Challenges and opportunities in applying vibration based condition monitoring in railways

Abstract

Electrical rotating machines are among the most commonassets used in industry. In railways applications these devicesare present in fixed and rolling stock systems, such asturnouts and traction components. Condition based maintenance(CBM) of rotating machines may significantly improvethe availability of critical railway assets. Moreover, by efficientlyassessing the state of health of targeted components,it becomes possible to introduce advanced asset managementstrategies for life cycle cost optimization. In comparison withtraditional maintenance approaches, health monitoring enablesbetter maintenance scheduling, fleet size optimizationand maintenance costs reduction. CBM applied to rotatingmachines has been actively studied by many researchers in awide variety of fields such as: signal processing, anomaly detection,failure diagnostic and failure prognostics. However,there is still a considerable gap between the methods studiedin research and the ones successfully applied in industry,and especially in the railway field. This paper discusses thechallenges and opportunities for application of CBM methodsto electrical rotating machines in railway applications. Forthe purpose of illustration, a case study focusing on tractionmotor bearings is considered. Time domain and frequencydomain signal processing techniques are employed to extractfeatures from bearing degradation data. The data analyzed inthe present study have been obtained in a bearing test benchand during a test conducted on a real traction motor used intrains. The results of the considered methods are discussedand future research directions are suggested.