TRB Pubsindex
Text Size:

Title:

Predicting Potential Railway Operational Disruptions with Echo State Networks

Accession Number:

01475534

Record Type:

Component

Availability:

Transportation Research Board Business Office

500 Fifth Street, NW
Washington, DC 20001 United States
Order URL: http://www.trb.org/main/blurbs/170148.aspx

Find a library where document is available


Order URL: http://worldcat.org/isbn/9780309286893

Abstract:

European passenger rail systems are massively interconnected and operate with very high frequency. The effects of single-component failures on these types of systems can significantly affect technical and operational reliability. Today advanced diagnostic tools with broad functionalities are being added to systems and system components. These tools control the operation of, support the maintenance of, and monitor the highly sophisticated and interconnected components. A set of diagnostic event data from a passenger train exterior door system was used to predict the occurrence of events that might evolve into operational disruptions that affect train operation and therefore railway reliability. This approach used a neural network algorithm with dynamic temporal behavior (the echo state network) in combination with principal component analysis. The proposed approach exhibited a prediction accuracy of up to 99%.

Monograph Title:

Railroads 2013

Monograph Accession #:

01503754

Report/Paper Numbers:

13-0676

Language:

English

Authors:

Fink, Olga
Nash, Andrew
Weidmann, Ulrich

Pagination:

pp 66–72

Publication Date:

2013

Serial:

Transportation Research Record: Journal of the Transportation Research Board

Issue Number: 2374
Publisher: Transportation Research Board
ISSN: 0361-1981

ISBN:

9780309286893

Media Type:

Print

Features:

Figures (3) ; References (22) ; Tables (2)

Geographic Terms:

Subject Areas:

Operations and Traffic Management; Railroads; I72: Traffic and Transport Planning

Files:

TRIS, TRB, ATRI

Created Date:

Feb 5 2013 12:15PM

More Articles from this Serial Issue: