为保障船舶航行安全，本文基于海上交通工程理论和航行大数据，提出一种通过计算多船碰撞风险检测船舶碰撞高风险区域的方法。首先，对船舶自动识别系统（Automatic Identification System，AIS）数据进行深入分析，从中提取出船舶会遇场景相关数据；其次，通过构建船舶会遇关系网解构这些场景；然后，深入探讨船舶会遇场景的特征，创新性地提出一种基于Sigmod函数和船舶会遇关系网的多船碰撞风险计算模型；最终，检测出目标海域内的船舶碰撞高风险区域，并揭示这些区域的时空分布特征。为验证该方法的有效性，本文选取宁波-舟山以东部分海域AIS数据进行大量实验，结果表明，该方法在检测船舶碰撞高风险区域方面取得了显著效果。
To ensure the safety of maritime navigation, this article proposes a method for detecting high-risk areas of ship collisions by calculating the risk of multi-ship collisions based on maritime traffic engineering and big data technology. The study first conducts an in-depth analysis of AIS (Automatic Identification System) data, extracting relevant data on ship encounter scenarios. Secondly, it constructs a ship encounter relationship network to deconstruct these scenarios. Then, it deeply discusses the characteristics of ship encounter scenarios and innovatively proposes a multi-ship collision risk calculation model based on the Sigmod function and the ship encounter relationship network. Finally, it detects high-risk areas of ship collisions in the target sea area and reveals the spatiotemporal distribution characteristics of these areas. To verify the effectiveness of this method, the article selected AIS data from the sea area east of Ningbo-Zhoushan for a large number of experiments, and the results showed that the method achieved significant effects in detecting high ship collision risk areas.
2025,47(18): 161-165 收稿日期：2024-9-3
DOI：10.3404/j.issn.1672-7649.2025.18.026
分类号：U675.79
基金项目：国家自然科学基金重点项目（52231014）；大连海事大学团队项目（3132023511）
作者简介：姜致远（1998 – ），男，硕士，研究方向为海上智能运输系统
参考文献：
[1] 欧阳知雨, 张安民, 张永兵. 基于AIS的船舶会遇局面紧迫度量化分析[J]. 海洋通报, 2019, 38(2): 225-232.
OUYANG Z Y, ZHANG A M, ZHANG Y B. Quantitative analysis of the degree of ship urgency based on AIS data[J]. Marine Science Bulletin, 2019, 38(2): 225-232.
[2] 贾立校. 船舶碰撞危险度模型应用与验证[J]. 舰船科学技术, 2016, 38(10): 16-18.
JIA L X. Application and validation of ship collision risk model[J]. Ship Science and Technology, 2016, 38(10): 16-18.
[3] JIE W, YAO T F. Risk analysis based on the ship collision modeling and forecasting system[C]//2008 IEEE International Conference on Systems, Man and Cybernetics, IEEE, 2008.
[4] QU X, MENG Q, SUYI L. Ship collision risk assessment for the singapore strait[J]. Accident Analysis & Prevention, 2011, 43(6): 2030-2036.
[5] LIU R W, HUO X, LIANG M, et al. Ship collision risk analysis: modeling, visualization and prediction[J]. Ocean Engineering, 2022, 266: 112895.
[6] LIU J, ZHANG J, YANG Z, et al. A novel data-driven method of ship collision risk evolution evaluation during real encounter situations[J]. Reliability Engineering & System Safety, 2024, 249: 110228.
[7] 任亚磊. 基于AIS数据的船舶会遇特征研究[D]. 武汉: 武汉理工大学, 2013.
[8] ZHU X, XU H, LIN J. Domain and its model based on neural networks[J]. The Journal of Navigation, 2001, 54(1): 97-103.
[9] PERERA L P, CARVALHO J P, GUEDES S C. Fuzzy logic based decision making system for collision avoidance of ocean navigation under critical collision conditions[J]. Journal of Marine Science and Technology, 2011, 16: 84-99.
[10] 张金奋, 游斌, 蔡明佑, 等. AIS数据驱动下的渡船横越场景识别与碰撞风险建模[J]. 中国航海, 2023, 46(2): 46-53+59.
ZHANG J F, YOU B, CAI M Y, et al. Identification of behavior of ferry boat crossing channel and modeling of collision risk[J]. Navigation of China, 2023, 46(2): 46-53+59.
[11] 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. Ship encounter situation recognition by processing AIS data from traffic intersection waters[J]. Navigation of China, 2021, 44(1): 68-74.
[12] 郑中义. 船舶自动避碰决策系统的研究[D]. 大连: 大连海事大学, 2000.
