A Hybrid Model for Predicting Oil Pipeline Leakage Accident Risk Based on the Integration of the Kent Muhlbauer Method and Artificial Neural Networks پیش بینی ریسک
Irtiqa Imini Pishgiri Masdumiyat (Safety Promotion and Injury Prevention),
Vol. 13 No. 2 (1404),
11 July 2026
,
Page 6-19
https://doi.org/10.22037/iipm.v13i2.52128
Abstract
Background and Aim: The present study was conducted in 2023 with the aim of developing a model for predicting the risk of leakage accidents in two 42-inch and 48-inch oil transmission pipelines located in southwestern Iran through the integration of the Kent Muhlbauer risk assessment method and Artificial Neural Networks (ANNs).
Methods: In this study, five indices of the Kent Muhlbauer method, including third-party damage, corrosion, design, incorrect operation, and leak impact factor, were used as input variables. Multi-Layer Perceptron (MLP) and Radial Basis Function (RBF) neural network models were developed to estimate accident risk levels across ten different pipeline zones. The neural network architectures consisted of an input layer, hidden layers, and an output layer. Model performances were evaluated and compared using the Mean Squared Error (MSE) and correlation coefficient (R).
Results: The results indicated that Zone 5 (the Jarahi River crossing section) exhibited the highest risk level according to the Kent Muhlbauer method, with priority numbers of 2.7684 and 2.8475 for the 42-inch and 48-inch pipelines, respectively. The risk levels associated with the 48-inch pipeline were generally higher than those of the 42-inch pipeline. The artificial neural network modeling results showed that the MSE values for the MLP and RBF networks were 0.00015891 and 0.0002917, respectively, while the corresponding R values were 0.7767 and 0.7227. These results demonstrated acceptable agreement with the risk data derived from qualitative expert judgments. Overall, the MLP network exhibited superior predictive performance compared with the RBF network.
Conclusion: Considering the presence of residential areas and populations living along the pipeline corridor, as well as environmentally sensitive ecosystems such as reservoir lakes, the Jarahi River, sparsely forested regional habitats, and urban areas, oil transmission pipelines possess considerable potential for accident occurrence and associated environmental consequence
- Artificial neural networks
- MLP network
- Oil pipelines
- Oil pollution
- RBF network
How to Cite
References
1. Sarkheil H, Dehdari F, Azimi Y, Araghi MT. Identification of process hazards in the hot stripping tower of common crude oil sweetening projects using HAZOP study. Journal of Safety Promotion and Injury Prevention. 2020;8(3).
2. Yao Z, Zhang Y, Zheng Y, Xing C, Hu Y. Enhance flows of waxy crude oil in offshore petroleum pipeline: A review. Journal of Petroleum Science and Engineering. 2022;208:109530. https://doi.org/10.1016/j.petrol.2021.109530
3. Vairo T, Pontiggia M, Fabiano B. Critical aspects of natural gas pipelines risk assessments. A case-study application on buried layout. Process Safety and Environmental Protection. 2021;149:258-268. https://doi.org/10.1016/j.psep.2020.10.050
4. Liu A, Chen K, Huang X, Li D, Zhang X. Dynamic risk assessment model of buried gas pipelines based on system dynamics. Reliability Engineering & System Safety. 2021;208:107326. https://doi.org/10.1016/j.ress.2020.107326
5. Emerson MR, Hall DM, Gilbertz SJ. Pipeline pipedreams: Oil spills, pipeline accidents, and the local truths embedding fossil fuels in the Yellowstone River Valley, United States. Energy Research & Social Science. 2021;72:101859. https://doi.org/10.1016/j.erss.2020.101859
6. Lu H, Xi D, Qin G. Environmental risk of oil pipeline accidents. Science of the total environment. 2023;874:162386. https://doi.org/10.1016/j.scitotenv.2023.162386
7. Dancy JR, Dancy VA. Terrorism and oil & gas pipeline infrastructure: Vulnerability and potential liability for cybersecurity attacks. Oil and Gas, Natural Resources, and Energy Journal. 2017;2(6):579.
8. Hosmer AW, Stanton CE, Beane JL. Intent to spill: Environmental effects of oil spills caused by war, terrorism, vandalism, and theft. InInternational Oil Spill Conference Proceedings 1997 (Vol. 1997, No. 1, pp. 157-163). American Petroleum Institute. https://doi.org/10.7901/2169-3358-1997-1-157
9. Gong Y, Xiong Y. HFACS-OGP: an analysis framework for oil and gas pipeline accident causation. Journal of Loss Prevention in the Process Industries. 2025:105747. https://doi.org/10.1016/j.jlp.2025.105747
10. Barron MG, Vivian DN, Heintz RA, Yim UH. Long-term ecological impacts from oil spills: comparison of Exxon Valdez, Hebei Spirit, and Deepwater Horizon. Environmental science & technology. 2020;54(11):6456-6467. https://doi.org/10.1021/acs.est.9b05020
11. Belvederesi C, Thompson MS, Komers PE. Statistical analysis of environmental consequences of hazardous liquid pipeline accidents. Heliyon. 2018;4(11). https://doi.org/10.1016/j.heliyon.2018.e00901
12. Zhang S, Wang X, Cheng YF, Shuai J. Modeling and analysis of a catastrophic oil spill and vapor cloud explosion in a confined space upon oil pipeline leaking. Petroleum science. 2020;17(2):556-566. https://doi.org/10.1007/s12182-019-00403-2
13. Badparva F, Varharami V, Lahijanian A. Risks economical analysis HSE based on fine Kinney and Nokia Siemens network techniques in one of electronic kits assembly and production company. Journal of Safety Promotion and Injury Prevention (Irtiqa Imini Pishgiri Masdumiyat). 2023;11(1):1-6. (In Persian). https://doi.org/10.22037/iipm.v11i1.33515
14. Soltanzadeh A, Mohammadfam I, Mahmoudi SH, Alizadeh Savareh B, Mohamadi Arani A. Analysis and forecasting the severity of construction accidents using artificial neural network. Journal of Safety Promotion and Injury Prevention (Irtiqa Imini Pishgiri Masdumiyat). 2016;4(3):185-192. (In Persian). https://doi.org/10.22037/meipm.v4i3.15823
15. Aljaroudi A, Khan F, Akinturk A, Haddara M, Thodi P. Risk assessment of offshore crude oil pipeline failure. Journal of Loss Prevention in the Process Industries. 2015;37:101-109. https://doi.org/10.1016/j.jlp.2015.07.004
16. Bonvicini S, Antonioni G, Cozzani V. Assessment of the risk related to environmental damage following major accidents in onshore pipelines. Journal of Loss Prevention in the Process Industries. 2018;56:505-516. https://doi.org/10.1016/j.jlp.2018.11.005
17. Qin G, Zhang P, Hou X, Wu S, Wang Y. Risk assessment for oil leakage under the common threat of multiple natural hazards. Environmental Science and Pollution Research. 2020;27(14):16507-16520. https://doi.org/10.1007/s11356-020-08184-7
18. Badida P, Balasubramaniam Y, Jayaprakash J. Risk evaluation of oil and natural gas pipelines due to natural hazards using fuzzy fault tree analysis. Journal of Natural Gas Science and Engineering. 2019;66:284-292. https://doi.org/10.1016/j.jngse.2019.04.010
19. Samuel OW, Asogbon GM, Sangaiah AK, Fang P, Li G. An integrated decision support system based on ANN and Fuzzy_AHP for heart failure risk prediction. Expert Systems with Applications. 2017;68:163-172. https://doi.org/10.1016/j.eswa.2016.10.020
20. Lin SS, Shen SL, Zhou A, Xu YS. Risk assessment and management of excavation system based on fuzzy set theory and machine learning methods. Automation in Construction. 2021;122:103490. https://doi.org/10.1016/j.autcon.2020.103490
21. Feng X, Li Q, Zhu Y, Hou J, Jin L, Wang J. Artificial neural networks forecasting of PM2. 5 pollution using air mass trajectory based geographic model and wavelet transformation. Atmospheric Environment. 2015;107:118-128. https://doi.org/10.1016/j.atmosenv.2015.02.030
22. Sajedi-Hosseini F, Malekian A, Choubin B, Rahmati O, Cipullo S, Coulon F, Pradhan B. A novel machine learning-based approach for the risk assessment of nitrate groundwater contamination. Science of the Total Environment. 2018;644:954-962. https://doi.org/10.1016/j.scitotenv.2018.07.054
23. Abdolrasol MG, Hussain SS, Ustun TS, Sarker MR, Hannan MA, Mohamed R, Ali JA, Mekhilef S, Milad A. Artificial neural networks based optimization techniques: A review. Electronics. 2021;10(21):2689. https://doi.org/10.3390/electronics10212689
24. Hegde J, Rokseth B. Applications of machine learning methods for engineering risk assessment–A review. Safety science. 2020;122:104492. https://doi.org/10.1016/j.ssci.2019.09.015
25. Akbarinia GR, Gilani N, Mohhamadzadeh S, Alizadeh SS. Application of Kent Muhlbauer method to risk assessment of urban gas pipelines. Journal of Pipeline Systems Engineering and Practice. 2022;13(1):05021011. https://doi.org/10.1061/(ASCE)PS.1949-1204.0000601
26. Mahmoodi E, Mortazavi SB, Ahmadi O, Mahabadi HA. Analysis of liquid pipelines accidents causes, consequences and contributing factors: a review study. Journal of Failure Analysis and Prevention. 2021;21(2):348-362. https://doi.org/10.1007/s11668-020-01054-x
27. Muhlbauer WK, Murray J. Pipeline risk assessment. InHandbook of Pipeline Engineering 2024 Jul 26 (pp. 959-1004). Cham: Springer International Publishing. https://doi.org/10.1007/978-3-031-05735-9_24-1
28. Han K, Wang Y. A review of artificial neural network techniques for environmental issues prediction. Journal of Thermal Analysis and Calorimetry. 2021;145(4):2191-2207. https://doi.org/10.1007/s10973-021-10748-9
29. You H, Ma Z, Tang Y, Wang Y, Yan J, Ni M, Cen K, Huang Q. Comparison of ANN (MLP), ANFIS, SVM, and RF models for the online classification of heating value of burning municipal solid waste in circulating fluidized bed incinerators. Waste Management. 2017;68:186-197. https://doi.org/10.1016/j.wasman.2017.03.044
30. Hong H, Zhang Z, Guo A, Shen L, Sun H, Liang Y, Wu F, Lin H. Radial basis function artificial neural network (RBF ANN) as well as the hybrid method of RBF ANN and grey relational analysis able to well predict trihalomethanes levels in tap water. Journal of Hydrology. 2020;591:125574. https://doi.org/10.1016/j.jhydrol.2020.125574
31. Isherwood A, Samcheck A, Savigny W. Deformation Analysis of a Pipeline River Crossing. InInternational Pipeline Conference 2002 (Vol. 36207, pp. 571-584). https://doi.org/10.1115/IPC2002-27343
32. DiDonato DA. Alternative methods to reduce aqueous pollutants from hydrostatic pressure testing of natural gas pipelines: A feasibility study. State University of New York College of Environmental Science and Forestry; 1995.
33. Simpson DA. Comparative risks of hydrostatic and pneumatic pipeline testing. Journal of Pressure Vessel Technology. 2020;142(5):054503. https://doi.org/10.1115/1.4046981
34. Olabisi OT, Chukwuka A. Experimental investigation of pipeline corrosion in a polluted Niger Delta River. International Journal of Oil, Gas and Coal Engineering. 2020;8(1):17-21. https://doi.org/10.11648/j.ogce.20200801.13
35. Biber PD, Wu W, Peterson MS, Liu Z, Pham L. Oil contamination in Mississippi salt marsh habitats and the impacts to Spartina alterniflora photosynthesis. InImpacts of Oil Spill Disasters on Marine Habitats and Fisheries in North America 2014 (Vol. 17, p. 133). Boca Raton, FL, USA: CRC Press.
36. Shafie A, Fard NJ, Monavari M, Sabzalipour S, Fathian H. Artificial neural network and multi-criteria decision-making methods for the remediation of soil oil pollution in the southwest of Iran. Modeling Earth Systems and Environment. 2024;10(1):417-424. https://doi.org/10.1007/s40808-022-01601-5
- Abstract Viewed: 23 times
- 1 (فارسی) Downloaded: 12 times