TY - JOUR
T1 - Physics_GNN
T2 - Towards Physics-informed graph neural network for the real-time simulation of obstructed gas explosion
AU - Shi, Jihao
AU - Li, Junjie
AU - Tam, Wai Cheong
AU - Gardoni, Paolo
AU - Usmani, Asif Sohail
N1 - Publisher Copyright:
© 2024
PY - 2025/4
Y1 - 2025/4
N2 - 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.
AB - 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.
KW - Gas explosion
KW - Graph neural network
KW - Real-time simulation
KW - Risk assessment and management
UR - http://www.scopus.com/inward/record.url?scp=85213543984&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85213543984&partnerID=8YFLogxK
U2 - 10.1016/j.ress.2024.110777
DO - 10.1016/j.ress.2024.110777
M3 - Article
AN - SCOPUS:85213543984
SN - 0951-8320
VL - 256
JO - Reliability Engineering and System Safety
JF - Reliability Engineering and System Safety
M1 - 110777
ER -