An interval prediction system for track irregularity after tamping based on multi-module machine learning and pointwise scaling approach

Abstract

Predicting changes in track irregularity after tamping is important for assisting maintenance decisions and improving construction efficiency. To date, most prediction methods lack consideration for the uncertainties related to tamping effects. To fill this gap, a multi-module prediction interval system composed of feature selection, interval scaling, and intelligent predictor has been constructed. The feature selection module integrates the processes of relevance, redundancy, complementarity, and weighting. The interval scaling module assigns scaling factors to each point in a data-driven manner, offering great flexibility. Research found that the composite model has significant advantages over traditional models, improving the interval coverage probability by 5.83%–40.62%. It can accurately predict the track relative smoothness after tamping, with the R² between the measurement and the prediction of the 60 m mid-chord offset reaching 0.95. This model can serve as a reliable and feasible tool for predicting the static irregularity of ballasted tracks after tamping.