以充分掌握船舶航行动态为目的,设计基于数据挖掘的船舶航迹自动识别系统。该系统使用跟踪监控单元内的海事雷达和船载单片机监控终端获取船舶航行数据后,利用无线通信单元内的无线传感器、网络协调器等设备将船舶航行数据发送至数据存储与集成单元;利用该单元对船舶航行数据进行打包分发、在线压缩和存储等处理。航迹识别单元从数据存储与集成单元内调取压缩存储的船舶航行数据,并对其进行区域航迹提取、坐标转换和时间校准后,再利用基于数据挖掘的轨迹融合方法完成其航迹识别,然后将识别结果发送至展示单元呈现给用户。实验结果表明:该系统在应用过程中其运行稳定性接近99.5%,并且具备良好的通信传输能力;也可在船舶航迹复杂交错和存在其他船舶干扰情况下有效识别目标船舶航迹,应用效果显著。
In order to fully grasp the ship navigation dynamics, an automatic ship track identification system based on data mining is designed. The system uses the maritime radar in the tracking and monitoring unit and the ship borne single chip microcomputer monitoring terminal to obtain the ship navigation data, and then uses the wireless sensor, network coordinator and other equipment in the wireless communication unit to send the ship navigation data to the data storage and integration unit. The shipping data is compressed, packaged and distributed online by the unit. The track identification unit retrieves the compressed and stored ship navigation data from the data storage and integration unit, extracts the regional track, coordinates conversion and time calibration, and then completes its track identification by using the track fusion method based on data mining, and then presents the identification results to the user. The experimental results show that the program stability of the system is close to 99.5% and has good communication transmission ability. It can also effectively identify the target ship track in the case of complex and staggered ship tracks and other ship interference, and the application effect is remarkable.
2022,44(10): 151-154 收稿日期:2021-12-14
DOI:10.3404/j.issn.1672-7649.2022.10.032
分类号:U675
基金项目:浙江省教育厅一般项目 (Y202146585)
作者简介:常青丽(1983-),女,硕士,讲师,研究方向为产业经济学(航运与物流)、交通运输规划与管理
参考文献:
[1] 鄢博冉, 高大为, 朱永生, 等. 基于低信噪比AIS数据的船舶航迹精准预测[J]. 船舶工程, 2021, 43(10): 111–117
[2] 游兰, 韩雪薇, 何正伟, 等. 基于改进Seq2Seq的短时AIS轨迹序列预测模型[J]. 计算机科学, 2020, 47(9): 169–174
[3] 王颢程, 左毅, 李铁山, 等. 基于宽度学习系统的内河航道船舶轨迹分类算法[J]. 上海海事大学学报, 2021, 42(3): 91–100
[4] 刘文, 汪文博. 基于秩最小化矩阵去噪的船舶轨迹重构方法[J]. 交通运输系统工程与信息, 2022, 22(1): 106–114
[5] 姜佰辰, 关键, 周伟, 等. 基于多项式卡尔曼滤波的船舶轨迹预测算法[J]. 信号处理, 2019, 35(5): 741–746
[6] 徐垚, 李卓然, 孟金龙, 等. 基于大规模船舶轨迹数据的航道边界提取方法[J]. 计算机应用, 2019, 39(1): 105–112
[7] 胡明月, 于双和, 李云云, 等. 基于指令滤波的全状态约束海洋水面船舶有限时间轨迹跟踪控制[J]. 南京理工大学学报(自然科学版), 2021, 45(3): 271–280
[8] 凡甲甲, 祁云嵩, 葛霓琳. 基于改进BP神经网络的船舶轨迹识别方法[J]. 计算机工程与设计, 2019, 40(12): 3639–3644
[9] 郑振涛, 赵卓峰, 王桂玲, 等. 面向港口停留区域识别的船舶停留轨迹提取方法[J]. 计算机应用, 2019, 39(1): 113–117