Doctoral Dissertations

Keywords and Phrases

Artificial Intelligence; Drilling Fluid; Lost Circulation; Mud Loss

Abstract

”Lost circulation is a challenging problem in the oil and gas industry. Each year, millions of dollars are spent to mitigate or stop this problem. The aim of this work is to utilize machine learning and other intelligent solutions to help to make better decision to mitigate or stop lost circulation. A detailed literature review on the applications of decision tree analysis, expected monetary value, and artificial neural networks in the oil and gas industry was provided. Data for more than 3000 wells were gathered from many sources around the world. Detailed economics and probability analyses for lost circulation treatments’ strategies were conducted for three formations in southern Iraq which are the Dammam, Hartha, and Shuaiba formations.

Multiple machine learning methods such as support vector machine, decision trees, logistic regression, artificial neural networks, and ensemble trees were used to create models that can predict lost circulation and recommend the best lost circulation treatment based on the type of loss and reason of loss. The results showed that the created models can predict lost circulation and recommend the best lost circulation strategy within a reasonable margin of error. The created models can be used globally which avoids the shortcoming in the literature. Intelligence solutions and machine learning have proven their applicability to solve complicated problems and make better future decisions. With the large data available in the oil and gas industry, these methods can help the decision-makers to make better future decisions that will save time and money”--Abstract, page iv.

Advisor(s)

Dunn-Norman, Shari

Committee Member(s)

Flori, Ralph E.
Rogers, J. David
Hilgedick, Steven Austin
Dogan, Fatih

Department(s)

Geosciences and Geological and Petroleum Engineering

Degree Name

Ph. D. in Petroleum Engineering

Publisher

Missouri University of Science and Technology

Publication Date

Fall 2019

Journal article titles appearing in thesis/dissertation

  • Review of the applications of decision tree analysis in petroleum engineering with a rigorous analysis
  • Robust methodology to select the best lost circulation treatment using decision tree analysis
  • Applications of artificial neural networks in the petroleum industry: A review
  • Artificial neural network models to predict lost circulation for natural and induced fractures formations
  • Intelligent data-driven decision-making for lost circulation treatments: A machine learning approach

Pagination

xvi, 133 pages

Note about bibliography

Includes bibliographic references.

Rights

© 2019 Husam Hasan Alkinani, All rights reserved.

Document Type

Dissertation - Open Access

File Type

text

Language

English

Thesis Number

T 12072

Share

 
COinS