Diagnostics of Direct Current motor with application of acoustic signals, reflection coefficients and K-Nearest Neighbor classifier

One of the main problems faced by engineers, is to ensure the operation of Direct Current motors. In this paper a pattern recognition method was used to provide the diagnostics of dc motor. This method is based on a study of acoustic signal. Plan of study of acoustic signals for two conditions of Direct Current motor was proposed. Studies were carried out for algorithms of data processing: reflection coefficients and K-Nearest Neighbor classifier with Manhattan distance. Developed method can be performed automatically. This system is a significant step towards the maintenance-free diagnostic systems of Direct Current motors.