A Bayesian assessment for railway track geometry degradation prognostics

Abstract

Advanced PHM techniques have the potential to substantially reduce railway track maintenance costs while increasing safety and availability. However, there is still a significant lack of knowledge and experience in relation to suitable PHM models and algorithms within the context of railway track geometry degradation. This paper proposes a Bayesian model class methodology for prognostics performance assessment whereby different prognostics algorithms can be rigorously assessed and ranked according to their relative probability to predict the future degradation process. The proposed framework is exemplified and tested for a case study about track degradation prognostics using published data about track settlement, taken from a simulated traffic loading experiment carried out at the Nottingham Railway Test Facility.