Throughout the digitization of the petrochemical industry, the Beidou technology-based disaster monitoring, evaluation, and early warning network system has supported emergency decision making for oil and gas accidents. Many problems arise throughout the emergency decision-making process during oil–gas accidents, such as the limited time for decision making, high complexity, and inadequate emergency plans. Targeting these issues, we propose the construction of a case library using a Bayesian network. This way, when a new accident occurs, its similarity and deviation indexes could be matched against those of historical cases registered in the database. As such, the candidate cases are adjusted using a case combination and pruning method, yielding the final qualified case model. A case verification of the “11.22” Sinopec Oil pipeline leak and explosion in Qingdao reveals that the proposed method only requires an oil and gas accident database to be built in advance, eliminating the need for sampling data to make decisions, and reducing the search space. Using the proposed case-based reasoning, historical data and experience regarding oil and gas emergency decisions can be activated and reused, which would greatly improve the modeling efficiency of the Bayesian network.

1. [1] N. Wang, H. Y. Huang, Q. Y. Zhong, and Y. Z. Wang, “Emergency Case Retrieval Method Based on Knowledge Element,” Syst. Eng., Vol.32, No.1, pp. 124-132, 2014.
2. [2] J. Yang, Z. Zeng, and L. She, “Study on method of case retrieval matching with multi-attribute utility in unconventional emergency,” Application Res. Comput., Vol.35, No.2, pp. 386-390+395, 2018.
3. [3] D. Xia, X. Qian, and Z. Duan, “Scenario deduction model of unconventional emergency based on dynamic Bayesian network,” J. Northeastern University Natural Science, Vol.36, No.6, pp. 897-902, 2015.
4. [4] J. Li, D. Xia, and X. Wu, “Scenario analysis of unconventional emergency disaster accidents based on the knowledge elements and dynamic Bayesian networks,” J. Safety and Environ., Vol.14, No.4, pp. 165-170, 2014.
5. [5] M. R. Martins and M. C. Maturana, “Application of Bayesian Belief networks to the human reliability analysis of an oil tanker operation focusing on collision accidents,” Reliability Eng. Syst. Safety, Vol.110, pp. 89-109, 2013.
6. [6] R. I. Hapsari, S. Oishi, M. Syarifuddin, R. A. Asmara, and D. Legono, “X-MP Radar for developing a lahar rainfall threshold for the Merapi volcano using a Bayesian approach,” J. Disaster Res., Vol.14, No.5, pp. 811-828, 2019.
7. [7] L. Xu, “Research on emergent events decision-making information analysis method based on Bayesian network,” Harbin Institute of Technology, 2013.
8. [8] R. C. Schank, “Dynamic Memory: A Theory of Reminding and Learning in Computers and People,” Cambridge University Press, 1983.
9. [9] A. Aamodt and E. Plaza, “Case-based reasoning: Foundational issues, methodological variations, and system approaches,” AI Commun., Vol.7, No.1, pp. 39-59, 1994.
10. [10] D. Putra and M. Matsuyuki, “The disaster-management capabilities of local governments: A case study in Indonesia,” J. Disaster Res., Vol.15, No.4, pp. 471-480, 2020.
11. [11] Y. Song, K. Yu, W. Lv et al., “Research on case similarity matching of city bus fire incidents,” China Safety Sci. J., Vol.27, No.4, pp. 163-168, 2017.
12. [12] F. Ricci, P. Avesani, and A. Perini, “Case on fire: Applying CBR to an emergency management,” The New Review of Applied Expert Syst., Vol.5, No.6, pp. 175-190, 1999.
13. [13] Q. Wang and T. Song, “Heavy oil FCCU fire and explosion risk analysis based on BN-LOPA method,” Fire Sci. Technol., Vol.36, No.2, pp. 262-265, 2017.
14. [14] F. Chen, M. Zhang, Y. Wang et al., “Risk analysis of coupling domino effect in petroliferous tank farm,” China Safety Sci. J., Vol.10, pp. 111-116, 2017.
15. [15] L. Da, “Oilfield accident emergency resource scheduling system based on HS algorithm,” Computer and Digital Eng., Vol.2, pp. 232-234, 2015.
16. [16] X. Wang, S. Li, X. Dai et al., “A leakage accident tracing method for the oil and gas pipelines based on fault tree and dynamic Bayesian network,” Oil & Gas Storage and Transportation, Vol.36, No.9, pp. 1013-1018, 2017.
17. [17] X. Gao and Y. Xu, “Visualization decision-making support system for oilfield accident emergency rescue,” Comput. Eng., Vol.36, No.15, pp. 236-239, 2010.
18. [18] X. Gao and Y. Xu, “Design and implementation of emergency rescue system for oilfield accident disaster,” Petroleum Drilling Techniques, Vol.39, No.6, pp. 49-55, 2011.
19. [19] X. Hou, “A sketch recognition algorithm based on Bayesian network and convolution neural network,” J. Adv. Comput. Intell. Intell. Inform., Vol.23, No.2, pp. 261-267, 2019.
20. [20] The State Council of the People’s Republic of China, “Standards for the classification of especially major and major public emergencies,” 2012.