The invention discloses a ship short-time traffic flow fuzzy prediction method based on a chaos theory, and the method comprises the steps: constructing a classification mode of an air strip, collecting AIS data of MMSI codes, real-time longitude and latitude, channel speed difference and channel occupancy rate, and carrying out the preprocessing analysis; calculating the AIS data by using a wolfmethod, judging the Lyapunov index of the ship traffic flow, and analyzing chaotic characteristics; realizing phase space reconstruction of the chaotic time sequence based on the takens theorem to obtain a prediction data basis; comparing different prediction theoretical models, and adopting a support vector regression (SVR) machine model for prediction; and calculating an ambiguity function of aprediction result data point by adopting an algorithm of a fuzzy structural element, and constructing a fuzzy prediction result of the ship short-term traffic flow together with the prediction value.According to the invention, the AIS data of the channel speed difference and the channel occupancy rate are collected, and a fuzzy prediction algorithm based on a fuzzy structure element method is adopted, so that the information characteristics of the real ship traffic flow can be comprehensively contained, and the short-time ship prediction precision is improved.
本发明公开了一种基于混沌理论的船舶短时交通流模糊预测方法,包括:构建航带的划归方式,采集MMSI码、实时经纬度、航道速差、占道率的AIS数据,并进行预处理分析;使用wolf法对AIS数据进行计算,对船舶交通流的Lyapunov指数进行判定,并分析混沌特性;以takens定理实现对混沌时间序列的相空间重构,得到预测数据基础;对比不同预测理论模型,采用支持向量回归机模型(SVR)进行预测;采用模糊结构元的算法计算预测结果数据点的模糊度函数,并与预测数值一起构建船舶短时交通流的模糊预测结果。本发明中对航道速差、占道率的AIS数据的采集,以及基于模糊结构元方法的模糊预测算法,能全面地包含真实船舶交通流的信息特征,提高短时船舶预测的精度。
Ship short-term traffic flow fuzzy prediction method based on chaos theory
一种基于混沌理论的船舶短时交通流模糊预测方法
2020-11-20
Patent
Electronic Resource
Chinese
IPC: | G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS |
Short-term traffic flow prediction based on fuzzy time series
Automotive engineering | 2002
|Short-Term Traffic Flow Prediction Based on Fuzzy Time Series
SAE Technical Papers | 2002
|