Page 105 - 《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

of obstructed gas explosion [J]. Reliability Engineering & System Safety, 2025, 256: 110777. DOI: 10.1016/j.ress.2024.
110777.
[31] SANCHEZ-GONZALEZ A, GODWIN J, PFAFF T, et al. Learning to simulate complex physics with graph networks [C]//
Proceedings of the 37th International Conference on Machine Learning. PMLR, 2020: 8459–8468.
[32] LI B B, FENG B, CHEN L. A graph network-based learnable simulator for spatial-temporal prediction of rigid projectile
penetration [J]. International Journal of Impact Engineering, 2025, 195: 105123. DOI: 10.1016/j.ijimpeng.2024.105123.
[33] GEXCON. FLACS-CFD v25.2 user’s manual [EB/OL]. 2025. https://www.gexcon.com/support/flacs-documents/.
[34] MA J Q, ZHAO Z, YI X Y, et al. Modeling task relationships in multi-task learning with multi-gate mixture-of-experts [C]//
Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. London: ACM,
2018: 1930–1939. DOI: 10.1145/3219819.3220007.
[35] LI Q L, LI L, SHAO Y D, et al. A multi-task machine learning approach for data efficient prediction of blast loading [J].
Engineering Structures, 2025, 326: 119577. DOI: 10.1016/j.engstruct.2024.119577.
[36] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition [C]//2016 IEEE Conference on
Computer Vision and Pattern Recognition (CVPR). Las Vegas: IEEE, 2016: 770–778. DOI: 10.1109/CVPR.2016.90.
[37] MICHAUD E J, LIU Z M, TEGMARK M. Precision machine learning [J]. Entropy, 2023, 25(1): 175. DOI: 10.3390/
e25010175.
[38] WANG Y J, LAI C Y. Multi-stage neural networks: function approximator of machine precision [J]. Journal of Computational
Physics, 2024, 504: 112865. DOI: 10.1016/j.jcp.2024.112865.
[39] YUE C J, CHEN L, LI Z, et al. Experimental study on gas explosions of methane-air mixtures in a full-scale residence
building [J]. Fuel, 2023, 353: 129166. DOI: 10.1016/j.fuel.2023.129166.
[40] KANG Y, MA S Y, SONG B X, et al. Study on the hydrogen leakage diffusion behavior by obstacles in confined spaces [J].
Fuel, 2024, 358: 130110. DOI: 10.1016/j.fuel.2023.130110.
[41] 国家安全生产监督管理总局. 化工企业定量风险评价导则: AQ/T 3046—2013 [S]. 北京: 煤炭工业出版社, 2013.
[42] 国家市场监督管理总局, 国家标准化管理委员会. 家用燃气灶具: GB 16410—2020 [S]. 北京: 中国标准出版社, 2020.
[43] 贾烁宇. 室内燃气泄漏扩散规律及预警机制研究 [D]. 青岛: 中国石油大学 (华东), 2022.
JIA S Y. Study on the law and early warning mechanism of indoor gas leakage and diffusion [D]. Qingdao: China University
of Petroleum (East China), 2022.
[44] 中华人民共和国建设部和国家质量监督检验检疫总局. 城镇燃气设计规范: GB 50028—2006 [S]. 北京: 中国建筑工业出
版社, 2020.
[45] 中华人民共和国化学工业部. 家用煤气软管: HG 2486—1993 [S]. 北京: 中国标准出版社, 1993.
[46] YUE C J, CHEN L, LI Z, et al. Research on the hazards of gas leakage and explosion in a full-scale residential building [J].
Defence Technology, 2025, 43: 168–181. DOI: 10.1016/j.dt.2024.06.014.
[47] HUANG L, QIN J, ZHOU Y, et al. Normalization techniques in training DNNs: methodology, analysis and application [J].
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(8): 10173–10196. DOI: 10.1109/TPAMI.2023.
3250241.
[48] BA J L, KIROS J R, HINTON G E. Layer normalization [EB/OL]. arXiv: 1607.06450. (2016-07-21)[2024-10-11]. http://
arxiv.org/abs/1607.06450. DOI: 10.48550/arXiv.1607.06450.
[49] KINGMA D P, BA J. Adam: a method for stochastic optimization [C]//3rd International Conference on Learning
Representations. San Diego: ICLR, 2015.
[50] LINO M, CANTWELL C, BHARATH A A, et al. Simulating continuum mechanics with multi-scale graph neural networks
[EB/OL]. [2021-06-09]. http://arxiv.org/abs/2106.04900. DOI: 10.48550/arXiv.2106.04900.
[51] HAN X, GAO H, PFAFF T, et al. Predicting physics in mesh-reduced space with temporal attention [C]//The Tenth
International Conference on Learning Representations. ICLR, 2022.
(责任编辑 曾月蓉)

051431-20