Signal-based Intelligent Diagnostic Method for BLDC Motors

This article describes an intelligent signal-based diagnosis method. It makes possible to see the difference between true object malfunction and changing its operating mode. As experimental results for brushless DC motors (BLDC) the dependence of wavelet transformation measurement coefficients on the characteristic scales of a serviceable and faulty motor under different loading modes has been revealed. Based on the received information a neural classification network, which makes it possible to reveal the current state of the object has been developed. It is established that all types of mother wavelet can be used for this method realization. The validity of the theoretical calculations and model adequacy are confirmed in the large volume of pilot studies.