انجمن مهندسی معدن ایراننشریه علمی-پژوهشی مهندسی معدن1735-761651020101201Application of Supervised Committee Machine Neural Networks (SCMNN) to Improve Neural Networks’ Algorithm in Permeability Prediction of Petroleum Reservoirاستفاده از شبکه عصبی مرکب (Committee Machine) نظارت شده جهت بهبود
الگوریتم شبکه های عصبی در تخمین تراوایی مخازن نفتی21301501FAصادقکریم پولیدانشگاه صنعتی امیرکبیرنادرفتحیان پوردانشگاه صنعتی اصفهانجابرروحیدانشگاه صنعتی اصفهانJournal Article20121226 Reservoir permeability is a critical parameter for the evaluation of hydrocarbon reservoirs. There are a lot of well log data related with this parameter. In this study, permeability is predicted using them and a supervised committee machine neural network (SCMNN) which is combined of 30 estimators. All of data were divided in two low and high permeability populations using statistical study. Each estimator of SCMNN was combined of two simple networks to predict permeability in both low and high classes and one gating network, considered as a classifier, classified data to these two classes. Thus, each low and/or high input data would predict in related network. This SCMNN was used to predict permeability on the data of one of petroleum reservoirs of south-west of Iran. 210 samples of this reservoir were available. Because of the fewness of data 80% of them were used as training data and 20% of them were used as validation and testing data. The overall fitting between predicted permeability versus measured ones was qualified through R2 (R=correlation coefficient) to be 97.72% which is considered appropriate. Whereas, R2 in the simple network in the best stat was 84.14%. The high power and efficiency of SCMNN are indicated by lower bias and better R2 in results.
Reservoir permeability is a critical parameter for the evaluation of hydrocarbon reservoirs. There are a lot of well log data related with this parameter. In this study, permeability is predicted using them and a supervised committee machine neural network (SCMNN) which is combined of 30 estimators. All of data were divided in two low and high permeability populations using statistical study. Each estimator of SCMNN was combined of two simple networks to predict permeability in both low and high classes and one gating network, considered as a classifier, classified data to these two classes. Thus, each low and/or high input data would predict in related network. This SCMNN was used to predict permeability on the data of one of petroleum reservoirs of south-west of Iran. 210 samples of this reservoir were available. Because of the fewness of data 80% of them were used as training data and 20% of them were used as validation and testing data. The overall fitting between predicted permeability versus measured ones was qualified through R2 (R=correlation coefficient) to be 97.72% which is considered appropriate. Whereas, R2 in the simple network in the best stat was 84.14%. The high power and efficiency of SCMNN are indicated by lower bias and better R2 in results.
<em> </em>
<em> </em>http://ijme.iranjournals.ir/article_1501_b3c5f44ce8b437c40737df04588cce6b.pdf