機械学習を応用した軌道回路の状態基準保全に関する研究

抄録

The track circuit is an important equipment for the railway operation to be safe and reliable. The maintenance of the currently used track circuit is based on the Time Based Maintenance (TBM). However, TBM has a problem to require excessive maintenance. Therefore we focus on the Condition Based Maintenance (CBM), which expects the reduced cost for maintaining the equipment. In this paper, we propose a maintenance method of the track circuit applying Machine Learning, which finds an appropriate time to perform the maintenance.