Langxiong Gan

Directly measuring the mooring cable load while a ship is moored at a wharf poses significant practical challenges. This paper proposes an indirect load measurement method to identify mooring cable static loads based on the Influence Coefficient Matrix (ICM) method. First, a finite element analysis of the bollard is conducted to obtain the full-field strains under each unit load. A solution procedure based on the genetic algorithm (GA) is then implemented to determine the optimal placement and orientation of strain gauges, aiming to improve load identification accuracy. An optimal load coefficient matrix is derived to establish the correlation between cable loads and bollard strains. Subsequently, following the established measured point placement scheme, strain gauges are installed on the bollard surface to capture the strains, enabling inverse identification of mooring cable loads through the measured strains and the pre-established load–strain relationship. A numerical case study validated the feasibility of this method, demonstrating high identification accuracy. Furthermore, experimental verification was conducted to assess its reliability under different conditions. Results confirmed the effectiveness of this indirect approach for mooring cable static loads measurement. The research findings provide a technical framework for real-time monitoring of mooring cable loads.

The Port State Control (PSC) inspection of liquefied natural gas (LNG) carriers is crucial in maritime transportation. PSC inspection requires rapid and accurate identification of defects with limited resources, necessitating professional knowledge and efficient technical methods. Knowledge distillation, as a model lightweighting approach in the field of artificial intelligence, offers the possibility of enhancing the responsiveness of LNG carrier PSC inspections. In this study, a knowledge distillation method is introduced, namely, the multilayer dynamic multi-teacher weighted knowledge distillation (MDMD) model. This model fuses multilayer soft labels from multi-teacher models by extracting intermediate feature soft labels and minimizing intermediate feature knowledge fusion. It also employs a comprehensive dynamic weight allocation scheme that combines global loss weight allocation with label weight allocation based on the inner product, enabling dynamic weight allocation across multiple teachers. The experimental results show that the MDMD model achieves a 90.6% accuracy rate in named entity recognition, which is 6.3% greater than that of the direct training method. In addition, under the same experimental conditions, the proposed model achieves a prediction speed that is approximately 64% faster than that of traditional models while reducing the number of model parameters by approximately 55%. To efficiently assist in PSC inspections, an LNG carrier PSC inspection knowledge graph is constructed on the basis of the recognition results to quickly and effectively support knowledge queries and assist PSC personnel in making decisions at inspection sites.

With the growth of global trade, port shipping is becoming more and more important. In this paper, an analysis of a ship’s inbound and outbound track characteristics is conducted using the OD–Hausdorff distance. The accuracy and efficiency of trajectory data analysis have been enhanced through clustering analysis. Trajectories are arranged in a time sequence, and representative port segments are selected. An improved OD–Hausdorff distance method is employed to capture the dynamic characteristics of a ship’s movements, such as speed and heading. Additionally, the DBSCAN algorithm is utilized for clustering, allowing for the processing of multidimensional AIS data. Data cleaning and preprocessing have ensured the reliability of the AIS data, and the Douglas–Peucker algorithm is used for trajectory simplification. Significant improvements in the accuracy and efficiency of trajectory clustering have been observed. Therefore, the main channel of the Guan River and the right side of Yanwei Port are usually followed by ships greater than 60 m in length, with a lateral Relative Mean Deviation (RMD) of 7.06%. Vessels shorter than 60 m have been shown to have greater path variability, with a lateral RMD of 7.94%. Additionally, a crossing pattern at Xiangshui Port is exhibited by ships shorter than 60 m due to the extension of berths and their positions at turns. Enhanced clustering accuracy has provided more precise trajectory patterns, which aids in better channel management.

Over-height ships pose serious danger to bridges when sailing along inland rivers. Measuring ship height from a long distance with high precision is a very challenging problem. This paper proposes a novel co-linear optical axes binocular stereo vision system to meet this goal. The system is equipped with two arrays of cameras, each consisting of a long-focus camera (LFC) and a short-focus camera (SFC), located face-to-face on each sides of a river. The SFC, i.e., wide-angle-lens camera, is used for ship detection, while the LFC, i.e., tele lens camera, is used for precise ship height measurement. Different from conventional binoculars, the optical axis of the two LFCs are arranged to be co-linear in our setup. The advantage of this configuration is in two-fold. Firstly, it’s simple and precise to calibrate the measuring apparatus and the system error since the two LFCs are mutually visible to each other; secondly, due to its face-to-face configuration across the river, the entire navigation waterway is under constant monitoring without blind spot, hence the shortcoming of limited field of view (FOV) of tele lens is overcome with conventional parallel optical axis stereo vision setup. In this work, detailed error analysis were performed and in-field experiments were well designed. The experimental data matched very well with the theoretical prediction. The proposed system can achieve a ship height measuring error below 0.1m for a distance of 1.46 km.

Ship exhaust gas has become an essential source of air pollution in recent years. To assess the impact of ship exhaust gas on the atmospheric environment and human health, this paper studies the problem of ship exhaust gas diffusion in the port area. According to automatic identification system (AIS) data, ship exhaust gas is estimated based on the bottom-up method, and the result of emission calculation is entered into a Gaussian puff model to calculate the superposition of the diffusion of gaseous pollutants from multiple ships. In addition, the results of a case study of the diffusion of ship exhaust gas in the western area of Shenzhen Port in China show that the distribution of the NO₂ concentration in the studied area is not stable, the diffusion of exhaust gas from multiple ships mainly affects some areas near large ship berths at night, and there is a small impact on the whole study area. This lays a foundation for monitoring and treating the atmospheric environment in the port area.

The flag state control (FSC) inspection is an important measure to ensure maritime safety. However, it is difficult to improve ship safety management efficiency using data mining due to the scattered and multi-source ship inspection knowledge. In this paper, the emerging knowledge graph technology is used to integrate multi-source knowledge for the FSC inspection. Firstly, an ontology model is built to systematically describe the knowledge and guide the construction of the data layer of the knowledge graph. Then, the BERT-BiGRU-CRF model is used to extract entities from the unstructured data of the FSC inspection. The extracted results are associated with structured and semi-structured data and stored in the graph database Neo4j to construct the knowledge graph. In addition, a case study of the FSC inspection knowledge graph of Dafeng Port in Yancheng, China, is conducted to verify the strength of the proposed method. The results show that the knowledge graph can correlate trivial knowledge and benefit the efficiency of the FSC inspection. Moreover, the knowledge graph can reflect the deficiency characteristics of ships and support the safety management of water transportation.

This paper aims at resolving the path planning problem in a time‐varying environment based on the idea of overall conflict resolution and the algorithm of time baseline coordination. The basic task of the introduced path planning algorithms is to fulfill the automatic generation of the shortest paths from the defined start poses to their end poses with consideration of generous constraints for multiple mobile robots. Building on this, by using the overall conflict resolution, within the polynomial based paths, we take into account all the constraints including smoothness, motion boundary, kinematics constraints, obstacle avoidance, and safety constraints among robots together. And time baseline coordination algorithm is proposed to process the above formulated problem. The foremost strong point is that much time can be saved with our approach. Numerical simulations verify the effectiveness of our approach.

Based on analyzing the variation of ship's track and width of the swept path of bridge area caused by wind and current quantitatively, the paper presents the modified geometrical ship-bridge collision frequency model considering the impacts of wind and current based on the classical model. The observation data and experimental data based on large-scale maneuvering simulator are used to modify the model too. The improved model introduces path deviation coefficient and path width correction coefficient and establishes a quantitative formula with the relation of geometrical ship-bridge collision frequency to the wind-induced drift, current-induced drift and the corresponding deflection. Quantitative analysis results show that this modification can reflect properly the influence of wind and current on the characteristic of ship-bridge collision frequency. The improved model decreases systemic error with the selection of correction parameter regarding to wind and current and has more practical applicability.