Optimized exploitation of gas-condensate reservoirs using neuro-simulation

Luis Ayala H., Turgay Ertekin, Michael A. Adewumi

Research output: Contribution to conferencePaper

2 Citations (Scopus)

Abstract

Gas-condensate reservoirs have been the subject of intensive research throughout the years as they represent an important class of the world's hydrocarbon reserves. Their exploitation for maximum hydrocarbon recovery involves additional complexities that cast them as a different class of reservoirsapart from dry-gas and black-oil reservoirs. Gas-condensate reservoirs are good candidates for compositional simulation studies as their depletion performance is highly influenced by changes in fluid composition. Often times, highly sophisticated and computationally intensive compositional simulations are needed for the accurate modeling of their performance, phase behavior, and fluid flow characteristics. The desirable outcome of a simulation study for gas condensate reservoirs is the identification and development of the best operational production schemes that maximizes hydrocarbon recovery with the minimum loss of condensate at reservoir conditions. However, compositional simulations are demanding in terms of computational overhead, manpower, and software and hardware requirements. Artificial neural network technology (soft-computing) has proven instrumental in establishing expert systems capable of learning the existing vaguely understood relationships between the input parameters and output responses of highly sophisticated hard-computing protocols such as compositional simulation of gas-condensate reservoirs. In this study, we conduct parametric studies that identify the most influential reservoir and fluid characteristics in the establishment of optimum production protocols for the exploitation of gas-condensate reservoirs. During the training phase of the artificial neural network, an internal mapping that accurately estimates the corresponding output for a range of input parameters is created. In this paper, a powerful screening and optimization tool for the production of gas-condensate reservoirs is presented. This tool is capable of screening the eligibility of different gas-condensate reservoirs to exploitation as well as assisting in designing the optimized exploitation scheme for a particular reservoir under consideration for development.

Original languageEnglish (US)
Pages209-228
Number of pages20
StatePublished - Dec 1 2004
EventSPE Asia Pacific Oil and Gas Conference and Exhibition, 2004 APOGCE - Perth, Australia
Duration: Oct 18 2004Oct 20 2004

Other

OtherSPE Asia Pacific Oil and Gas Conference and Exhibition, 2004 APOGCE
CountryAustralia
CityPerth
Period10/18/0410/20/04

Fingerprint

Gas condensates
Hydrocarbons
Screening
Neural networks
Recovery
Soft computing
Fluids
Phase behavior
Expert systems
Flow of fluids
Hardware
Chemical analysis
Gases

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Ayala H., L., Ertekin, T., & Adewumi, M. A. (2004). Optimized exploitation of gas-condensate reservoirs using neuro-simulation. 209-228. Paper presented at SPE Asia Pacific Oil and Gas Conference and Exhibition, 2004 APOGCE, Perth, Australia.
Ayala H., Luis ; Ertekin, Turgay ; Adewumi, Michael A. / Optimized exploitation of gas-condensate reservoirs using neuro-simulation. Paper presented at SPE Asia Pacific Oil and Gas Conference and Exhibition, 2004 APOGCE, Perth, Australia.20 p.
@conference{ddcf4d43ec614f99977011f7db0f7968,
title = "Optimized exploitation of gas-condensate reservoirs using neuro-simulation",
abstract = "Gas-condensate reservoirs have been the subject of intensive research throughout the years as they represent an important class of the world's hydrocarbon reserves. Their exploitation for maximum hydrocarbon recovery involves additional complexities that cast them as a different class of reservoirsapart from dry-gas and black-oil reservoirs. Gas-condensate reservoirs are good candidates for compositional simulation studies as their depletion performance is highly influenced by changes in fluid composition. Often times, highly sophisticated and computationally intensive compositional simulations are needed for the accurate modeling of their performance, phase behavior, and fluid flow characteristics. The desirable outcome of a simulation study for gas condensate reservoirs is the identification and development of the best operational production schemes that maximizes hydrocarbon recovery with the minimum loss of condensate at reservoir conditions. However, compositional simulations are demanding in terms of computational overhead, manpower, and software and hardware requirements. Artificial neural network technology (soft-computing) has proven instrumental in establishing expert systems capable of learning the existing vaguely understood relationships between the input parameters and output responses of highly sophisticated hard-computing protocols such as compositional simulation of gas-condensate reservoirs. In this study, we conduct parametric studies that identify the most influential reservoir and fluid characteristics in the establishment of optimum production protocols for the exploitation of gas-condensate reservoirs. During the training phase of the artificial neural network, an internal mapping that accurately estimates the corresponding output for a range of input parameters is created. In this paper, a powerful screening and optimization tool for the production of gas-condensate reservoirs is presented. This tool is capable of screening the eligibility of different gas-condensate reservoirs to exploitation as well as assisting in designing the optimized exploitation scheme for a particular reservoir under consideration for development.",
author = "{Ayala H.}, Luis and Turgay Ertekin and Adewumi, {Michael A.}",
year = "2004",
month = "12",
day = "1",
language = "English (US)",
pages = "209--228",
note = "SPE Asia Pacific Oil and Gas Conference and Exhibition, 2004 APOGCE ; Conference date: 18-10-2004 Through 20-10-2004",

}

Ayala H., L, Ertekin, T & Adewumi, MA 2004, 'Optimized exploitation of gas-condensate reservoirs using neuro-simulation', Paper presented at SPE Asia Pacific Oil and Gas Conference and Exhibition, 2004 APOGCE, Perth, Australia, 10/18/04 - 10/20/04 pp. 209-228.

Optimized exploitation of gas-condensate reservoirs using neuro-simulation. / Ayala H., Luis; Ertekin, Turgay; Adewumi, Michael A.

2004. 209-228 Paper presented at SPE Asia Pacific Oil and Gas Conference and Exhibition, 2004 APOGCE, Perth, Australia.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Optimized exploitation of gas-condensate reservoirs using neuro-simulation

AU - Ayala H., Luis

AU - Ertekin, Turgay

AU - Adewumi, Michael A.

PY - 2004/12/1

Y1 - 2004/12/1

N2 - Gas-condensate reservoirs have been the subject of intensive research throughout the years as they represent an important class of the world's hydrocarbon reserves. Their exploitation for maximum hydrocarbon recovery involves additional complexities that cast them as a different class of reservoirsapart from dry-gas and black-oil reservoirs. Gas-condensate reservoirs are good candidates for compositional simulation studies as their depletion performance is highly influenced by changes in fluid composition. Often times, highly sophisticated and computationally intensive compositional simulations are needed for the accurate modeling of their performance, phase behavior, and fluid flow characteristics. The desirable outcome of a simulation study for gas condensate reservoirs is the identification and development of the best operational production schemes that maximizes hydrocarbon recovery with the minimum loss of condensate at reservoir conditions. However, compositional simulations are demanding in terms of computational overhead, manpower, and software and hardware requirements. Artificial neural network technology (soft-computing) has proven instrumental in establishing expert systems capable of learning the existing vaguely understood relationships between the input parameters and output responses of highly sophisticated hard-computing protocols such as compositional simulation of gas-condensate reservoirs. In this study, we conduct parametric studies that identify the most influential reservoir and fluid characteristics in the establishment of optimum production protocols for the exploitation of gas-condensate reservoirs. During the training phase of the artificial neural network, an internal mapping that accurately estimates the corresponding output for a range of input parameters is created. In this paper, a powerful screening and optimization tool for the production of gas-condensate reservoirs is presented. This tool is capable of screening the eligibility of different gas-condensate reservoirs to exploitation as well as assisting in designing the optimized exploitation scheme for a particular reservoir under consideration for development.

AB - Gas-condensate reservoirs have been the subject of intensive research throughout the years as they represent an important class of the world's hydrocarbon reserves. Their exploitation for maximum hydrocarbon recovery involves additional complexities that cast them as a different class of reservoirsapart from dry-gas and black-oil reservoirs. Gas-condensate reservoirs are good candidates for compositional simulation studies as their depletion performance is highly influenced by changes in fluid composition. Often times, highly sophisticated and computationally intensive compositional simulations are needed for the accurate modeling of their performance, phase behavior, and fluid flow characteristics. The desirable outcome of a simulation study for gas condensate reservoirs is the identification and development of the best operational production schemes that maximizes hydrocarbon recovery with the minimum loss of condensate at reservoir conditions. However, compositional simulations are demanding in terms of computational overhead, manpower, and software and hardware requirements. Artificial neural network technology (soft-computing) has proven instrumental in establishing expert systems capable of learning the existing vaguely understood relationships between the input parameters and output responses of highly sophisticated hard-computing protocols such as compositional simulation of gas-condensate reservoirs. In this study, we conduct parametric studies that identify the most influential reservoir and fluid characteristics in the establishment of optimum production protocols for the exploitation of gas-condensate reservoirs. During the training phase of the artificial neural network, an internal mapping that accurately estimates the corresponding output for a range of input parameters is created. In this paper, a powerful screening and optimization tool for the production of gas-condensate reservoirs is presented. This tool is capable of screening the eligibility of different gas-condensate reservoirs to exploitation as well as assisting in designing the optimized exploitation scheme for a particular reservoir under consideration for development.

UR - http://www.scopus.com/inward/record.url?scp=22144458340&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=22144458340&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:22144458340

SP - 209

EP - 228

ER -

Ayala H. L, Ertekin T, Adewumi MA. Optimized exploitation of gas-condensate reservoirs using neuro-simulation. 2004. Paper presented at SPE Asia Pacific Oil and Gas Conference and Exhibition, 2004 APOGCE, Perth, Australia.