Geometrical risk evaluation of the collisions between ships and offshore installations using rule-based Bayesian reasoning

Abstract

Increasing human installations and vessel traffic in offshore waters render a collision risk between ships and offshore installations (SOI). Past decades have witnessed many accidents occurred in the offshore waters involving complex traffic networks. To safeguard offshore installations and improve water-bound transport safety, this paper proposes a novel Bayesian-based model to assess the SOI collision risk involving passing ships. It first identifies the relevant risk factors with the aid of a geometrical analysis concerning SOI collisions. The causal relationships between the risk factors are numerically defined by causal rules with a degree of belief structure, while a Bayesian network (BN) is constructed to aggregate the evaluated value of each risk factor and to assess the collision risks involving different navigational environments. To illustrate the new model, a real case on SOI collision risk in the Liverpool Burbo Bank offshore wind farm is investigated. The results provide empirical evidence for SOI collision risk analysis under complex water conditions and uncertain navigational environments and hence useful insights on SOI collision avoidance.