Irregularities in railway tracks influence the running behavior of trains; large irregularities can result in poor ride comfort and in some cases derailment. Thus, it is important that the relationship between track irregularities and the running behavior of trains is identified and criteria for track irregularities are adequately established. However, the questions of how track irregularities affect the vehicle responses that determine running safety and ride comfort and how the wavelength and amplitude of each track irregularity influence the vehicle responses are barely addressed in the literature. This paper reports the results of computer simulation studies that were performed to investigate the influence of the longitudinal level, alignment and cross level of track irregularities on the running behavior of the 300 km/h KTX (Korea Train Express) train. A straight track was assumed in the calculations to ensure a focus on the effect of track irregularities. Track irregularities with various wavelengths and amplitudes were modeled using the VAMPIRE program; a vehicle dynamics modeling package that is widely utilized to study railway environments. Simulations on the effects of derailment coefficients, lateral loads, bogie acceleration and body acceleration created by track irregularities were performed to evaluate how the track irregularities affect the safety and ride comfort of the KTX. The results of the simulations indicate that track alignment has a significant impact on running safety whereas longitudinal level does not have any significant impacts.

The maintenance and renewal of ballasted track can be optimized in terms of time and cost if a proper statistical model of track deterioration is derived from previous maintenance history and measurement data. In this regard, quite a few models with simplified assumptions on the parameters have been suggested for the deterioration of ballasted track. Meanwhile, data driven models such as the artificial neural network (ANN) and support vector regression (SVR), which are basic ingredients of machine learning (ML) technology, were introduced in this study to better represent the deterioration phenomena of track segments so that the results can be directly plugged into the optimization schemes. For this purpose, the influential parameters of track deterioration have been selected based on the maintenance history, and two ML models have been studied to find the best combination of input parameters. Through numerical experiments, it was found that at least 2 years of maintenance data were needed in our case to obtain a stable prediction of track deterioration.

Although reliability centered maintenance (RCM) has been used widely in the maintenance and renewal (M&R) of railway infrastructures, M&R methods and maintenance frequencies still require considerable study to obtain information on optimum decisions. Recently, various attempts have been made to optimize the maintenance works in railway engineering, although a decision support system on selecting the maintenance or renewal works has not been suggested distinctly. Therefore, a genetic algorithm on the basis of the nondominated sorting method (NSGA) was used in this study to optimize the biobjective functions on M&R interventions and costs. The results showed that the optimum frequency of M&R could be determined using the NSGA method with various constraints. Moreover, field application of the suggested method also was considered. Future work will be concentrated on the systematic approach of the decision support model with RCM and the enterprise resource planning (ERP) system of the infrastructure manager (IM).

Maintenance of ballasted track has been carried out with the concept of TBM (Time Based Maintenance) by employing TQI (Track Quality Information) estimated from the TMV (Track Measurement Vehicle) and previous maintenance experience. In this regard, much research work has been concentrated on efficient and optimal maintenance practice, but practical difficulties have been observed during application of complicated algorithms or purchasing of expensive commercial software. Therefore, a maintenance scheduling simulator with a fast algorithm for minimum maintenance cost and reasonable track quality is developed in this study, based on a commercial spreadsheet. The results of this study will be used in maintenance decision making, budget allocation and track quality control. In the future, additional maintenance constraints, such as insufficient budget and weather conditions, will be included to enhance the decision support of track maintenance.