Addressing safety is considered a priority starting from the design stage of any vessel until end-of-life. However, despite all safety measures developed, accidents are still occurring. This is a consequence of the complex nature of shipping accidents where too many factors are involved including human factors. Therefore, there is a need for a practical method, which can identify the importance weightings for each contributing factor involved in accidents. As a result, by identifying the importance weightings for each factor, risk assessments can be informed, and risk control options can be developed and implemented more effectively. To this end, Marine Accident Learning with Fuzzy Cognitive Maps (MALFCM) approach incorporated with Bayesian networks (BNs) is suggested and applied in this study. The MALFCM approach is based on the concept and principles of fuzzy cognitive maps (FCMs) to represent the interrelations amongst accident contributor factors. Thus, MALFCM allows identifying the importance weightings for each factor involved in an accident, which can serve as prior failure probabilities within BNs. Hence, in this study, a specific accident will be investigated with the proposed MALFCM approach.

Maritime accidents are complex processes in which many factors are involved and contribute to accident development. In order to capture underlying factors in accidents, countries adapted an accident investigation system with the aim of learning from these rare events and prevent similar occurrences in the future. Often these accident investigation reports are converted into databases, which lack a concise and user-friendly classification system, as a result, there are a lot of inadequacies in data-collection and tagging procedures. Therefore, the authors propose to apply an approach to classify human factors (HFs) appeared in past maritime accidents, aiming to develop a set of HF categories which can be used for accidents learning. For this purpose, an accident database was obtained and a two-stage approach was adapted to conduct analysis: first, an open card-sorting case study is organised to group the HFs extracted from an historical accident database. Second, a hybrid card-sorting method was utilized to fully achieve the classification of HFs. Our study revealed issues where HFs are weakly defined and similar factors are duplicated by investigators who populate the database. High-level categories were developed and presented which covers the great majority of HF concerns involved in accidents.