Marine accident learning with fuzzy cognitive maps (MALFCMs) and Bayesian networks

Abstract

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. Keywords Maritime accidents. Maritime safety. Maritime accident learning with fuzzy cognitive maps (MALFCMs). Human factors. Bayesian networks (BNs)

Marine accident learning with Fuzzy Cognitive Maps: a method to model and weight human-related contributing factors into maritime accidents

“…In de Maya et al (2019), historical data for maritime accidents involving UK vessels worldwide and all vessels operating in UK territorial waters between 2011 and 2016 was obtained and analyzed. Thus, general cargo vessels were selected due to the higher number of data entries when compared with other vessel categories, and nine HFs were identified as highly contributing into maritime accidents, as shown in Table 1.…”

“…For the purpose of this case study, marine accidents involving UK vessels worldwide and all vessels operating in UK territorial waters between 2011 and 2016 were analyzed. In addition, grounding/stranding accidents in general cargo vessels were selected for this study due to the higher number of data entries when compared with other accidents and vessel categories, as highlighted in de Maya, Babaleye, and Kurt (2019).…”

“…The MALFCM method developed by the authors has been already introduced in a previous paper (de Maya et al, 2019). The method has been applied and tested for different case studies to finalize the methodology for the historical data analysis stage (de Maya et al Thus, this paper is making a significant advancement by reporting the complete MALFCM framework which now includes the expert opinion stage, demonstrates results from a completed case study for the first time and conducts a sensitivity analysis to compare results against results obtained from solely from historical data analysis stage (de Maya et al, 2019). Results of sensitivity analysis are used to decide on the appropriateness of applying different coefficients to FCMs obtained from historical data and expert data stages, in order to reach a mixed weight.…”

“…Azadeh et al, 2014). Hence, in order to combine the finding from the historical data analysis stage obtained by de Maya et al (2019) and the expert opinion stage developed on this study, a sensitivity analysis is performed in this section. Table 13 includes the weights of each HF normalized from both, the historical data analysis stage and the expert opinion stage, and the final weights proposed, in which the same importance has been assigned to both sources of data.…”

Maritime accident prevention strategy formulation from a human factor perspective using Bayesian Networks and TOPSIS

“…Through the review of 41 accident investigation reports, Schroder-Hinrichs et al (2011) found that organisational factors were not identified by maritime accident investigators to the extent which the IMO guidelines expected. In addition, Fuzzy Cognitive Map (FCM)-based technique (de Maya et al 2019) was applied to generating weight the importance of human factors as prior failure probabilities, which helped create the BN model. The accident scenario analysis showed that the lack of safety culture contributed the most to the system failure.…”