Predicting congestions in a ship fire evacuation: A dynamic bayesian networks simulation

Abstract

In this paper, some new simulation results achieved from our proposed simulation model for analyzing congestions in ship evacuation are presented. To guarantee a safe evacuation, this model considers the most important real-life factors including, but not limited to, the passengers’ panic, the age and sex of the passengers, the structure of the ship, and so on. The qualitative factors have been quantized in order to compute the probability of congestion during the entire evacuation. We then utilize the dynamic Bayesian network (DBN) to predict congestion and to handle the non-stationarity of the scenario with respect to the time. Considering the most important scenarios and running the simulation, we demonstrate the distinct effects of these factors on congestion. The role of decision supports (DS), i.e. smartphone evacuation applications and rescue team presence on congestion is also studied. In addition, the impact of congested escape routes on the evacuation time is also investigated. The presented model and results of this paper are possible decision support tools for maritime organizations, emergency management sectors, and rescuers onboard the ships, which try to alleviate the human or property losses.