Jiao Liu

Ship–bridge collisions in cross-sea bridge waterways are rare but potentially catastrophic events, making conventional accident-based risk assessment difficult to implement effectively. Existing AIS-based indicators capture vessel behaviors but insufficiently quantify bridge-passage safety margins, especially dynamic aspects such as crossing posture and readiness prior to bridge transit. To address this limitation, this study proposes a data-driven framework for detecting unsafe ship–bridge passages using two bridge-passage-oriented surrogate safety measures (SSMs) and extreme value theory (EVT). The Bridge-passage Lateral Clearance Margin (BLCM) quantifies the effective lateral safety margin retained during the realized bridge-crossing stage, while the Bridge-passage Readiness Lead Time (BRLT) measures how early a vessel becomes stably prepared for bridge passage before crossing. The Peaks Over Threshold (POT) model is first used to characterize the marginal extremes of the two indicators, and a bivariate threshold exceedance model (BTE) is then established to examine their joint risk behavior. Case studies of the Jintang Bridge and Zhoudai Bridge waterways demonstrate that the proposed framework can effectively screen and identify trajectories with unsafe or margin-deficient bridge-passage characteristics. The results show that unsafe passages are typically associated with both reduced lateral clearance and insufficient preparation time, and that joint modeling of the two indicators improves risk identification performance. The findings suggest that ship–bridge risk is better interpreted from the perspective of passage quality deficiency rather than simple geometric proximity. The proposed framework provides an interpretable tool for retrospective unsafe passage screening, traffic monitoring support, and post-event safety analysis in complex bridge waterways.

Deep-sea navigation represents the future trend of maritime navigation; however, complex seakeeping conditions often lead to unconventional ship attitudes. Conventional calculation methods are insufficient for accurately assessing hull performance under heeled or extreme trim conditions. Drawing inspiration from Bonjean curve principles, this study proposes a Quasi-Bonjean (QB) method to compute ship performance elements in arbitrary attitudes. Specifically, the QB method first constructs longitudinally distributed hull sections from the Non-Uniform Rational B-Spline (NURBS) surface model, then simulates arbitrary attitudes through dynamic waterplane adjustments, and finally calculates performance elements via sectional integration. Furthermore, an Adaptive Surface Tessellation (AST) method is proposed to optimize longitudinal section distribution by minimizing the number of stations while maintaining high geometric fidelity, thereby enhancing the computational efficiency of the QB method. Comparative experiments reveal that the AST-generated 100-station sections achieve computational precision comparable to 200-station uniform distributions under optimal conditions, and the performance elements calculated by the QB method under multi-attitude conditions meet International Association of Classification Societies accuracy thresholds, particularly excelling in the displacement and vertical center of buoyancy calculations. These findings confirm that the QB method effectively addresses the critical limitations of traditional hydrostatic tables, providing a theoretical foundation for analyzing damaged ship equilibrium and evaluating residual stability.

Ship collisions pose a significant threat to maritime safety, especially in congested precautionary areas with high vessel traffic density. Traditional collision risk assessment methods, such as distance to closest point of approach (DCPA) and time to closest point of approach (TCPA), often overlook environmental uncertainties and variations in human response. To address these limitations, this study proposes a novel approach for collision risk assessment using automatic identification system (AIS) data. AIS data from vessels in precautionary areas are resampled to synchronize their temporal frameworks, enabling the systematic identification of ship encounters. Each encounter is analyzed by evaluating critical parameters, including the minimum ship encounter distance (MSED), relative azimuth angles, and trajectories, within a customized ship domain model that incorporates vessel characteristics such as ship length and course. Key metrics, such as intrusion depth and time, are calculated based on vessels’ entry and exit points during each encounter. A set of collision risk indices, which integrates both intrusion depth and time, is introduced, with particular emphasis on intrusion depth due to its heightened sensitivity to proximity danger and constrained maneuvering space. An extensive analysis of vessel interactions in the precautionary area establishes a holistic collision risk index. A case study using AIS data from Ningbo–Zhoushan Port, involving a dataset of 1000 ship encounters, demonstrates the effectiveness of the proposed method. Specifically, the holistic collision risk in the No.2 precautionary area is 0.456, while the No.3 precautionary area shows a risk value of 0.443. These results confirm the effectiveness and feasibility of the proposed method for evaluating and classifying collision risks, offering a more precise and reliable framework for collision risk assessment in complex navigational environments.

Abnormal ship navigation behaviors in cross-sea bridge waters pose significant threats to maritime safety, creating a critical need for accurate anomaly detection methods. Ship AIS trajectory data contain complex temporal features but often lack explicit labels. Most existing anomaly detection methods heavily rely on labeled or semi-supervised data, thus limiting their applicability in scenarios involving completely unlabeled ship trajectory data. Furthermore, these methods struggle to capture long-term temporal dependencies inherent in trajectory data. To address these limitations, this study proposes an unsupervised trajectory anomaly detection model combining a transformer architecture with a variational autoencoder (transformer–VAE). By training on large volumes of unlabeled normal trajectory data, the transformer–VAE employs a multi-head self-attention mechanism to model both local and global temporal relationships within the latent feature space. This approach significantly enhances the model’s ability to learn and reconstruct normal trajectory patterns, with reconstruction errors serving as the criterion for anomaly detection. Experimental results show that the transformer–VAE outperforms conventional VAE and LSTM–VAE in reconstruction accuracy and achieves better detection balance and robustness compared to LSTM–-VAE and transformer–GAN in anomaly detection. The model effectively identifies abnormal behaviors such as sudden changes in speed, heading, and trajectory deviation under fully unsupervised conditions. Preliminary experiments using the POT method validate the feasibility of dynamic thresholding, enhancing the model’s adaptability in complex maritime environments. Overall, the proposed approach enables early identification and proactive warning of potential risks, contributing to improved maritime traffic safety.

This research addresses the critical issue of major fishing vessel accidents, which traditionally suffer from a lack of focused analysis due to their rarity and the subjective nature of their classification. We propose an innovative methodology of Peaks Over Threshold to overcome subjectivity in accident classification. This approach ensures a more representative and accurate analysis of major accidents, distinguishing them from more common, less severe incidents. Employing a Bayesian network model, we further explore the most influential factors contributing to these major accidents. The key innovation lies in our novel approach to data handling and analysis, enabling us to uncover hidden patterns and causal relationships that traditional methods often overlook. The results show that the approach proposed in this study can effectively capture the key factors of major fishing vessel accidents. This study identifies accident type, vessel-related factors, and accident location as the key influential factors leading to major accidents. The findings from our research are intended to inform sustainable fisheries management practices, promoting interventions that aim to decrease the occurrence and impact of severe maritime accidents while balancing economic, safety, and sustainable development considerations.

The accurate timing for collision avoidance actions is crucial for preventing maritime collisions. Traditional methods often rely on collision risk assessments, using quantitative indicators like the Distance to the Closest Point of Approach (DCPA) and the Time to the Closest Point of Approach (TCPA). Ship Officers on Watch (OOWs) are required to execute avoidance maneuvers once these indicators reach or exceed preset safety thresholds. However, the effectiveness of these indicators is limited by uncertainties in the maritime environment and the human behaviors of OOWs. To address these limitations, this study introduces a machine learning method to learn collision avoidance behavior from empirical data of ship collision avoidance, particularly in cross-encounter situations. The research utilizes Automatic Identification System (AIS) data from the open waters around Ningbo Zhoushan Port. After data preprocessing and applying spatio-temporal constraints, this study identifies ship trajectory pairs in crossing scenarios and calculates their relative motion parameters. The Douglas–Peucker algorithm is used to identify the timing of ship collision avoidance actions and a collision avoidance decision dataset is constructed. The Random Forest algorithm was then used to analyze the factors affecting the timing of collision avoidance, and six key factors were identified: the distance, relative speed, relative bearing, DCPA, TCPA, and the ratio of the lengths of the giving-way and stand-on ships. These factors serve as inputs for the XGBoost algorithm model, which is enhanced with Particle Swarm Optimization (PSO), and thus constructing a ship collision avoidance decision model. In addition, considering the inherent errors in any model and the dynamic nature of the ship collision avoidance process, an action time window for collision avoidance is introduced, which provides a more flexible time range for ships to make timely collision avoidance responses based on actual conditions and the specific encounter environment. This model provides OOWs with accurate timing for taking collision avoidance decisions. Case studies have validated the practicality and effectiveness of this model, offering new theoretical foundations and practical guidance for maritime collision avoidance.