Cause analysis of ship collision accident based on Bayesian network

Abstract

With the development of society, international trade is playing an important role. Maritime transport has become the main mode of transport in international trade with its advantages of low transport price, large transport volume and low environmental pollution. However, the rapid development of maritime transport is accompanied by the risk of maritime accidents. Studies show that ship collision accident has always been the main type of maritime accidents, and ship collision caused by human factors accounts for more than 90% of the total accidents. It has become a key issue in the research field of ship navigation safety to analyze the causes of ship collision and explore the mechanism of human factors. By analyzing the ship collision accident reports, this paper summarizing the main human factors of ship collision, and through analyzing the causal chain of ship collision accident to determine the Bayesian network structure. Finally, this paper using the accident reports into the model to illustrate the effectiveness of the Bayesian network model; meanwhile, by analyzing the cause of the Bayesian network model, this paper gets most likely cause chain that cause collision accident happens, so as to providing safety management countermeasures for the crew, ship company and ship safety management department.