船舶避碰行为分析对于船舶碰撞风险评估、智能避碰决策、导助航设备研发和船舶交通管理等方面的研究具有重要意义。本文提出一种基于海量AIS时空数据的船舶避碰行为提取方法。该方法包括会遇态势判别、避碰样本提取和避碰行为提取3个模块，依据避碰规则和航海实践对会遇态势判别和避碰样本提取中的关键参数及判别条件进行确定，通过船舶航行轨迹还原和避碰行为特征参数迭代，识别出表征避碰时机和避碰行为的具体参数。应用实际AIS数据对算法的有效性和准确性进行验证，并将算法提取结果与实际船舶航迹进行对比分析，结果表明该方法能够有效地从AIS数据中提取出船舶会遇和避碰行为数据，可以为后续船舶避碰相关研究提供数据支持。
Ship collision avoidance analysis is crucial for research in risk assessment, automated decision-making, navigation aid development, and traffic management. This study presents a method for extracting collision avoidance behavior from extensive AIS data. The method includes modules for encounter discrimination, sample extraction, and behavior extraction, using collision rules and maritime practices to define key parameters and conditions. It identifies specific avoidance parameters through trajectory restoration and iterative feature analysis. Validated with AIS data, the method effectively extracts encounter and avoidance actions, supporting further research.
2025,47(3): 141-147 收稿日期：2024-3-29
DOI：10.3404/j.issn.1672-7649.2025.03.023
分类号：U675.96
基金项目：国家自然科学基金资助项目（52171345）
作者简介：冮龙晖(1979-),女,副教授,研究方向为海上交通安全与海事保障
参考文献：
[1] 甄荣, MARIA R, 金永兴. 一种基于DBSCAN的船舶会遇实时识别方法 [J]. 上海海事大学学报, 2018, 39(1): 1?5.
ZHEN R , MARIA R, JIN Y X. A Real-time identification method for ship encounters based on DBSCAN [J]. Journal of Shanghai Maritime University, 2018, 39(1): 1?5.
[2] 马杰, 李文楷, 张春玮, 等. 基于AIS数据的交汇水域船舶会遇态势辨识[J]. 中国航海, 2021, 44(1): 68?74.
MA J, LI W K, ZHANG C W, et al. Situation identification of ships in intersecting waters based on AIS data[J]. China Navigation, 2021, 44(1): 68?74.
[3] ZHANG W, GOERLANDT F, MONTEWKA J, et al. A method for detecting possible near miss ship collisions from AIS data[J]. Ocean Engineering, 2015, 107: 60?69.
[4] ZHANG W, GOERLANDT F, KUJALA P, et al. An advanced method for detecting possible near miss ship collisions from AIS data[J]. Ocean Engineering, 2016, 124: 141?156.
[5] GAO M, SHI G Y. Ship-handling behavior pattern recognition using AIS sub-trajectory clustering analysis based on the T-SNE and spectral clustering algorithms [J]. Ocean Engineering, 2020.
[6] RONG H, TEIXEIRA A P, SOARES C G. Ship collision avoidance behaviour recognition and analysis based on AIS data [J]. Ocean Engineering, 2022.
[7] 大连海事大学. 海上交通工程 [Z].
[8] GAO M, SHI G Y, LIU J. Ship encounter azimuth map division based on automatic identification system data and support vector classification [J]. Ocean Engineering, 2020, 213.
[9] 翁建军. 各种避让措施下DCPA与TCPA的变化规律及最佳避让方案研究 [D]. 武汉: 武汉理工大学, 2004.
[10] MIAO G, ZHEN K, ANMIN Z, et al. MASS autonomous navigation system based on AIS big data with dueling deep Q networks prioritized replay reinforcement learning [J]. Ocean Engineering, 2022.
[11] RIBEIRO C V, PAES A, OLIVEIRA D D. AIS-based maritime anomaly traffic detection: A review [J]. Expert Systems with Applications, 2023: 120561.
[12] MOU J M, VAN DER TAK C, LIGTERINGEN H. Study on collision avoidance in busy waterways by using AIS data[J]. Ocean Engineering, 2010, 37(5?6): 483?490.
[13] ZHOU Y, DAAMEN W, VELLINGA T, et al. Ship behavior during encounters in ports and waterways based on AIS data: From theoretical definitions to empirical findings[J]. Ocean Engineering, 2023, 272: 113879.
