Railroad Maintenance Predictor System for Metro Railroad Systems

Abstract

Railways have been expanding its roots since their inception from conventional ballasted rail systems to ballastless metro's and high-speed rail. Metro rail systems are predicted to revolutionise the transportation sector's outlook practically in every metropolitan city catering to the needs of day-to-day routine traffic essence. In order to provide fast and efficient transportation modes the railways are dependent on moving and non-moving components. One among the major non movable component is said to be the railway tracks commonly known as railroad systems. Railroad systems are prone to regular maintenance interventions depending on traffic intensity and various other external factors namely rail temperature, climatic variations etc. Periodic and corrective maintenance activities are disrupted by service runs during daytime and hence they are planned to be performed overnight. In order to perform effective railroad maintenance a proper schedule is required along with the intervention requirement rate. The study adopts clustering algorithm to identify the probability of intervention rates by categorizing the maintenance interventions into three probability levels namely low, medium, and high. The results of the study indicate that the segments falling in the category of medium levels require higher maintenance intervention than the high and low severity levels.