IDEAS home Printed from https://ideas.repec.org/a/eee/reensy/v256y2025ics0951832024008482.html
   My bibliography  Save this article

Physics_GNN: Towards Physics-informed graph neural network for the real-time simulation of obstructed gas explosion

Author

Listed:
  • Shi, Jihao
  • Li, Junjie
  • Tam, Wai Cheong
  • Gardoni, Paolo
  • Usmani, Asif Sohail

Abstract

Explosion risk assessment (ERA) is essential for ensuring effective process safety and reliability management. Deep learning has been used to reduce the computational burden of computational fluid dynamics (CFD)-based ERA, but its 'black-box' nature without considering relevant physics can lead to inaccuracies, especially in complex, obstructed scenarios. This paper develops a Physics-informed graph neural network approach, i.e., Physics_GNN for real-time obstructed gas explosion simulation. An autoregressive GNN, namely GNN_f is first applied to iteratively predict the spatiotemporal flame evolution. An ordinary differential equation (ODE) governing the interaction mechanism between the flame and blast wave propagation is used to predict the blast dynamics with the GNN_f. A physical enhancement factor β is proposed to calibrate the overpressure dynamics prediction with congestions, which can be predicted by developing another GNN, namely GNN_β. The integration of GNN_f, GNN_β and ODE leads to the final Physics_GNN. A benchmark numerical dataset is constructed, using which Physics_GNN and the state-of-the-art are then compared. The comparison demonstrates the superior accuracy of the proposed approach in real-time blast load prediction in congested scenarios. The Physics_GNN approach also enables the description of the physical interactions between congestion, flame propagation, and blast load distribution. This paper provides an efficient and accurate approach to predict industrial explosion consequences, supporting robust ERA and risk-informed decision-makings about mitigation design of industrial facilities.

Suggested Citation

  • Shi, Jihao & Li, Junjie & Tam, Wai Cheong & Gardoni, Paolo & Usmani, Asif Sohail, 2025. "Physics_GNN: Towards Physics-informed graph neural network for the real-time simulation of obstructed gas explosion," Reliability Engineering and System Safety, Elsevier, vol. 256(C).
  • Handle: RePEc:eee:reensy:v:256:y:2025:i:c:s0951832024008482
    DOI: 10.1016/j.ress.2024.110777
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0951832024008482
    Download Restriction: Full text for ScienceDirect subscribers only

    File URL: https://libkey.io/10.1016/j.ress.2024.110777?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to

    for a different version of it.

    References listed on IDEAS

    as
    1. Necci, Amos & Cozzani, Valerio & Spadoni, Gigliola & Khan, Faisal, 2015. "Assessment of domino effect: State of the art and research Needs," Reliability Engineering and System Safety, Elsevier, vol. 143(C), pages 3-18.
    2. Meng, Huixing & Hu, Mengqian & Kong, Ziyan & Niu, Yiming & Liang, Jiali & Nie, Zhenyu & Xing, Jinduo, 2024. "Risk analysis of lithium-ion battery accidents based on physics-informed data-driven Bayesian networks," Reliability Engineering and System Safety, Elsevier, vol. 251(C).
    3. Li, Qilin & Wang, Yang & Chen, Wensu & Li, Ling & Hao, Hong, 2024. "Machine learning prediction of BLEVE loading with graph neural networks," Reliability Engineering and System Safety, Elsevier, vol. 241(C).
    4. Xie, Cheng & Huang, Liwen & Wang, Rui & Deng, Jian & Shu, Yaqing & Jiang, Dan, 2022. "Research on quantitative risk assessment of fuel leak of LNG-fuelled ship during lock transition process," Reliability Engineering and System Safety, Elsevier, vol. 221(C).
    5. Masum Jujuly, Muhammad & Rahman, Aziz & Ahmed, Salim & Khan, Faisal, 2015. "LNG pool fire simulation for domino effect analysis," Reliability Engineering and System Safety, Elsevier, vol. 143(C), pages 19-29.
    6. Bhardwaj, U. & Teixeira, A.P. & Guedes Soares, C. & Ariffin, A.K. & Singh, S.S., 2021. "Evidence based risk analysis of fire and explosion accident scenarios in FPSOs," Reliability Engineering and System Safety, Elsevier, vol. 215(C).
    7. Worrell, Clarence & Luangkesorn, Louis & Haight, Joel & Congedo, Thomas, 2019. "Machine learning of fire hazard model simulations for use in probabilistic safety assessments at nuclear power plants," Reliability Engineering and System Safety, Elsevier, vol. 183(C), pages 128-142.
    8. Amin, Md. Tanjin & Scarponi, Giordano Emrys & Cozzani, Valerio & Khan, Faisal, 2024. "Improved pool fire-initiated domino effect assessment in atmospheric tank farms using structural response," Reliability Engineering and System Safety, Elsevier, vol. 242(C).
    9. Xu, Yanwen & Kohtz, Sara & Boakye, Jessica & Gardoni, Paolo & Wang, Pingfeng, 2023. "Physics-informed machine learning for reliability and systems safety applications: State of the art and challenges," Reliability Engineering and System Safety, Elsevier, vol. 230(C).
    10. Li, Xiaofeng & Chen, Guohua & Amyotte, Paul & Khan, Faisal & Alauddin, Mohammad, 2023. "Vulnerability assessment of storage tanks exposed to simultaneous fire and explosion hazards," Reliability Engineering and System Safety, Elsevier, vol. 230(C).
    11. Chen, Chao & Khakzad, Nima & Reniers, Genserik, 2020. "Dynamic vulnerability assessment of process plants with respect to vapor cloud explosions," Reliability Engineering and System Safety, Elsevier, vol. 200(C).
    12. Yuan, Shuaiqi & Cai, Jitao & Reniers, Genserik & Yang, Ming & Chen, Chao & Wu, Jiansong, 2022. "Safety barrier performance assessment by integrating computational fluid dynamics and evacuation modeling for toxic gas leakage scenarios," Reliability Engineering and System Safety, Elsevier, vol. 226(C).
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Zeng, Tao & Wei, Lijun & Reniers, Genserik & Chen, Guohua, 2024. "A comprehensive study for probability prediction of domino effects considering synergistic effects," Reliability Engineering and System Safety, Elsevier, vol. 251(C).
    2. Celano, Francesca & Dolšek, Matjaž, 2021. "Fatality risk estimation for industrialized urban areas considering multi-hazard domino effects triggered by earthquakes," Reliability Engineering and System Safety, Elsevier, vol. 206(C).
    3. Ma, Weikai & Wang, Yanfu & Xing, Peijie & Yang, Ming, 2025. "A Monte Carlo-based modeling method for the spatial-temporal evolution process of multi-hazard and higher-order domino effect," Reliability Engineering and System Safety, Elsevier, vol. 253(C).
    4. Quinci, Gianluca & Paolacci, Fabrizio & Fragiadakis, Michalis & Bursi, Oreste S., 2025. "A machine learning framework for seismic risk assessment of industrial equipment," Reliability Engineering and System Safety, Elsevier, vol. 254(PB).
    5. Luan, Tianyi & Gai, Wenmei & Sun, Diange & Dong, Hao, 2025. "Emergency evacuation risk assessment for toxic gas attacks in airport terminals: Model, algorithm, and application," Reliability Engineering and System Safety, Elsevier, vol. 253(C).
    6. Amin, Md. Tanjin & Scarponi, Giordano Emrys & Cozzani, Valerio & Khan, Faisal, 2024. "Improved pool fire-initiated domino effect assessment in atmospheric tank farms using structural response," Reliability Engineering and System Safety, Elsevier, vol. 242(C).
    7. Landucci, Gabriele & Necci, Amos & Antonioni, Giacomo & Argenti, Francesca & Cozzani, Valerio, 2017. "Risk assessment of mitigated domino scenarios in process facilities," Reliability Engineering and System Safety, Elsevier, vol. 160(C), pages 37-53.
    8. Gholamizadeh, Kamran & Zarei, Esmaeil & Yazdi, Mohammad & Ramezanifar, Ehsan & Aliabadi, Mostafa Mirzaei, 2024. "A hybrid model for dynamic analysis of domino effects in chemical process industries," Reliability Engineering and System Safety, Elsevier, vol. 241(C).
    9. Ricci, Federica & Yang, Ming & Reniers, Genserik & Cozzani, Valerio, 2024. "Emergency response in cascading scenarios triggered by natural events," Reliability Engineering and System Safety, Elsevier, vol. 243(C).
    10. Lin, Qindong & Zhu, Xinguang & Gan, Yundan & Feng, Chun & Jiao, Wenjun, 2024. "Simulation-based personal fatality risk assessment due to the fragmentation hazard," Reliability Engineering and System Safety, Elsevier, vol. 251(C).
    11. Wang, Ning & Xu, Yan & Wang, Sutong, 2022. "Interpretable boosting tree ensemble method for multisource building fire loss prediction," Reliability Engineering and System Safety, Elsevier, vol. 225(C).
    12. Marroni, Giulia & Casini, Leonardo & Bartolucci, Andrea & Kuipers, Sanneke & Casson Moreno, Valeria & Landucci, Gabriele, 2024. "Development of fragility models for process equipment affected by physical security attacks," Reliability Engineering and System Safety, Elsevier, vol. 243(C).
    13. Shi, Zhiyi & Feng, Yuan & Egbelakin, Temitope & Yang, Chengwei & Gao, Wei, 2025. "Computational fluid dynamics -informed virtual safety assessment of steel-framed structure with fire-induced ductile failure," Reliability Engineering and System Safety, Elsevier, vol. 258(C).
    14. Chen, Chao & Reniers, Genserik & Khakzad, Nima, 2019. "Integrating safety and security resources to protect chemical industrial parks from man-made domino effects: A dynamic graph approach," Reliability Engineering and System Safety, Elsevier, vol. 191(C).
    15. Deng, Wanyi & Ma, Xiaoxue & Qiao, Weiliang, 2024. "A novel methodology to quantify the impact of safety barriers on maritime operational risk based on a probabilistic network," Reliability Engineering and System Safety, Elsevier, vol. 243(C).
    16. He, Zhichao & Shen, Kaixin & Lan, Meng & Weng, Wenguo, 2024. "The effects of dynamic multi-hazard risk assessment on evacuation strategies in chemical accidents," Reliability Engineering and System Safety, Elsevier, vol. 246(C).
    17. Li, Xiaofeng & Chen, Guohua & Amyotte, Paul & Khan, Faisal & Alauddin, Mohammad, 2023. "Vulnerability assessment of storage tanks exposed to simultaneous fire and explosion hazards," Reliability Engineering and System Safety, Elsevier, vol. 230(C).
    18. Cuesta, Jokin & Leturiondo, Urko & Vidal, Yolanda & Pozo, Francesc, 2025. "A review of prognostics and health management techniques in wind energy," Reliability Engineering and System Safety, Elsevier, vol. 260(C).
    19. Laobing Zhang & Gabriele Landucci & Genserik Reniers & Nima Khakzad & Jianfeng Zhou, 2018. "DAMS: A Model to Assess Domino Effects by Using Agent‐Based Modeling and Simulation," Risk Analysis, John Wiley & Sons, vol. 38(8), pages 1585-1600, August.
    20. Chen, Chao & Yang, Ming & Reniers, Genserik, 2021. "A dynamic stochastic methodology for quantifying HAZMAT storage resilience," Reliability Engineering and System Safety, Elsevier, vol. 215(C).

    More about this item

    Keywords

    ;
    ;
    ;
    ;

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:reensy:v:256:y:2025:i:c:s0951832024008482. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: https://www.journals.elsevier.com/reliability-engineering-and-system-safety .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.