Influencing factors for condition-based maintenance in railway tracks using knowledge-based approach
A. Jamshidi (TU Delft - Railway Engineering)
S Hajizadeh (TU Delft - Railway Engineering)
M. Naeimi (TU Delft - Railway Engineering)
Alfredo Núñez (TU Delft - Railway Engineering)
Zili Li (TU Delft - Railway Engineering)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
In this paper, we present a condition-based maintenance decision method using
knowledge-based approach for rail surface defects. A railway track may contain a considerable number of surface defects which influence track maintenance decisions. The proposed method is based on two sets of maintenance decision factors i.e. (1) defect detection data and (2) prior knowledge of the track. A defect detection model is proposed to monitor surface defects of the track
including squats. The detection model relies on track images and Axle Box Acceleration (ABA) signals to give both positions of severity and defects. To acquire the prior knowledge, a set of track monitoring data is selected. A fuzzy inference model is proposed relying on the maintenance factors
to give the track health condition in a case study of the Dutch railway network. The proposed condition-based maintenance model enables infrastructure manager to prioritize critical pieces of the track based on the health condition.