liu.seSearch for publications in DiVA
Change search
ReferencesLink to record
Permanent link

Direct link
Modeling delay relations based on mining historical train monitoring data: a Chinese railway case
Beijing Jiaotong University, State Key Laboratory of Rail Traffic Control and Safety.
Beijing Jiaotong University, State Key Laboratory of Rail Traffic Control and Safety.
Linköping University, Department of Science and Technology, Communications and Transport Systems. Linköping University, Faculty of Science & Engineering.
Delft University of Technology, Section Transport Engineering & Logistics, Maritime and Transport Technology.
2015 (English)In: Proceedings of the 6th International Conference on Railway Operations Modelling and Analysis - RailTokyo2015, Tokyo, 2015Conference paper (Refereed)
Abstract [en]

Development of high-speed railway systems greatly shortens people’s travel time in China. However, the reliability of travel time still cannot meet expectations of passengers. In order to reduce delays and delay propagation, predictive railway traffic management is attracting more and more attention from researchers in recent years. It is widely accepted that precise prediction of future train events is one of the keys for implementing predictive traffic management and knowing delay characteristics (e.g. probability density distributions) is the basis for accurate system status prediction. In this paper, we aim to provide a case study about delay characteristics of Beijing-Shanghai high-speed railway line in China. We first derive probabilistic distribution functions of both train arrival and departure delays at individual station. Then, we investigate the relations of delays along this rail line by Chi-square independence test and Pearson correlation test (if necessary). In particular, correlation coefficients are used to describe relations of delays. In this part, we also compare the impact of realized running times on the final delay with that of dwell time. Finally, numerical experiments are conducted to predict final arrival delay using the delay relations we get.

Place, publisher, year, edition, pages
Tokyo, 2015.
National Category
Transport Systems and Logistics
Identifiers
URN: urn:nbn:se:liu:diva-119747OAI: oai:DiVA.org:liu-119747DiVA: diva2:826698
Conference
6th International Conference on Railway Operations Modelling and Analysis - RailTokyo2015
Available from: 2015-06-25 Created: 2015-06-25 Last updated: 2015-06-26Bibliographically approved

Open Access in DiVA

No full text

Search in DiVA

By author/editor
Kecman, Pavle
By organisation
Communications and Transport SystemsFaculty of Science & Engineering
Transport Systems and Logistics

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 102 hits
ReferencesLink to record
Permanent link

Direct link