Vehicle scheduling at shipyards can involve delays due to numerous risk factors encountered in the complicated shipyard road environment. This paper studies the problems of risk coupling in shipyard vehicle scheduling based on the risk matrix approach, considering the complicated road environment, assessing the degrees of coupling and disorder. Based on safety-engineering theory and comprehensive analysis of the road environment, four key criteria are identified, vehicles, the road environment, the working environment, and humans, including 12 factors and their specific contents. The degree of coupling between various combinations of risk criteria is quantitatively determined utilizing the N-K model. Additionally, the degree of disorder in the risk criteria is assessed based on information entropy theory. The model’s correction coefficients are determined through comparative analysis of experimental data. By integrating the degree of coupling and disorder, delays caused by different combinations of risk criteria in scheduling tasks are computed. The quantitative evaluation model enables accurate appraisal of risk events during shipyard vehicle scheduling. The model provides a valuable managerial tool to analyze delays caused when specific risk criteria are met and to compare these delays to the potential impact on time resulting from adjusting vehicle scheduling plans. This research has significant implications for enhancing vehicle distribution efficiency in shipyards.

Typhoon avoidance is critical for ship maneuvering safety under extreme meteo-ocean conditions. This study proposes a data-driven framework that converts AIS trajectories into interpretable course deviation and speed change responses for navigational decision support. After AIS cleaning, temporal resampling, and matching with gridded wind, wave, and current fields, rule-based sliding-window and regression procedures, informed by experienced captains and company staff, automatically generate proxy labels for deviation and speed reduction. Samples are stratified by vessel size to reflect differences in inertia and maneuverability, and XGBoost classifiers are trained with simple resampling to mitigate class imbalance. The framework is demonstrated on a single-event case study of Typhoon Yagi in the South China Sea, covering 8609 vessels and reconstructed sailing fragments. On the test set, the deviation model achieves 89.8% accuracy and high recall for deviation cases, while the speed change model reaches 82% balanced accuracy under the proxy-label setting. Results suggest a scale-dependent response: smaller vessels exhibit more frequent course deviation, whereas larger vessels more often reduce speed under severe wind-wave loading. The framework offers a proof-of-concept approach to derive behavior-based indicators from AIS and environmental data and may support situational assessment under adverse weather.