BIC-Based Data-Driven Rail Track Deterioration Adaptive Piecewise Modeling Framework

The records of maintenance activities are required for modeling the track irregularity deterioration process. However, it is hard to guarantee the completeness and accuracy of the maintenance records. To tackle this problem, an adaptively-piecewise modeling framework for rail track deterioration process driven by historical measurement data from comprehensive inspection train (referred as CIT) are proposed. The identification of when maintenance activities were operated is reformulated as a model selection optimization problem based on Bayesian Information Criterion. An efficient solution algorithm utilizing adaptive thresholding and dynamic programming is proposed for solving this optimization problem. The validity and practicability of this framework are illustrated by the measurement data from CIT inspecting the mileage section of K21+184 to K220+308 on the Nanchang-Fuzhou railway track from 2014 to 2019. The results indicate that this framework is capable of overcoming the disturbance of contaminated measurement data and accurately estimating when maintenance activities were operated without any historical maintenance records. What is more, the adaptively-piecewise fitting model provided by this framework can describe the corresponding rail track section’s irregularity deterioration process.