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.
|Commitee:||Mokhtari, Mehdi, Seibi, Abdennour|
|School:||University of Louisiana at Lafayette|
|School Location:||United States -- Louisiana|
|Source:||MAI 56/05M(E), Masters Abstracts International|
|Keywords:||Artificial neural networks, Relative permeability|
Copyright in each Dissertation and Thesis is retained by the author. All Rights Reserved
The supplemental file or files you are about to download were provided to ProQuest by the author as part of a
dissertation or thesis. The supplemental files are provided "AS IS" without warranty. ProQuest is not responsible for the
content, format or impact on the supplemental file(s) on our system. in some cases, the file type may be unknown or
may be a .exe file. We recommend caution as you open such files.
Copyright of the original materials contained in the supplemental file is retained by the author and your access to the
supplemental files is subject to the ProQuest Terms and Conditions of use.
Depending on the size of the file(s) you are downloading, the system may take some time to download them. Please be