Condition Based Maintenance in Mine Railway Transportation Systems Based on Big Data Analysis

Organisation: Vale – The University of Genova
Start and Estimated Duration: 12 – February – 2018, 24 Months

Summary: Streaming Data Analysis (SDA) of Big Data Streams (BDS) for Condition Based Maintenance (CBM) in the context of Rail Transportation Systems (RTS) in the mining industry is a state-of-the-art field of research. SDA of BDS is the problem of analysing, modelling and extracting information from vast amounts of data that continuously come from several sources. Among others, CBM for Mine Rail Transportation is one of the most challenging SDA complications, consisting of the implementation of a predictive maintenance system for evaluating the future status of the monitored assets to reduce risks related to failures and to avoid service disruptions. The challenge is to collect and analyse all the data streams that come from the numerous onboard sensors monitoring the assets. This project deals with the problem of CBM applied to the condition monitoring and predictive maintenance of train axle bearings based on sensors data collection, with the purpose of maximising their Remaining Useful Life (RUL). This project proposes an innovative algorithm for CBM based on SDA that takes advantage of the Online Support Vector Regression (OL-SVR) for predicting the RUL. The novelty of this proposal is the heuristic approach for optimising the trade-off between the accuracy of the OL-SVR models and the computational time and resources needed to build them. Results from tests on real collected datasets show the real benefits brought by the proposed methodology.