Page 104 - 《爆炸与冲击》2026年第5期

第 46 卷 冯 彬，等： 基于图神经网络的可燃气体泄漏扩散预测方法 第 5 期

approaches of gas explosion in the chemical process industry: a review [J]. Process Safety and Environmental Protection,
2023, 170: 112–138. DOI: 10.1016/j.psep.2022.11.090.
[12] PRASAD K, PITTS W M, YANG J C. A numerical study of the release and dispersion of a buoyant gas in partially confined
spaces [J]. International Journal of Hydrogen Energy, 2011, 36(8): 5200–5210. DOI: 10.1016/j.ijhydene.2011.01.118.
[13] MEI Y, SHUAI J. Research on natural gas leakage and diffusion characteristics in enclosed building layout [J]. Process Safety
and Environmental Protection, 2022, 161: 247–262. DOI: 10.1016/j.psep.2022.03.040.
[14] SU Y, LI J F, YU B, et al. Numerical investigation on the leakage and diffusion characteristics of hydrogen-blended natural
gas in a domestic kitchen [J]. Renewable Energy, 2022, 189: 899–916. DOI: 10.1016/j.renene.2022.03.038.
[15] KANG Y, MA S Y, SONG B X, et al. Simulation of hydrogen leakage diffusion behavior in confined space [J]. International
Journal of Hydrogen Energy, 2024, 53: 75–85. DOI: 10.1016/j.ijhydene.2023.12.026.
[16] WANG B, CHEN B Z, ZHAO J S. The real-time estimation of hazardous gas dispersion by the integration of gas detectors,
neural network and gas dispersion models [J]. Journal of Hazardous Materials, 2015, 300: 433–442. DOI: 10.1016/j.jhazmat.
2015.07.028.
[17] QIU S H, CHEN B, WANG R X, et al. Atmospheric dispersion prediction and source estimation of hazardous gas using
artificial neural network, particle swarm optimization and expectation maximization [J]. Atmospheric Environment, 2018, 178:
158–163. DOI: 10.1016/j.atmosenv.2018.01.056.
[18] TANG X, WU D L, WANG S M, et al. Research on real-time prediction of hydrogen sulfide leakage diffusion concentration
of new energy based on machine learning [J]. Sustainability, 2023, 15(9): 7237. DOI: 10.3390/su15097237.
[19] ZHANG X Q, SHI J H, LI J J, et al. Hydrogen jet and diffusion modeling by physics-informed graph neural network [J].
Renewable and Sustainable Energy Reviews, 2025, 207: 114898. DOI: 10.1016/j.rser.2024.114898.
[20] HANSEN O R, GAVELLI F, DAVIS S G, et al. Equivalent cloud methods used for explosion risk and consequence studies [J].
Journal of Loss Prevention in the Process Industries, 2013, 26(3): 511–527. DOI: 10.1016/j.jlp.2012.07.006.
[21] TAM V H Y, TAN F, SAVVIDES C. A critical review of the equivalent stoichiometric cloud model Q9 in gas explosion
modelling [J]. Eng, 2021, 2(2): 156–180. DOI: 10.3390/eng2020011.
[22] 齐心歌, 王海清, 田英帅, 等. 基于等价气云爆炸风险评估的气体防护区域定量划分 [J]. 化工进展, 2019, 38(3): 1587–
1594. DOI: 10.16085/j.issn.1000-6613.2018-0153.
QI X G, WANG H Q, TIAN Y S, et al. Quantitative division of gas protection area based on risk assessment of equivalent gas
cloud explosion [J]. Chemical Industry and Engineering Progress, 2019, 38(3): 1587–1594. DOI: 10.16085/j.issn.1000-6613.
2018-0153.
[23] 师吉浩. 海洋平台燃爆风险分析及抗爆减灾设计研究 [D]. 青岛: 中国石油大学 (华东), 2018. DOI: 10.27644/d.cnki.
gsydu.2018.001848.
SHI J H. Research on explosion risk analysis and mitigation design of offshore platforms [D]. Qingdao: China University of
Petroleum (East China), 2018. DOI: 10.27644/d.cnki.gsydu.2018.001848.
[24] 师燕超, 么志远, 袁明德, 等. 综合管廊天然气泄漏爆炸的定量风险评估 [J]. 建筑结构学报, 2023, 44(11): 129–136. DOI:
10.14006/j.jzjgxb.2021.0677.
SHI Y C, YAO Z Y, YUAN M D, et al. Quantitative risk assessment of natural gas leakage and explosion in utility tunnel [J].
Journal of Building Structures, 2023, 44(11): 129–136. DOI: 10.14006/j.jzjgxb.2021.0677.
[25] BATTAGLIA P W, HAMRICK J B, BAPST V, et al. Relational inductive biases, deep learning, and graph networks [EB/OL].
arXiv: 1806.01261. (2018-10-17)[2024-01-17]. http://arxiv.org/abs/1806.01261. DOI: 10.48550/arXiv.1806.01261.
[26] SCARSELLI F, GORI M, TSOI A C, et al. The graph neural network model [J]. IEEE Transactions on Neural Networks,
2009, 20(1): 61–80. DOI: 10.1109/TNN.2008.2005605.
[27] GILMER J, SCHOENHOLZ S S, RILEY P F, et al. Neural message passing for quantum chemistry [C]//Proceedings of the
34th International Conference on Machine Learning. Sydney: PMLR, 2017: 1263–1272.
[28] PFAFF T, FORTUNATO M, SANCHEZ-GONZALEZ A, et al. Learning mesh-based simulation with graph networks [C]//9th
International Conference on Learning Representations. ICLR, 2021.
[29] LI Q L, WANG Y, CHEN W S, et al. Machine learning prediction of BLEVE loading with graph neural networks [J].
Reliability Engineering & System Safety, 2024, 241: 109639. DOI: 10.1016/j.ress.2023.109639.
[30] SHI J H, LI J J, TAM W C, et al. Physics_GNN: towards physics-informed graph neural network for the real-time simulation

051431-19