Application of First- and Second-Order Derivatives of Track Irregularity to Plan Local Maintenance Activities

Abstract

A large part of the railway track geometry maintenance burden concerns local maintenance activates conducted to rectify isolated defects. Isolated defects are short irregularities in the track geometry that can dramatically increase the dynamic forces between the wheel and rail, which in turn will accelerate the growth or occurrence of internal rail defects. The dynamic force between the wheel and rail is dependent on the shape of the isolated geometry defects. However, the severity of isolated defects is mainly defined only by their amplitude. Therefore, in addition to amplitude, other characteristics of geometry defects must be considered to analyze severity of defects and to prioritize local maintenance actions. This study aims to use the first-and second-order derivatives of the longitudinal level defects to plan local maintenance activities. The derivatives of geometry defects provide useful information about the shape of defects. The information is used to categorize the isolated defects based on their severities and prioritize maintenance actions. In this regard, K-means clustering technique is applied. The results of this study will support the decision-making process regarding the planning of local maintenance activities. The foot-by-foot track geometry data collected from Main Western Line in Sweden is used to implement and test the model.

Modelling tamping effectiveness for track geometry longitudinal levelling defects

“…49,50 The shape of the defects has already been identified as a factor with a significant impact on their degradation rates. [31][32][33][34] Within the scope of the investigation carried out, it was found that the shape of defects also partially explains the high levels of uncertainty in the geometry recovery data. In fact, throughout the different modelling attempts, it was found that the degradation rates before tamping and the ballast age lose statistical significance when the shape proxy parameter is introduced in the regression model.…”

“…Among other factors, the uncertainty in tamping recovery could also be linked to the shape of the defects which, in turn, seems to be linked to geometry degradation rates. [31][32][33][34] The main objectives of this paper are to study and discuss the influence of infrastructure clusters, defect level, ballast age, degradation rate before tamping, and the still little-studied shape of defects on the geometry recovery achieved for LL defects and to model tamping effectiveness based on historical records of the Portuguese national railway network. For this purpose, data from 2,819 defects of LL are analysed considering 66,892 km of inspections carried out on 19 lines over 10 years.…”

“…Among other factors, the uncertainty in tamping recovery could also be linked to the shape of the defects which, in turn, seems to be linked to geometry degradation rates. 31–34…”

Optimal track geometry maintenance limits using machine learning: A case study

“…Gerume and et al 15 used the K-means algorithm to make two decisions including feature selection, and selection of the optimal number of clusters. In another study, Khajehei and et al 16 applied K-means clustering technique to categorize the isolated defects based on their severities and prioritize maintenance actions. In this paper, the line divided into track sections and the track sections with the most similarity have been grouped in different clusters.…”