A neurosimulation tool for predicting performance in enhanced coalbed methane and CO2 sequestration projects

F. B. Gorucu, T. Ertekin, G. S. Bromhal, D. H. Smith, W. N. Sams, S. A. Jikich

Research output: Contribution to conferencePaper

4 Citations (Scopus)

Abstract

One of the more important environmental issues is the increase in atmospheric carbon dioxide (CO2) concentration resulting from anthropogenic sources. The CO2 sequestration process includes capturing, separation and storage of carbon dioxide, and targets a potential solution mitigating the amount of CO2 in the atmosphere. This work focuses on the last component of the aforementioned sequestration process, storage of CO2. Coal seams are chosen as potential repositories because there are several advantages where the sequestration costs can be offset in various ways. The purpose of this study is to develop a tool for the practicing engineer to predict the important performance indicators that are critical in CO2 storage projects in coal seams. The neuro-simulation methodology coupling the hard computing protocols with the soft computing protocols is used. PSU-COALCOMP, a compositional coalbed methane reservoir simulator (hard computing protocol), is used to generate the necessary training data sets utilized in the training of the artificial neural networks (soft computing protocol) that are developed in this study. The tested neural network predictions are found to be accurate and sufficiently precise to establish confidence in the tool. Accordingly, the developed neural network can be used to screen thousands of possible scenarios of operational conditions in the optimization of the coal sequestration project design parameters in few seconds without going through intensive numerical simulations.

Original languageEnglish (US)
Pages4429-4442
Number of pages14
StatePublished - Dec 1 2005
EventSPE Annual Technical Conference and Exhibition, ATCE 2005 - Dallas, TX, United States
Duration: Oct 9 2005Oct 12 2005

Other

OtherSPE Annual Technical Conference and Exhibition, ATCE 2005
CountryUnited States
CityDallas, TX
Period10/9/0510/12/05

Fingerprint

Soft computing
Coal
Neural networks
Carbon dioxide
Simulators
Engineers
Computer simulation
Coal bed methane
Costs

All Science Journal Classification (ASJC) codes

  • Fuel Technology
  • Energy Engineering and Power Technology

Cite this

Gorucu, F. B., Ertekin, T., Bromhal, G. S., Smith, D. H., Sams, W. N., & Jikich, S. A. (2005). A neurosimulation tool for predicting performance in enhanced coalbed methane and CO2 sequestration projects. 4429-4442. Paper presented at SPE Annual Technical Conference and Exhibition, ATCE 2005, Dallas, TX, United States.
Gorucu, F. B. ; Ertekin, T. ; Bromhal, G. S. ; Smith, D. H. ; Sams, W. N. ; Jikich, S. A. / A neurosimulation tool for predicting performance in enhanced coalbed methane and CO2 sequestration projects. Paper presented at SPE Annual Technical Conference and Exhibition, ATCE 2005, Dallas, TX, United States.14 p.
@conference{a1535341bc0141f29c6f2e034436986a,
title = "A neurosimulation tool for predicting performance in enhanced coalbed methane and CO2 sequestration projects",
abstract = "One of the more important environmental issues is the increase in atmospheric carbon dioxide (CO2) concentration resulting from anthropogenic sources. The CO2 sequestration process includes capturing, separation and storage of carbon dioxide, and targets a potential solution mitigating the amount of CO2 in the atmosphere. This work focuses on the last component of the aforementioned sequestration process, storage of CO2. Coal seams are chosen as potential repositories because there are several advantages where the sequestration costs can be offset in various ways. The purpose of this study is to develop a tool for the practicing engineer to predict the important performance indicators that are critical in CO2 storage projects in coal seams. The neuro-simulation methodology coupling the hard computing protocols with the soft computing protocols is used. PSU-COALCOMP, a compositional coalbed methane reservoir simulator (hard computing protocol), is used to generate the necessary training data sets utilized in the training of the artificial neural networks (soft computing protocol) that are developed in this study. The tested neural network predictions are found to be accurate and sufficiently precise to establish confidence in the tool. Accordingly, the developed neural network can be used to screen thousands of possible scenarios of operational conditions in the optimization of the coal sequestration project design parameters in few seconds without going through intensive numerical simulations.",
author = "Gorucu, {F. B.} and T. Ertekin and Bromhal, {G. S.} and Smith, {D. H.} and Sams, {W. N.} and Jikich, {S. A.}",
year = "2005",
month = "12",
day = "1",
language = "English (US)",
pages = "4429--4442",
note = "SPE Annual Technical Conference and Exhibition, ATCE 2005 ; Conference date: 09-10-2005 Through 12-10-2005",

}

Gorucu, FB, Ertekin, T, Bromhal, GS, Smith, DH, Sams, WN & Jikich, SA 2005, 'A neurosimulation tool for predicting performance in enhanced coalbed methane and CO2 sequestration projects', Paper presented at SPE Annual Technical Conference and Exhibition, ATCE 2005, Dallas, TX, United States, 10/9/05 - 10/12/05 pp. 4429-4442.

A neurosimulation tool for predicting performance in enhanced coalbed methane and CO2 sequestration projects. / Gorucu, F. B.; Ertekin, T.; Bromhal, G. S.; Smith, D. H.; Sams, W. N.; Jikich, S. A.

2005. 4429-4442 Paper presented at SPE Annual Technical Conference and Exhibition, ATCE 2005, Dallas, TX, United States.

Research output: Contribution to conferencePaper

TY - CONF

T1 - A neurosimulation tool for predicting performance in enhanced coalbed methane and CO2 sequestration projects

AU - Gorucu, F. B.

AU - Ertekin, T.

AU - Bromhal, G. S.

AU - Smith, D. H.

AU - Sams, W. N.

AU - Jikich, S. A.

PY - 2005/12/1

Y1 - 2005/12/1

N2 - One of the more important environmental issues is the increase in atmospheric carbon dioxide (CO2) concentration resulting from anthropogenic sources. The CO2 sequestration process includes capturing, separation and storage of carbon dioxide, and targets a potential solution mitigating the amount of CO2 in the atmosphere. This work focuses on the last component of the aforementioned sequestration process, storage of CO2. Coal seams are chosen as potential repositories because there are several advantages where the sequestration costs can be offset in various ways. The purpose of this study is to develop a tool for the practicing engineer to predict the important performance indicators that are critical in CO2 storage projects in coal seams. The neuro-simulation methodology coupling the hard computing protocols with the soft computing protocols is used. PSU-COALCOMP, a compositional coalbed methane reservoir simulator (hard computing protocol), is used to generate the necessary training data sets utilized in the training of the artificial neural networks (soft computing protocol) that are developed in this study. The tested neural network predictions are found to be accurate and sufficiently precise to establish confidence in the tool. Accordingly, the developed neural network can be used to screen thousands of possible scenarios of operational conditions in the optimization of the coal sequestration project design parameters in few seconds without going through intensive numerical simulations.

AB - One of the more important environmental issues is the increase in atmospheric carbon dioxide (CO2) concentration resulting from anthropogenic sources. The CO2 sequestration process includes capturing, separation and storage of carbon dioxide, and targets a potential solution mitigating the amount of CO2 in the atmosphere. This work focuses on the last component of the aforementioned sequestration process, storage of CO2. Coal seams are chosen as potential repositories because there are several advantages where the sequestration costs can be offset in various ways. The purpose of this study is to develop a tool for the practicing engineer to predict the important performance indicators that are critical in CO2 storage projects in coal seams. The neuro-simulation methodology coupling the hard computing protocols with the soft computing protocols is used. PSU-COALCOMP, a compositional coalbed methane reservoir simulator (hard computing protocol), is used to generate the necessary training data sets utilized in the training of the artificial neural networks (soft computing protocol) that are developed in this study. The tested neural network predictions are found to be accurate and sufficiently precise to establish confidence in the tool. Accordingly, the developed neural network can be used to screen thousands of possible scenarios of operational conditions in the optimization of the coal sequestration project design parameters in few seconds without going through intensive numerical simulations.

UR - http://www.scopus.com/inward/record.url?scp=33644787876&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33644787876&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:33644787876

SP - 4429

EP - 4442

ER -

Gorucu FB, Ertekin T, Bromhal GS, Smith DH, Sams WN, Jikich SA. A neurosimulation tool for predicting performance in enhanced coalbed methane and CO2 sequestration projects. 2005. Paper presented at SPE Annual Technical Conference and Exhibition, ATCE 2005, Dallas, TX, United States.