A Comparative Study of Machine Learning Models for Early Corrosion Detection in Oil Pipelines

Metenova, Aida (2024) A Comparative Study of Machine Learning Models for Early Corrosion Detection in Oil Pipelines. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (6MB) | Preview
Preview	PDF (Configuration Manual) Download (3MB) | Preview

Abstract

This study seeks to explore the application of machine learning algorithms to predict corrosion rate in oil refinery pipelines in order to enhance the early detection strategies. The comparative analysis included four supervised machine learning models such as random forest, support vector regression (SVR), convolutional neural network (CNN), and the long short-term memory (LSTM). Additionally, the study focuses on using the operational data like temperature, pressure, flow rate, and pH level from the existing transmitters and flow meters to demonstrate a cost-efficient method that would not require additional investments in new equipment installation. Given, the harsh nature of hydrocarbon fluid, oil leakage caused by corrosion can significantly damage the environment leading to contamination and ecological disaster as well as substantial financial loss for the companies. The findings of the study underscore the importance of implementing effective early detection strategies to prevent such severe outcomes and show the potential of machine learning to advance corrosion management and elevate the overall safety in oil industry.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Jameel Syed, Muslim UNSPECIFIED
Uncontrolled Keywords:	Convolutional neural network (CNN); corrosion detection; long short-term memory (LSTM); machine learning; oil and gas industry; random forest; support vector regression (SVR)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Oil Industry
Divisions:	School of Computing > Master of Science in Artificial Intelligence for Business
Depositing User:	Ciara O'Brien
Date Deposited:	02 Jul 2025 16:52
Last Modified:	02 Jul 2025 16:52
URI:	https://norma.ncirl.ie/id/eprint/7993

Actions (login required)

View Item