Abstract
To provide safe, secure, and environment-friendly maritime transport, it is an essential point to define and take appropriate countermeasures against the substandard ships in maritime transport. Port State Control (PSC) is one of the critical inspection regimes recognized worldwide to define substandard ships. However, one of the biggest challenge faced in ship inspection is the necessity of checking many items through limited time and qualified human resources. Therefore, in this study, it is aimed to develop a decision support system to increase the effectiveness of ship inspections. In accordance with this, we proposed an intelligent ship inspection analytics (I-SIA) model based on the Knowledge Discovery in Database (KDD) process by utilizing fuzzy c-means clustering and apriori algorithms. The I-SIA model provides the determination of ship deficiency patterns based on specific ship attributes, and subsequently predicts main/sub inspection items to be focused on through former inspection records of the ship to be inspected. In the case study performed for a selected ship, I-SIA predicts critical 5 main and 23 sub-inspection items that need to be checked with high priority, among 17 main inspection items and out of more than 500 sub-inspection items. Herewith, I-SIA provides a ship-specific and dynamic ship inspection based on deficiencies recorded in previous inspections and detected during inspection. Thus, it becomes possible to enhance the effectiveness of the inspection via defined deficiency patterns.
| Original language | English |
|---|---|
| Article number | 114232 |
| Journal | Ocean Engineering |
| Volume | 278 |
| DOIs | |
| Publication status | Published - 15 Jun 2023 |
Bibliographical note
Publisher Copyright:© 2023 Elsevier Ltd
Funding
Apart from the investigated relationships, several studies have been conducted to improve SRP calculation and predict the high-risk ship, accurately. Xu et al. (2007) proposed an improved ship risk assessment system based on support vector machines (SVM) by analyzing 8 ship generic and 26 ship historic factors obtained from Tokyo MoU web page crawling. The study revealed that new factors produced by deficiency records improve ship targeting systems. In order to develop risk assessment model proposed by Xu et al. (2007), Gao et al. (2008) proposed Bag of Words (BW) approaches to extract some new target factors and used combination of Support Vector Machine and K-nearest neighbor (KNN-SVM) to remove noisy training examples in the PSC inspection database. Also, Yang et al. (2018a) suggested a data-driven Bayesian network to study factors impacting PSC inspection, and then used the model to estimate bulk carrier detention rates. Followingly, Yang et al. (2018b) proposed model by integrating Bayesian network and game model between PSC port authorities and ship owners to offer an ideal PSC inspection system. Recently, Yan et al. (2021a) developed a classification model by using balanced random forest algorithms to predict ship detention and a fuzzy rule-based ship risk profile prediction model proposed by Demirci et al. (2022).
Keywords
- Apriori algorithm
- Data analytics
- Data mining
- Fuzzy clustering
- Inspection
- Maritime transport
- Port state control