Search

• Develop a new estimation model to predict the duration of detention in inspections. • Propose a novel machine learning-based methodology to train Bayesian network. • Identify the key variables of having a significant effect on duration of detention. • Raise the implications for different stakeholders to improve vessel quality. Port state control (PSC) inspections are deemed as an effective way to detect substandard vessels and ensure maritime safety around the world. Despite great efforts on PSC in recent years, one challenge that still exists in today's PSC inspection practice is that there lack relevant scheme or academic research focusing on the duration of vessel detention, which is of great importance to the inspection system. To assist port authorities in estimating detention duration and minimizing the existence of substandard vessels, this paper aims to develop a novel data-driven machine learning based model based on the inspection records collected within the jurisdiction of Paris MoU from January 2015 to March 2022. The model is trained via the incorporation of an Improved Tree Augmented Naïve (ITAN) learning approach and a maximum a posteriori probability (MAP) of Expectation Maximization (EM) approach for the first time within the context of PSC research, which could be used as a prediction tool to determine rational durations for detained vessels. Thorough analysis of the proposed model enables the identification of risk variables and deficiency types having significant effects leading to long duration of detention. Further, the research findings could reveal managerial suggestions and insights for port authorities to reduce the occurrence of substandard vessels via the inspection system, i.e., identify specific risk level of vessels and ensure a more-efficient vessel selection process; design specific instructions and rules to regulate risk variables and deficiencies with huge effect on a long duration of detention. This research will provide insightful reference for effectively improving vessel quality, inspection efficiency, and maritime safety. [ABSTRACT FROM AUTHOR]

• A tool is developed to aid the selection of PSC detention risk control strategies. • BNs and TOPSIS are incorporated as a new methodology for decision-making. • Detention risk control strategies are quantitatively measured in a dynamic manner. • Useful insights are provided to reduce possible ship detention risk in PSC. Port State Control (PSC) inspections have been implemented as an administrative measure to detect and detain substandard ships and thus to ensure maritime safety. Advanced risk models were developed to investigate the impact of factors influencing ship detention. Although showing much attractiveness, current studies still reveal a key challenge on how such analysis can improve the ship performance in PSC inspections and aid PSC detention risk control decision. By incorporating a data-driven Bayesian network (BN) into the Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) method, this paper proposes a new ship detention risk control methodology, in which the decision criteria are generated from the root risk variables, and the alternatives refer to the established strategies adopted by ship-owners in their practical ship detention risk control. Along with the new methodology, the main technical novelty of this paper lies in the quantitative measurement of the effectiveness of each strategy in terms of the reduction of detention rate in a dynamic manner. Its practical contributions are seen, from both ship owner and port authority perspectives, through the provisions of useful insights on dynamic evaluation of rational control strategies to reduce ship detention risk under various PSC inspection scenarios. [ABSTRACT FROM AUTHOR]

• A data-driven machine learning based BN model is developed to improve the inspection efficiency in PSC inspections. • New risk variables influencing the duration of ship detention are identified and the major deficiency types in different port states are revealed. • The influence of different deficiency types on the duration of detention is analyzed to generate managerial insights for safety management of port authorities. Port State Control (PSC) inspections are essential for port authorities to improve vessel quality and ensure maritime safety worldwide. However, the increasing frequency and duration of ship detentions indicate serious deficiencies of visiting vessels still largely exist, highlighting the urgent need for scientific solutions. This research aims to improve the efficiency of inspection policy and reduce the duration of detention by developing a data-driven Bayesian Network (BN) model using an improved machine-learning (ML) based methodology. New risk variables influencing the duration of ship detention, especially deficiency types, are identified based on the established database containing detention records within the jurisdiction of the Paris MoU from January 2015 to March 2022. Thorough analysis using the developed model allows the identification of deficiency types with a significant impact on the duration of detention, the discovery of interdependencies between these types and the clarification of the major and abnormal deficiency types in different port states. Policy implications and managerial recommendations for port authorities are presented. These include developing clear instructions on types of deficiencies that significantly impact detention time and proposing a selection strategy for vessels in different countries based on their specific circumstances. The proposed model utilizes big data analytics to support the development of inspection policies that are rational and effective. This research will provide good reference for effectively reducing the duration of ship detention, providing policy recommendations, improving ship standards, and ensuring maritime safety. [ABSTRACT FROM AUTHOR]

• New data training method is applied to improve BN in detention risk analysis in PSC. • Interrelationships among major factors in SRP systems are revealed comprehensively. • Insightful policy implications are proposed for both different stakeholders. • The rules of PSC inspection system are improved based on the obtained findings. Given to the increasing traffic volume in ports in recent years, ship selection and inspection procedure in the port state control (PSC) should be improved to reduce any unnecessary delay caused by the inefficient inspections. This study aims to newly use a data training technique and the newest PSC data to improve the usage of Bayesian Network (BN) to assess detention risk to a point where risk factors are identified, interrelationships among the factors are analysed and prior probability training based on big data is obtained more easily. To construct the BN model, a Bayesian theorem-based machine learning approach is adopted to ensure the obtained model is objective and reliable. The model is developed based on 1880 inspection records in the Paris Memorandum of Understanding (MoU) regime between 1st January 2017 and 31st March 2020. The obtained model not only present the probability distribution of each factor but also explore interrelationships among them. Compared to the Ship Risk Profiles (SRP) model, the used data-driven structure learning algorithm is more convenient and useful. The analysis results provide insights for ship owners to manage ship detention risk while support port authorities to prioritize the ship checklist and utilise more efficient ship inspection. [ABSTRACT FROM AUTHOR]