基于优化RBF网络的港口船舶交通流量预测  

Ship Traffic Volume Forecast in Port Based on Optimized RBF Neural Networks

作　　者：郝勇[1,2] 王怡[1,2] 

机构地区：[1]武汉理工大学航运学院,武汉430063 [2]内河航运技术湖北省重点实验室,武汉430063

出　　处：《中国航海》2014年第2期81-84,117,共5页Navigation of China

摘　　要：港口船舶交通流量预测能为港口规划、交通管理提供决策支持。RBF神经网络在交通流预测领域有着广泛的应用,但其在网络权值等参数的选取算法上存在缺陷。遗传算法具有全局搜索速度快的优点,利用该算法对RBF神经网络的权值进行遗传操作,可获得具有一定遍历性的初始权值。文章尝试将基于遗传算法优化的RBF神经网络应用到港口船舶交通流量预测领域并以芜湖港为例进行验证。结果显示,优化后的RBF神经网络的预测误差比普通的RBF神经网络小5%左右,表明优化后的RBF神经网络计算量更小、识别速度更快、预测误差更小,在港口船舶交通流量预测领域具有广阔的应用前景。Good port planning and traffic management need accurate prediction of ship traffic volume in a port,which is made by means of the ship traffic volume forecasting algorithm.The RBF neural network has a wide range of applications in this regard.The problem with RBF is the difficulties in determining parameters,such as the weights.The genetic algorithm has the advantages of fast global searching,therefore,is good for finding the ergodic initial values of weights for the RBF neural network.The RBF neural network,optimized with the genetic algorithm,is verified through the case of Wuhu port.The results show that the optimized RBF neural network is 5 percent more accurate than ordinary RBF neural network,while it uses less computing resources and shorter computing time.

关 键 词：水路运输 船舶交通流量 RBF神经网络 遗传算法 港口 预测 

分 类 号：U691[交通运输工程—港口、海岸及近海工程]