Bayesian methods in domino effect analysis

Abstract

High complexity and growing interdependencies of chemical and process facilities have made them increasingly vulnerable to domino effects. Domino effects are spatial-temporal processes where not only the location of involved units but also their temporal entailment in the accident chain matter. Spatial-temporal dependencies and uncertainties prevailing during domino effects, arising mainly from possible synergistic effects and randomness of potential events, restrict the use of conventional risk assessment techniques such as fault tree and event trees. Bayesian networks—including both conventional and dynamic Bayesian networks and limited memory influence diagrams—have proved as a reliable and robust technique for modeling and risk assessment of domino effects. This chapter exemplifies some applications of Bayesian networks to modeling and safety assessment and management of domino effects, with an emphasis on fire domino effects and optimal firefighting.