基于AIS信息和BP神经网络的船舶航行行为预测

发布时间：2018-06-17 23:12

本文选题：水路运输 + 船舶行为　；参考：《中国航海》2017年02期

【摘要】：针对船舶航行行为多维度的特点和船舶交通服务系统(Vessel Traffic Service,VIS)对船舶行为预测的精确度和实时性需求,提出结合船舶自动识别系统(Automatic Identification System,AIS)信息和BP(Back Propagation)神经网络的船舶航行行为预测方法。构造基于AIS信息的船舶航行行为特征表达方法,根据BP神经网络预测的基本原理,以连续3个时刻的船舶航行行为特征值为输入,以第4个时刻的船舶航行行为特征值为输出,对BP神经网络进行训练,用于对未来船舶航行行为进行预测。以成山角VTS水域内的船舶AIS信息为例进行试验,结果表明:利用该方法对船舶航行行为特征值进行预测的结果准确、实时,误差在可接受的范围内。
[Abstract]:In view of the multi-dimensional characteristics of ship navigation behavior and the demand of ship traffic service system (Vessel Traffic Service vis) for the accuracy and real-time performance of ship behavior prediction, This paper presents a method of ship navigation behavior prediction based on automatic system of identification (AIS) information and BP identification (back propagation) neural network. According to the basic principle of BP neural network prediction, the characteristic value of ship's navigation behavior at three consecutive times is taken as input and the characteristic value of ship's navigation behavior at the fourth moment is taken as output, according to the basic principle of BP neural network prediction, which is based on AIS information. BP neural network is trained to predict the future navigation behavior of ships. Taking the ship AIS information in the VTS waters of the mountain corner as an example, the results show that the prediction results of the characteristic values of ship navigation behavior by this method are accurate, real-time, and the error is within the acceptable range.
【作者单位】：上海海事大学商船学院;
【基金】：国家自然科学基金(51379121) 国家留学基金委联合培养博士生项目(201608310093) 上海市科委地方院校能力建设项目(15590501600) 上海海事大学研究生创新基金(2016ycx077);上海海事大学优秀博士学位论文培养项目(2017bxlp003)
【分类号】：TP183;U675.7

【相似文献】