Development of a Machine Learning Base with Hybrid Vector Support and Smell Agent Algorithm for Oil and Gas Pipe Leak Detection and Location

Momoh I. O., Isah I. A., Usman A. L., Yusuf O. A.

Abstract


This research proposed a novel leak detection and location method for oil and natural gas pipelines using machine learning with a hybrid of vector support and smell agent algorithm; a propagation model is developed and refined. Initially, theoretical propagation laws are derived by analyzing the damping factors that cause attenuation. Next, wavelet transform analysis was used in experiments to identify the dominant energy frequency bands of leakage sound waves. Subsequently, the actual propagation model is adjusted using a correction factor based on these speed and time bands. This leads to the proposal of a new leak detection and location method grounded in the propagation law, which was validated through experiments on oil pipelines. Finally, the method was tested on gas pipelines. The results were demonstrated using machine learning with a hybrid of support vector machine and smell agent algorithm model; these were established experimentally, which suffice to demonstrate the effectiveness of the proposed method. Conventional SVM achieves 93.2% accuracy, while optimization using PSO and GA improves the performance to 95.6% and 96.4%, respectively. The proposed SAO-SVM model achieves the highest accuracy of 99.1%, indicating that SAO effectively optimized the SVM hyperparameters and significantly enhances classification performance. The proposed leak location and detection method proved superior to traditional methods based on velocity and time difference, distance, and it accurately detects and locates leaks in both oil and gas pipelines. 


Full Text:

PDF

References


S. El-Zahab and T. Zayed, "Leak detection in water distribution networks: an introductory overview," Smart Water, vol. 4, no. 1, p. 5, 2019.

G. Ofualagba and O. t. Ejofodomi, "Automated oil and gas pipeline vandalism detection system," in SPE Nigeria Annual International Conference and Exhibition, 2020: SPE, p. D013S011R006.

D. Zaman, M. K. Tiwari, A. K. Gupta, and D. Sen, "A review of leakage detection strategies for pressurised pipeline in steady-state," Engineering Failure Analysis, vol. 109, p. 104264, 2020.

A. Ebrahimi-Moghadam, M. Farzaneh-Gord, A. Arabkoohsar, and A. J. Moghadam, "CFD analysis of natural gas emission from damaged pipelines: Correlation development for leakage estimation," Journal of Cleaner Production, vol. 199, pp. 257-271, 2018.

J. Sekhavati, S. H. Hashemabadi, and M. Soroush, "Computational methods for pipeline leakage detection and localization: A review and comparative study," Journal of Loss Prevention in the Process Industries, vol. 77, p. 104771, 2022.

J. Li, Q. Zheng, Z. Qian, and X. Yang, "A novel location algorithm for pipeline leakage based on the attenuation of negative pressure wave," Process Safety and Environmental Protection, vol. 123, pp. 309-316, 2019.

W. Wang, X. Mao, H. Liang, D. Yang, J. Zhang, and S. Liu, "Experimental research on in-pipe leaks detection of acoustic signature in gas pipelines based on the artificial neural network," Measurement, vol. 183, p. 109875, 2021.

M. Zhou et al., "A pipeline leak detection and localization approach based on ensemble TL1DCNN," IEEE Access, vol. 9, pp. 47565-47578, 2021.

T. Zhang, Y. Tan, X. Zhang, and J. Zhao, "A novel hybrid technique for leak detection and location in straight pipelines," Journal of Loss Prevention in the Process Industries, vol. 35, pp. 157-168, 2015.

Bello, S., Amadi, M. D., & Rawayau, A. H. (2023). Internet of Things-Based Wireless Sensor Network System for Early Detection and Prevention of Vandalism/Leakage on Pipeline Installations in The Oil and Gas Industry in Nigeria. Fudma journal of sciences, 7(5), 240-246.

Wu, T., Chen, Y., Deng, Z., Shen, L., Xie, Z., Liu, Y., ... & Li, Y. (2023). Oil pipeline leakage monitoring developments in China. Journal of Pipeline Science and Engineering, 3(4), 100129.

Hu, Q., Zhang, Z., Su, Z., Zhou, J., Liu, W., & Zhang, Z. (2025). Investigation and numerical simulation of a severe leakage in an ultra-deep buried gas pipeline: A case study. Construction and Building Materials, 491, 142745.

Tajalli, S. A. M., Moattari, M., Naghavi, S. V., & Salehizadeh, M. R. (2024). A novel hybrid internal pipeline leak detection and location system based on modified real-time transient modelling. Modelling, 5(3), 1135-1157.

Adenubi, S., Appah, D., Okafor, E., & Aimikhe, V. (2023). A review of leak detection systems for natural gas pipelines and facilities. International Journal of Energy Technology and Policy, 13(2), 9-19.

Taheri, A., Beryani, A. A., Motavassel, M., & Nassab, E. A. (2025). Integrated Quantitative Explosion Risk Assessment and Safety Zone Delineation Applied in a Pressure Vessel Adopting PHAST Numerical Simulation Approach: An Iranian Case Analysis. Results in Engineering, 105581.

Liu, T., Cai, X., Zhou, W., Wang, K., & Wang, J. (2025). Enhanced Detection of Pipeline Leaks Based on Generalized Likelihood Ratio with Ensemble Learning. Processes, 13(2), 558.

Sankar, K. M., & Booba, B. (2025). Performance Evaluation of Machine Learning Algorithms for Detecting Gas Leakage System. CLEI Electronic Journal, 28(3).

Wu, T., Chen, Y., Deng, Z., Shen, L., Xie, Z., Liu, Y., ... & Li, Y. (2023). Oil pipeline leakage monitoring developments in China. Journal of Pipeline Science and Engineering, 3(4), 100129.

Al-Sabaeei, A. M., Alhussian, H., Abdulkadir, S. J., & Jagadeesh, A. (2023). Prediction of oil and gas pipeline failures through machine learning approaches: A systematic review. Energy Reports, 10, 1313-1338.

Wang, S., Liang, W., & Shi, F. (2024). Identification of coating layer pipeline defects based on the GA-SENet-ResNet18 model. International Journal of Pressure Vessels and Piping, 212, 105327.

Aljameel, S. S., Alabbad, D. A., Alomari, D., Alzannan, R., Alismail, S., Alkhudir, A., ... & Rahman, A. U. (2024). Oil and Gas Pipelines Leakage Detection Approaches: A Systematic Review of Literature. International Journal of Safety & Security Engineering, 14(3).

Wang, J., Zhao, L., Liu, T., Li, Z., Sun, T., & Grattan, K. T. (2016). Novel negative pressure wave-based pipeline leak detection system using fiber Bragg grating-based pressure sensors. Journal of Lightwave Technology, 35(16), 3366-3373

Ren, L., Jiang, T., Jia, Z. G., Li, D. S., Yuan, C. L., & Li, H. N. (2018). Pipeline corrosion and leakage monitoring based on the distributed optical fiber sensing technology. Measurement, 122, 57-65.

Pan, N., Jiang, S., Du, Y., & Hu, Z. (2020). Infrared thermal imaging for intelligent leakage detection in underground integrated pipe corridors. Journal of Testing and Evaluation, 48(6), 4503-4515.

Kim, J., Han, S., Kim, D., & Lee, Y. (2024). Gas pipeline leak detection by integrating dynamic modeling and machine learning under the transient state. Energies, 17(21), 5517.

Weber, D., & Schwille, F. (1991). Passive vapor monitoring of underground storage tanks for leak detection. Environmental monitoring and assessment, 16(2), 99-116.

Yao, L., Zhang, Y., He, T., & Luo, H. (2023). Natural gas pipeline leak detection based on acoustic signal analysis and feature reconstruction. Applied Energy, 352, 121975.

Meng, G., & Hu, H. (2024). Research on multi-point monitoring data grid model and inversion positioning method for gas leakage in oil and gas stations. Sustainability, 16(4), 1638.


Refbacks

  • There are currently no refbacks.