relation: https://khub.utp.edu.my/scholars/10677/
title: Surrogate reservoir model for average reservoir pressure
creator: Memon, P.Q.
creator: Yong, S.-P.
creator: Pao, W.
description: Reservoir models comprise of number of grid blocks, multiple layers and production/injection wells. Reservoir models also contain a number of different characteristics in its structure. Such as gas-oil ratio, water/oil saturation, permeability and volume factor, etc. As characteristics of the reservoir model increases, then also the time to calculate the reservoir outputs increase exponentially. This situation leads to a very cumbersome process. And this situation is considered as a very cumbersome process. There are other alternatives available, such as artificial neural network (ANN) techniques, which are utilized to manufacture the surrogate reservoir model (SRM) for multiphase flow. In this paper, Black Oil Applied Simulation Tool (BOAST) is utilized to gather the reservoir characteristics to build the spatio-temporal database. The spatio-temporal database is used to train the SRM. SRM is used to predict or calculate the result of Average Reservoir Pressure in a short amount of time as compared to the black oil simulator. It is also proposed that SRM is based on Radial Basis Neural Network (Radil Basis NN) to enhance the simulation process. © Springer International Publishing AG 2018.
publisher: Springer
date: 2018
type: Article
type: PeerReviewed
identifier:   Memon, P.Q. and Yong, S.-P. and Pao, W.  (2018) Surrogate reservoir model for average reservoir pressure.  Lecture Notes in Networks and Systems, 15.  pp. 737-746.  ISSN 23673370     
relation: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85062900565&doi=10.1007%2f978-3-319-56994-9_50&partnerID=40&md5=f49303f0a9dfdcc5b9d8a5a266105058
relation: 10.1007/978-3-319-56994-9₅₀
identifier: 10.1007/978-3-319-56994-9₅₀