一种并行LSTM-FCN模型在船舶航迹预测中的应用
CSTR:
作者:
作者单位:

1. 中国科学院国家空间科学中心 复杂航天系统电子信息技术重点实验室,北京 100190;2. 中国科学院大学, $ $北京 100049;3. 中科天智运控科技有限公司,深圳 518052;4. 国防科技大学 系统工程学院,长沙 410073

作者简介:

通讯作者:

E-mail: mengxin@nssc.ac.cn.

中图分类号:

TP183

基金项目:


Parallel LSTM-FCN model applied to vessel trajectory prediction
Author:
Affiliation:

1. Key Laboratory of Electronics and Information Technology for Space Systems,National Space Science Center,Chinese Academy of Sciences,Beijing 100190,China;2. University of Chinese Academy of Sciences,Beijing 100049,China;3. Zhong Ke Tian Zhi Operation Control Technology Company,Shenzhen 518052 China;4. College of Systems Engineering,National University of Defense Technology,Changsha 410073,China

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    航迹预测是保障船舶航行安全、提高海洋交通管制效能、高效搜索海面目标的关键技术.为提高船舶航迹预测精确度,针对航迹特征多维度的特点,提出一种并行LSTM-FCN(parallel LSTM-FCN,PLSTM-FCN)模型.该模型有效结合LSTM模型对时间序列数据长期趋势预测的优势和全卷积网络(FCN)模型擅于提取时间序列数据细节变化规律的特点,通过并行结构设计保证相同训练效率下提取特征参数翻倍,实现较高精确度的高维航迹数据特征提取和趋势预测.基于动态时间规整算法和拉依达准则的船舶历史航迹数据预处理方法,可提高PLSTM-FCN模型从不同类型船舶历史航迹中深度学习航行趋势和转弯细节的效率.基于船舶自动识别系统(AIS)数据的仿真实验结果表明,PLSTM-FCN模型对多维特征船舶航迹预测的精确度明显优于传统循环神经网络.

    Abstract:

    Trajectory prediction is very important to navigation safety, marine traffic control and surface vessels search. In order to improve the accuracy of vessel trajectory prediciton and according to the multi-dimensional characteristics of vessel trajectory features, a new model named parallel LSTM-FCN(PLSTM-FCN) is proposed. The model can exact features and trend from multi-dimensional vessel trajectory, because of combining with the LSTM which has advanced to predict time series trend and the fully convolutional networks(FCN) which is adept in exacting detail features of time series. Simultaneously, the training efficiency of the PLSTM-FCN which has more parameters is the same as the LSTM-FCN, because of the concurrent design. In order to improve the learning efficiency, a preprocessing method based on the dynamic time warping algorithm and the Laida criterion is proposed. The simulation experiment is carried out based on the data of automatic identification systems(AIS). Experimental results show that the PLSTM-FCN is more accurate than the typical RNN in vessel trajectory prediction.

    参考文献
    相似文献
    引证文献
引用本文

胡丹,孟新,路帅,等.一种并行LSTM-FCN模型在船舶航迹预测中的应用[J].控制与决策,2022,37(8):1955-1961

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2022-06-29
  • 出版日期: 2022-08-20
文章二维码