 4

Performances of a specific simulation case: (a) oil recovery factor and oil rate, (b) CO2 production and net CO2 sequestration, and (c) mole fraction profile of CO2 at 5.5 cycles

Grahic Jump Location
Fig. 5

Distribution in values obtained from the numerical samples: (a) oil recovery factor, (b) CO2 production, and (c) net CO2 sequestration

Grahic Jump Location
Fig. 6

Performances obtained from training the essential objectives: (a) oil recovery factor, (b) CO2 production, and (c) net CO2 storage

Grahic Jump Location
Fig. 7

Plots of comparison between the numerical samples and recomputed targets using the generated networks: (a) oil recovery factor, (b) cumulative CO2 production, and (c) and net CO2 storage

Grahic Jump Location
Fig. 8

Dependences of oil recovery factor and carbon sequestration on reservoir factors achieved using the ANN models: (a) Sw and Kv/Kh versus RF and (b) Sw and Kv/Kh versus net CO2 storage

Grahic Jump Location
Fig. 9

Relationships between the critical targets on the surface operation parameters at 15 and 35 cycles: (a) oil recovery, (b) net CO2 storage, and (c) cumulative CO2 production

Grahic Jump Location
Fig. 10

Effects of well spacing and fluid injection ratio on the targets at 35 cycles: (a) oil recovery factor, (b) cumulative CO2 production, and (c) net CO2 sequestration

Grahic Jump Location
Fig. 11

Progression of RF, net CO2 storage and CO2 production (recycled) at two cases of Sw, where Kv/Kh = 0.5, T = 60, WAG ratio = 1 and well distance = 300 m

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In