Oil and gas fires are frequent disasters that occur during oil and gas storage and transportation. In order to prevent the occurrence of oil and gas fires and reduce human and material losses, this paper studied the risk prediction of oil and gas fires based on the fusion of fuzzy fault tree analysis (FFTA) and Bayesian network (BN) algorithm. Firstly, by conducting statistical analysis of accidents, 9 causal factors leading to oil and gas fires were identified. A fuzzy fault tree was established with oil and gas fire accidents as the top event, management issues, oil product issues, protection failures, and hazardous states as intermediate events, and 9 causal factors as basic events. The logical network connections between the fault trees were utilized to organize the causal relationships between each causal factor, and mapping relationships were used to connect the fault tree with Bayesian networks. Finally, combined with expert evaluation, fuzzy processing was performed to obtain the probability of occurrence for each root node (causal factor), and then the prior probabilities of intermediate nodes and leaf nodes were obtained through logical operations and Bayesian network full probability formulas. Through backward inference analysis, it was found that the posterior probability of the intermediate event “dangerous state” was relatively high. Combined with sensitivity analysis, it can be concluded that the fundamental cause of the intermediate event “dangerous state” is the basic event “equipment damage”, and the fundamental cause of the intermediate event “protection failure” is the basic event “protective system failure”. Therefore, it is recommended to take measures such as regular maintenance and inspection, installation of fault monitoring and early warning systems, backup equipment, backup power supply, development of emergency plans and training, and regular drills and evaluations. These measures help to improve the reliability and stability of protective systems and reduce the potential risk of oil and gas fires.

Yao Hu, Liguang Qiao and Feng Gu. Oil and Gas Fire Risk Based on Fuzzy Fault Tree and Bayesian Network. International Journal of Big Data Intelligent Technology (2025), Vol. 6, Issue 2: 21-35. https://doi.org/10.38007/IJBDIT.2025.060203.

[1]Fan Y. Management and maintenance measures of oil and Gas storage and transportation equipment [J]. Chemical Design Communication, 2021,47(11):7-8.

[2]Zhang Xinlin, Wei Ran. Analysis on Daily management and maintenance of oil and gas storage and transportation equipment in the Information Age [J]. China Petroleum and Chemical Standards and Quality, 21,41(04):109-111.

[3]Hosseinnia Davatgar B, Paltrinieri N, Bubbico R. Safety barrier management: risk-based approach for the oil and gas sector[J].Journal of Marine Science and Engineering, 2021, 9(7): 722.

[4]Dimaio F, Scapinello O, Zio E, et al. Accounting for safety barriers degradation in the risk assessment of oil and gas systems by multistate Bayesian networks[J]. Reliability Engineering & System Safety, 2021, 216: 107943.

[5]Zhang huan. The fault tree analysis method in the application of a certain commercial air source system troubleshooting [J]. Journal of internal combustion engine and accessories, 2023, (18) : 4-7. DOI: 10.19475 / j.carol carroll nki issn1674-957 - x. 2023.18.007.

[6]Zhang Weidong, Yu Youmin. Reliability Analysis of Subway Vehicle Air Conditioning System based on Bayesian Network [J]. Refrigeration and Air Conditioning,2023,23(08):78-83.

[7]Guo Zan. Risk Assessment of Cleaning device failure condition based on Fuzzy fault tree analysis [J]. Green science and technology, 2023, 25 (22) : 97-101. The DOI: 10.16663 / j.carol carroll nki LSKJ. 2023.22.040.

[8]Chen Yongjun, Li Xiaojian, Zhang Li, et al. Application of fault tree and Fuzzy Bayesian network in risk assessment of pipeline corridor operation and maintenance [J]. Journal of safety and environment, 2024, 24 (3) : 857-866. The DOI: 10.13637 / j.i SSN. 1009-6094.2023.0292.

[9]Sun Kuan, ZHANG Shuguang, Wang Zhu. Time and function based on fuzzy sets is harmful to the continuous changes in system analysis [J/OL]. Aviation engineering progress, 1-8 [2024-04-30]. http://192.144.236.110:8085/kcms/detail/61.1479.V.20240325.1316.006. html.

[10]Li Boyu, Liu Qigang. Research on safety risk factor decision of high-speed railway station based on fusion of fuzzy fault tree and Bayesian network [J/OL]. Railway standard design, 1-10 [2024-04-30]. https://doi.org/10.13238/j.issn.1004-2954.202212190002.

[11]Guo Jiming, Qi Jinping, Li Xingyun. Reliability Analysis of EMU Braking System Based on Fuzzy Dynamic Fault Tree[J]. China Mechanical Engineering, 2019, 30(13): 1585.

[12]Dong Tao, ZHAO Lei. Discussion on Safety Management of Oil Depot [J]. Science and Technology Innovation Review,2019,27(16):167-169.

[13]Wen Yacheng, KANG Yang. Safety Accident Analysis of Airport Oil Depot Based on Fault Tree [J]. Petrochemical Safety and Environmental Protection Technology,2021.

[14]Xu H J. Safety risk and Accident prevention and control of oil depot [J]. Chemical Industry Management, 2020.

[15]Guan Rui, TANG Huang. Analysis of Common Accidents in oil depot and Countermeasures [J]. Petrochemical Technology, 2021.

[16]Li T T. A brief discussion on the influencing factors and cognition of the safe operation of oil depots [J]. Chemical Management, 2019, 11.

[17]Yazdi M, Mohammadpour J, Li H, et al. Fault tree analysis improvements: A bibliometric analysis and literature review[J]. Quality and Reliability Engineering International, 2023, 39(5): 1639-1659.

[18]Kitson N K, Constantinou A C, Guo Z, et al. A survey of Bayesian Network structure learning[J]. Artificial Intelligence Review, 2023, 56(8): 8721-8814.

[19]Sevinc V, Kucuk O, Goltas M. A Bayesian network model for prediction and analysis of possible forest fire causes[J]. Forest Ecology and Management, 2020, 457: 117723.

[20]You BingyuLian Fumian, Meng Xianghai. Analysis of the causes of highway accidents in mountainous areas based on fault tree Bayesian nets[J]. Journal of Transportation Information and Safety, 2019, 37(4): 44-51.

[21]Wang C, Wang L, Chen H, et al. Fault diagnosis of train network control management system based on dynamic fault tree and Bayesian network[J]. IEEE Access, 2020, 9: 2618-2632.

[22]Lin S S, Shen S L, Zhou A, et al. Risk assessment and management of excavation system based on fuzzy set theory and machine learning methods[J]. Automation in Construction, 2021, 122: 103490.

[23]Pappas I O, Woodside A G. Fuzzy-set Qualitative Comparative Analysis (fsQCA): Guidelines for research practice in Information Systems and marketing[J]. International Journal of Information Management, 2021, 58: 102310.

[24]Liu Y, Jiang W. A new distance measure of interval-valued intuitionistic fuzzy sets and its application in decision making[J]. Soft Computing, 2020, 24: 6987-7003.

[25]Li Z H, Chen J, Bi J. Multiple object tracking with appearance feature prediction and similarity fusion[J]. IEEE Access, 2023.

[26]Rosso-Mateus A, Montes-y-Gómez M, Rosso P, et al. Deep fusion of multiple term-similarity measures for biomedical passage retrieval[J]. Journal of Intelligent & Fuzzy Systems, 2020, 39(2): 2239-2248.

[27]Sun J, Ding Y, Zhu X, et al. Extended Gaussian sphere and similarity fusion method for reassembly of 3D cultural relics[J]. Multimedia Tools and Applications, 2020, 79: 30187-30203.

[28]Razavi S, Jakeman A, Saltelli A, et al. The future of sensitivity analysis: an essential discipline for systems modeling and policy support[J]. Environmental Modelling & Software, 2021, 137: 104954.

[29]Liu B, Meng K, Dong Z Y, et al. Load balancing in low-voltage distribution network via phase reconfiguration: An efficient sensitivity-based approach[J]. IEEE Transactions on Power Delivery, 2020, 36(4): 2174-2185.

[30]Agbo C, Mehrpouyan H. Achieving Cyber-Informed Engineering Through Bayesian Belief Network and Sensitivity Analysis[C]//2023 10th International Conference on Dependable Systems and Their Applications (DSA). IEEE, 2023: 260-271.