The Turkish Straits System (TSS) is one of the world’s busiest maritime corridors, facing congestion challenges due to larger ships, increased transit demand, and regulatory constraints. To address these issues, the Canal Istanbul Project (CIP) has been proposed as an alternative route to improve traffic efficiency and navigational safety. This study develops a maritime traffic system and queuing model based on the Vessel Traffic Flow Problem (VTFP) framework to evaluate the potential impact of CIP on TSS ship traffic. Two traffic models, namely one-way and two-way transit configurations, are simulated using Simio software, integrating historical AIS data and traffic constraints. Scenario analyses indicate that redirecting 90 % of transit ships to Canal Istanbul and 10 % to the Istanbul Strait results in a 36 % reduction in ship density and a 50 % decrease in waiting times. These findings demonstrate that Canal Istanbul has the potential to enhance efficiency and safety in the TSS, offering a data-driven basis for optimizing ship traffic flow in constrained waterways.

As the development of intelligent ships rapidly progresses, the importance of maritime network security escalates. Intrusion Detection Systems (IDS) serve as a pivotal defense mechanism against cyberattacks targeting these vessels. To augment the efficacy of IDS in detecting anomalous network traffic, this paper introduces a novel intrusion detection method utilizing both Transformer and Kolmogorov-Arnold Networks (KAN), designated as Transformer-KAN. This approach effectively mitigates the limitations of traditional intrusion detection algorithms, which include inadequate feature extraction capabilities and the excessive parameterization required to delineate complex patterns. The proposed method employs a Transformer encoder to discern long-range dependencies within input sequences, while KAN layers enhance the model’s ability to approximate complex patterns through non-linear transformations. This integrative strategy ensures elevated accuracy for the intrusion detection algorithm and proves particularly beneficial in intelligent ship environments, where training data may be sparse or computational resources limited. Experimental results confirm that the Transformer-KAN model attains exceptionally high accuracy in both binary and five-class classification tasks, outperforming the capabilities of standalone Transformer and KAN models. Comparative analyses with conventional algorithms—such as Convolutional Neural Networks (CNN), Gated Recurrent Units (GRU), Deep Belief Networks (DBN), and Support Vector Machines (SVM)-further substantiate the superior effectiveness of the proposed method. This research establishes a new theoretical framework and provides a direction for the practical implementation of network security measures in contemporary intelligent ships.

In this study, a floating offshore wind turbine with a foundation constructed from steel–UHPC (ultrahigh performance concrete) is investigated. The structural design and strength performance of the floating foundation are evaluated through a combination of numerical simulation and wave tank experiments. Load assessment and feasibility analyses, which reveal that the proposed steel–UHPC foundation satisfies structural safety requirements while exhibiting significant potential for material cost reduction, are conducted. With respect to the numerical simulation, a coupling of computational fluid dynamics (CFD) and finite element analysis (FEA) solvers is employed to address the fluid–structure interaction (FSI) problem. External hydrodynamic pressure obtained from the CFD solver is used to derive the structural response in the FEA solver. Given that the deformation of the steel–UHPC structure has a negligible effect on the surrounding flow field, one-way CFD–FEA coupling, in which fluid loads are transferred to the structural model without feedback of structural deformation to the fluid solver, is used. Wave tank experiments are conducted to validate the accuracy and reliability of the proposed one-way coupling methodology. Furthermore, an equivalent constitutive model for steel–UHPC is implemented within the FEA solver. The corresponding physical and mechanical properties are derived, and key structural design parameters of the floating foundation are determined accordingly.

Collaborative optimization with relaxation factor is proposed for the lines design of an underwater vehicle. The hydrodynamic performances and energy consumption are considered in optimization framework. Hydrodynamic performances include the resistance, sway force and yaw moment. The efficient power of the propeller is selected to reflect the energy consumption. Analytic hierarchy process (AHP) combined with Delphi method is used to allocate the weights of disciplines in the objective function at the top level. A gradient-based algorithm, sequential quadratic programming (SQP) in combination with an intelligent-based algorithm, the multi-island genetic algorithm (MIGA) is taken into account as the optimization algorithm. To increase the efficiency of optimization, an approximate model based on optimal Latin hypercube and radial basis function (RBF) is introduced to replace the time-consuming discipline analysis model. Full-appendage SUBOFF model is used to test the proposed optimization scheme. The optimization results show that the drag of the underwater vehicle is reduced by 2.05 %, the lateral force by 6.38 %, the yaw moment by 5.90 %, and the energy consumption by 2.15 %. Compared with a single algorithm (e.g., PSO), the proposed hybrid algorithm (MIGA-SQP) reduces the value of the comprehensive objective function by 2.5-4.8 %.The innovations of this paper are as follows: 1. The Delphi-AHP method is combined with the cooperative optimization of relaxation factors to improve the objectivity of weights; 2. An OLH-RBF surrogate model is constructed, which increases the CFD calculation efficiency by 4 times.

LiDAR, a crucial sensor for Unmanned Surface Vehicles (USVs), allows for precise 3D modelling but encounters challenges in real-time target detection due to sparse point clouds. Current 3D point cloud detectors struggle to effectively capture fine-grained details and dynamic water surface features, while high-performance models often rely on custom operators, making deployment more complicated. Additionally, current water surface datasets lack the resolution necessary for small target detection. To tackle these issues, this study enhances the PointPillars model with the Voxel-Guided Label Assignment (VGLA) strategy, improving feature extraction through adaptive label assignment. A high-resolution point cloud dataset focused on small aquatic objects has also been developed based on 128-beam LiDAR. The proposed PointPillars-VGLA achieves 3D AP scores of 89.50%, 83.70%, and 75.20%, as well as BEV AP scores of 95.20%, 91.00%, and 86.70% across three target categories. Ablation experiments confirm the effectiveness of the VGLA module, with accuracy gains of up to 2.27% over CenterPoint. Deployed on the Jetson AGX Orin with TensorRT, the model achieves real-time inference at 30 FPS, enabling efficient detection and tracking in dynamic aquatic environments.

The towing system is one of the most crucial parts of a tug boat. The towing process in tugboats, where a lot of machines and ship equipment are involved in the process, carries many risks and potential failures. Therefore, this operation can cause serious injuries, fatal accidents, equipment damage, disruption of towing operations and loss of time and money. In this study, a comprehensive risk analysis was conducted to increase the reliability of the tugboat towing system. Firstly, the failure modes, causes and results of the towing system were determined. Then, the failure modes and effect analysis method were integrated with the rule-based fuzzy approach and risk prioritization was performed. According to the findings, the three critical failure modes among 23 failure modes were towing system rope failure, insufficient air supply to the towing system from the compressor and cracking or breaking of system components, respectively. Additionally, corrective and preventive actions were suggested for a total of eleven failure modes with high RPN values. This study aims not only to provide a theoretical contribution to the prevention of towing system-related accidents, but also to provide a practical framework that can be used in practice for all maritime stakeholders, especially tugboat owners and crews.

In this paper, the scale effects on a container ship’s roll motion are investigated by numerical approach. The accuracy of the numerical method is verified by comparing numerical results with experimental data through a grid sensitivity study. The roll decay tests of the vessel at full-scale and model-scale at various forward speeds are simulated, and it is noticed that scale effects on roll motion occur when forward speed is nil or low. To further understand the impacts of scale on damping components, forced roll tests with different forward speeds are simulated, roll damping coefficients are determined, the flow field created by roll motion and forward speed near bilge keels is observed. It is found that the scale effects affect both the frictional and bilge keel damping components. At low Froude number, the difference of the relative velocity distributions for the height (or breadth) of bilge keels between model (model-scale) and ship (full-scale) is proved as the cause of the scale effects on the bilge keel component.

Anchorage areas are essential for safe and efficient maritime operations. However, conventional forecasting models often underperform in dynamic port conditions, as they rely heavily on historical averages and static assumptions. To address these limitations, this study proposes a forecasting framework for anchorage occupancy. This framework uses stacked ensemble learning, integrating both statistical and machine learning models to enhance predictive accuracy and operational reliability. The proposed approach was applied to occupancy data from the E1 anchorage at Ulsan Port, with performance evaluated across various forecasting models and ensemble strategies. In addition, a hexagon-based occupancy estimation method was implemented to assess spatial efficiency and safety in comparison to the traditional anchor circle method. The results demonstrate that the stacking ensemble model effectively captures complex, nonlinear patterns in vessel traffic and delivers improved forecasting performance. These findings highlight the practical potential of stacking ensemble techniques and spatial modeling innovations in enabling proactive anchorage management, reducing congestion, and enhancing maritime safety in real-world port environments.

This study uses a CFD approach to perform numerical simulations of the hydrodynamic interactions between LNG ship motions induced by waves and the sloshing behavior of cargo tanks. First, a CFD simulation is performed by solving the RANS equations to analyze the sloshing behavior of liquid in a three-dimensional rectangular tank subjected to forced simple harmonic motion. The accuracy of the RANS solver in addressing the sloshing problem is validated through comparisons with experimental data and other numerical methods. Next, the study considers the coupling effects of both the internal sloshing flow field and the external wave field on the motion of a simplified LNG vessel. The motion response of the LNG carrier in regular waves was simulated, and the sloshing impact pressure on the bulkheads under various conditions was analyzed. The simulation results of the LNG ship’s hydrodynamic behavior were compared with experimental and numerical data from previous studies. The effect of liquid tank sloshing on ship motion and tank wall pressure was examined under both head and beam wave conditions. Additionally, different forward speeds under head wave conditions were considered. It is crucial to account for the coupled effects of tank sloshing and ship dynamics when designing and evaluating liquid cargo ships.

The maritime sector, while recognized as the most efficient mode of freight transportation, confronts significant challenges in reducing greenhouse gas emissions and enhancing energy efficiency. These challenges are intensified by the ageing fleet of merchant ships, which often lack the latest technologies intended to minimize atmospheric pollution. This paper aims to introduce an innovative tool designed to evaluate the energy efficiency of merchant ships and monitor their emissions, particularly concerning CO2 and its relation with the Carbon Intensity Indicator. The tool consolidates essential data into a centralized database to facilitate continuous monitoring of ship efficiency, taking into account both internal and external factors. In particular, it enables the collection and analysis of data for small/medium shipping companies, which typically lack the resources to allocate towards complex, tailored IT solutions for managing their fleet. Key features for this tool include the availability of accurate operational data and adherence to current emissions regulations. However, the applicability of the tool may be constrained by variations in ship types, operational conditions, and the availability of real-time data. The application of the tool to a case study of a tanker ship, designed to validate its functionality, demonstrates that the tool can effectively generate extensive data, which can be used to identify correlations between specific ship factors and GHG emissions. These findings offer a more accessible and self-explanatory approach to evaluating ship performance and efficiency, presenting a practical framework for compliance with evolving climate regulations and identifying the technical solutions to be implemented onboard for improvement.