A Bayesian network model for evacuation time analysis during a ship fire

We present an evacuation model for ships while a fire happens onboard. The model is designed by utilizing Bayesian networks (BN) and then simulated in GeNIe software. In our proposed model, the most important factors that have significant influence on a rescue process and evacuation time are identified and analyzed. By applying the probability distribution of the considered factors collected from the literature including IMO, real empirical data and practical experiences, the trend of the rescue process and evacuation time can be evaluated and predicted using the proposed model. The results of this paper help understanding about possible consequences of influential factors on the security of the ship and help to avoid exceeding evacuation time during a ship fire.

[1]  Jin-Hyoung Park,et al.  The current status and future issues in human evacuation from ships , 2003 .

[2]  Yan Lin,et al.  Computational Advantages of Relevance Reasoning in Bayesian Belief Networks , 1997, UAI.

[3]  Yu-hui Fu,et al.  Evacuation on Passenger Ship under Emergency Situation , 2011 .

[4]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[5]  Seungho Lee,et al.  Integrated human decision making model under Belief-Desire-Intention framework for crowd simulation , 2008, 2008 Winter Simulation Conference.

[6]  Huanxin Wang,et al.  Accident Causation Chain Analysis of Ship Collisions Based on Bayesian Networks , 2011 .

[7]  Nir Friedman,et al.  Probabilistic Graphical Models - Principles and Techniques , 2009 .

[8]  Wayne K. Talley.  The safety of ferries: an accident injury perspective , 2002 .

[9]  Jin-Hyoung Park,et al.  Establishing the methodologies for human evacuation simulation in marine accidents , 2004, Comput. Ind. Eng..

[10]  Yun Peng,et al.  A Bayesian network based framework for multi-criteria decision making , 2004 .

[11]  Michael Schreckenberg,et al.  Microscopic Simulation of Evacuation Processes on Passenger Ships , 2000, ACRI.

[12]  Dirk Helbing,et al.  How simple rules determine pedestrian behavior and crowd disasters , 2011, Proceedings of the National Academy of Sciences.

[13]  Dracos Vassalos,et al.  Fire safety onboard passenger ships , 2011 .

[14]  M. Misra,et al.  Early warning of ship fires using Bayesian probability estimation model , 2005, Proceedings of the 2005, American Control Conference, 2005..

[15]  Wentong Cai,et al.  Crowd modeling and simulation technologies , 2010, TOMC.

[16]  A. G. Eleye-Datubo,et al.  Enabling a Powerful Marine and Offshore Decision‐Support Solution Through Bayesian Network Technique , 2006, Risk analysis : an official publication of the Society for Risk Analysis.

[17]  Maria Hänninen,et al.  Influences of variables on ship collision probability in a Bayesian belief network model , 2012, Reliab. Eng. Syst. Saf..

[18]  Edwin R. Galea,et al.  Simulating ship evacuation under fire conditions , 2003 .

[19]  W. Dlamini.  Application of Bayesian networks for fire risk mapping using GIS and remote sensing data , 2011 .

[20]  Paolo Trucco,et al.  A Bayesian Belief Network modelling of organisational factors in risk analysis: A case study in maritime transportation , 2008, Reliab. Eng. Syst. Saf..

[21]  Yu-Chun Wang,et al.  Survey of pedestrian movement and development of a crowd dynamics model , 2008 .

[22]  M. Schreckenberg,et al.  Assessment and Analysis of Evacuation Processes on Passenger Ships by Microscopic Simulation , 2002 .

[23]  Peter Duchessi,et al.  A Bayesian Belief Network for IT implementation decision support , 2006, Decis. Support Syst..

[24]  David Maxwell Chickering,et al.  Learning Bayesian Networks: The Combination of Knowledge and Statistical Data , 1994, Machine Learning.