A neurofuzzy application for AC motor drives monitoring system

Currently industrial applications require suitable monitoring systems able to identify any decrease in efficiency resulting in economic losses. This paper shows that the information coming from a general purpose monitoring system can be usefully exploited to realize a sensorless instrument for the monitoring of an ac motor drive, and can be fed to a diagnostic tool for providing useful risk coefficients. The method is based on digital processing of the line signals acquired by means of a virtual instrument. The employed wavelet algorithms have been implemented within a Matlab environment, and risk coefficients are generated by means of suitable neurofuzzy algorithms.