Authors : Gambo Suleiman; Dr. Ridwan Kolapo

Volume/Issue : Volume 11 - 2026, Issue 3 - March

Google Scholar : https://tinyurl.com/2ktmvuvw

Scribd : https://tinyurl.com/5587yhcb

DOI : https://doi.org/10.38124/ijisrt/26mar1964

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : The challenges that are still being evident in the Nigerian oil and gas industry include leaks in the pipeline, losses of crude oil, and the slowness of spill detection, which causes massive losses of the economy, pollution, and inefficiency. Current monitoring methods, which are mainly relying on periodic inspection and traditional SCADA systems, are often not able to detect crude oil losses in real-time, precisely localize them, and automatically reconcile them. The proposed limitations of this study include the construction of a pipeline monitoring system based on the IoT to implement real-time leak identification, localization of leaks, estimation of crude oil loss, and the process of automated daily reconciliation. The study used Design Science Research (DSR) approach that entailed system design, prototype implementation, and experimental validation. The proposed architecture is a combination of distributed ESP32 sensor nodes to monitor pressure, flow and temperature, LoRa based long range communication to send node to gateway and GSM/4G cellular backhaul to report data centrally. The hybrid model of leak detection has been adopted where mass balance analysis and anomaly detection based on pressure gradients were used to enhance the reliability of the detection and minimized false alarms. Leak localization was also performed through segment-based pressure analysis and cumulative flow imbalance integration were also utilized to estimate crude oil loss, as well as provide automated reconciliation. The prototype was deployed and tested in Wokwi high-fidelity simulation environment because of the delays in hardware procurement. It has been shown that experimental results indicated that the system attained a high leakage detection rate of 95 percent, a localization rate of 80 percent, average loss estimation of less than 10 percent, and a self-gap of 2-4 seconds. Communication tests showed that there was effective data delivery with good buffering of gateways. The research comes up with a conclusion that the proposed IoT-enabled monitoring system is technically feasible and applicable to improving the pipeline visibility, minimizing the unreported losses, and increasing the responsibility of the crude oil in the Nigerian pipeline setting. The system offers low cost scalable base of next generation intelligent pipeline integrity management. The future work must be aimed at the deployment on the field scale, the increase of sensor density, and the combination of edge AI and live operational dashboards.

Keywords : Internet of Things (IoT); Pipeline Leak Detection; LoRa; Real-Time Monitoring; Crude Oil Loss Estimation; Design Science Research; Nigerian Oil and Gas Industry.

References :

1. Abubakar, A. (2025). Monitoring and detection of pipeline leaks: A bibliometric and systematic review. Journal of Pipeline Engineering.
2. Adebayo, T., & Dada, O. (2022). Pipeline integrity challenges in the Nigerian oil and gas sector. Journal of Petroleum Infrastructure, 14(2), 55–67.
3. Agbolade, O. (2023). IoT-based pipeline leak detection and localization using LoRaWAN. International Journal of Industrial IoT, 9(1), 21–34.
4. Ahmed, M., & Zhou, Y. (2023). Integrated approaches to pipeline monitoring: A review. Journal of Energy Systems, 12(3), 201–219.
5. Akinwale, A., Bello, S., & Musa, I. (2022). Challenges in real-time pipeline leak localization in remote environments. Nigerian Journal of Engineering Research, 17(1), 88–99.
6. Alghamdi, A., et al. (2022). Feasibility of LPWAN technologies for large-scale monitoring systems. IEEE Access, 10, 44521–44535.
7. Bakhder, T., et al. (2022). LoRa-based IoT networks for oil pipeline monitoring. Sensors, 22(14), 5120.
8. Boujelben, M., et al. (2023). Real-time pipeline leak detection using embedded 1D-CNN acoustic sensing. IEEE Sensors Journal, 23(6), 6543–6555.
9. Bukie, T. (2025). IoT-based pipeline leak monitoring with cloud integration. Journal of Smart Infrastructure, 8(2), 77–91.
10. Centenaro, M., Vangelista, L., Zanella, A., & Zorzi, M. (2022). Long-range communications in unlicensed bands: The rising stars in the IoT and smart city scenarios. IEEE Wireless Communications, 23(5), 60–67.
11. Chen, H., et al. (2024). Pressure transient analysis for pipeline leak localization. Journal of Loss Prevention in the Process Industries, 84, 105089.
12. Dere, K. (2023). Design of an IoT pressure profiling device for pipeline monitoring. Instrumentation Review, 11(4), 145–156.
13. Ibrahim, M., Yusuf, A., & Lawal, K. (2023). Limitations of manual crude oil reconciliation in pipeline operations. Energy Accounting Review, 6(1), 33–48.
14. Ikechukwu, P., & Nwankwo, C. (2023). Deployment considerations for distributed IoT sensor networks in harsh environments. African Journal of Embedded Systems, 5(2), 90–104.
15. Javid, R., et al. (2025). Hybrid Kalman–LSTM framework for real-time pipeline leak detection. IEEE Internet of Things Journal.
16. Khan, S., et al. (2022). Multi-sensor IoT framework for pipeline anomaly detection. Sensors, 22(9), 3312.
17. Korlapati, V. (2022). Review of pipeline leak detection methodologies. Journal of Pipeline Systems Engineering, 18(1), 1–15.
18. Li, X., et al. (2023). Pressure-based pipeline leak localization using multi-point sensing. Journal of Petroleum Science and Engineering, 221, 111256.
19. Li, Y., et al. (2024). Hybrid LoRa-cellular architectures for industrial IoT monitoring. IEEE Communications Surveys & Tutorials, 26(1), 455–478.
20. Maia, R., et al. (2024). IoT-based onshore oil leak monitoring using thermal sensing and 4G connectivity. Journal of Petroleum Technology, 76(3), 44–53.
21. NOSDRA. (2022). National oil spill statistics report. National Oil Spill Detection and Response Agency, Nigeria.
22. NOSDRA. (2023). Oil spill monitor annual report. National Oil Spill Detection and Response Agency, Nigeria.
23. NOSDRA. (n.d.). Oil spill monitoring data portal. National Oil Spill Detection and Response Agency.
24. Nwazor, K., & Ogbondamati, J. (2025). Reinforcement learning for adaptive pipeline leak detection. AI in Energy Systems, 4(1), 59–73.
25. Okeke, E., & Bello, A. (2023). Environmental and economic impacts of pipeline vandalism in Nigeria. Energy Policy Review, 15(2), 120–134.
26. Okoli, J., & Orinya, S. (2022). Aging infrastructure and leak risks in petroleum pipelines. Journal of Petroleum Engineering, 10(3), 99–112.
27. Rahman, F. (2024). Leak detection techniques for multiphase pipelines: A review. Process Safety Progress, 43(2), e12567.
28. Saleem, M., et al. (2024). Real-time leak detection using acoustic emission and deep learning. Mechanical Systems and Signal Processing, 198, 110456.
29. Saleem, M., et al. (2025). Leak size identification using AE and DenseNet. Engineering Applications of Artificial Intelligence, 128, 107456.
30. Sharma, P., et al. (2023). Comparative analysis of mass balance leak detection methods. Journal of Pipeline Engineering, 22(1), 45–60.
31. Zhang, Y., et al. (2022). Limitations of SCADA-based pipeline monitoring systems. IEEE Transactions on Industrial Informatics, 18(7), 4890–4899.