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.

Change points indicate significant shifts in the statistical properties in data streams at some time points. Detecting change points efficiently and effectively are essential for us to understand the underlying data-generating mechanism in modern data streams with versatile parameter-varying patterns. However, it becomes a highly challenging problem to locate multiple change points in the noisy data. Although the Bayesian information criterion has been proven to be an effective way of selecting multiple change points in an asymptotical sense, its finite sample performance could be deficient. In this article, we have reviewed a list of information criterion-based methods for multiple change point detection, including Akaike information criterion, Bayesian information criterion, minimum description length, and their variants, with the emphasis on their practical applications. Simulation studies are conducted to investigate the actual performance of different information criteria in detecting multiple change points with possible model mis-specification for the practitioners. A case study on the SCADA signals of wind turbines is conducted to demonstrate the actual change point detection power of different information criteria. Finally, some key challenges in the development and application of multiple change point detection are presented for future research work.