基于改进贝叶斯网络的海盗袭击风险评价模型

A risk assessment model for pirate attacks based on an improved Bayesian network

摘要

海盗袭击严重威胁海运安全，准确的风险评价对航线规划与应急决策至关重要。为科学评价海盗袭击风险，本文提出了一种基于改进贝叶斯网络的海盗袭击风险评价模型。为解决传统模型对连续型数据易进行不合理划分的缺陷，本文引入了Fisher最优分割算法，提升了贝叶斯网络模型节点状态设定的准确性和科学性。在完成样本筛选和节点状态设定优化的基础上，采用期望最大化算法（EM）进行贝叶斯网络参数学习。同时，通过改进的树形结构学习算法有效降低了模型结构学习的复杂性。研究结果表明，与传统贝叶斯网络模型相比，本模型的预测准确率提高了5.44%，结构学习任务的复杂性降低了21.43%。此外，本文模型的预测准确率比随机森林模型和反向传播（BP）神经网络模型分别提升了1.23%和2.83%。本文模型可为海盗袭击风险的科学预测提供有力支持。

Abstract

Pirate attacks pose a serious threat to maritime shipping security. An accurate risk assessment model is critical for route planning and emergency decision-making. To scientifically assess piracy risks, a pirate attack risk assessment model based on an improved Bayesian network was proposed in this study. The Fisher optimal segmentation algorithm was introduced to enhance the model’s node-state settings, classification accuracy and scientific validity. Based on the screened samples and node-state settings, the expectation-maximization (EM) algorithm was used for Bayesian network parameter learning. Meanwhile, an improved tree structure learning algorithm was adopted to reduce the complexity of model structure learning. The proposed model improves prediction accuracy by 5.44% compared with the traditional Bayesian networks while reducing structure learning complexity by 21.43%. In addition, compared with random forest and back propagation (BP) neural network models, it achieves improvements of 1.23% and 2.83% in prediction accuracy, respectively. This study provides robust decision support for the scientific prediction of piracy risks.

关键词

水路运输 / 风险评价 / 贝叶斯网络 / 海盗袭击 / 海上通道安全

Key words

waterway transportation / risk assessment / Bayesian network / pirate attacks / maritime sea lanes safety

参考文献

[1] FAN H W, YANG Z L. A novel risk assessment framework for piracy threats: mapping system theoretic process analysis and complex network into Bayesian networks[J]. Reliability Engineering & System Safety, 2026, 272: 112686.

[2] 吕靖, 齐海迪, 李宝德. 基于扩展置信规则库的海盗袭击事件风险预测[J]. 交通运输系统工程与信息, 2022, 22(3): 247-254.

[3] LV J, QI H D, LI B D. Extended belief rule based system for risk prediction of pirate attacks[J]. Journal of Transportation Systems Engineering and Information Technology, 2022, 22(3): 247-254. (in Chinese)

[4] FAN H W, LU J, CHANG Z. A risk-based game theory model of navy and pirate behaviors[J]. Ocean & Coastal Management, 2022, 225: 106200.

[5] LIANG M H, LI H H, LIU R W, et al. Piracy analyzer: spatial temporal patterns analysis of global piracy incidents[J]. Reliability Engineering & System Safety, 2024, 243: 109877.

[6] 李杰, 曾叙砜, 王雪琰, 等. 重点船型受海盗袭击的时空特征挖掘[J]. 安全与环境学报, 2020, 20(3): 1034-1041.

[7] LI J, ZENG X F, WANG X Y, et al. Spatio-temporal analysis of the global piracy attack over the main types of ships[J]. Journal of Safety and Environment, 2020, 20(3): 1034-1041. (in Chinese)

[8] 孙茂金, 吕靖, 高天航, 等. 海盗袭击事件预警模型[J]. 大连海事大学学报, 2018, 44(3): 28-32.

[9] SUN M J, LV J, GAO T H, et al. An early warning model for pirate attacks[J]. Journal of Dalian Maritime University, 2018, 44(3): 28-32. (in Chinese)

[10] 吕靖, 王佳鑫, 范瀚文. 海运通道韧性评价与关键因素识别[J]. 重庆交通大学学报(自然科学版), 2025, 44(1): 86-95.

[11] LÜ J, WANG J X, FAN H W. Resilience evaluation and key factors identification of sea lanes[J]. Journal of Chongqing Jiaotong University (Natural Sciences), 2025, 44(1): 86-95. (in Chinese)

[12] WANG L K, YANG Z L. Bayesian network modelling and analysis of accident severity in waterborne transportation: a case study in China[J]. Reliability Engineering & System Safety, 2018, 180: 277-289.

[13] FU S S, ZHANG Y, ZHANG M Y, et al. An object-oriented Bayesian network model for the quantitative risk assessment of navigational accidents in ice-covered Arctic waters[J]. Reliability Engineering & System Safety, 2023, 238: 109459.

[14] YANG Z S, WAN C P, YU Q, et al. A machine learning-based Bayesian model for predicting the duration of ship detention in PSC inspection[J]. Transportation Research Part E: Logistics and Transportation Review, 2023, 180: 103331.

[15] 田延飞, 乔慧, 滑林, 等. 海上船舶碰撞贝叶斯网络模型及其应用[J]. 海军工程大学学报, 2023, 35(6): 28-33.

[16] TIAN Y F, QIAO H, HUA L, et al. Bayesian network model for ship collisions at sea and its applications[J]. Journal of Naval University of Engineering, 2023, 35(6): 28-33. (in Chinese)

[17] LI H H, REN X J, YANG Z L. Data-driven Bayesian network for risk analysis of global maritime accidents[J]. Reliability Engineering & System Safety, 2023, 230: 108938.

[18] WANG J X, FAN H W, CHANG Z, et al. Unleashing data power: driving maritime risk analysis with Bayesian networks[J]. Reliability Engineering & System Safety, 2025, 264: 111310.

[19] FAN H W, WANG J X, CHANG Z, et al. Embracing imperfect data: a novel data-driven Bayesian network framework for maritime accidents severity risk assessment[J]. Ocean Engineering, 2025, 329: 121212.

[20] 陈映彬, 季盛, 董国祥, 等. 基于半机理模型与Fisher最优分割的航速优化研究[J]. 舰船科学技术, 2026, 48(1): 165-173.

[21] CHEN Y B, JI S, DONG G X, et al. Research on speed optimization based on FISHER optimal segmentation and semi-mechanism model[J]. Ship Science and Technology, 2026, 48(1): 165-173. (in Chinese)

[22] 李登辉, 彭其渊, 鲁工圆, 等. 城市轨道交通高峰线路客流协同控制方法[J]. 交通运输系统工程与信息, 2019, 19(6): 141-147.

[23] LI D H, PENG Q Y, LU G Y, et al. Control method for passenger inflow control with coordination on urban rail transit line in peak hours[J]. Journal of Transportation Systems Engineering and Information Technology, 2019, 19(6): 141-147. (in Chinese)

[24] 欧阳艳敏, 王长峰, 刘柳, 等. 基于改进自适应最优分割法的风险预警区间模型研究: 针对重大突发公共卫生事件[J]. 中国管理科学, 2022, 30(11): 196-206.

[25] OUYANG Y M, WANG C F, LIU L, et al. Study on the risk early warning interval model based on improved adaptive optimal partition method: large-scale public health emergency[J]. Chinese Journal of Management Science, 2022, 30(11): 196-206. (in Chinese)

[26] FAN H W, CHANG Z, JIA H Y, et al. How do navy escorts influence piracy risk in East Africa? A Bayesian network approach[J]. Risk Analysis, 2024, 44(9): 2025-2045.

[27] 范瀚文, 吕靖, 常征, 等. 海盗袭击风险评估与反海盗应对策略评价[J]. 上海海事大学学报, 2024, 45(2): 83-88.

[28] FAN H W, LYU J, CHANG Z, et al. Pirate attack risk assessment and anti-piracy response strategy evaluation[J]. Journal of Shanghai Maritime University, 2024, 45(2): 83-88. (in Chinese)

[29] MUNIM H Z, SØRLI A M, KIM H, et al. Predicting maritime accident risk using automated machine learning[J]. Reliability Engineering & System Safety, 2024, 248: 110148.

[30] LU J, SU W, JIANG M Z, et al. Severity prediction and risk assessment for non-traditional safety events in sea lanes based on a random forest approach[J]. Ocean & Coastal Management, 2022, 225: 106202.

[31] WANG J X, FAN H W, WU Z M, et al. Navigating straits/canals safety: a data-driven Copula Bayesian network risk assessment framework[J]. Reliability Engineering & System Safety, 2026, 270: 112157.

基金资助

国家自然科学基金面上项目(71974023)

国家社会科学基金重大项目(19VHQ012)