Probabilistic analysis of natural gas pipeline network accident based on Bayesian network

Natural gas pipeline network (NGPN) accident is a kind of catastrophic disaster as the hazard of natural gas may present a large-scale extension in NGPN that can easily result in cascading accidents. In this paper, the Bayesian network (BN) was employed to probabilistically analyze natural gas pipeline network accidents. On the basis of case-studies of typical NGPN accidents, eleven BN nodes were proposed to represent the evolution process of natural gas pipeline network accidents from failure causes to consequences. The conditional probabilities of every BN node were determined by expert knowledge with weighted treatments by the Dempster-Shafer evidence theory. Through giving evidences of some BN nodes with certain state values, the probabilities of evolution stages and consequences of the natural gas pipeline network accident can be estimated. The results indicate that the combination of Bayesian network and Dempster-Shafer evidence theory is an alternative method for evaluating NGPN accident, and the proposed framework can provide a more realistic consequence analysis since it could consider the conditional dependency in the evolution process of the NGPN accident. This study could be helpful for emergency response decision-making and loss prevention.