Title: Leak detection in petroleum pipelines using fuzzy logic and statistical simulation methods

Authors: Pham Son Tung; Vo Quoc Thong

Addresses: Department of Drilling and Production Engineering, Faculty of Geology and Petroleum Engineering, Ho Chi Minh University of Technology (HCMUT), 268 Ly Thuong Kiet Street, District 10, Ho Chi Minh City, Vietnam; Vietnam National University Ho Chi Minh City, Linh Trung Ward, Thu Duc City, Ho Chi Minh City, Vietnam ' Department of Drilling and Production Engineering, Faculty of Geology and Petroleum Engineering, Ho Chi Minh University of Technology (HCMUT), 268 Ly Thuong Kiet Street, District 10, Ho Chi Minh City, Vietnam; Vietnam National University Ho Chi Minh City, Linh Trung Ward, Thu Duc City, Ho Chi Minh City, Vietnam

Abstract: This paper proposed a novel approach that combined fuzzy logic with statistical simulation methods to continuously monitor pipelines for potential leaks. Detailed workflows and real data were given for analysis and comparison. Results indicated that integrating fuzzy logic with either Monte Carlo simulation or the bootstrap method yielded more accurate predictions than using only fuzzy logic. This approach addressed uncertainties in real-world scenarios, such as faulty measuring devices and the limited availability of data for validation. Additionally, the paper provided detailed programming to automate result extraction, eliminating the need for manual data processing and reducing response time. By requiring, continuous monitoring of pressures and flow rates at just two locations – both ends of the pipeline – this method can be easily integrated into existing control systems, enhancing leak detection while maintaining a low computational cost. [Received for review: September 30, 2023; Accepted: September 17, 2024]

Keywords: leak detection; pipelines; fuzzy logic; Monte Carlo simulation; bootstrap method.

DOI: 10.1504/IJOGCT.2025.148750

International Journal of Oil, Gas and Coal Technology, 2025 Vol.38 No.3, pp.303 - 338

Received: 27 Sep 2023
Accepted: 17 Sep 2024
Published online: 22 Sep 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article