Predicting the Remaining Useful Life of Railway Wheels: a Data-Driven Approach for Predictive Maintenance

Abstract

Building on previous work on wear law modeling, this paper focuses on the prediction of the remaining useful life (RUL) of a complex system, whose state is characterized by multivariate time-series data. Our study is framed within the context of predictive maintenance applied to rolling stock, particularly railway wheels. We propose an approach to estimate future wear based on the wear law, while using the Remaining Useful Life (RUL) prediction as a key performance indicator. We also evaluate the accuracy and reliability of the prediction model. We demonstrate the performance of RUL predictions for three factors (Flange height, Flange width, Flange gradient), with improvements of up to 8 % in the Mean Absolute Percentage Error (MAPE) for Flange width, a 60 % gain for Flange height, and 32 % for Flange gradient. These results highlight the generalizability and relevance of our approach.