In the global energy transportation landscape, maritime transport accounts for over 70% of crude oil shipments, making the reliability of its channels paramount to national energy security. Escalating geopolitical tensions have significantly elevated the risk of disruption to critical maritime channels, posing severe challenges to the stability of energy supply chains. To accurately assess this risk, this study employs complex network theory and integrates Automatic Identification System (AIS) trajectory data with vessel capacity weights to construct a global directed weighted network for crude oil maritime transportation, in which critical channels are abstracted as network nodes. Based on this framework, three progressive attack simulation strategies are designed-single channel disruption, compound scenario failure, and optimal disruption sequence-to systematically investigate the multidimensional vulnerability of the network to channel blockages. The findings indicate: 1) Functional differentiation. critical channels exhibit significant functional differentiation. Some are vital for global efficiency; for instance, removing the Strait of Malacca reduces network efficiency by 1.99%. Conversely, others demonstrate structural suboptimality, as exemplified by the removal of the Panama Canal, which paradoxically increases topological efficiency by 2.57%, revealing quantifiable suboptimal paths within the network. 2) Asynchronous vulnerability. The network exhibits asynchronous responses across performance dimensions. While macro-connectivity remains highly robust against single-point or regional failures, the core structure is highly fragile. For example, the network's K-Core value plummets after attacks targeting only four optimal nodes. 3) Non-linear degradation. Under optimal sequence attacks, global network efficiency follows a "U-shaped" trajectory-initially declining before rebounding beyond its original value due to topological reconfiguration. Notably, the collapse of the core structure occurs significantly earlier than the deterioration of overall transmission functionality, with the latter even showing a paradoxical recovery in the later stages of the attack. This study elucidates the underlying failure mechanisms of the global crude oil maritime transportation network under channel blockages, offering a new analytical paradigm and decision-making basis for ensuring national energy transportation security and enhancing the resilience of global supply chains.

To accurately predict the thermal fire hazard of these containers under different stowage methods on a ship, this paper establishes typical working conditions, such as the position of the fire container, stowage height and wind speed. It then simulates the fire scene of lithium battery containers on the deck using FLACS 10.9 and establishes a prediction model for the temperature and heat flow density of the fire flow field using the CatBoost algorithm. The results demonstrate that the air volume within the upper and lower spaces of the lithium battery container is directly proportional to the change in fire temperature. The maximum temperature occurs when the fire layer is in the 7th layer, and the range of damage caused by high temperatures and heat flux is minimised when the fire layer is between the 7th and 8th layers. Increasing the stowage height decreases airflow, resulting in higher maximum fire temperatures, a larger temperature influence range and a longer vertical diffusion distance of heat flux. When the wind speed is in the range of 1-4 m/s, it helps to dissipate heat and reduce the maximum temperature. However, when the wind speed reaches 5 m/s, the oxygen uptake rate of the flame increases, resulting in a higher maximum temperature. When the wind speed reaches 6 m/s, the heat dissipation effect dominates and the maximum fire temperature decreases again. The higher the wind speed, the smaller the area of damage caused by high temperatures and heat flux. Comparing the temperature and heat flux density values predicted by the CatBoost algorithm with the measured samples shows that the model is highly accurate and can identify overheating spots. These research results can inform the determination of lithium battery container accumulation modes and the corresponding fire monitoring.

Collision accidents pose a serious threat to the navigation and operational safety of fishing vessels. To enhance the decision-making capability of fishing vessel operators, this paper proposes an intelligent collision avoidance decision-making method based on the Convention on the International Regulations for Preventing Collisions at Sea (COLREGS). This method determines the encounter situation of the vessel in accordance with the COLREGS requirements and calculates the degree of collision risk, represented by the Collision Risk Index (I_CR), based on the Distance to the Closest Point of Approach (d_CPA) and the Time to the Closest Point of Approach (t_CPA). By investigating the collision avoidance behaviors of multiple fishing vessel operators, the Goodwin marine observation results were revised to establish the Safe Distance Approach (S_DA) specific to fishing vessels. Furthermore, the traditional Artificial Potential Field (APF) method was improved and integrated with a Genetic Algorithm (GA) to ensure that fishing vessels can avoid collisions safely and effectively. Finally, simulation experiments were conducted to validate the effectiveness of the proposed algorithm. The results demonstrate that the proposed method overcomes the limitations of the single artificial potential field approach in previous vessel collision avoidance decision-making systems. It achieves optimal steering amplitude and determines the appropriate timing for returning to the original course, thereby providing a safe and collision-free decision-making solution that complies with COLREGS. This study can serve as a valuable reference for practical collision avoidance operations by deck officers.

To address challenges such as significant scale variations, high aspect ratios, dense arrangements, and complex backgrounds in ship target detection from remote sensing images, this paper proposes an improved YOLOv7-based algorithm. Using YOLOv7 as the baseline network, the prior anchor generation algorithm is optimized for the dataset. A long-edge representation method combined with circular smooth labeling is introduced to detect ship targets with uncertain rotation directions. The YOLOv7 network is enhanced by embedding both the GAM (Global Attention Mechanism) and SimAM (Simple Attention Mechanism) modules, which effectively suppress interference from complex background regions in remote sensing images and improve target detection accuracy. Additionally, the coordinate loss function is optimized to accelerate model convergence. Experimental results on the DOTA-ship and HRSC2016 datasets for both single-class and multi-class detection tasks show mAP values of 86.1%, 97.7%, and 87.1%, respectively-representing improvements of 7.8%, 4.6%, and 7.9% over the original YOLOv7 model. These results validate the effectiveness and superiority of the proposed method.

Reasonable maritime route planning contributes to enhancing both the safety and economic efficiency of ship navigation. To address the challenges associated with route planning in complex waters, this paper proposes a method for extracting maritime traffic routes based on ship behavior patterns. Using Automatic Identification System (AIS) data, characteristic points of ship behavior patterns are identified through threshold judgment and a sliding window approach. A clustering algorithm is then applied to determine centroid points within each cluster, which represent the distribution of point sets. Finally, connection rules are established to sequentially link these centroids, thereby generating maritime traffic routes. Experimental analysis was conducted using AIS data from the Beibu Gulf waters. The results indicate that the routes extracted by this method align closely with the recommended routes published in the Navigation Guide for Ships in the Guangxi Area of the Beibu Gulf.

To further standardize the management of ship dismantling, it is essential to evaluate and analyze relevant policies as a basis for improving the full life cycle management system of ships. This paper reviews and analyzes 42 policy documents issued by governmental and industrial organizations over the past five years. Based on the content analysis of these policies, a Policy Consistency Index model (abbreviated as the "P Index Model") is established. The ship dismantling policies are categorized into three types: macro guidance, supplementary refinement, and guidance and encouragement. Representative policy documents are selected as evaluation targets, and their rationality is empirically analyzed. The results indicate that China's ship dismantling policies require improvements at three levels. At the national level, it is recommended to establish a coordinated ship dismantling management mechanism involving relevant regulatory departments and to develop unified planning and industry support policies. At the local level, local governments should promptly formulate and implement specific measures to ensure effective policy enforcement. At the industry level, associations need to enhance communication and collaboration with local governments, particularly in establishing consensus on the qualifications of compliant ship dismantling companies, to jointly promote the standardized development of the industry.

Ship trajectory prediction and behavior recognition can help effectively assess navigational risks and provide an important basis for decision-making in collision avoidance and traffic management. To improve the accuracy of ship trajectory prediction and behavior recognition, this paper studies a multi-task Informer model for simultaneous trajectory prediction and behavior recognition. Based on the Informer framework, the model incorporates a multi-task learning approach. It addresses the issue that inaccurate ship behavior records in AIS data cannot be directly used as model inputs by designing a multi-task loss function that jointly trains behavior recognition and trajectory prediction in parallel. During training, an adaptive updating strategy for the loss function-based on homoscedastic uncertainty-is designed to automatically allocate weights to the losses of the two tasks. Evaluated using real AIS data from the Taicang sector waters, the multi-task Informer model reduces trajectory prediction loss by 40.2% and 14.7% compared to LSTM and Informer models, respectively. In behavior recognition, the multi-task model improves accuracy by 11.7% and 5.95% compared to LSTM and Informer models, respectively. The results demonstrate that the multi-task model effectively enhances the performance of ship trajectory prediction while achieving accurate recognition of ship behavior.

Addressing the requirements for ship’s autonomous navigation and high-precision path following control, this paper proposes a fuzzy control method with partitioned integral regions based on the Integral Line-of-Sight (ILOS) guidance law for path following control of autonomous navigation ships. Based on the established ship motion model, an extended Kalman filter is employed to estimate ship states such as speed and heading using GNSS measurement data. Fuzzy controllers are designed to dynamically adjust the look-ahead distance parameter according to different navigation conditions, thereby improving tracking performance. The 700 Twenty-foot Equivalent Unit (TEU) battery-powered container ship built by COSCO Shipping Group is taken as the plant for path following experiments on a simulation platform. Comparative analyses with results from different algorithms show that the proposed control algorithm achieves superior performance and smoother rudder angle manipulation. This method can provide reference for path following control of autonomous navigation ships.

Ship trajectory prediction has become increasingly important in marine traffic management, shipping safety, and related fields. Current methods for ship time-series prediction exhibit certain limitations when handling multi-feature data inputs in water traffic scenarios, as they fail to adequately capture the correlations among features or focus on the critical information within time-series data. To address these shortcomings and further improve the accuracy of ship trajectory prediction, this study proposes a method named GCAU, which integrates an improved Graph Convolutional Network (GCN) with a Recurrent Attention Unit (RAU). First, Graph Convolutional Networks are employed to capture interdependencies between features, thereby enhancing the model's capability to extract feature correlations. Second, an attention gate is incorporated into the Recurrent Attention Unit (RAU), enabling selective emphasis on time-level features. Finally, the study evaluates four different ship time-series prediction methods across three distinct scenarios. The results demonstrate that GCAU outperforms the other methods in all tested scenarios, achieving lower values in Mean Squared Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and Mean Absolute Error (MAE). The proposed method can effectively enhance the accuracy and stability of ship trajectory prediction, thereby providing more reliable decision support for maritime traffic management and other related applications.

In accordance with the MARPOL Annex Ⅵ Nitrogen Oxide (NO_x) Technical Code issued by the International Maritime Organization (IMO), this paper proposes a simplified on-board test scheme for measuring NO_x emissions from marine diesel engines. The scheme employs the carbon balance method to calculate exhaust flow, requiring only the measurement of NO_x and CO₂ concentrations in diesel exhaust at selected load points, and adopts the default fuel element content values provided in the IMO Technical Code. The results show that the weighted average NO_x deviation of the simplified method is approximately 2% compared with the standard cycle, while also reducing the complexity of emission testing equipment and shortening the testing process. The findings provide a theoretical basis for streamlining NO_x emission on-board tests.