Exploiting Machine Learning for the Identification of Locomotives’ Position in Large Freight Trains

Abstract

Accurate identification of locomotives’ position in large freight trains is important due to maintenance and management aspects. Current solutions employ RFIDs, image cameras or GPS, while the first two are expensive, the third is not an off-the-shelf hardware for all locomotives. In this paper we investigate a data driven solution to automatically identify locomotives’ position in large freight trains. We take into account off-the-shelf hardware alone (that gather instant fuel consumption) seeking for a less expensive solution. We evaluate different machine learning approaches and algorithms and different inputs attributes, achieving significant results.