Prediction of Railcar Remaining Useful Life by Multiple Data Source Fusion

Nowadays, railway networks are instrumented with various wayside detectors. Such detectors, automatically identifying potential railcar component failures, are able to reduce rolling stock inspection and maintenance costs and improve railway safety. In this paper, we present a methodology to predict remaining useful life (RUL) of both wheels and trucks (bogies), by fusing data from three types of detectors, including wheel impact load detector, machine vision systems, and optical geometry detectors. A variety of new features is created from feature normalization, signal characteristics, and historical summary statistics. Missing data are handled by missForest, a Random Forests-based nonparametric missing value imputation algorithm. Several data mining techniques are implemented and compared to predict the RUL of wheels and trucks in a U.S. Class I railroad railway network. Numerical tests show that the proposed methodology can accurately predict RUL of the components of a railcar, particularly in a middle-term range.