Data-driven Bayesian Network model for detecting fire safety non-conformities in detained ships under port state controls

Kamal B., Sevgili C.

OCEAN ENGINEERING, cilt.340, sa.1, ss.1-13, 2025 (SCI-Expanded)

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 340 Sayı: 1
  • Basım Tarihi: 2025
  • Doi Numarası: 10.1016/j.oceaneng.2025.122249
  • Dergi Adı: OCEAN ENGINEERING
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, PASCAL, Aerospace Database, Applied Science & Technology Source, Aquatic Science & Fisheries Abstracts (ASFA), Communication Abstracts, Compendex, Computer & Applied Sciences, Environment Index, ICONDA Bibliographic, INSPEC, Metadex, Civil Engineering Abstracts
  • Sayfa Sayıları: ss.1-13
  • Dokuz Eylül Üniversitesi Adresli: Evet

Özet

A shipboard fire can have a catastrophic impact on the marine environments in addition to posing a risk to the ship and its crew. In preventing fire occurrence on board ships, it is crucial to investigate the influential factors that lead to fire safety deficiency code-related detention of ships since fire safety deficiency code appear as the most frequent detention in ship inspections. For this purpose, this paper discloses and assesses the correlation of various influential factors and deficiency types and their impact on detention incidence that stems from fire safety deficiency under the port state controls. In this respect, this paper develops a data-driven Bayes network model approach utilizing 4541 PSC reports of Tokyo Mou performed between 2017 and 2023. Thus, one of the most widely used and high-performance data-driven Bayesian Network algorithms, Tree Augmented Naive Bayes (TAN) is employed. Findings of the research indicate that Singapore and Hong Kong as port states have the highest impact on the explanation of detention caused by fire safety deficiency. The outcomes of the paper may provide port authorities, ship operating firms, and other industry stakeholders an effective scheme in establishing priorities and developing policies for mitigating the risk of detention.