基于灰色-BP神经网络模型的短时交通量预测  

Short-term Traffic Volume Forecast Based on grey-BP Neural Network Model

作　　者：田家成 陆严晨 TIAN Jiacheng;LU Yanchen(School of Management Studies,Shanghai University of Engineering Science,Shanghai 201620,China;School of Urban Railway Transportation,Shanghai University of Engineering Science,Shanghai 201620,China)

机构地区：[1]上海工程技术大学管理学院,上海201620 [2]上海工程技术大学城市轨道交通学院,上海201620

出　　处：《信息与电脑》2021年第9期61-64,共4页Information & Computer

摘　　要：短时交通量具有明显周期性、非线性的特点,为提高短时交通量预测的精度,笔者提出将灰色GM(1,1)模型与BP神经网络相结合的方法,并以上海市浦东新区陆家嘴东路真实数据为样本进行实验计算与对预测结果对比.该灰色神经网络模型GNNM(1,1)兼具两种模型的优势。实验结果表明,相较于传统的灰色GM(1,1)模型,灰色BP神经网络模型具有更高的预测精度,为预测短时交通量提供了一种新思路.Short-term traffic volume has obvious periodic and non-linear characteristics.In order to improve the accuracy of short-term traffic volume prediction,the author proposes a method that combines the gray GM(1,1)model with BP neural network,and uses the method of Pudong New District,Shanghai.The real data of Lujiazui East Road is a sample for experimental calculation and comparison of prediction results.The grey neural network model GNNM(1,1)has the advantages of both models.The experimental results show that,compared with the traditional gray GM(1,1)model,the gray BP neural network model has higher prediction accuracy and provides a new idea for predicting short-term traffic volume.

关 键 词：灰色-BP神经网络预模型 短时交通量 预测 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]