A Machine Learning Based Decision Support Framework for Early – Stage Fault Detection in Nigerian Oil Pipelines

Melissa Oma Ekuma; Abdullahi Gimba; Petrus Nzerem; Ayuba Salihu; Ikechukwu Okafor; Mojeed Ologun; Khaleel Jakada; Chinaza Enwere; Abiodun Adeboye Osomo; Samuel Oyewole Oni; Ajiri Otedheke; Fabian Ugochukwu Okonji; Collintins Ezeja

doi:10.5455/NJEAS.323989

, Vol:

Current Volume Archive Aims and Scope Abstracting & Indexing

Required files to be uploaded

NJEAS TEMPLATE FOR AUTHORS_(v2r)_

Original Research

NJEAS. 2026; 3(2):

doi: 10.5455/NJEAS.323989

A Machine Learning Based Decision Support Framework for Early – Stage Fault Detection in Nigerian Oil Pipelines

Melissa Oma Ekuma, Abdullahi Gimba, Petrus Nzerem, Ayuba Salihu, Ikechukwu Okafor, Mojeed Ologun, Khaleel Jakada, Chinaza Enwere, Abiodun Adeboye Osomo, Samuel Oyewole Oni, Ajiri Otedheke, Fabian Ugochukwu Okonji, Collintins Ezeja.

Abstract
The integrity of Oil pipeline infrastructure in Nigeria’s Petroleum Industry continues to be threatened by a mix of operational faults, equipment failures and external interfering factors, highlighting a real need for unique, intelligent and data driven monitoring solutions. In a bid to provide such a solution, this project developed and evaluated a Machine Learning based Binary decision support framework for early fault detection in Oil pipelines using data sourced from an operational flowline located in the Niger Delta region of Nigeria. The methodology adopted in carrying out the project was systematic, commencing with meticulous data preprocessing and finishing with rigorous model testing and evaluation. The result was a fault detection framework based on the XGBoost classifier algorithm trained on 263,053 points of data generated from operational field reports which yielded an AUC-ROC value of 0.9893 following a series of targeted algorithm optimization stages. Accuracy, Precision and Recall scores of 98.78%, 65.51% and 70.60% at a 0.80 decision threshold also served as further proof that the final model was effective and adequately adapted for reliable early fault detection in a real time deployment situation, while maintaining sufficiently low rates for false alarms. Additionally, the study proposed a low cost, integration pathway requiring minimal modification to existing systems, designed to seamlessly integrate the final binary model into existing pipeline monitoring frameworks. The final result was a self-improving intelligent decision support layer that meets the need for proactive and optimized pipeline integrity management in the Nigerian Oil and Gas industry.

Key words: Pipeline Integrity, Fault Detection, RTTM, Machine Learning, XGBoost, Niger Delta, SCADA systems.

	ARTICLE TOOLS
	Abstract
	PDF Fulltext
	How to cite this article
	Citation Tools
	Related Records
	Articles by Melissa Oma Ekuma Articles by Abdullahi Gimba Articles by Petrus Nzerem Articles by Ayuba Salihu Articles by Ikechukwu Okafor Articles by Mojeed Ologun Articles by Khaleel Jakada Articles by Chinaza Enwere Articles by Abiodun Adeboye Osomo Articles by Samuel Oyewole Oni Articles by Ajiri Otedheke Articles by Fabian Ugochukwu Okonji Articles by Collintins Ezeja
	on Google
	on Google Scholar

How to Cite this Article

Pubmed Style

Ekuma MO, Gimba A, Nzerem P, Salihu A, Okafor I, Ologun M, Jakada K, Enwere C, Osomo AA, Oni SO, Otedheke A, Okonji FU, Ezeja C. A Machine Learning Based Decision Support Framework for Early – Stage Fault Detection in Nigerian Oil Pipelines. NJEAS. 2026; 3(2): -. doi:10.5455/NJEAS.323989

Web Style

Ekuma MO, Gimba A, Nzerem P, Salihu A, Okafor I, Ologun M, Jakada K, Enwere C, Osomo AA, Oni SO, Otedheke A, Okonji FU, Ezeja C. A Machine Learning Based Decision Support Framework for Early – Stage Fault Detection in Nigerian Oil Pipelines. https:///?mno=323989 [Access: August 25, 2026]. doi:10.5455/NJEAS.323989

AMA (American Medical Association) Style

Ekuma MO, Gimba A, Nzerem P, Salihu A, Okafor I, Ologun M, Jakada K, Enwere C, Osomo AA, Oni SO, Otedheke A, Okonji FU, Ezeja C. A Machine Learning Based Decision Support Framework for Early – Stage Fault Detection in Nigerian Oil Pipelines. NJEAS. 2026; 3(2): -. doi:10.5455/NJEAS.323989

Vancouver/ICMJE Style

Harvard Style

Ekuma, M. O., Gimba, . A., Nzerem, . P., Salihu, . A., Okafor, . I., Ologun, . M., Jakada, . K., Enwere, . C., Osomo, . A. A., Oni, . S. O., Otedheke, . A., Okonji, . F. U. & Ezeja, . C. (2026) A Machine Learning Based Decision Support Framework for Early – Stage Fault Detection in Nigerian Oil Pipelines. NJEAS, 3 (2), -. doi:10.5455/NJEAS.323989

Turabian Style

Ekuma, Melissa Oma, Abdullahi Gimba, Petrus Nzerem, Ayuba Salihu, Ikechukwu Okafor, Mojeed Ologun, Khaleel Jakada, Chinaza Enwere, Abiodun Adeboye Osomo, Samuel Oyewole Oni, Ajiri Otedheke, Fabian Ugochukwu Okonji, and Collintins Ezeja. 2026. A Machine Learning Based Decision Support Framework for Early – Stage Fault Detection in Nigerian Oil Pipelines. Nile Journal of Engineering and Applied Science, 3 (2), -. doi:10.5455/NJEAS.323989

Chicago Style

Ekuma, Melissa Oma, Abdullahi Gimba, Petrus Nzerem, Ayuba Salihu, Ikechukwu Okafor, Mojeed Ologun, Khaleel Jakada, Chinaza Enwere, Abiodun Adeboye Osomo, Samuel Oyewole Oni, Ajiri Otedheke, Fabian Ugochukwu Okonji, and Collintins Ezeja. "A Machine Learning Based Decision Support Framework for Early – Stage Fault Detection in Nigerian Oil Pipelines." Nile Journal of Engineering and Applied Science 3 (2026), -. doi:10.5455/NJEAS.323989

MLA (The Modern Language Association) Style

Ekuma, Melissa Oma, Abdullahi Gimba, Petrus Nzerem, Ayuba Salihu, Ikechukwu Okafor, Mojeed Ologun, Khaleel Jakada, Chinaza Enwere, Abiodun Adeboye Osomo, Samuel Oyewole Oni, Ajiri Otedheke, Fabian Ugochukwu Okonji, and Collintins Ezeja. "A Machine Learning Based Decision Support Framework for Early – Stage Fault Detection in Nigerian Oil Pipelines." Nile Journal of Engineering and Applied Science 3.2 (2026), -. Print. doi:10.5455/NJEAS.323989

APA (American Psychological Association) Style

Author Login Reviewer Login About Publisher

About Nile Journal of Engineering and Applied Science

Contact Information

How to cite this article


About Nile Journal of Engineering and Applied Science The Nile Journal of Engineering and Applied Sciences publishes original peer-reviewed articles on fundamental and applied research and reviews ... Read more. For best results, please use Internet Explorer or Google Chrome.	Contact Information 1. Prof. Abdulhameed Danjuma Mambo Editor-in-Chief abdulhameed.mambo@nileuniversity.edu.ng 2. Dr. Adekunle Adeleke Associate Editor-in-Chief adekunle.adeleke@nileuniversity.edu.ng 3. Dr. Ifeyinwa Obianyo Managing Editor ifeyinwa.obianyo@nileuniversity.edu.ng