Measured condition data may contain lots of information that is not efficiently used. By using techniques from the field of pattern recognition, this article outlines a methodology for eliciting new information. The methodology is demonstrated on a large set of condition data originating from track geometry quality, dynamic stiffness, and ground penetrating radar. The case study gives evidence for the importance of dynamic stiffness measurements as to determine soil- and embankment-related track problems, whereas problems originating from the upper part or the track structure do not benefit significantly.
ERRI D 187/DT 299Decision support system for track maintenance and renewal - ecotrack, Utrecht, April 1994.
2.
EbersöhnW.Track maintenance management philosophy. In Proceedings of the 6th IHHA Conference, Cape Town, 1997.
3.
HyslipJ. P.Substructure maintenance management - its time has come. In Proceedings of the AREMA Conference, Chicago, 9–12 September 2007.
4.
PaulssonB.EkbergA. (Eds). INNOTRACK - Concluding Technical Report. 2010, Paris, available from www.innotrack.eu.
5.
BerggrenE.LiM.SpännarJ.A new approach to the analysis and presentation of vertical track geometry quality and rail roughness. J. Wear, 2008, 265, 1488–1496.
6.
BishopC. M.Pattern recognition and machine learning, 2006 (SpringerNew York).
7.
BurrowM.TeixeiraP.DahlbergT.BerggrenE.Track stiffness considerations for high speed railway lines'Railway transportation: policies, technology and perspectives2009 (Nova Publishers, New York).
8.
BerggrenE.JahléniusÅ.BengtssonB. E.BergM.Simulation, development and field testing of a track stiffness measurement vehicle. In Proceedings of the 8the IHHA Conference, Rio de Janeiro, 13–16 June 2005.
