Collision risk assessment for complex navigable waters based on ship dynamic cluster
Article Text (Baidu Translation)
-
摘要: 针对复杂通航水域船舶碰撞风险感知时空精细度不足、动态实时性不强等问题，提出了基于船舶动态群组的碰撞风险评估框架；在船舶轨迹数据预处理的基础上，构建了复杂通航水域船舶交通拓扑网络模型，表征区域内船舶碰撞风险的相互作用关系；考虑船舶动态时空变化特性，引入了谱聚类算法进行交通划分，界定船舶动态群组，并通过Davies-Bouldin指数进一步优化船舶动态群组划分策略；基于图论知识，引入船间干扰复杂度量化指标，建立了船舶动态群组风险评估方法，辨识复杂通航水域内船舶碰撞高风险区域；选取典型复杂通航水域——宁波-舟山港核心港区开展研究，采集该水域1个月的船舶交通流数据，评估了多船会遇场景下船舶碰撞风险状态。研究结果表明：通过自适应确定船舶动态群组划分方法，将水域内船舶划分为若干群组，简化船舶碰撞风险关系，同时保留全局范围内最主要的碰撞风险；所提船舶碰撞风险评估方法可保留全局84.98%的风险，与传统基于距离的聚类算法、K-means、层次聚类、带噪声的基于密度的空间聚类(DBSCAN)算法等经典聚类算法相比，本文方法的保留风险值更大，并可以减少不必要的风险关系，在精度、群组紧凑性、尺度均衡性上综合效果最优，可有效降低虚警率、离散区域整体风险；进一步利用所提风险评估方法对8 640个的多船会遇场景的风险状态进行叠加计算，识别出的港区高风险区域与实际调研情况相符。Abstract: To address the challenges of insufficient spatial-temporal granularity and limited real-time dynamics in perceiving collision risk within complex navigable waters, a collision risk assessment framework based on ship dynamic clusters was developed. After preprocessing of ship trajectory data, a ship traffic topology network model for complex navigable waters was constructed to depict the interplay of ship collision risk within the region. By taking into account the dynamic spatial-temporal characteristics of ships, the spectral clustering algorithm was introduced for traffic segmentation, defining ship dynamic clusters. Further optimization of the ship dynamic cluster partitioning strategy was performed through the Davies-Bouldin index. Based on the graph theory, measures for ship interference complexity were introduced to establish a ship dynamic cluster risk assessment method, discerning high-risk collision areas within the complex navigable waters. A study was conducted on a representative complex navigable waters, the core port area of Ningbo-Zhoushan Port, where one-month ship traffic flow data was collected to assess ship collision risk under multi-ship encounter scenarios. Research results show that the proposed adaptive method for ship dynamic cluster partitioning effectively divides ships within navigable waters into several clusters. This approach simplifies ship-to-ship collision risk relationship, while retaining the most critical collision risk across the entire spatial scope. The proposed ship collision risk assesment method preserves 84.98% of the global risk. Compared to traditional distance-based clustering algorithm and other classical clustering algorithms such as K-means, hierarchical clustering, and density-based spatial clustering of applications with noise (DBSCAN), the proposed method has a larger retained risk value and can reduce unnecessary risk relationships. It achieves optimal comprehensive performance in terms of accuracy, cluster compactness, and scale balance, effectively reducing false positive rates and discretizing the overall regional risk. By further utilizing the proposed risk assessment model, the risk states of 8 640 multi-ship encounter scenarios are computed through superimposition, identifying high-risk areas within the port area and align with actual survey results.
-
图 13 基于距离度量的群组划分结果
Figure 13. Partitioning result of clusters based on distance measurement
表 1 各聚类算法性能对比
Table 1. Performance comparison of various clustering algorithms
划分方法 划分群组数/个 连边数/条 保留风险值/% 本文方法 15 292 84.98 传统基于距离的聚类算法 15 272 70.36 K-means算法 8 241 79.62 DBSCAN算法 12 399 89.37 层次聚类算法 14 208 62.53 
下载: 导出CSV
表 2 部分船舶动态群组特征
Table 2. Characteristics of partial ship dynamic clusters
群组编号 U X Q J H 群组风险值 7 4 0.80 0.91 1.00 1.50 0.91 6 6 0.74 0.74 1.00 0.50 0.82 8 8 0.37 0.87 1.00 1.00 0.75 4 8 0.24 0.75 0.89 3.56 0.63 1 5 0.16 0.84 0.29 1.77 0.43
下载: 导出CSV
-
[1] CHAI Tian, WENG Jin-xian, XIONG De-qi. Development of a quantitative risk assessment model for ship collisions in fairways[J]. Safety Science, 2017, 91: 71-83. doi: 10.1016/j.ssci.2016.07.018 [2] FANG Zhi-xiang, YU Hong-chu, KE Ran-xuan, et al. Automatic identification system-based approach for assessing the near-miss collision risk dynamics of ships in ports[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(2): 534-543. doi: 10.1109/TITS.2018.2816122 [3] CAI Ming-you, ZHANG Jin-fen, ZHANG Di, et al. Collision risk analysis on ferry ships in Jiangsu Section of the Yangtze River based on AIS data[J]. Reliability Engineering and System Safety, 2021, 215: 107901. doi: 10.1016/j.ress.2021.107901 [4] 雷进宇, 初秀民, 蒋仲廉, 等. 基于可视分析的船舶航行态势感知系统设计[J]. 中国航海, 2018, 41(3): 47-52. doi: 10.3969/j.issn.1000-4653.2018.03.010LEI Jin-yu, CHU Xiu-min, JIANG Zhong-lian, et al. Situation awareness system for vessel navigation based on visual analytics[J]. Navigation of China, 2018, 41(3): 47-52. doi: 10.3969/j.issn.1000-4653.2018.03.010 [5] CHEN Peng-fei, HUANG Ya-min, MOU Jun-min, et al. Probabilistic risk analysis for ship-ship collision: state-of-the-art[J]. Safety Science, 2019, 117: 108-122. doi: 10.1016/j.ssci.2019.04.014 [6] HUANG Ya-min, CHEN Lin-yin, CHEN Peng-fei, et al. Ship collision avoidance methods: state-of-the-art[J]. Safety Science, 2020, 121: 451-473. doi: 10.1016/j.ssci.2019.09.018 [7] DU Lei, GOERLANDT F, KUJALA P. Review and analysis of methods for assessing maritime waterway risk based on non-accident critical events detected from AIS data[J]. Reliability Engineering and System Safety, 2020, 200: 106933. doi: 10.1016/j.ress.2020.106933 [8] GOERLANDT F, MONTEWKA J. Maritime transportation risk analysis: review and analysis in light of some foundational issues[J]. Reliability Engineering and System Safety, 2015, 138: 115-134. doi: 10.1016/j.ress.2015.01.025 [9] CHEN Peng-fei, HUANG Ya-min, MOU Jun-min, et al. Ship collision candidate detection method: a velocity obstacle approach[J]. Ocean Engineering, 2018, 170: 186-198. doi: 10.1016/j.oceaneng.2018.10.023 [10] DEBNATH A K, CHIN H C. Navigational traffic conflict technique: a proactive approach to quantitative measurement of collision risks in port waters[J]. The Journal of Navigation, 2010, 63(1): 137-152. doi: 10.1017/S0373463309990233 [11] 朱清华, 胡甚平, 吴建军, 等. 基于情景反演的船舶追越碰撞风险推理方法[J]. 中国航海, 2023, 46(3): 29-35. doi: 10.3969/j.issn.1000-4653.2023.03.005ZHU Qing-hua, HU Shen-ping, WU Jian-jun, et al. Inference method for overtaking-related collision risk analysis based on accident scenario inversion[J]. Navigation of China, 2023, 46(3): 29-35. doi: 10.3969/j.issn.1000-4653.2023.03.005 [12] LIU Zhao, ZHANG Bo-yuan, ZHANG Ming-yang, et al. A quantitative method for the analysis of ship collision risk using AIS data[J]. Ocean Engineering, 2023, 272: 113906. [13] LIU Ke-zhong, WU Xiao-lie, ZHOU Yang, et al. A conflict cluster-based method for collision avoidance decision-making in multi-ship encounter situations[J]. Ocean Engineering, 2023, 288: 116038. doi: 10.1016/j.oceaneng.2023.116038 [14] WANG Miao-miao, WANG Yan-fu, CUI Er-hua, et al. A novel multi-ship collision probability estimation method considering data-driven quantification of trajectory uncertainty[J]. Ocean Engineering, 2023, 272: 113825. [15] XIN Xu-ri, YANG Zai-li, LIU Ke-zhong, et al. Multi-stage and multi-topology analysis of ship traffic complexity for probabilistic collision detection[J]. Expert Systems with Applications, 2023, 213: 118890. [16] KUNDAKÇI B, NAS S, GUCMA L. Prediction of ship domain on coastal waters by using AIS data[J]. Ocean Engineering, 2023, 273: 113921. doi: 10.1016/j.oceaneng.2023.113921 [17] SUI Bo-wen, ZHANG Jian-qiang, LIU Zhong. A real-time ship encounter collision risk detection approach in close-quarters situation[J]. Measurement and Control, 2023, 56(9/10): 1613-1625. [18] LIU Zi-hao, WU Zhao-lin, ZHENG Zhong-yi. A cooperative game approach for assessing the collision risk in multi-vessel encountering[J]. Ocean Engineering, 2019, 187: 106175. doi: 10.1016/j.oceaneng.2019.106175 [19] ZHEN Rong, SHI Zi-qiang, SHAO Zhe-ping, et al. A novel regional collision risk assessment method considering aggregation density under multi-ship encounter situations[J]. The Journal of Navigation, 2022, 75(1): 76-94. doi: 10.1017/S0373463321000849 [20] WEN Yuan-qiao, HUANG Ya-min, ZHOU Chun-hui, et al. Modelling of marine traffic flow complexity[J]. Ocean Engineering, 2015, 104: 500-510. doi: 10.1016/j.oceaneng.2015.04.051 [21] ZHANG Fan, LIU Yi-hao, DU Lei, et al. A rule-based maritime traffic situation complex network approach for enhancing situation awareness of vessel traffic service operators[J]. Ocean Engineering, 2023, 284: 115203. doi: 10.1016/j.oceaneng.2023.115203 [22] SUI Zhong-yi, WEN Yuan-qiao, HUANG Ya-min, et al. Empirical analysis of complex network for marine traffic situation[J]. Ocean Engineering, 2020, 214: 107848. doi: 10.1016/j.oceaneng.2020.107848 [23] LIU Zi-hao, WU Zhao-lin, ZHENG Zhong-yi. A molecular dynamics approach for modeling the geographical distribution of ship collision risk[J]. Ocean Engineering, 2020, 217: 107991. [24] LUONG T N, HWANG S, IM N. Harbour Traffic Hazard Map for real-time assessing waterway risk using Marine Traffic Hazard Index[J]. Ocean Engineering, 2021, 239: 109884. doi: 10.1016/j.oceaneng.2021.109884 [25] ZHEN R, RIVERIRO M, JIN Y X. A novel analytic framework of real-time multi-vessel collision risk assessment for maritime traffic surveillance[J]. Ocean Engineering, 2017, 145: 492-501. doi: 10.1016/j.oceaneng.2017.09.015 [26] TONG Yan-ting, ZHEN Rong, DONG Han, et al. Identifying influential ships in multi-ship encounter situation complex network based on improved WVoteRank approach[J]. Ocean Engineering, 2023, 284: 115192. doi: 10.1016/j.oceaneng.2023.115192 [27] ZHEN Rong, SHI Zi-qiang, LIU Jia-lun, et al. A novel arena-based regional collision risk assessment method of multi-ship encounter situation in complex waters[J]. Ocean Engineering, 2022, 246: 110531. doi: 10.1016/j.oceaneng.2022.110531 [28] VU D T, JEONG J Y. Collision risk assessment by using hierarchical clustering method and real-time data[J]. Journal of the Korean Society of Marine Environment and Safety, 2021, 27(4): 483-491. doi: 10.7837/kosomes.2021.27.4.483 [29] ORUC M F, ALTAN Y C. Risky maritime encounter patterns via clustering[J]. Journal of Marine Science and Engineering, 2023, 11(5): 11050950. [30] PAVLIDIS T, ALI F. Computer recognition of handwritten numerals by polygonal approximations[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1975, 5(6): 610-614. [31] 李俊杰, 刘鹏程, 顿玉多吉. 基于步行轨迹的复杂道路中心线提取方法[J]. 华中师范大学学报(自然科学版), 2020, 54(1): 89-95.LI Jun-jie, LIU Peng-cheng, DUNYU Duo-ji. Method to extract the center line of a complex road based on walking trajectory[J]. Journal of Central China Normal University (Natural Sciences), 2020, 54(1): 89-95. [32] 胡景峰, 郝江凌, 童晨涛. 电子海图中船位推算算法的实现[J]. 大连海事大学学报, 2005, 31(4): 24-26.HU Jing-feng, HAO Jiang-ling, TONG Chen-tao. Research on calculated reckoning in ECDIS[J]. Journal of Dalian Maritime University, 2005, 31(4): 24-26. [33] MOU Jun-min, 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. [34] JIANG Xu-rui, WEN Xiang-xi, WU Ming-gong, et al. A complex network analysis approach for identifying air traffic congestion based on independent component analysis[J]. Physica A: Statistical Mechanics and Its Applications, 2019, 523: 364-381. [35] LIU Hong-lu, TIAN Zhi-hong, HUANG An-qiang, et al. Analysis of vulnerabilities in maritime supply chains[J]. Reliability Engineering and System Safety, 2018, 169: 475-484. [36] SHI J B, MALIK J. Normalized cuts and image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(8): 888-905. [37] 殷辰堃, 方茹, 李拓. 基于交通流时间序列相似性的NCut城市路网分区算法[J]. 交通运输工程学报, 2021, 21(5): 238-250. doi: 10.19818/j.cnki.1671-1637.2021.05.020YIN Chen-kun, FANG Ru, LI Tuo. NCut partitioning algorithm for urban road networks based on similarity of traffic flow time series[J]. Journal of Traffic and Transportation Engineering, 2021, 21(5): 238-250. doi: 10.19818/j.cnki.1671-1637.2021.05.020 [38] BACH F R, JORDAN M I. Learning spectral clustering, with application to speech separation[J]. Journal of Machine Learning Research, 2006, 7: 1963-2001. [39] BIAN Tian, HU Jian-tao, DENG Yong. Identifying influential nodes in complex networks based on AHP[J]. Physica A: Statistical Mechanics and Its Applications, 2017, 479: 422-436. [40] DU Yu-xian, GAO Cai, HU Yong, et al. A new method of identifying influential nodes in complex networks based on TOPSIS[J]. Physica A: Statistical Mechanics and Its Applications, 2014, 399: 57-69. [41] PARAND F A, RAHIMI H, GORZIN M. Combining fuzzy logic and eigenvector centrality measure in social network analysis[J]. Physica A: Statistical Mechanics and Its Applications, 2016, 459: 24-31. [42] WEN Xiang-xi, TU Cong-liang, WU Ming-gong, et al. Fast ranking nodes importance in complex networks based on LS-SVM method[J]. Physica A: Statistical Mechanics and Its Applications, 2018, 506: 11-23. [43] FRIEDMAN J H, TUKEY J W. A projection pursuit algorithm for exploratory data analysis[J]. IEEE Transactions on Computers, 1974, 23(9): 881-890. [44] MIRJALILI S. Moth-flame optimization algorithm: a novel nature-inspired heuristic paradigm[J]. Knowledge-Based Systems, 2015, 89: 228-249. -
点击查看大图
图(18) / 表(2)
计量
- 文章访问数: 20
- HTML全文浏览量: 37
- PDF下载量: 7
- 被引次数: 0
