Data mining in rail transport delay chain analysis

Wallander, Jouni; Mäkitalo, Miika

doi:10.1504/ijstl.2012.047492

Cited by 24 publications

(8 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is a very common practice of transport operators to provide live data on delays recorded on their own network, which can be recorded accessing public websites. Furthermore, the partition of operation into recurrent delay patterns allows inference on individual clusters, which is not possible with association or succession rules [25][26][27]. These methods do not provide causality connection and can only be used to compare scenarios, for example, before and after delay mitigation countermeasures have been implemented.…”

Section: Discussionmentioning

confidence: 99%

“…However, association rules can highlight common recurrences but cannot explain relations of causality between two events, so primary and secondary delays cannot be distinguished. Similarly, Wallander and Mäkitalo [26] identify delay chains according to the manual delay cause records from the dispatchers and based on timestamps at stations with granularity of 1 minute. The succession rules used are very similar to association rules but consider the time dependencies, so that events taking place earlier can be assumed to be the cause of events happening later under the same circumstances.…”

Section: Literature Surveymentioning

confidence: 99%

See 1 more Smart Citation

Application of Data Clustering to Railway Delay Pattern Recognition

Cerreto

Nielsen

et al. 2018

Journal of Advanced Transportation

View full text Add to dashboard Cite

K-means clustering is employed to identify recurrent delay patterns on a high traffic railway line north of Copenhagen, Denmark. The clusters identify behavioral patterns in the very large ("big data") datasets generated automatically and continuously by the railway signal system. The results reveal the conditions where corrective actions are necessary, showing the cases where recurrent delay patterns take place. Delay profiles and delay change profiles are generated from timestamps to compare different train runs and to partition the set of observations into groups of similar elements. K-means clustering can identify and discriminate different patterns affecting the same stations, which is otherwise difficult in previous approaches based on visual inspection. Classical methods of univariate analysis do not reveal these patterns. The demonstrated methodology is scalable and can be applied to any system of transport.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Literature Surveymentioning

confidence: 99%

Application of Data Clustering to Railway Delay Pattern Recognition

Cerreto

Nielsen

et al. 2018

Journal of Advanced Transportation

View full text Add to dashboard Cite

show abstract

“…Van der Meer et al mined data from peak hours, including rolling stock, and weather data and developed a predictive model involving the mining of track occupation data for delay estimations [9]. A data-mining approach was used for analyzing rail transport delay chains, with data from passenger train traffic on the Finnish rail network, but the data from the train running process was limited to one month [4]. Murali et al reported a delay regression-based estimation technique that models delay as a function of train mix and network topology [17].…”

Section: Literature Reviewmentioning

confidence: 99%

“…In practice, some skilled dispatchers usually predict HSTD empirically, which leads to differences in dispatching even for the same dispatcher when working in different situations. Data-driven approaches have recently gained more attention due to their better understanding of train delay concatenation and the fact they are more supportive of robust timetables and real-time dispatching [4]. In addition to the availability of train operation records, advanced data-mining techniques enable us to address these problems from a dataanalysis perspective.…”

Section: Introductionmentioning

confidence: 99%

Modeling the Influence of Disturbances in High-Speed Railway Systems

Huang

Wen

Peng

et al. 2019

Journal of Advanced Transportation

View full text Add to dashboard Cite

Accurately forecasting the influence of disturbances in High-Speed Railways (HSR) has great significance for improving real-time train dispatching and operation management. In this paper, we show how to use historical train operation records to estimate the influence of high-speed train disturbances (HSTD), including the number of affected trains (NAT) and total delayed time (TDT), considering the timetable and disturbance characteristics. We first extracted data about the disturbances and their affected train groups from historical train operation records of Wuhan-Guangzhou (W-G) HSR in China. Then, in order to recognize the concatenations and differences of disturbances, we used a K-Means clustering algorithm to classify them into four categories. Next, parametric and nonparametric density estimation approaches were applied to fit the distributions of NAT and TDT of each clustered category, and the goodness-of-fit testing results showed that Log-normal and Gamma distribution probability densities are the best functions to approximate the distribution of NAT and TDT of different disturbance clusters. Specifically, the validation results show that the proposed models accurately revealed the characteristics of HSTD and that these models can be used in real-time dispatch to predict the NAT and TDT, once the basic features of disturbances are known.

show abstract

“…Total train running time was predicted based on free running time predictors (horsepower per ton, track topography and slow orders) and congestion-related factors (meets, passes, overtakes, number of trains, total train hours, train spacing variability and train departure headway). Wallander and mäkitalo [22] used a data-mining approach for analysing rail transport delays with the aim of developing a more robust timetable structure and provide tools for rail network planning.…”

Section: Introductionmentioning

confidence: 99%

Delays for passenger trains on a regional railway line in southern Sweden

Palmqvist¹,

Olsson²,

Hiselius³

2017

Int. J. TDI

View full text Add to dashboard Cite

The aim of this article is to study how selected variables influence delays in train traffic. Data has been collected on train movements, timetables, weather and capacity utilization on a highly utilized single-track railway line in southern Sweden during 2014. based on this dataset, we have analysed how different factors affect delays in passenger traffic. We measure delays in a novel way, as deviations from the scheduled duration for each line section and station stop, not as deviations from a published or operational timetable, and this allows us to identify when and where the delays first occur. average delays were much larger at station stops. The most significant factor affecting delays was the scheduled duration time at station stops and the existence of margins on line sections. If trains arrive to a line section or station stop slightly delayed they speed up the activity, otherwise they are typically delayed. The influence of weather was less significant and somewhat contradictory: snow and cold temperatures increase delays on line sections but reduce them at station stops, while precipitation made no difference. Capacity utilization seems to have a negative correlation with delays, but we have too little variation in the levels to be confident. all studied variables, except for precipitation, have impacts that are statistically significant to a very high degree of confidence, using both t-tests and regression analysis. The results of this study have important practical implications for timetable construction; for instance we estimate that a reallocation of scheduled time at stations could reduce delays by as much as 80%.

show abstract

Data mining in rail transport delay chain analysis

Cited by 24 publications

References 32 publications

Application of Data Clustering to Railway Delay Pattern Recognition

Application of Data Clustering to Railway Delay Pattern Recognition

Modeling the Influence of Disturbances in High-Speed Railway Systems

Delays for passenger trains on a regional railway line in southern Sweden

Contact Info

Product

Resources

About