1. Prediction of railway track geometry defects: a case study.
- Author
-
Soleimanmeigouni, Iman, Ahmadi, Alireza, Nissen, Arne, and Xiao, Xun
- Subjects
- *
FORECASTING , *GEOMETRY , *STANDARD deviations , *RAILROADS , *REGRESSION analysis - Abstract
The aim of this study has been to develop a data-driven analytical methodology for prediction of isolated track geometry defects, based on the measurement data obtained from a field study. Within the study, a defect-based model has been proposed to identify the degradation pattern of isolated longitudinal level defects. The proposed model considered the occurrence of shock events in the degradation path. Furthermore, the effectiveness of tamping intervention in rectifying the longitudinal level defects was analysed. The results show that the linear model is an appropriate choice for modelling the degradation pattern of longitudinal level defects. In addition, a section-based model has been developed using binary logistic regression to predict the probability of occurrence of isolated defects associated with track sections. The model considered the standard deviation and kurtosis of longitudinal level as explanatory variables. It has been found that the kurtosis of the longitudinal level is a statistically significant predictor of the occurrence of isolated longitudinal level defects in a given track section. The validation results show that the proposed binary logistic regression model can be used to predict the occurrence of isolated defects in a track section. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF