船舶自动识别系统数据修复和预测算法研究
|
摘要
针对船舶AIS数据丢失或错误等问题,本文借助分段三次Hermite插值实现AIS数据初步修复或预测,建立神经网络训练集和测试集,开展单点和连续多点AIS数据修复和预测;对比分析了BP神经网络与三次样条插值、分段三次Hermite插值方法以及组合算法在船舶AIS数据修复和预测中的精度。以重庆弯曲河段和武汉顺直河段为例,分析了航道平面形态、算法组合等对于船舶AIS数据修复和预测精度的影响。结果表明:联合算法有效提升了船舶AIS数据修复精度;在船舶AIS预测中,神经网络模型表现最优。研究成果可为船舶行为特征分析、建模等相关领域的研究提供借鉴。
We established models for single-point and continuous multipoint automatic identification system(AIS) data restoration and prediction on the basis of the training and testing sets of the BP neural network and the piecewise cubic Hermite interpolation to resolve AIS data loss or error. The precisions of the BP neural network, traditional cubic spline interpolation, piecewise cubic Hermite interpolation and combinecl algorithm in ship AIS data restoration and prediction were compared. Finally, the Chongqing and Wuhan Waterways were investigated in case studies. The influence of river configuration and algorithm combinations on the accuracy of AIS data restoration and prediction models was analyzed. Results indicated that the data repairing accuracy of the combined algorithm is dramatically improved, and the neural network model demonstrated the best AIS data prediction performance. Results can provide references to research on ship behavior characteristic analysis, modeling, and other related fields.
We established models for single-point and continuous multipoint automatic identification system(AIS) data restoration and prediction on the basis of the training and testing sets of the BP neural network and the piecewise cubic Hermite interpolation to resolve AIS data loss or error. The precisions of the BP neural network, traditional cubic spline interpolation, piecewise cubic Hermite interpolation and combinecl algorithm in ship AIS data restoration and prediction were compared. Finally, the Chongqing and Wuhan Waterways were investigated in case studies. The influence of river configuration and algorithm combinations on the accuracy of AIS data restoration and prediction models was analyzed. Results indicated that the data repairing accuracy of the combined algorithm is dramatically improved, and the neural network model demonstrated the best AIS data prediction performance. Results can provide references to research on ship behavior characteristic analysis, modeling, and other related fields.
引文
[1] 邹秋花.基于模糊综合函数的AIS与雷达信息融合研究[D].大连:大连海事大学,2013.ZOU Qiuhua.Study on AIS and radar information fusion based on fuzzy comprehensive function[D].Dalian:Dalian Maritime University,2013.
[2] 于俊逸,陈伟,刘建,等.内河航道VTS与AIS系统信息融合关键技术的研究[C]//第十三届海峡两岸智能运输系统学术研讨会论文集.成都,2013.YU Junyi,CHEN Wei,LIU Jian,et al.Research on VTS and AIS information fusion in the inland waterway[C]//The Taiwan Strait intelligent transportation systems Symposium.Chengdu,2013.
[3] 林祎珣.数据挖掘技术在海上交通特征分析中的应用研究[D].厦门:集美大学,2011.LIN Yixun.Application of data mining technology in analysis of marine traffic characteristics[D].Xiamen:JiMei University,2011.
[4] 吴青,崔建平,马枫,等.基于奥村模型的内河AIS基站监测范围研究[J].武汉理工大学学报(信息与管理工程版),2011,33(1):36-39,42.WU Qing,CUI Jianping,MA Feng,et al.Research of monitoring scope of inland ais base station based on Okumura-Hata model[J].Journal of Wuhan University of Technology (information & management engineering),2011,33(1):36-39,42.
[5] 魏冰.AIS的应用及前景展望[J].中国水运,2012,12(7):70,92.WEI Bing.AIS application and prospects[J].China water transport,2012,12(7):70,92.
[6] 童笑.基于AIS的电子海图导航系统设计与实现[D].武汉:武汉理工大学,2012.TONG Xiao.The design and implementation of electronic chart navigation system based on AIS[D].Wuhan:Wuhan University of Technology,2012.
[7] WANG Yang,ZHANG Jinfen,CHEN Xianqiao,et al.A spatial-temporal forensic analysis for inland-water ship collisions using AIS data[J].Safety science,2013,57:187-202.
[8] FIORINI M,CAPATA A,BLOISI D D.AIS data visualization for maritime spatial planning (MSP)[J].International journal of e-navigation and maritime economy,2016,5:45-60.
[9] 刘兴龙,初秀民,马枫,等.山区航道虚拟航标基站布设间距研究[J].哈尔滨工程大学学报,2016,37(3):382-387.LIU Xinglong,CHU Xiumin,MA Feng,et al.Base station spacing of virtual aids to navigation in mountain waterways[J].Journal of Harbin Engineering University,2016,37(3):382-387.
[10] 戴鹏睿.AIS轨迹动态插值在实时视景显示中的应用[J].电子设计工程,2016,24(14):172-175.DAI Pengrui.Application of AIS trajectory dynamic interpolation in real-time visual display[J].Electronic design engineering,2016,24(14):172-175.
[11] 吴建华,吴琛,刘文,等.舶舶AIS轨迹异常的自动检测与修复算法[J].中国航海,2017,40(1):8-12,101.WU Jianhua,WU Chen,LIU Wen,et al.Automatic detection and restoration algorithm for trajectory anomalies of ship AIS[J].Navigation of China,2017,40(1):8-12,101.
[12] 刘立群,吴超仲,褚端峰,等.基于Vondrak滤波和三次样条插值的船舶轨迹修复研究[J].交通信息与安全,2015,33(4):100-105.LIU Liqun,WU Chaozhong,CHU Duanfeng,et al.A study of ship trajectory restoration based on Vondrak filtering and cubic spline interpolation[J].Journal of transport information and safety,2015,33(4):100-105.
[13] NGUYEN V S,IM N K,LEE S M.The interpolation method for the missing AIS data of ship[J].Journal of navigation and port research,2015,39(5):377-384.
[14] 姚志洪,蒋阳升,韩鹏,等.基于神经网络的小时间粒度交通流预测模型[J].交通运输系统工程与信息,2017,17(1):67-73.YAO Zhihong,JIANG Yangsheng,HAN Peng,et al.Traffic flow prediction model based on neural network in small time granularity[J].Journal of transportation systems engineering and information technology,2017,17(1):67-73.
[15] 徐婷婷,柳晓鸣,杨鑫.基于BP神经网络的船舶航迹实时预测[J].大连海事大学学报,2012,38(1):9-11.XU Tingting,LIU Xiaoming,YANG Xin.BP neural network-based ship track real-time prediction[J].Journal of Dalian Maritime University,2012,38(1):9-11.
[16] 甄荣,金永兴,胡勤友,等.基于AIS信息和BP神经网络的船舶航行行为预测[J].中国航海,2017,40(2):6-10.ZHEN Rong,JIN Yongxing,HU Qinyou,et al.Vessel behavior prediction based on AIS data and BP neural network[J].Navigation of China,2017,40(2):6-10.
[17] 戴吾蛟,丁晓利,朱建军.基于观测值质量指标的GPS观测量随机模型分析[J].武汉大学学报(信息科学版),2008,33(7):718-722.DAI Wujiao,DING Xiaoli,ZHU Jianjun.Comparing GPS stochastic models based on observation quality indices[J].Geomatics and Information Science of Wuhan University,2008,33(7):718-722.
[18] GLOROT X,BENGIO Y.Understanding the difficulty of training deep feedforward neural networks[J].Journal of machine learning research,2010,9:249-256.
[2] 于俊逸,陈伟,刘建,等.内河航道VTS与AIS系统信息融合关键技术的研究[C]//第十三届海峡两岸智能运输系统学术研讨会论文集.成都,2013.YU Junyi,CHEN Wei,LIU Jian,et al.Research on VTS and AIS information fusion in the inland waterway[C]//The Taiwan Strait intelligent transportation systems Symposium.Chengdu,2013.
[3] 林祎珣.数据挖掘技术在海上交通特征分析中的应用研究[D].厦门:集美大学,2011.LIN Yixun.Application of data mining technology in analysis of marine traffic characteristics[D].Xiamen:JiMei University,2011.
[4] 吴青,崔建平,马枫,等.基于奥村模型的内河AIS基站监测范围研究[J].武汉理工大学学报(信息与管理工程版),2011,33(1):36-39,42.WU Qing,CUI Jianping,MA Feng,et al.Research of monitoring scope of inland ais base station based on Okumura-Hata model[J].Journal of Wuhan University of Technology (information & management engineering),2011,33(1):36-39,42.
[5] 魏冰.AIS的应用及前景展望[J].中国水运,2012,12(7):70,92.WEI Bing.AIS application and prospects[J].China water transport,2012,12(7):70,92.
[6] 童笑.基于AIS的电子海图导航系统设计与实现[D].武汉:武汉理工大学,2012.TONG Xiao.The design and implementation of electronic chart navigation system based on AIS[D].Wuhan:Wuhan University of Technology,2012.
[7] WANG Yang,ZHANG Jinfen,CHEN Xianqiao,et al.A spatial-temporal forensic analysis for inland-water ship collisions using AIS data[J].Safety science,2013,57:187-202.
[8] FIORINI M,CAPATA A,BLOISI D D.AIS data visualization for maritime spatial planning (MSP)[J].International journal of e-navigation and maritime economy,2016,5:45-60.
[9] 刘兴龙,初秀民,马枫,等.山区航道虚拟航标基站布设间距研究[J].哈尔滨工程大学学报,2016,37(3):382-387.LIU Xinglong,CHU Xiumin,MA Feng,et al.Base station spacing of virtual aids to navigation in mountain waterways[J].Journal of Harbin Engineering University,2016,37(3):382-387.
[10] 戴鹏睿.AIS轨迹动态插值在实时视景显示中的应用[J].电子设计工程,2016,24(14):172-175.DAI Pengrui.Application of AIS trajectory dynamic interpolation in real-time visual display[J].Electronic design engineering,2016,24(14):172-175.
[11] 吴建华,吴琛,刘文,等.舶舶AIS轨迹异常的自动检测与修复算法[J].中国航海,2017,40(1):8-12,101.WU Jianhua,WU Chen,LIU Wen,et al.Automatic detection and restoration algorithm for trajectory anomalies of ship AIS[J].Navigation of China,2017,40(1):8-12,101.
[12] 刘立群,吴超仲,褚端峰,等.基于Vondrak滤波和三次样条插值的船舶轨迹修复研究[J].交通信息与安全,2015,33(4):100-105.LIU Liqun,WU Chaozhong,CHU Duanfeng,et al.A study of ship trajectory restoration based on Vondrak filtering and cubic spline interpolation[J].Journal of transport information and safety,2015,33(4):100-105.
[13] NGUYEN V S,IM N K,LEE S M.The interpolation method for the missing AIS data of ship[J].Journal of navigation and port research,2015,39(5):377-384.
[14] 姚志洪,蒋阳升,韩鹏,等.基于神经网络的小时间粒度交通流预测模型[J].交通运输系统工程与信息,2017,17(1):67-73.YAO Zhihong,JIANG Yangsheng,HAN Peng,et al.Traffic flow prediction model based on neural network in small time granularity[J].Journal of transportation systems engineering and information technology,2017,17(1):67-73.
[15] 徐婷婷,柳晓鸣,杨鑫.基于BP神经网络的船舶航迹实时预测[J].大连海事大学学报,2012,38(1):9-11.XU Tingting,LIU Xiaoming,YANG Xin.BP neural network-based ship track real-time prediction[J].Journal of Dalian Maritime University,2012,38(1):9-11.
[16] 甄荣,金永兴,胡勤友,等.基于AIS信息和BP神经网络的船舶航行行为预测[J].中国航海,2017,40(2):6-10.ZHEN Rong,JIN Yongxing,HU Qinyou,et al.Vessel behavior prediction based on AIS data and BP neural network[J].Navigation of China,2017,40(2):6-10.
[17] 戴吾蛟,丁晓利,朱建军.基于观测值质量指标的GPS观测量随机模型分析[J].武汉大学学报(信息科学版),2008,33(7):718-722.DAI Wujiao,DING Xiaoli,ZHU Jianjun.Comparing GPS stochastic models based on observation quality indices[J].Geomatics and Information Science of Wuhan University,2008,33(7):718-722.
[18] GLOROT X,BENGIO Y.Understanding the difficulty of training deep feedforward neural networks[J].Journal of machine learning research,2010,9:249-256.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |