自然科学版 英文版
自然科学版 英文版
自然科学版 英文版
自然科学版 英文版
英文版编委
自然科学版 英文版
英文版首届青年编委

您目前所在的位置:首页 - 期刊简介 - 详细页面

中南大学学报(自然科学版)

Journal of Central South University

第45卷    第12期    总第244期    2014年12月

[PDF全文下载]    [Flash在线阅读]

    

文章编号:1672-7207(2014)12-4422-09
铁路客运专线模糊k近邻客流预测模型
豆飞1, 2,贾利民3,秦勇1, 3,徐杰1, 3,王莉1, 3

(1. 北京交通大学 交通运输学院,北京,100044;
2. 北京市地铁运营有限公司 地铁运营技术研发中心, 北京,102208;
3. 北京交通大学 轨道交通控制与安全国家重点实验室,北京,100044
)

摘 要: 客运专线客运量在短时期内体现准周期的规律性变化,且受多种因素的影响呈现出一种复杂的非线性特点。传统的预测方法不能完全反映客流量准周期性和非线性的特点,预测结果误差相对较大。为更准确地预测铁路客运专线客运量,通过分析客运专线的客流特征,总结相邻时段客流变化规律,在确定相邻时段之间客流变化率的基础上,将客流变化情况划分为8个不同的等级,依据客流变化情况划分的不同等级对客流变化率模糊化,并利用客流变化率模糊值的时序关系,建立客运专线模糊k近邻客流预测模型。通过实例分析,与其他预测方法进行比较,证明该模糊k近邻客流预测结果误差更小,精度更高,为预测铁路客运专线客运量提出一种新思路。

 

关键词: 客运专线;客运量;客流预测;模糊;k近邻法

Fuzzy k-nearest neighbor passenger flow forecasting model of passenger dedicated line
DOU Fei1, 2, JIA Limin3, QIN Yong1, 3, XU Jie1, 3, WANG Li1, 3

1. School of Traffic and Transportation, Beijing Jiaotong University, Beijing 100044, China;
2. Subway Operation Technology Centre, Mass Transit Railway Operation Corporation LTD, Beijing 102208, China
3. State Key Laboratory of Rail Traffic Control and Safety, Beijing Jiaotong University, Beijing 100044, China

Abstract:Passenger flow of passenger dedicated line shows the quasi-periodic variations in the short-term forecasts, and also shows complex nonlinear characteristics because of many factors. The traditional prediction model can’t fully reflect quasi-periodic and nonlinear characteristics of the passenger flow, which result in larger errors in forecast results. In order to forecast the passenger flow more accurately, the passenger flow characteristics of the high-speed railway were analyzed, and variation of passenger flow in the adjacent period was summed up. Passenger flow change rate was divided into different grades and fuzzified on the basis of passenger flow change rate between adjacent periods. Also, fuzzy k-nearest neighbor prediction model was established on the basis of the fuzzy values timing relationship of passenger flow change rate. By comparing it with other predictive methods, the prediction result of fuzzy k-nearest neighbor prediction model is proved to be more accurate and precise, thus providing a new idea for the railway passenger flow forecast.

 

Key words: passenger dedicated line; traffic volume; passenger flow forecasting; fuzzy; k-nearest neighbor

中南大学学报(自然科学版)
  ISSN 1672-7207
CN 43-1426/N
ZDXZAC
中南大学学报(英文版)
  ISSN 2095-2899
CN 43-1516/TB
JCSTFT
版权所有:《中南大学学报(自然科学版、英文版)》编辑部
地 址:湖南省长沙市中南大学 邮编: 410083
电 话: 0731-88879765(中) 88836963(英) 传真: 0731-88877727
电子邮箱:zngdxb@csu.edu.cn 湘ICP备09001153号