As the CII regulations took effect in 2023, shipping companies are under increasing pressure to comply with these stringent regulations. This paper presents a fleet optimization method for CII regulatory constraints, considering the difference in main engine fuel consumption performance within the fleet. Two scenarios are optimized: "Fleet scheduling considering single ship CII rating limits" and "Fleet scheduling with no E-class ships and the least used biofuel". The results demonstrate that the proposed optimization algorithm outperforms random scheduling in maintaining fleet CII compliance and reducing biofuel usage. This study will help shipping companies meet fleet CII regulations and reduce carbon emissions, while improving their ability to respond to international green and low-carbon regulations.

To improve the comprehensive evaluation system of ports and move beyond the single evaluation mode of "throughput only," this study investigates a comprehensive evaluation index system for world-class ports. Firstly, the concept and connotation of world-class ports are interpreted using the "Theme-Objective-Path-Service" analysis framework. A comprehensive evaluation index system for world-class ports is proposed, centered around weighted throughput, ship service efficiency, connectivity, economic contribution, and green and security levels. The index weights are determined using the Analytic Hierarchy Process, and a fuzzy comprehensive evaluation model for world-class ports is established. Based on this model, 34 global sample ports are selected for comprehensive evaluation. The evaluation results show that the ports of Singapore and Shanghai rank among the top two in terms of comprehensive scores, placing them in the world's leading lineup. Nine other ports, including Rotterdam, Ningbo-Zhoushan, Busan, and Qingdao, rank among the top ports globally with scores above 80. Finally, suggestions for conducting comprehensive evaluations of world-class ports are proposed, focusing on establishing world-class port evaluation standards and strengthening the application of big data from the Automatic Identification System (AIS).

In order to study the safe deployment of tugboats under the uncontrolled situation of large LNG (Liquefied Natural Gas) ships in the dock-constrained waters, and to ensure the safety of port terminal operations, the study adopts the CFD (Computational Fluid Dynamics) analysis method, based on the wind flow interference model, and calculates the hydrodynamic parameters and determines the emergency tugboat deployment strategy by simulating the drift process of the large LNG ship under different working conditions. Taking Wenzhou Xiaomendao as a case study object, the study focuses on analyzing the ship motion process of Qmax LNG ship under the working condition of sudden loss of control, and calculates the drift distance, which is used to guide the emergency deployment of tugboats. The results of the study show that the emergency deployment strategy of tugboat under different working conditions can be clarified by CFD analysis. This study provides scientific support for the safety of large LNG vessels in port transportation and provides an effective basis for emergency decision-making for port management to ensure the safe operation of ports and shipping industries.

Complex meteorological sea conditions directly affect the safety of ship navigation, and the accuracy of the prediction of offshore wind speed, as a major factor in meteorological sea conditions, is of great significance to the navigation safety and trajectory planning. In order to effectively improve the accuracy of offshore wind speed prediction and overcome the limitations of a single prediction model, the offshore wind form data of Lianyungang station is used as an example study, and the Adaboost algorithm is used to integrate the advantages of multi-models to construct a combined prediction model of offshore wind speed. Four time series prediction models, including BP neural network, GA BPNN, long and short-term memory network and WOA-SVR, are used for wind speed prediction. Considering the prediction effect of a single model, Adaboost algorithm is applied to integrate the GA-BPNN model and WOA-SVR model to construct the combined offshore wind speed prediction model, and the integration accuracy is compared with that of Bagging algorithm. The results show that the root mean square error of the combined prediction model with the Adaboost algorithm is reduced by about 13% and the mean absolute error is reduced by about 16% compared with the single model, which effectively verifies the superiority of the combined prediction model in the prediction of offshore wind speed data, and it is of great significance for the enhancement of navigational safety and the optimization of the trajectory design.

In order to improve the safety of water transportation and reduce collision accidents, a quantitative model of ship collision hazard based on complex network is proposed. By constructing the complex network and calculating the relationship strength to reflect the relationship between ships, the RDF (Radial Distribution Function) is used to analyze the density factor of the ship and discuss the traffic situation around the ship; the centrality of the network is used to analyze the conflict factor of the ship; and the affiliation function based on the power law of Stevens is used to integrate the density factor and the conflict factor to improve the collision hazard quantification method based on ship pairs. In order to prove the accuracy of the model, example verification is carried out and compared with the method based on the superposition calculation of ship pairs, and the results show that the present model has a certain degree of accuracy. By analyzing the actual water situation, the corresponding warning mechanism is discussed, which can be used for monitoring the water traffic situation and hazard warning.

To ensure the safety of navigation in the bridge area, this paper proposes a ship automatic monitoring method based on the fusion of vision and AIS (Automatic Identification System). The ship contour information in the image is extracted by the YOLOv5 (You Only Look Once version 5) target detection algorithm and the Canny algorithm. A distance, azimuth, and height measurement model of the visual target in the bridge area is constructed to achieve the three-dimensional positioning of the ship. An abnormal behavior detection model is established using the ship navigation situation data from the fusion of vision and AIS to automatically identify and monitor monitoring of dangerous ships in the bridge area. The experimental results show that: In cases of single and multiple ships, the accuracy of visual and AIS data association is 98.45% and 91.29%, respectively; The method can effectively monitor the motion state of ships in the bridge area. This paper provides an effective method for ensuring the safety of ships and bridges.

To address the issues of the analytical-based F_QSD (Fuzzy Quaternion Ship Domain) model, such as the difficulty in defining its boundary, insufficient consideration of influencing factors, and challenges in practical application, this paper incorporates the human factor of ship navigator and establishes a D_QSD (Dynamic Quaternion Ship Domain) based on the ship navigator's state to enhance the analytical-based fuzzy quaternion ship domain. The shape parameter K value of the fuzzy quaternion ship domain is calculated according to the ship navigator's state, and the dynamic ship domain model under different ship navigator states is obtained through computer simulation. The results show that the shape and area of the ship domain dynamically change under different driving states. When the ship navigator's state is excellent, the ship domain shape is an irregular rhombus, and the domain area is the smallest. When the ship navigator's state is poor, the ship domain shape is approximately rectangular, and the domain area is the largest. Compared with the traditional analysis-based ship domain, the proposed model determines the fuzzy boundary of the ship domain according to the ship navigator's state, making the dynamic ship domain more flexible and adaptable.

Existing studies indicate that the longer the queue length of vessels, the greater the channel saturation. To predict channel congestion, this study proposes a congestion prediction method that considers the maximum queue length based on the fundamental principles of traffic wave theory. The model utilizes Automatic Identification System (AIS) data to extract traffic flow characteristic parameters and, considering the differences in navigation behavior among ships in different waters, proposes a method for dividing the channel into characteristic areas. The queue length in traffic wave theory is selected as the evaluation index for congestion, and a method for predicting the maximum queue length based on Gaussian process regression is proposed to achieve the prediction of waterway congestion levels. A case study is conducted in the Yuxi River section of the Yangtze River Basin. The results show that the theoretical value of the maximum queue length in this section in July 2020 is 0.98 km, and the Adjusted R² index of the established regression model is 0.88, predicting a maximum queue length of 1.34 km with an error of 0.37 km compared to the theoretical value. The research results demonstrate that the proposed model has a high degree of interpretability and can effectively predict the maximum queue length, thereby enabling the prediction of channel congestion. This study provides a theoretical basis for improving the level of maritime supervision services.

In order to solve the key problem of collision avoidance action of close ships, the steering avoidance process during collision encounter is studied, combining with the ship's maneuvering performance, the time characteristics of the ship's initial turning semicircle elements and turning angle are analyzed; through the decomposition of the relative motion diagram and the inverse approximation algorithm, the mathematical model of the close-quarter situation distance and collision distance is obtained when the ship is steering avoidance. The application of the model is also given; the results of the model application are verified by arithmetic examples and simulation tests. The results show that the proposed two distance models can be used to guide the collision avoidance actions of ships at close range, and provide a theoretical basis for the study of collision risk and the establishment of an automatic collision avoidance decision-making system for ships. At the same time, according to the model, the collision avoidance actions that should be taken by the ship at different stages of the encounter are analyzed for the target ships with different speed ratios and different bearings when there is a collision danger, and the close-range ship collision avoidance action mode is also given. It also gives the model of close-range ship collision avoidance action. It provides the ship deck officers with the support of close-range ship collision danger prediction and ship collision avoidance decision-making. The research results are of great significance to ship navigation safety and navigation intelligence.

Image feature registration is a critical step for stitching and generating large-field images during the inland navigation of ships. To address the problems of sparse water surface feature points and low efficiency in traditional feature matching algorithms for image registration in inland navigation environments, this paper proposes a feature matching method based on image super-resolution reconstruction. Firstly, the input images are subjected to super-resolution reconstruction using generative adversarial networks to enrich image details and increase the number of image feature points. Secondly, the ORB operator and BEBLID algorithm are employed for feature point detection and description. Then, coarse matching is performed based on Hamming distance. Finally, an improved random sampling consistency algorithm is utilized to further eliminate gross errors and purify inliers, achieving robust matching results. The study conducts experiments using five sets of inland navigation environment images with challenges such as low visibility, varying lighting conditions, scale changes, blur, and rotation. The results demonstrate that the proposed approach, leveraging image super-resolution reconstruction for feature point extraction, achieves an increased number of feature points and outperforms comparative algorithms in terms of matching accuracy and speed. This method meets the requirements of high-precision and real-time image matching in inland navigation environments.