Monitoring of the technical condition of tracks based on machine learning

This paper presents the concept of a simple system for the identification of the technical condition of tracks based on a trained learning system in the form of three independent neural networks. The studies conducted showed that basic measurements based on the root mean square of vibration acceleration allow for monitoring the track condition provided that the rail type has been included in the information system. Also, it is necessary to select data based on the threshold value of the vehicle velocity. In higher velocity ranges (above 40 km/h), it is possible to distinguish technical conditions with a permissible error of 5%. Such selection also enables to ignore the impact of rides through switches and crossings. Technical condition monitoring is also possible at lower ride velocities; however, this comes at the cost of reduced accuracy of the analysis.