Intelligent index for railway track quality evaluation based on Bayesian approaches

Concerning the optimal balance between the limited budget and maintaining the desired performance and safety level in railway infrastructure, it is necessary to prioritize railway track qualities. Although different directives recommend different indices, infrastructure managers often face difficulties in selecting the optimal track quality index. Despite the significant influence that assessing the accurate condition of railway track qualities have on planning maintenance actions, no known track quality index that offers easy construction from a large number of sampling points and is appropriate for the majority of situations has yet been published. This article proposes a stochastic track quality index that considers the uncertainty regarding the quality classification that remains even after the data have been observed. To achieve this, the problem is set into a probability context by selecting a Bayesian framework to characterize the unknown parameters of probabilistic models for track geometry parameters. To demonstrate the efficiency of the approach, the proposed quality index is applied to the data recorded from field observation. To verify the validity of the presented approach, the obtained results are compared to those of deterministic results and reasonable accuracy can be reported. Subsequently, this index enables the infrastructure manager to efficiently prioritize maintenance actions.