Dynamic Surrogate Reservoir Model with well constraints

Reservoir flow calculation is a significant aspect in oil and gas industries to calculate the results of a reservoir. Due to the large number of grid blocks and heterogeneity in reservoir models, extensive simulations are required to reduce the risk in reservoir's productivity. In order to miti...

Full description

Main Authors: Memon, P.Q., Yong, S.-P., Pao, W.
Format: Conference or Workshop Item
Institution: Universiti Teknologi Petronas
Record Id / ISBN-0: utp-eprints.30525 /
Published: Institute of Electrical and Electronics Engineers Inc. 2016
Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85010289418&doi=10.1109%2fICCOINS.2016.7783290&partnerID=40&md5=8b8f492e230867c7d782142fc0d880ca
http://eprints.utp.edu.my/30525/
Tags: Add Tag
No Tags, Be the first to tag this record!
id utp-eprints.30525
recordtype eprints
spelling utp-eprints.305252022-03-25T07:09:57Z Dynamic Surrogate Reservoir Model with well constraints Memon, P.Q. Yong, S.-P. Pao, W. Reservoir flow calculation is a significant aspect in oil and gas industries to calculate the results of a reservoir. Due to the large number of grid blocks and heterogeneity in reservoir models, extensive simulations are required to reduce the risk in reservoir's productivity. In order to mitigate this problem, Surrogate Reservoir Model (SRM) is used as a prime outcome to reduce the simulation time. However, this paper work presents the dynamic well SRM, that extracts the data from a conventional reservoir simulator, Black Oil Applied Simulation Tool (BOAST). The well SRM with two dynamic constraints(bottom-hole flowing pressure and production rate) is built with random switch on/off of well with discrete time steps. The prime input parameters, porosity, permeability and saturation are identified from the reservoir model using principal component analysis (PCA) technique. The Artificial Neural Network (RBNN) technique is adopted to build the well SRM with dynamic constraints. The trained model from the dynamic well SRM is validated with the output from BOAST. The dynamic SRM is flexible in handling different types of modeling with changeable constraints. It was found that the simulated results of the proposed dynamic well SRM is effective in producing the outputs as predicted by the conventional simulator. © 2016 IEEE. Institute of Electrical and Electronics Engineers Inc. 2016 Conference or Workshop Item NonPeerReviewed https://www.scopus.com/inward/record.uri?eid=2-s2.0-85010289418&doi=10.1109%2fICCOINS.2016.7783290&partnerID=40&md5=8b8f492e230867c7d782142fc0d880ca Memon, P.Q. and Yong, S.-P. and Pao, W. (2016) Dynamic Surrogate Reservoir Model with well constraints. In: UNSPECIFIED. http://eprints.utp.edu.my/30525/
institution Universiti Teknologi Petronas
collection UTP Institutional Repository
description Reservoir flow calculation is a significant aspect in oil and gas industries to calculate the results of a reservoir. Due to the large number of grid blocks and heterogeneity in reservoir models, extensive simulations are required to reduce the risk in reservoir's productivity. In order to mitigate this problem, Surrogate Reservoir Model (SRM) is used as a prime outcome to reduce the simulation time. However, this paper work presents the dynamic well SRM, that extracts the data from a conventional reservoir simulator, Black Oil Applied Simulation Tool (BOAST). The well SRM with two dynamic constraints(bottom-hole flowing pressure and production rate) is built with random switch on/off of well with discrete time steps. The prime input parameters, porosity, permeability and saturation are identified from the reservoir model using principal component analysis (PCA) technique. The Artificial Neural Network (RBNN) technique is adopted to build the well SRM with dynamic constraints. The trained model from the dynamic well SRM is validated with the output from BOAST. The dynamic SRM is flexible in handling different types of modeling with changeable constraints. It was found that the simulated results of the proposed dynamic well SRM is effective in producing the outputs as predicted by the conventional simulator. © 2016 IEEE.
format Conference or Workshop Item
author Memon, P.Q.
Yong, S.-P.
Pao, W.
spellingShingle Memon, P.Q.
Yong, S.-P.
Pao, W.
Dynamic Surrogate Reservoir Model with well constraints
author_sort Memon, P.Q.
title Dynamic Surrogate Reservoir Model with well constraints
title_short Dynamic Surrogate Reservoir Model with well constraints
title_full Dynamic Surrogate Reservoir Model with well constraints
title_fullStr Dynamic Surrogate Reservoir Model with well constraints
title_full_unstemmed Dynamic Surrogate Reservoir Model with well constraints
title_sort dynamic surrogate reservoir model with well constraints
publisher Institute of Electrical and Electronics Engineers Inc.
publishDate 2016
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85010289418&doi=10.1109%2fICCOINS.2016.7783290&partnerID=40&md5=8b8f492e230867c7d782142fc0d880ca
http://eprints.utp.edu.my/30525/
_version_ 1741197421575143424
score 11.62408

Similar Items