Artificial Neural Network Based Design Network For Dual Lateral Well Applications

Open Access
Author:
Enab, Khaled Ahmed
Graduate Program:
Energy and Mineral Engineering
Degree:
Master of Science
Document Type:
Master Thesis
Date of Defense:
May 07, 2012
Committee Members:
  • Turgay Ertekin, Thesis Advisor
Keywords:
  • Artificial Neural Network
  • Neural Network
  • Dual Lateral
  • Multi lateral well
Abstract:
Artificial neural networks (ANNs) have become an important tool for the petroleum industry, for performance analysis of reservoirs, because their ability of understanding highly non-linear relationships and its capacity to perform simulation studies in a rapid manner. Artificial neural networks is a computational tool that is based on the way that the brain performs computations as it depends on knowledge based training strategies to build an experience in predicting the results of problem within the range of the trained cases. Since the increased use of natural gas all over the world, it has become more important to increase the gas production worldwide. Accordingly, many efforts have been expended to improve the production techniques such as using the multi-lateral wells which are capable to accomplish higher production rates. Determining the cumulative gas recovery profile, is an important step in the gas production characteristics, which presents the recovery performance through the well-life time which helps in detecting the well life-time and the revenue that can be realized after the detected well-life time. Using the multi-lateral wells technique leads to increase the cumulative fluid recovery, decreases the environmental impacts and decreases the cost of drilling and completion. The neural network developed in this study is able to predict the cumulative gas recovery profile from a tight shale gas reservoir with a multi-lateral well (dual horizontal well completion). In this study two artificial neural networks have been developed to achieve two main objectives. The forward ANN has been developed to predict the gas recovery profile for a chosen dual horizontal well configuration over a specified production period. The inverse ANN has been developed to determine a dual horizontal well design that can be used to achieve a desired gas recovery over a specified production period.