In the context of the rapid development of deep learning theory, predicting future motion states based on time series sequence data of ship trajectories can significantly improve the safety of the traffic environment. Considering the spatiotemporal correlation of AIS data, a trajectory time window panning and smoothing filtering method is proposed for the abnormal values existing in the trajectory data. The application of this method can effectively deal with the jump values and outliers in the trajectory data, make the trajectory smooth and continuous, and ensure the temporal order and integrity of the trajectory data. In this paper, for the features of spatiotemporal data of trajectories, the LSTM structure is integrated on the basis of the deep learning Transformer algorithm framework, abbreviated as TRFM-LS. The LSTM module can learn the temporal features of spatiotemporal data in the process of computing the target sequence, while the self-attention mechanism in Transformer can solve the drawback of applying LSTM to capture the sequence information weakly at a distance. The advantage of complementarity of the fusion model in the training process of trajectory sequences with respect to the long-range dependence of temporal and spatial features is realized. Finally, in the comparative analysis section of the error metrics, by comparing with current state-of-the-art methods, the algorithm in this paper is shown to have higher accuracy in predicting time series trajectory data. The research in this paper provides an early warning information reference for autonomous navigation and autonomous collision avoidance of ships in practice.

As maritime transportation develops, the pressure of port traffic increases. To improve the management of ports and the efficiency of their operations, vessel scheduling must be optimized. The vessel scheduling problem can be divided into channel scheduling and berth allocation. We considered the complex problem of vessel scheduling in a restricted channel and the berth allocation problem, and a combined model that considers carbon emissions was developed. This model should reduce vessel waiting times, improve the quality of the berth loading and unloading service, meet the requirements of “green” shipping, and improve the overall scheduling efficiency and safety of ports. An adaptive, double-population, multi-objective genetic algorithm NSGA-II-DP is proposed to calculate the mathematical model. In the case study, the rationality verification and sensitivity analysis of the model and algorithm are conducted, and the NSGA-II-DP and NSGA-II were compared. Results demonstrate that the overall convergence of the NSGA-II-DP algorithm is better than that of NSGA-II, demonstrating that the NSGA-II-DP algorithm is a useful development of NSGA-II. In terms of port scheduling, the results of our model and algorithm, compared with the decisions provided by the traditional First Come First Service (FCFS) strategy, are more in line with the requirements for efficiency and cost in the actual port management, and more dominant in the port management can provide better decision support for the decision-makers.

The research on decision-making models of ship collision avoidance is confronted with numerous challenges. These challenges encompass inadequate consideration of complex factors, including but not limited to open water scenarios, the absence of static obstacle considerations, and insufficient attention given to avoiding collisions between manned ships and MASSs. A decision model for MASS collision avoidance is proposed to overcome these limitations by integrating the strengths of model-based and model-free methods in reinforcement learning. This model incorporates S-57 chart information, AIS data, and the Dyna framework to improve effectiveness. (1) When the MASS’s navigation task is known, a static navigation environment is built based on S-57 chart information, and the Voronoi diagram and improved A* algorithm are used to obtain the energy-saving optimal static path as the planned sea route. (2) Given the small main dimensions of an MASS, which is easily affected by wind and current factors, the motion model of an MASS is established based on the MMG model considering wind and current factors. At the same time, AIS data are used to extract the target ship (manned ship) data. (3) According to the characteristics of the actual navigation of ships at sea, the state space, action space, and reward function of the reinforcement learning algorithm are designed. The MASS collision avoidance decision model based on the Dyna-DQN model is established. Based on the DQN algorithm, the agent (MASS) and the environment interact continuously, and the actual interaction data generated are used for the iterative update of the collision avoidance strategy and the training of the environment model. Then, the environment model is used to generate a series of simulated empirical data to promote the iterative update of the strategy. Using the waters near the South China Sea as the research object for simulation verification, the navigation tasks are divided into three categories: only considering static obstacles, following the planned sea route considering static obstacles, and following the planned sea route considering both static and dynamic obstacles. The results show that through repeated simulation experiments, an MASS can complete the navigation task without colliding with static and dynamic obstacles. Therefore, the proposed method can be used in the intelligent collision avoidance module of MASSs and is an effective MASS collision avoidance method.

The fast reconstruction of the ship hull nonuniform rational B-spline (NURBS) surface with uniform continuity is essential for calculating hydrostatic elements such as waterplane area and molded volume in real time. Thus, this study proposes a fast reconstruction model with uniform continuity to solve the problem of uniform continuity and splicing in the separate model of hull bow and stern surfaces. The proposed model includes the NURBS curve generation (UCG) algorithm with uniform continuity and the hybrid NURBS surface generation (HSG) algorithm. The UCG algorithm initially fits the feature points using the global interpolation algorithm and then precisely constructs straight-line segments in the curve using the improved flattening algorithm. In comparison, the HSG algorithm adaptively selects the surface knot vectors according to the parameters of the section curves. In this study, the profile of discontinuous compartments is uniformly expressed, effectively avoiding various articulation problems in separation modeling. The results of comparative experiments show that the NURBS surface generated using the HSG algorithm can accurately express the characteristics of various parts of the hull with uniform continuity, and the calculation speed of the proposed model can be increased by up to 8.314% compared with the existing best-performing algorithms. Thus, the proposed model is effective and can improve computational efficiency to a certain extent. The NURBS surfaces generated by the proposed model can be further applied to calculating the hydrostatic elements of hulls and compartments.

It is important to accurately calculate flattening points when reconstructing ship hull models, which require fast and high-precision computation. However, some search algorithms, such as the bisection method, iterate near the optimal value too many times before converging in high-precision computation. The paper proposes a fast high-precision bisection feedback search (FHP-BFS) algorithm to solve the problem. In the FHP-BFS algorithm, the Newton–Raphson (NR) method is adopted to accelerate the convergence speed by considering the iteration characteristics of subintervals. Furthermore, a new feedback mechanism is proposed to control the feedback directions. In addition, an acceleration algorithm, called the interval reformation method, is used to guide the FHP-BFS algorithm for fast convergence. Finally, the flattening algorithm is improved by the FHP-BFS algorithm. In the comparative experiments, the practical efficacy of the FHP-BFS algorithm is first demonstrated, and then the optimal range of the threshold precision is determined. Next the FHP-BFS algorithm is compared to the best existing algorithms. Finally, the performance of the improved flattening algorithm is verified. The experiments demonstrate that the FHP-BFS algorithm has optimal performance among the compared algorithms, and it has an improved computation efficiency while maintaining robustness. The improved flattening algorithm reduces the computation time, ensures smoothness and meets practical engineering requirements.