A method for classifying red signal approaches using train operational data

Yunshi Zhao, Julian Stow, Chris Harrison

Research output: Contribution to journalArticle

Abstract

The paper describes a novel technique to reliably classify whether or not a train approaching a signal at red actually came to a stand before the signal cleared (red aspect approaches) using the data from conventional signalling systems. This data is limited to the times at which the signal aspect changes and the times at which the train enters and leaves the signalling section ('berth') in advance of the signal. Knowing the percentage of red aspect approaches is potentially important for understanding the likelihood of a signal being passed at danger (SPAD) at individual signals and also for normalisation of SPAD data, both locally and nationally, for trending and benchmarking. The industry currently uses the number of red aspect approaches based on driver surveys as estimates, which are considered to have significant shortcomings. The development of the classification model is described together with the validation procedures. The techniques presented in this paper allow red approach rates to be reliably determined without the need for complex integration of signalling system and on-train data recorder data. The initial study of 94 million train approaches shows that 5% of them stopped at red aspects. It is also highlighted that there is a large variation in the red aspect approach rates between signalling areas and between individual signals. SPAD risk assessment at individual signals could be significantly enhanced by the ability to estimate red aspect approach rates using the techniques described.

LanguageEnglish
Pages67-74
JournalSafety Science
Volume110
Issue numberPart B
Early online date15 Dec 2017
DOIs
Publication statusPublished - Dec 2018

Fingerprint

Systems Integration
Benchmarking
Industry
Risk assessment
benchmarking
normalization
risk assessment
driver
industry
ability
Surveys and Questionnaires
time

Cite this

Zhao, Yunshi ; Stow, Julian ; Harrison, Chris. / A method for classifying red signal approaches using train operational data. In: Safety Science. 2018 ; Vol. 110, No. Part B. pp. 67-74.
@article{1483049fe5d24de5beaf9345ffa5110e,
title = "A method for classifying red signal approaches using train operational data",
abstract = "The paper describes a novel technique to reliably classify whether or not a train approaching a signal at red actually came to a stand before the signal cleared (red aspect approaches) using the data from conventional signalling systems. This data is limited to the times at which the signal aspect changes and the times at which the train enters and leaves the signalling section ('berth') in advance of the signal. Knowing the percentage of red aspect approaches is potentially important for understanding the likelihood of a signal being passed at danger (SPAD) at individual signals and also for normalisation of SPAD data, both locally and nationally, for trending and benchmarking. The industry currently uses the number of red aspect approaches based on driver surveys as estimates, which are considered to have significant shortcomings. The development of the classification model is described together with the validation procedures. The techniques presented in this paper allow red approach rates to be reliably determined without the need for complex integration of signalling system and on-train data recorder data. The initial study of 94 million train approaches shows that 5{\%} of them stopped at red aspects. It is also highlighted that there is a large variation in the red aspect approach rates between signalling areas and between individual signals. SPAD risk assessment at individual signals could be significantly enhanced by the ability to estimate red aspect approach rates using the techniques described.",
keywords = "Big data, Classification, Railway safety, Railway signals, Red aspect approach to signals, Signals passed at danger, SPAD",
author = "Yunshi Zhao and Julian Stow and Chris Harrison",
year = "2018",
month = "12",
doi = "10.1016/j.ssci.2017.12.007",
language = "English",
volume = "110",
pages = "67--74",
journal = "Safety Science",
issn = "0925-7535",
publisher = "Elsevier",
number = "Part B",

}

A method for classifying red signal approaches using train operational data. / Zhao, Yunshi; Stow, Julian; Harrison, Chris.

In: Safety Science, Vol. 110, No. Part B, 12.2018, p. 67-74.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A method for classifying red signal approaches using train operational data

AU - Zhao, Yunshi

AU - Stow, Julian

AU - Harrison, Chris

PY - 2018/12

Y1 - 2018/12

N2 - The paper describes a novel technique to reliably classify whether or not a train approaching a signal at red actually came to a stand before the signal cleared (red aspect approaches) using the data from conventional signalling systems. This data is limited to the times at which the signal aspect changes and the times at which the train enters and leaves the signalling section ('berth') in advance of the signal. Knowing the percentage of red aspect approaches is potentially important for understanding the likelihood of a signal being passed at danger (SPAD) at individual signals and also for normalisation of SPAD data, both locally and nationally, for trending and benchmarking. The industry currently uses the number of red aspect approaches based on driver surveys as estimates, which are considered to have significant shortcomings. The development of the classification model is described together with the validation procedures. The techniques presented in this paper allow red approach rates to be reliably determined without the need for complex integration of signalling system and on-train data recorder data. The initial study of 94 million train approaches shows that 5% of them stopped at red aspects. It is also highlighted that there is a large variation in the red aspect approach rates between signalling areas and between individual signals. SPAD risk assessment at individual signals could be significantly enhanced by the ability to estimate red aspect approach rates using the techniques described.

AB - The paper describes a novel technique to reliably classify whether or not a train approaching a signal at red actually came to a stand before the signal cleared (red aspect approaches) using the data from conventional signalling systems. This data is limited to the times at which the signal aspect changes and the times at which the train enters and leaves the signalling section ('berth') in advance of the signal. Knowing the percentage of red aspect approaches is potentially important for understanding the likelihood of a signal being passed at danger (SPAD) at individual signals and also for normalisation of SPAD data, both locally and nationally, for trending and benchmarking. The industry currently uses the number of red aspect approaches based on driver surveys as estimates, which are considered to have significant shortcomings. The development of the classification model is described together with the validation procedures. The techniques presented in this paper allow red approach rates to be reliably determined without the need for complex integration of signalling system and on-train data recorder data. The initial study of 94 million train approaches shows that 5% of them stopped at red aspects. It is also highlighted that there is a large variation in the red aspect approach rates between signalling areas and between individual signals. SPAD risk assessment at individual signals could be significantly enhanced by the ability to estimate red aspect approach rates using the techniques described.

KW - Big data

KW - Classification

KW - Railway safety

KW - Railway signals

KW - Red aspect approach to signals

KW - Signals passed at danger

KW - SPAD

UR - http://www.scopus.com/inward/record.url?scp=85039443385&partnerID=8YFLogxK

U2 - 10.1016/j.ssci.2017.12.007

DO - 10.1016/j.ssci.2017.12.007

M3 - Article

VL - 110

SP - 67

EP - 74

JO - Safety Science

T2 - Safety Science

JF - Safety Science

SN - 0925-7535

IS - Part B

ER -