Probabilistic approach for characterising the static risk of ships using Bayesian networks

• Published in: Reliability engineering & system safety Vol. 203; p. 107073
• Main Authors: Dinis, D., Teixeira, A.P., Guedes Soares, C.
• Format: Journal Article
• Language: English
• Published: Barking Elsevier Ltd 01.11.2020; Elsevier BV
• Subjects: Automatic identification system data; Bayesian analysis; Bayesian networks; Inspection; Reliability engineering; Risk analysis; Risk assessment; Risk factors; Risk management; Sensitivity analysis; Ship risk profile; Ships; Static risk factors; Static risk factors; Bayesian networks; Automatic identification system data; Ship risk profile
• DOI: 10.1016/j.ress.2020.107073
• ISSN: 0951-8320

•Static risk modelling of individual ships based on Bayesian networks.•Ship Risk Profile parameters of Port State Control inspection used as risk variables.•Characterization of static risk profile of the maritime traffic.•Static risk profile of individual ships under incomplete information. This paper proposes a probabilistic approach for characterising the static risk of individual ships based on Bayesian networks (BNs). The approach uses the Ship Risk Profile parameters of the New Inspection Regime of the Paris Memorandum of Understanding (MoU) on Port State Control (PSC), not as risk factors for ship selection in PSC inspections, but as risk variables for ship risk assessment and maritime traffic monitoring. The objectives of the proposed approach are threefold: the characterisation of the static risk profile of the maritime traffic crossing a given geographic area; the identification of the most likely circumstances under which a specific static risk profile is expected to occur; and the characterisation of the static risk profile of individual ships in the presence of incomplete information, such as that obtained from the Automatic Identification System. A dataset collected from the Paris MoU platform is used for the development of the BN model and its validity is assessed. A quantitative assessment for the predictive validity of the model is also conducted by a sensitivity analysis that shows the consistency of the model with the Ship Risk Profile criteria and with the results of other studies developed also from historical PSC inspection data.