以避免船舶AIS数据内噪声对船舶流量检测干扰，准确、实时实现船舶流量智能交通检测，设计船舶流量智能交通检测系统。采集模块采集海上航线船舶AIS数据，使用逻辑分析模块内的船舶交通流状态空间模型，获取当前海上航线船舶交通流空间状态，卡尔曼滤波算法将上一个航线船舶交通流空间状态作为观测向量，同时抑制船舶交通流空间状态观测向量内干扰噪声，建立船舶流量智能交通检测模型，不断更新海上航线船舶流量空间状态转移矩阵，推理当前时刻船舶交通流量空间状态，得到船舶流量智能交通检测结果。实验表明，该方法具备较强的船舶AIS数据获取能力，可准确获得海上航线船舶流量状态，并有效检测不同时刻船舶流量，应用效果较好。
To avoid interference from noise in ship AIS data on ship flow detection, and to achieve accurate and real-time intelligent traffic detection of ship flow, a ship flow intelligent traffic detection system is designed. The collection module collects AIS data of ships on sea routes, uses the ship traffic flow state space model in the logic analysis module to obtain the current ship traffic flow spatial state on sea routes. The Kalman filtering algorithm takes the previous ship traffic flow spatial state as the observation vector, while suppressing the interference noise in the ship traffic flow spatial state observation vector, establishes an intelligent traffic detection model for ship flow, continuously updates the ship traffic flow spatial state transition matrix on sea routes, infers the current ship traffic flow spatial state, and obtains the intelligent traffic detection result for ship flow. The experiment shows that this method has strong ability to obtain ship AIS data, accurately obtain the flow status of ships on the sea route, and effectively detect the flow of ships at different times. The application effect is good.
2024,46(17): 158-161 收稿日期：2024-3-27
DOI：10.3404/j.issn.1672-7649.2024.17.028
分类号：TP391
作者简介：王志宽(1976-),男,硕士,助理研究员,研究方向为交通运输管理
参考文献：
[1] 李振福, 彭世杰, 刘坤, 等. 北极东北航线船舶交通流时空特征分析[J]. 地域研究与开发, 2022, 41(5): 43-49.
LI Zhenfu, PENG Shijie, LIU Kun, et al. Analysis of spatial-temporal characteristics of ship traffic flow on arctic northeast route[J]. Areal Research and Development, 2022, 41(5): 43-49.
[2] 韩成浩, 马吉林, 刘佳仑, 等. 基于虚拟仿真测试平台的船舶智能航行系统设计及应用[J]. 中国航海, 2023, 46(1): 148-154.
HAN Chenghao, MA Jilin, LIU Jialun, et al. Virtual test platform in design and application of intelligent navigation system[J]. Navigation of China, 2023, 46(1): 148-154.
[3] 孙瑀隆, 郑建风, 韩佳轩, 等. 面向宽窄交替航道的船舶交通元胞自动机模型[J]. 系统仿真学报, 2023, 35(11): 2419-2428.
SUN Yulong, ZHENG Jianfeng, HAN Jiaxuan, et al. A cellular automata model for simulating ships passing through waterways with alternating wide and narrow sections[J]. Journal of System Simulation, 2023, 35(11): 2419-2428.
[4] 齐绪存, 黄常海, 沈佳, 等. 复合潮汐信息的感潮河段船舶交通流滚动预测模型[J]. 上海海事大学学报, 2022, 43(4): 37-43,82.
QI Xucun, HUANG Changhai, SHEN Jia, et al. A rolling prediction model of ship traffic flow in tidal reaches combined with tidal information[J]. Journal of Shanghai Maritime University, 2022, 43(4): 37-43,82.
[5] 刘敬贤, 高广旭, 刘奕, 等. 基于卷积神经网络及长短时记忆网络的短时船舶交通流量预测[J]. 中国航海, 2022, 45(2): 56-61,68.
LIU Jingxian, GAO Guangxu, LIU Yi, et al. Short-term water traffic flow prediction with convolutional neural network and long short-term memory network[J]. Navigation of China, 2022, 45(2): 56-61,68.
[6] 周翔宇, 吉哲, 王凤武. 基于EEMD-PE-LSTM的短时船舶交通流量预测与航道交通状态可视化[J]. 大连海事大学学报, 2023, 49(2): 58-68.
ZHOU Xiangyu, JI Zhe, WANG Fengwu. Short-term ship traffic flow prediction based on EEMD-PE-LSTM and visualization of channel traffic state[J]. Journal of Dalian Maritime University, 2023, 49(2): 58-68.
