针对风速传感器在恶劣天气条件下因信号干扰或数据丢失导致测量偏差，从而影响风险预测准确性的问题，提出一种恶劣天气条件下船舶航行安全风险预警方法。首先，分析恶劣天气环境因素对船舶航行安全的影响，并采集相关数据；其次，基于XGBoost算法构建风险预测模型，预测船舶航行风险情况；最后，利用加权平均法计算船舶航行安全风险预警分数值，划分风险等级并进行预警。测试结果表明，本文方法在恶劣天气条件下具有显著优势，能够依据天气条件数据准确获取安全风险预警分数值，预警结果的分散度熵低于0.1，显著优于对比方法。说明本文方法能够有效提升恶劣天气条件下船舶航行安全风险预警的准确性和可靠性，为船舶航行安全提供及时有效指导。
A ship navigation safety risk warning method under adverse weather conditions is proposed to address the issue of measurement deviation caused by signal interference or data loss in wind speed sensors, which affects the accuracy of risk prediction. Firstly, analyze the impact of adverse weather conditions on ship navigation safety and collect relevant data; Secondly, a risk prediction model based on XGBoost algorithm is constructed to predict the risk situation of ship navigation; Finally, the weighted average method is used to calculate the score of ship navigation safety risk warning, classify the risk level, and issue warnings. The test results show that the proposed method has significant advantages under adverse weather conditions, and can accurately obtain safety risk warning scores based on weather condition data. The dispersion entropy of the warning results is less than 0.1, which is significantly better than the comparative methods. This method can effectively improve the accuracy and reliability of ship navigation safety risk warning under adverse weather conditions, providing timely and effective guidance for ship navigation safety.
2025,47(11): 180-184 收稿日期：2025-1-24
DOI：10.3404/j.issn.1672-7649.2025.11.032
分类号：U692
基金项目：九江市2025年度市级重点研发计划—研发投入专项（2025_001129）
作者简介：张伟(1990-),男,硕士,副教授,研究方向为航海安全保障、航运运营优化
参考文献：
[1] 张笛, 韩吉如, 吴达, 等. 基于人工势能场的破冰船护航下船舶航行风险场建模[J]. 哈尔滨工程大学学报, 2024, 45(1): 119-128.
ZHANG D, HAN J R, WU D, et al. Modeling of ship navigation risk field for the icebreaker escort operations based on an artificial potential field[J]. Journal of Harbin Engineering University, 2024, 45(1): 119-128.
[2] 范存龙, 张笛, 翁金贤, 等. 远程控制船舶内河航行风险评价研究[J]. 安全与环境学报, 2024, 24(1): 72-83.
FAN C L, ZHANG D, WENG J X, et al. Quantitative risk assessment on the remote control ship navigation in inland waterway[J]. Journal of Safety and Environment, 2024, 24(1): 72-83.
[3] 张文君, 张英俊, 张闯. 基于HHM-RFRM理论的智能船舶航行风险识别与筛选[J]. 安全与环境学报, 2023, 23(2): 333-340.
ZHANG W J, ZHANG Y J, ZHANG C. Intelligent ship navigation risk identification and screening based on HHM-RFRM method[J]. Journal of Safety and Environment, 2023, 23(2): 333-340.
[4] 杜晓雨, 胡甚平, 李圣媛, 等. 船舶会遇过程碰撞风险演化随机Petri网模型[J]. 上海海事大学学报, 2023, 44(4): 25-32+98.
DU X Y, HU S P, LI S Y, et al. Evolution model on risk of collision in process of ship encoutering using stochastic Petri net[J]. Journal of Shanghai Maritime University, 2023, 44(4): 25-32+98.
[5] 徐东星, 尹建川, 孙珽. 大型船舶会船区碰撞风险的灰色评判模型[J]. 中国航海, 2023, 46(3): 1-8.
XU D X, YIN J C, SUN T. Grey model for evaluating collision risks in a meeting area for large ships[J]. Navigation of China, 2023, 46(3): 1-8.
[6] 陈信强, 史飞翔, 王梓创, 等. 基于模糊逻辑方法的多船会遇安全态势评估[J]. 广西大学学报(自然科学版), 2022, 47(5): 1327-1336.
CHEN X Q, SHI F X, WANG Z C, et al. Safety evaluation of multi-ship encountering situation via fuzzy logic model[J]. Journal of Guangxi University(Natural Science Edition), 2022, 47(5): 1327-1336.
[7] 张新宇, 姚沅辛, 齐壮, 等. 基于改进DBSCAN算法的受限航道船舶会遇规律挖掘研究[J]. 重庆交通大学学报(自然科学版), 2023, 42(6): 84-92.
ZHANG X Y, YAO Y X, QI Z, et al. Mining the rules of ships encountering in restricted channel based on improved DBSCAN algorithm[J]. Journal of Chongqing Jiaotong University (Natural Sciences), 2023, 42(6): 84-92.
[8] 王永亮, 李超, 许恩永, 等. 基于XGBoost算法的商用车驾驶风险辨识模型[J]. 机械设计与制造, 2024, 40(8): 84-89,95.
WANG Y L, LI C, XU E Y, et al. Commercial vehicle driving risk recognition model based on XGBoost algorithm[J]. Machinery Design & Manufacture, 2024, 40(8): 84-89, 95.
