Dissertation/Thesis Abstract

Determining Relative Permeability of North American Sandstone Utilizing Artificial Neural Networks
by Hamblin, Spencer, M.S., University of Louisiana at Lafayette, 2016, 63; 10245198
Abstract (Summary)

Accurate relative permeability prediction is necessary to more effectively conduct reservoir simulations and accurately predict fluid flow. Although lab testing is the most accurate way to determine relative permeability, it is expensive and time-consuming. Mathematical modeling of relative permeability is a necessary alternative when lab testing is not a viable option for a project. Artificial Neural Networks (ANNs) have shown promising results in petroleum related fields of well testing, flow unit prediction, increased oil recovery evaluation, and more. Widely accessible statistical computer programs now offer ANN modeling capabilities that, while not as customizable as an ANN personally created and coded, removes much of the difficulty in utilizing neural networks as tools for analyzing data.

In this study, an ANN is utilized to create a model to predict the relative permeability of oil and water in North American water-wet sandstone reservoirs. Two models will be presented and available for use. The models for oil and water relative permeability had to be separated to increase their accuracy. The two models only require basic formation properties and endpoint saturations values. While the presented model is more complex than past relative permeability models, it can be easily programmed into calculation spreadsheets or reservoir simulators, which is their recommended use. The presented models are more accurate than comparable relative permeability models highlighting the fact that despite having limited data, a simple neural network can predict relative permeability extremely well.

Indexing (document details)
Advisor: Boukadi, Fathi
Commitee: Mokhtari, Mehdi, Seibi, Abdennour
School: University of Louisiana at Lafayette
Department: Petroleum Engineering
School Location: United States -- Louisiana
Source: MAI 56/05M(E), Masters Abstracts International
Source Type: DISSERTATION
Subjects: Petroleum engineering
Keywords: Artificial neural networks, Relative permeability
Publication Number: 10245198
ISBN: 978-0-355-11306-8
Copyright © 2019 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy
ProQuest