Diagnostics and predictive maintenance of industrial electric motors

Abstract

Automatic continuous or periodic control is the most promising method of diagnosing electric motors in
production nowadays. It is aimed at predicting breakdowns and the remaining useful lifetime of motors.
However, research in this area remains purely theoretical and eitherfocuses on very narrow problems or
provides too superficial overview. Consequently,manual control devices or partially automated devices are
mainly used in practice [1]. In view of this, there is great interest in the development of a software method for
predictive maintenance of electric motors. In this research recurrent neural networks with long short-term
memory layers (LSTM-layers) are investigated due to their ability to effectively model sequential data and
learn complex dependencies [2].