Dynamic risk analysis of fire and explosion domino accidents at hydrogen refueling stations using Dynamic Bayesian Network

Hydrogen is a promising energy source and hydrogen refueling stations (HRS) are the main hydrogen supply infrastructures. Unwanted hydrogen leaks and releases at the hydrogen station may cause serious explosion accidents and even induce domino effects due to intensive hazardous equipment in the station. However, scant attention has been accorded to the dynamic risks of fire, explosion, and domino effects at HRS, posing a threat to the safe functioning of HRS and the advancement of the hydrogen energy. This study thus first develops Dynamic Bayesian networks to model the primary fire and explosion accidents as well as domino effects at HRS. By the developed models, the critical factors that lead to accidents and the critical equipment that contributes to the initiation or propagation of domino effects can be identified. Moreover, the failure probability of different equipment exposed to possible accidents can also be obtained, supporting safety management of HRS.