Missouri S&T Scholar's Mine Research RepositoryMissouri S&T Research
print 
Title: Predicting injection profiles using ANFIS
Author (s): Wei, Mingzhen
Bai, Baojun
Sung, Andrew H.
Liu, Qingzhong
Wang, Jiachun
Cather, Martha E.
Department/Lab Affiliations: Energy Research and Development Center
Geological Sciences & Engineering
Keywords: ANFIS
data quality problems
grid partition
petroleum industry
subtractive clustering
Issue Date: 2007-10-15
Publisher: Elsevier
Citation: Wei, Mingzhen, Baojun Bai, Andrew H. Sung, Qingzhong Liu, Jiachun Wang, and Martha E. Cather. "Predicting Injection Profiles Using ANFIS." Information Sciences, vol. 177, no. 20, 2007.
Abstract: Decision making pertaining to injection profiles during oilfield development is one of the most important factors that affect the oilfield's performance. Since injection profiles are affected by multiple geological and development factors, it is difficult to model their complicated, non-linear relationships using conventional approaches. In this paper, two adaptive-network-based fuzzy inference systems (ANFIS) based neuro-fuzzy systems are presented. The two neuro-fuzzy systems are: (1) grid partition based fuzzy inference system (FIS), named ANFIS-GRID, and (2) subtractive clustering based FIS, named ANFIS-SUB. We compare the performance of resultant FIS and study the effect of parameters. A real-world injection profile data set from the Daqing Oilfield, China is used. FIS are generated and tested using training and testing data from that data set. The impact of data quality on the performance of FIS is also studied. Experiments demonstrate that although soft computing methods are somewhat of tolerant of inaccurate inputs, cleaned data results in more robust models for practical problems. ANFIS-GRID outperforms ANFIS-SUB due to its simplicity in parameter selection and its fitness in the target problem.
Type: Article - Journal
text
In Title: Information Sciences
Copyright Notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.
Pre-print: author can archive with restrictions;Restriction: This does not include Cell Press; Post-print: author can archive;
FULL COPYRIGHT INFORMATION:
http://www.elsevier.com/wps/find/authorsview.authors/authorsrights
Publisher URL:
http://dx.doi.org/10.1016/j.ins.2007.03.021
Link to this page:
http://scholarsmine.mst.edu/post_prints/PredictingInjectionProfilesUsingANFIS_09007dcc8053769a.html



titlePredicting injection profiles using ANFIS
contributor.authorWei, Mingzhen
contributor.authorBai, Baojun
contributor.authorSung, Andrew H.
contributor.authorLiu, Qingzhong
contributor.authorWang, Jiachun
contributor.authorCather, Martha E.
contributor.deptlabEnergy Research and Development Center
contributor.deptlabGeological Sciences & Engineering
contributor.sponsorNew Mexico Petroleum Recovery Research Center
subjectANFIS
subjectdata quality problems
subjectgrid partition
subjectpetroleum industry
subjectsubtractive clustering
date.issued2007-10-15
publisherElsevier
identifier.citationWei, Mingzhen, Baojun Bai, Andrew H. Sung, Qingzhong Liu, Jiachun Wang, and Martha E. Cather. "Predicting Injection Profiles Using ANFIS." Information Sciences, vol. 177, no. 20, 2007.
identifier.pub.URI
http://dx.doi.org/10.1016/j.ins.2007.03.021
description.abstractDecision making pertaining to injection profiles during oilfield development is one of the most important factors that affect the oilfield's performance. Since injection profiles are affected by multiple geological and development factors, it is difficult to model their complicated, non-linear relationships using conventional approaches. In this paper, two adaptive-network-based fuzzy inference systems (ANFIS) based neuro-fuzzy systems are presented. The two neuro-fuzzy systems are: (1) grid partition based fuzzy inference system (FIS), named ANFIS-GRID, and (2) subtractive clustering based FIS, named ANFIS-SUB. We compare the performance of resultant FIS and study the effect of parameters. A real-world injection profile data set from the Daqing Oilfield, China is used. FIS are generated and tested using training and testing data from that data set. The impact of data quality on the performance of FIS is also studied. Experiments demonstrate that although soft computing methods are somewhat of tolerant of inaccurate inputs, cleaned data results in more robust models for practical problems. ANFIS-GRID outperforms ANFIS-SUB due to its simplicity in parameter selection and its fitness in the target problem.
typeArticle - Journal
type.DCMITypetext
rightsThis material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.
rightsPre-print: author can archive with restrictions;Restriction: This does not include Cell Press; Post-print: author can archive;
rights.URI
http://www.elsevier.com/wps/find/authorsview.authors/authorsrights
relation.isPartOfInformation Sciences
date.accessioned2008-09-19T20:56:56Z
date.available2008-07-29T14:19:47Z
identifier.persist.URI
http://scholarsmine.mst.edu/post_prints/PredictingInjectionProfilesUsingANFIS_09007dcc8053769a.html